A low-latency intelligent algorithmic trading system for enhancing intraday trading profitability

Abstract

The application relates to the technical field of computer information processing, and discloses a low-delay intelligent algorithm transaction system for enhancing intraday transaction income, which comprises an order feature analysis module, a market state sensing module, an algorithm matching module, a dynamic order splitting module, an execution feedback adjustment module and a risk constraint control module; order state feature information is generated according to transaction order data, market state information is generated according to real-time market quotation data, a target execution algorithm is determined based on the order state feature information and the market state information, a plurality of sub-transaction orders are generated according to the target execution algorithm, subsequent execution parameters are adjusted according to execution feedback information, and transaction order execution states are adjusted according to transaction execution states. The target execution algorithm is determined by fusing the order state feature information and the market state information, and joint algorithm selection based on order states and market environments is realized.

Description

Technical Field

[0001] This invention relates to the field of computer information processing technology, and in particular to a low-latency intelligent algorithm trading system that enhances intraday trading profits. Background Technology

[0002] With the development of computer technology and financial trading systems, securities trading is gradually shifting from manual operation to algorithmic trading. Existing algorithmic trading systems acquire trading order data and market data, generate trading instructions based on preset trading strategies, and execute trading orders through trading interfaces.

[0003] Existing algorithmic trading systems typically include an order input module, a market data acquisition module, an algorithm execution module, and a trading interface module. The order input module receives user-submitted trading order data, the market data acquisition module acquires real-time market data, and the algorithm execution module selects the corresponding trading strategy based on preset trading rules and generates trading execution instructions.

[0004] However, existing algorithmic trading systems typically select trading algorithms based on preset trading rules when determining the trading execution algorithm. This lacks joint analysis of trading order status characteristics and real-time market status information. Consequently, information such as trading order size, price status, time constraints, market liquidity, price fluctuations, and order book status are not correlated and processed, making it difficult for the trading execution algorithm to match the current trading order status and market environment. Summary of the Invention

[0005] To overcome the above shortcomings, this invention provides a low-latency intelligent algorithm trading system to enhance intraday trading profits, aiming to improve the problem that existing trading execution algorithms have difficulty matching with the current trading order status and market environment.

[0006] In a first aspect, the present invention provides the following technical solution: a low-latency intelligent algorithm trading system for enhancing intraday trading profits, comprising: The module includes an order feature analysis module, a market status perception module, an algorithm matching module, a dynamic order splitting module, an execution feedback adjustment module, and a risk constraint control module. The order feature parsing module is connected to the transaction order input terminal and is used to generate order status feature information based on the transaction order data; The market status perception module is connected to the market data acquisition terminal and is used to generate market status information based on real-time market data. The algorithm matching module is connected to the order feature parsing module and the market status perception module respectively, and is used to determine the target execution algorithm based on the order status feature information and the market status information; The dynamic order splitting module is data-connected to the algorithm matching module and is used to split the transaction order according to the target execution algorithm to generate multiple sub-transaction orders; The execution feedback adjustment module is connected to the dynamic order splitting module and the market status perception module respectively, and is used to adjust the execution parameters of the multiple sub-transaction orders according to the sub-transaction order execution feedback information; The risk constraint control module is connected to the dynamic order splitting module and is used to adjust the execution status of transaction orders based on transaction execution status information.

[0007] Preferably, the order feature parsing module generates order status feature information based on transaction order data, specifically including: Generate order size characteristic information based on transaction volume information; Generate price status feature information based on transaction price information; Generate time constraint feature information based on order time information; The order status feature information is generated based on the order size feature information, the price status feature information, and the time constraint feature information.

[0008] Preferably, the market status perception module generates market status information based on real-time market data, specifically including: Market liquidity status information is generated based on trading volume data; Generate price fluctuation status information based on price change data; Generate order book status information based on buy and sell order book data; The market status information is generated based on the market liquidity status information, the price fluctuation status information, and the order book status information.

[0009] Preferably, the algorithm matching module determines the target execution algorithm based on the order status feature information and the market status information, specifically including: Determine order compatibility information based on the order status feature information; Market fit information is determined based on the aforementioned market status information; The target execution algorithm is determined based on the order adaptation information and the market adaptation information.

[0010] Preferably, the dynamic order splitting module generates multiple sub-transaction orders according to the target execution algorithm, specifically including: The order execution rules are determined based on the target execution algorithm. Adjust the quantity distribution of transaction orders according to the order execution rules; The execution order information corresponding to the multiple sub-transaction orders is determined according to the order execution rules.

