Transaction equipment data processing method and system based on SAC
Through the neural network and SAC model, the coordination between trading equipment is optimized, and the problem of insufficient coordination between multiple devices in the existing technology is solved, and the overall efficiency and equipment energy efficiency of the trading system are improved.
Patent Information
- Application Number
- CN202410599877.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-15
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-05-15
AI Technical Summary
The existing quantitative trading technology fails to effectively consider the coordination of multiple devices when improving the operation efficiency of trading strategies, resulting in difficult operational results, and high equipment energy consumption and high error rate.
The SAC-based trading equipment data processing method is adopted to determine the coordinated cooperation parameters between devices through the neural network prediction model, and a device task allocation strategy is generated in combination with the SAC model to optimize the task allocation of each trading equipment.
It improves the operation efficiency and effectiveness of equipment execution trading strategies in multi-equipment scenarios, saves equipment energy consumption and reduces errors.
Smart Images

Figure CN118364311B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a transaction device data processing method and system based on SAC. Background Art
[0002] The operating efficiency of quantitative trading equipment is not only related to the execution efficiency of the program code corresponding to the quantitative strategy itself and the performance of the equipment itself, but also has a lot to do with the collaborative operating efficiency between trading devices. In particular, quantitative trading execution in the context of big data often requires the coordinated cooperation of multiple trading devices to achieve stable operating results. Existing quantitative trading technologies often only focus on code optimization within a single trading device when improving the operating effect of trading strategies, or simply increase computing power by adding devices, without considering the interactive data between devices and the characteristics of trading strategies to improve the collaborative cooperation strategy between multiple devices. Therefore, the improvement effect is general and the operating effect is difficult to guarantee. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention
[0003] The technical problem to be solved by the present invention is to provide a SAC-based trading device data processing method and system, which can effectively improve the operating efficiency and effect of devices executing trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a transaction device data processing method based on SAC, the method comprising:
[0005] Acquire a current trading strategy of a target trading system