[0011] Preferably, the execution feedback adjustment module adjusts the execution parameters based on the sub-transaction order execution feedback information, specifically including: Generate order execution status information based on the sub-transaction order execution feedback information; Execution adjustment information is generated based on the order execution status information; Adjust the execution parameters of subsequent sub-transaction orders based on the aforementioned execution adjustment information.

[0012] Preferably, the risk constraint control module adjusts the transaction order execution status based on the transaction execution status information, specifically including: Risk status information is generated based on transaction execution status information; The execution status of the transaction order is adjusted based on the matching result between the risk status information and the preset risk constraints.

[0013] Ideally, it also includes a low-latency data interaction module; The low-latency data interaction module is communicatively connected to the market status perception module, the algorithm matching module, and the dynamic order splitting module, respectively. The low-latency data interaction module is used to transmit real-time market data, target execution algorithm information, and sub-transaction order information.

[0014] Preferably, the execution feedback adjustment module is connected to the dynamic order splitting module via feedback. The dynamic order splitting module updates the execution parameters corresponding to the multiple sub-transaction orders based on the execution adjustment information generated by the execution feedback adjustment module.

[0015] Secondly, this invention provides the following technical solution: a low-latency intelligent algorithm trading method to enhance intraday trading profits, comprising the following steps: S1. Obtain transaction order data and generate order status feature information based on the transaction order data; S2. Obtain real-time market data and generate market status information based on the real-time market data; S3. Determine the target execution algorithm based on the order status feature information and the market status information; S4. Split the transaction order according to the execution rules corresponding to the target execution algorithm to generate multiple sub-transaction orders, and determine the execution order of the multiple sub-transaction orders; S5. Obtain sub-transaction order execution feedback information, and adjust the execution parameters corresponding to subsequent sub-transaction orders based on the sub-transaction order execution feedback information and the market status information; S6. Obtain transaction execution status information, generate transaction control instructions based on the transaction execution status information, and adjust the transaction order execution status based on the transaction control instructions.

[0016] The present invention has the following beneficial effects: 1. This invention generates order status feature information and market status information through an order feature parsing module and a market status perception module, respectively. The algorithm matching module determines the target execution algorithm based on the two types of information, thereby realizing joint algorithm selection based on order status and market environment.

[0017] 2. This invention determines the target execution algorithm through an algorithm matching module, and generates multiple sub-transaction orders by a dynamic order splitting module according to the execution rules corresponding to the target execution algorithm, thereby realizing the dynamic splitting and execution of transaction orders.

[0018] 3. This invention obtains sub-transaction order execution feedback information through an execution feedback adjustment module, and adjusts the execution parameters of subsequent sub-transaction orders according to the execution status, thereby realizing feedback adjustment of the transaction execution process.

[0019] 4. The present invention generates transaction control instructions based on transaction execution status information through a risk constraint control module, and adjusts the execution status of transaction orders to achieve risk constraint control during the transaction process. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the overall structure of a low-latency intelligent algorithm trading system for enhancing intraday trading profits proposed in this invention; Figure 2 This is a flowchart illustrating the order status feature information generation process proposed in this invention. Figure 3 This is a flowchart illustrating the market status information generation process proposed in this invention. Figure 4 This is a flowchart of the target execution algorithm matching and dynamic order splitting proposed in this invention; Figure 5 This is a flowchart illustrating the sub-transaction order execution feedback adjustment process proposed in this invention. Figure 6 This is a flowchart illustrating the risk constraint control and low-latency data interaction proposed in this invention. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1: Refer to Figure 1 In a first embodiment of the present invention, the present invention provides a low-latency intelligent algorithm trading system for enhancing intraday trading profits, comprising: The module includes an order feature analysis module, a market status perception module, an algorithm matching module, a dynamic order splitting module, an execution feedback adjustment module, and a risk constraint control module. The order feature parsing module is connected to the transaction order input terminal and is used to generate order status feature information based on transaction order data; The market status perception module is connected to the market data acquisition terminal and is used to generate market status information based on real-time market data. The algorithm matching module is connected to the order feature parsing module and the market status perception module respectively, and is used to determine the target to execute the algorithm based on the order status feature information and the market status information. The dynamic order splitting module is connected to the algorithm matching module and is used to split transaction orders according to the target algorithm to generate multiple sub-transaction orders; The execution feedback adjustment module is connected to the dynamic order splitting module and the market status perception module respectively, and is used to adjust the execution parameters of multiple sub-transaction orders based on the execution feedback information of sub-transaction orders; The risk constraint control module is connected to the dynamic order splitting module to adjust the execution status of transaction orders based on transaction execution status information.

[0023] Specifically, in this embodiment, when the system is running, the order feature parsing module first processes the input transaction order data to form order status feature information that describes the status of the transaction order; at the same time, the market status perception module processes the real-time market data to form market status information that describes the current market status.

[0024] The algorithm matching module determines the corresponding target execution algorithm based on the received order status characteristics and market status information, and sends the target execution algorithm to the dynamic order splitting module. The dynamic order splitting module generates multiple sub-transaction orders based on the target execution algorithm and controls these sub-transaction orders to be processed according to the corresponding execution rules.

[0025] During the execution of a sub-transaction order, the execution feedback adjustment module obtains transaction execution feedback information and adjusts the execution parameters of subsequent sub-transaction orders according to changes in execution status; the risk constraint control module controls the execution status of the transaction order according to the transaction execution status information, thus forming a transaction processing process consisting of order input, algorithm matching, order execution, feedback adjustment, and risk control.

[0026] In this embodiment, the modules communicate with each other through data interfaces, enabling data exchange between transaction order data, real-time market data, target execution algorithm information, sub-transaction order information, and execution feedback information. These modules together constitute a low-latency intelligent algorithm trading system that enhances intraday trading profits.

[0027] Reference Figure 2 Furthermore, the order feature parsing module generates order status feature information based on the transaction order data, specifically including: Generate order size characteristic information based on transaction volume information; Generate price status feature information based on transaction price information; Generate time constraint feature information based on order time information; Order status feature information is generated based on order size feature information, price status feature information, and time constraint feature information.

[0028] Specifically, the order feature parsing module receives transaction order data sent from the transaction order input terminal, parses and processes the transaction order data, and obtains transaction quantity information, transaction price information, and order time information. Among them, the transaction quantity information is used to represent the order quantity corresponding to the current transaction order, the transaction price information is used to represent the order price corresponding to the current transaction order, and the order time information is used to represent the submission time and execution time constraints of the current transaction order.

[0029] The order feature analysis module generates order size feature information based on the correlation between transaction quantity information and the corresponding market transaction data of the traded asset. It obtains the market transaction data of the traded asset within the current trading period, performs correlation analysis between the transaction quantity information and the market transaction data, and determines the size status of the current transaction order. The order size feature information is represented as follows:

[0030] ; in, Indicates order size characteristics; This indicates the number of transaction orders; This indicates the market trading data corresponding to the trading target.

[0031] The order feature parsing module generates price status feature information based on the correlation between transaction price information and real-time market price information. It obtains the real-time market price information corresponding to the current trading instrument, compares the transaction order price information with the real-time market price information, and generates price status feature information describing the price status of the transaction order. The price status feature information is represented as follows:

[0032] ; in, Indicates price status characteristics; This indicates the price information for the transaction order; This indicates real-time market price information.

[0033] The order feature parsing module generates time constraint feature information based on order time information. It determines the time constraint status of a transaction order based on the order submission time and the preset execution deadline. The time constraint feature information is represented as follows: ;in, Represents time constraint feature information; Indicates the execution deadline for the corresponding transaction order; This indicates the time the transaction order was submitted.

[0034] Furthermore, the order feature parsing module combines the order size feature information, price status feature information, and time constraint feature information to generate order status feature information, which is represented as follows: ;in, Indicates order status characteristics; Indicates order size characteristics; Indicates price status characteristics; This represents time constraint feature information.

[0035] Through the above processing, the order feature parsing module converts the original transaction order data into order status feature information that includes order size status, price status, and time constraint status, providing a data foundation for the subsequent algorithm matching module to determine the target execution algorithm based on the transaction order status.

[0036] Reference Figure 3 Furthermore, the market status perception module generates market status information based on real-time market data, specifically including: Market liquidity status information is generated based on trading volume data; Generate price fluctuation status information based on price change data; Generate order book status information based on buy and sell order book data; Market status information is generated based on market liquidity status information, price fluctuation status information, and order book status information.

[0037] Specifically, the market status perception module connects to the market data acquisition terminal to obtain real-time market data corresponding to the trading target. This real-time market data includes trading volume data, price change data, and order book data. The market status perception module parses and processes the real-time market data, generating corresponding market status features based on different types of market data, and combining multiple market status features to form market status information.

[0038] The market status perception module generates market liquidity status information based on trading volume data. It analyzes the circulation status of trading orders in the current market based on the trading volume data, the number of buy orders, and the number of sell orders within the current trading period, generating market liquidity status information to describe the market's liquidity state. The market liquidity status information is represented as follows:

[0039] ; in, This indicates information about the state of market liquidity. Indicates the quantity of the buyer's order; Indicates the quantity offered by the seller; This indicates the current demand for transaction orders.

[0040] The market status perception module generates price fluctuation status information based on price change data. It acquires market price data for the current and previous time periods, determines the price change status based on the price change relationships within consecutive time periods, and describes the current price changes of the trading instrument. The price fluctuation status information is represented as follows:

[0041] ; in, This indicates information about price fluctuations. This indicates the market price corresponding to the current time period; This indicates the market price corresponding to the previous time period.

[0042] The market status perception module generates order book status information based on buy and sell order book data. It obtains the order quantity information corresponding to the buy and sell orders, analyzes the distribution of buy and sell order quantities, and generates order book status information to describe the current order book structure.

[0043] Furthermore, the market status perception module combines market liquidity status information, price fluctuation status information, and order book status information to generate market status information, which is represented as follows: ;in, Indicates market status information; This indicates information about the state of market liquidity. This indicates information about price fluctuations. This indicates the status information of the betting market.

[0044] Through the above processing, the market state perception module converts real-time market data into market state information that includes market liquidity status, price fluctuation status, and order book structure status. This enables the subsequent algorithm matching module to jointly determine the target execution algorithm based on real-time market state information and order status feature information, providing a data foundation for the selection of trading order execution strategies.

[0045] Reference Figure 4 Furthermore, the algorithm matching module determines the target execution algorithm based on order status feature information and market status information, specifically including: Determine order compatibility information based on order status characteristics; Determine market fit information based on market status information; The target execution algorithm is determined based on order adaptation information and market adaptation information.

[0046] Specifically, the algorithm matching module is data-connected to the order feature parsing module and the market state perception module. It receives order state feature information and market state information, and performs matching analysis on different trading execution strategies based on a preset set of trading algorithms. The trading algorithm set includes multiple trading execution strategies, each corresponding to a different order processing method. The algorithm matching module determines the target execution algorithm to match based on the current order state and the current market state.

[0047] The algorithm matching module determines order adaptation information based on order status feature information. Specifically, it analyzes the execution requirements of transaction orders based on order size, price status, and time constraint features within the order status feature information, determines the matching relationship between the current transaction order and each transaction execution strategy, and generates order adaptation information. Specifically, the order size feature information is used to determine the execution requirements corresponding to the quantity of the transaction order, the price status feature information is used to determine the execution requirements corresponding to the price status of the transaction order, and the time constraint feature information is used to determine the execution requirements corresponding to the execution time of the transaction order.

[0048] Order compatibility information is represented as follows: ;in, Indicates the first Order adaptation information corresponding to each transaction execution strategy; Indicates order status characteristics; Indicates the first Each trading execution strategy.

[0049] The algorithm matching module determines market fit information based on market state information. It analyzes the fit between the current trading environment and various trading strategies based on market liquidity, price volatility, and order book information, generating market fit information. Specifically, market liquidity information describes the current market trading environment, price volatility information describes the current market price changes, and order book information describes the current distribution of buy and sell orders.

[0050] Market compatibility information is represented as follows: ; in, Indicates the first Market adaptation information corresponding to each trading execution strategy; MMM represents market status information; Indicates the first Each trading execution strategy.

[0051] Furthermore, the algorithm matching module determines the target execution algorithm based on order and market adaptation information. It comprehensively analyzes the order and market adaptation information corresponding to each trading execution strategy, generates matching results for each strategy, and determines the target execution algorithm based on these results.

[0052] The matching result is represented as follows: ; in, Indicates the first Matching results corresponding to each transaction execution strategy; Indicates the first Order adaptation information corresponding to each transaction execution strategy; Indicates the first Market fit information corresponding to each trading execution strategy; Indicates the first Risk adaptation information corresponding to each trading execution strategy; , , These represent the weight parameters corresponding to order adaptation information, market adaptation information, and risk adaptation information, respectively.

[0053] The algorithm matching module determines the trading execution strategy corresponding to the maximum matching result as the target execution algorithm based on the matching results of each trading execution strategy. Specifically, it is expressed as follows: ;in, Indicates the target execution algorithm; Indicates the first Matching results for each trading execution strategy.

[0054] Through the above processing, the algorithm matching module analyzes the transaction order execution requirements based on the order status feature information and analyzes the current transaction environment status based on the market status information. By combining the order adaptation information and the market adaptation information, the target execution algorithm is determined, so that the subsequent dynamic order splitting module can execute the transaction order processing according to the determined target execution algorithm.

[0055] Furthermore, the dynamic order splitting module generates multiple sub-transaction orders based on the target execution algorithm, specifically including: The order execution rules are determined based on the target execution algorithm; Adjust the quantity distribution of transaction orders according to the order execution rules; The execution order information for multiple sub-transaction orders is determined based on the order execution rules.

[0056] Specifically, the dynamic order splitting module is data-connected to the algorithm matching module to receive the target execution algorithm and determine the order execution rules based on the transaction execution strategy corresponding to the target execution algorithm. The order execution rules include rules for the number of transaction order splits, rules for the execution order of sub-transaction orders, and rules for the execution time of sub-transaction orders, which are used to process the original transaction order in stages.

[0057] The dynamic order splitting module determines the order execution rules based on the target execution algorithm. According to the transaction execution strategy corresponding to the target execution algorithm, it obtains the splitting method and execution constraints for the current transaction order, determines the quantity distribution method for the transaction order based on the splitting method, and determines the execution relationship between each sub-transaction order based on the execution constraints.

[0058] Furthermore, the dynamic order splitting module adjusts the quantity distribution of transaction orders according to the order execution rules. The original transaction order is divided into multiple sub-transaction orders, and the transaction quantity corresponding to each sub-transaction order is determined according to the order execution rules, so that the sum of the quantities of the multiple sub-transaction orders equals the quantity of the original transaction order. The transaction order splitting process is represented as follows: ;in, Indicates the original transaction order; Indicates the first Individual transaction orders.

[0059] The transaction quantity corresponding to each sub-transaction order satisfies: ; in, Indicates the number of original transaction orders; Indicates the first Number of individual transaction orders; This indicates the number of sub-transaction orders.

[0060] The dynamic order splitting module determines the quantity distribution of each sub-transaction order based on the order execution rules corresponding to the target execution algorithm, so that different sub-transaction orders are executed according to their corresponding quantities.

[0061] Furthermore, the dynamic order splitting module determines the execution order information for multiple sub-transaction orders based on the order execution rules. According to the execution strategy corresponding to the target execution algorithm, it sorts each sub-transaction order, generates execution order information, and controls the sending of each sub-transaction order to the transaction execution end based on this information. The execution order information includes sub-transaction order identification information, execution time information, and execution order information. The dynamic order splitting module determines the sending timing of each sub-transaction order based on this execution order information.

[0062] Through the above processing, the dynamic order splitting module adjusts the quantity distribution and determines the execution order of the original transaction orders according to the order execution rules corresponding to the target execution algorithm, generating multiple sub-transaction orders with corresponding execution information. This enables the transaction orders to be split according to the execution rules corresponding to the target execution algorithm and provides a data basis for the subsequent execution feedback adjustment module to adjust the execution parameters according to the execution status of the sub-transaction orders.

[0063] Reference Figure 5 Furthermore, the execution feedback adjustment module adjusts the execution parameters based on the sub-transaction order execution feedback information, specifically including: Generate order execution status information based on sub-transaction order execution feedback information; Generate execution adjustment information based on order execution status information; Adjust the execution parameters of subsequent sub-transaction orders based on the execution adjustment information.

[0064] The feedback adjustment module and the dynamic order splitting module are connected for feedback. The dynamic order splitting module updates the execution parameters corresponding to multiple sub-transaction orders based on the execution adjustment information generated by the execution feedback adjustment module.

[0065] Specifically, the execution feedback adjustment module is data-connected to the dynamic order splitting module to obtain execution feedback information from multiple sub-transaction orders during the transaction execution process. The sub-transaction order execution feedback information includes the transaction quantity, transaction status, and execution completion status information for each sub-transaction order. Based on this sub-transaction order execution feedback information, the execution feedback adjustment module analyzes the current transaction order execution status and generates order execution status information.

[0066] The execution feedback adjustment module determines the current execution status of a sub-transaction order based on the relationship between the target execution quantity and the actual transaction quantity. It then generates execution deviation information based on the target execution quantity and the actual transaction quantity, representing the difference between the current sub-transaction order's actual execution status and the target execution status.

[0067] Execution deviation information is represented as follows: ; in, This indicates execution deviation information; Indicates the target number of sub-transaction orders; This indicates the actual number of transactions corresponding to the sub-transaction order.

[0068] The execution feedback and adjustment module generates order execution status information based on execution deviation information and current market status information. Order execution status information includes the completion status of sub-transaction orders, execution deviation status, and the status of subsequent order adjustment requests.

[0069] Furthermore, the execution feedback adjustment module generates execution adjustment information based on the order execution status information. When the order execution status information indicates a deviation between the current sub-transaction order execution status and the target execution status, the execution feedback adjustment module determines the adjustment direction for subsequent sub-transaction orders based on the order execution status information and generates execution adjustment information.

[0070] The adjustment information includes quantity adjustment information, execution time adjustment information, and execution order adjustment information for subsequent sub-transaction orders. Quantity adjustment information is used to adjust the transaction quantity of subsequent sub-transaction orders; execution time adjustment information is used to adjust the execution time of subsequent sub-transaction orders; and execution order adjustment information is used to adjust the execution order of subsequent sub-transaction orders.

[0071] Furthermore, the execution feedback adjustment module sends the execution adjustment information to the dynamic order splitting module. The dynamic order splitting module updates the execution parameters corresponding to multiple sub-transaction orders based on the execution adjustment information. The dynamic order splitting module redetermines the quantity distribution of subsequent sub-transaction orders based on the quantity adjustment information, updates the execution time of subsequent sub-transaction orders based on the execution time adjustment information, updates the execution order of subsequent sub-transaction orders based on the execution order adjustment information, and generates the corresponding sub-transaction order execution information according to the updated execution parameters.

[0072] Through the above processing, the execution feedback adjustment module generates order execution status information based on the sub-transaction order execution feedback information, and adjusts the execution parameters corresponding to subsequent sub-transaction orders based on the order execution status information. This enables the dynamic order splitting module to update the sub-transaction order execution process according to the actual transaction execution status, thereby realizing feedback adjustment during the transaction order execution process.

[0073] Furthermore, the risk constraint control module adjusts the execution status of transaction orders based on the transaction execution status information, specifically including: Risk status information is generated based on transaction execution status information; Adjust the execution status of transaction orders based on the matching results between risk status information and preset risk constraints.

[0074] Specifically, the risk constraint control module is data-connected to the dynamic order splitting module to obtain transaction execution status information during the execution of transaction orders. This information includes the number of executed transaction orders, the execution status of sub-transaction orders, and the transaction account status. The risk constraint control module analyzes the risk status of the current transaction execution process based on this information, generating risk status information. This analysis combines multiple risk indicators from the transaction execution status information, including transaction order execution deviation information, transaction account status information, and abnormal transaction execution status information. Based on the status information corresponding to each risk indicator, risk status information is generated to describe the risk status of the current transaction order execution process.

[0075] Risk status information is represented as follows: ; in, Indicates risk status information; Indicates the first Risk status data corresponding to each risk indicator; Indicates the first The weighting parameters corresponding to each risk indicator; This indicates the number of risk indicators.

[0076] Furthermore, the risk constraint control module matches the risk status information with preset risk constraints. It compares the generated risk status information with the preset risk constraints and determines the execution status of the current transaction order based on the matching result. When the risk status information meets the preset risk constraints, a corresponding transaction control instruction is generated to maintain the current transaction order execution status; when the risk status information does not meet the preset risk constraints, an adjustment control instruction is generated based on the risk status information to adjust the transaction order execution status.

[0077] The execution status of a transaction order includes three states: Continued execution, Suspended execution, and Adjusted execution. The Continued execution state maintains the execution of the current sub-transaction order; the Suspended execution state stops the sending of subsequent sub-transaction orders; and the Adjusted execution state adjusts the execution parameters of subsequent sub-transaction orders based on risk status information.

[0078] Furthermore, after generating transaction control instructions, the risk constraint control module sends these instructions to the dynamic order splitting module. The dynamic order splitting module then adjusts the execution status of multiple sub-transaction orders based on the transaction control instructions. When the execution status is adjusted according to the transaction control instructions, the dynamic order splitting module re-determines the execution parameters of subsequent sub-transaction orders based on the updated execution status.

[0079] Through the above processing, the risk constraint control module generates risk status information based on the transaction execution status information, and adjusts the transaction order execution status according to the matching result between the risk status information and the preset risk constraint conditions, so that the transaction order execution process can be constrained and controlled in combination with the real-time execution status.

[0080] Reference Figure 6 Furthermore, it also includes a low-latency data interaction module; The low-latency data interaction module communicates with the market status perception module, the algorithm matching module, and the dynamic order splitting module, respectively. The low-latency data interaction module is used to transmit real-time market data, target execution algorithm information, and sub-trade order information.

[0081] Specifically, the low-latency data interaction module includes a market data transmission channel, an algorithm result transmission channel, and an order execution data transmission channel. The market data transmission channel is connected to the market status awareness module and is used to transmit real-time market data; the algorithm result transmission channel is connected to the algorithm matching module and is used to transmit target algorithm information; and the order execution data transmission channel is connected to the dynamic order splitting module and is used to transmit information on multiple sub-trade orders.

[0082] The low-latency data interaction module establishes corresponding data transmission priorities based on data type and executes data forwarding according to these priorities. Real-time market data that affects the transaction algorithm determination process is set as the first priority data, target execution algorithm information is set as the second priority data, and sub-transaction order information is set as the third priority data. Transmission scheduling is performed according to the priority order of each type of data.

[0083] Furthermore, the low-latency data interaction module performs time stamping processing on the data during transmission. When it receives real-time market data, target execution algorithm information, and sub-transaction order information, it generates corresponding data time stamps and determines the data transmission order based on the data time stamps.

[0084] Data time stamp is represented as: ; in, Indicates data transmission time information; Indicates the data reception time; Indicates the time the data was sent.

[0085] The low-latency data interaction module detects the data transmission status based on data transmission time information. When the data transmission time information meets the preset transmission conditions, it sends the corresponding data to the target module; when the data transmission time information does not meet the preset transmission conditions, it readjusts the data transmission order according to data priority. Furthermore, the low-latency data interaction module sends real-time market data to the market status perception module, sends the target execution algorithm information to the dynamic order splitting module, and sends sub-trade order information to the transaction execution end, maintaining data correlation between market status information generation, target execution algorithm determination, and sub-trade order execution processes.

[0086] Through the above processing, the low-latency data interaction module performs unified transmission management of real-time market data, target execution algorithm information, and sub-trade order information, and performs priority scheduling according to data type, so that the data transmission process between various modules within the system maintains a corresponding relationship with the transaction order processing process.

[0087] Example 2: In the second embodiment of the present invention, the present invention provides a low-latency intelligent algorithm trading method to enhance intraday trading profits, including the following steps: S1. Obtain transaction order data and generate order status feature information based on the transaction order data; S2. Obtain real-time market data and generate market status information based on the real-time market data; S3. Determine the target execution algorithm based on order status characteristics and market status information; S4. Split the transaction order according to the execution rules corresponding to the target execution algorithm to generate multiple sub-transaction orders, and determine the execution order of the multiple sub-transaction orders; S5. Obtain sub-trade order execution feedback information, and adjust the execution parameters of subsequent sub-trade orders based on the sub-trade order execution feedback information and market status information; S6. Obtain transaction execution status information, generate transaction control instructions based on the transaction execution status information, and adjust the transaction order execution status according to the transaction control instructions.

[0088] Specifically, during the transaction order processing, the system first acquires the transaction order data input by the user. This data includes transaction quantity, transaction price, and order time information. Based on the transaction order data, relevant order execution features are extracted to generate order status feature information, which describes the quantity status, price status, and time constraint status of the current transaction order.

[0089] Obtain real-time market data for the trading target, including trading volume, price changes, and order book data. Analyze the current market liquidity, price changes, and order book status based on the real-time market data to generate market status information.

[0090] Based on order status characteristics and market status information, the transaction execution strategies in the preset transaction algorithm set are matched and analyzed to determine the target execution algorithm corresponding to the current transaction order status and the current market environment, and the target execution algorithm is used as the basis for the subsequent execution of the transaction order.

[0091] Based on the execution rules corresponding to the target execution algorithm, the original transaction order is split into multiple sub-transaction orders, and the execution order information for each sub-transaction order is determined. Each sub-transaction order is sent to the transaction execution terminal for processing according to its corresponding execution order.

[0092] During the execution of a sub-trade order, obtain sub-trade order execution feedback information, generate order execution status information based on the transaction status, execution completion status, and current market status, determine the adjustment information for subsequent sub-trade orders based on the order execution status information, and update the execution parameters for subsequent sub-trade orders based on the adjustment information.

[0093] During the execution of a trading order, the system acquires the trading execution status information, analyzes the current trading execution status based on this information, and generates corresponding trading control instructions. When the trading execution status meets preset risk constraints, the current trading order execution status is maintained; when the trading execution status does not meet the preset risk constraints, the trading order execution status is adjusted according to the trading control instructions.

[0094] Through the above steps, this embodiment generates order status feature information based on transaction order data, generates market status information based on real-time market data, determines the target execution algorithm based on the order status feature information and market status information, and then performs order splitting, feedback adjustment and risk control processing according to the target execution algorithm, realizing the complete processing of transaction orders from algorithm selection, order execution to status adjustment.

[0095] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A low-latency intelligent algorithm trading system for enhancing intraday trading profits, characterized in that: include: The module includes an order feature analysis module, a market status perception module, an algorithm matching module, a dynamic order splitting module, an execution feedback adjustment module, and a risk constraint control module. The order feature parsing module is connected to the transaction order input terminal and is used to generate order status feature information based on the transaction order data; The market status perception module is connected to the market data acquisition terminal and is used to generate market status information based on real-time market data. The algorithm matching module is connected to the order feature parsing module and the market status perception module respectively, and is used to determine the target execution algorithm based on the order status feature information and the market status information; The dynamic order splitting module is data-connected to the algorithm matching module and is used to split the transaction order according to the target execution algorithm to generate multiple sub-transaction orders; The execution feedback adjustment module is connected to the dynamic order splitting module and the market status perception module respectively, and is used to adjust the execution parameters of the multiple sub-transaction orders according to the sub-transaction order execution feedback information; The risk constraint control module is connected to the dynamic order splitting module and is used to adjust the execution status of transaction orders based on transaction execution status information.

2. The low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The order feature parsing module generates order status feature information based on transaction order data, specifically including: Generate order size characteristic information based on transaction volume information; Generate price status feature information based on transaction price information; Generate time constraint feature information based on order time information; The order status feature information is generated based on the order size feature information, the price status feature information, and the time constraint feature information.

3. The low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The market status perception module generates market status information based on real-time market data, specifically including: Market liquidity status information is generated based on trading volume data; Generate price fluctuation status information based on price change data; Generate order book status information based on buy and sell order book data; The market status information is generated based on the market liquidity status information, the price fluctuation status information, and the order book status information.

4. The low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The algorithm matching module determines the target execution algorithm based on the order status feature information and the market status information, specifically including: Determine order compatibility information based on the order status feature information; Market fit information is determined based on the aforementioned market status information; The target execution algorithm is determined based on the order adaptation information and the market adaptation information.

5. The low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The dynamic order splitting module generates multiple sub-transaction orders according to the target execution algorithm, specifically including: The order execution rules are determined based on the target execution algorithm. Adjust the quantity distribution of transaction orders according to the order execution rules; The execution order information corresponding to the multiple sub-transaction orders is determined according to the order execution rules.

6. The low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The execution feedback adjustment module adjusts the execution parameters based on the sub-transaction order execution feedback information, specifically including: Generate order execution status information based on the sub-transaction order execution feedback information; Execution adjustment information is generated based on the order execution status information; Adjust the execution parameters of subsequent sub-transaction orders based on the aforementioned execution adjustment information.

7. The low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The risk constraint control module adjusts the execution status of transaction orders based on transaction execution status information, specifically including: Risk status information is generated based on transaction execution status information; The execution status of the transaction order is adjusted based on the matching result between the risk status information and the preset risk constraints.

8. A low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, It also includes a low-latency data interaction module; The low-latency data interaction module is communicatively connected to the market status perception module, the algorithm matching module, and the dynamic order splitting module, respectively. The low-latency data interaction module is used to transmit real-time market data, target execution algorithm information, and sub-transaction order information.

9. A low-latency intelligent algorithm trading system for enhancing intraday trading profits according to claim 1, characterized in that, The execution feedback adjustment module is connected to the dynamic order splitting module via feedback. The dynamic order splitting module updates the execution parameters corresponding to the multiple sub-transaction orders based on the execution adjustment information generated by the execution feedback adjustment module.

10. A low-latency intelligent algorithm trading method to enhance intraday trading profits, characterized in that, A low-latency intelligent algorithm trading system for enhancing intraday trading profits, as described in any one of claims 1-9, comprises the following steps: S1. Obtain transaction order data and generate order status feature information based on the transaction order data; S2. Obtain real-time market data and generate market status information based on the real-time market data; S3. Determine the target execution algorithm based on the order status feature information and the market status information; S4. Split the transaction order according to the execution rules corresponding to the target execution algorithm to generate multiple sub-transaction orders, and determine the execution order of the multiple sub-transaction orders; S5. Obtain sub-transaction order execution feedback information, and adjust the execution parameters corresponding to subsequent sub-transaction orders based on the sub-transaction order execution feedback information and the market status information; S6. Obtain transaction execution status information, generate transaction control instructions based on the transaction execution status information, and adjust the transaction order execution status based on the transaction control instructions.

Images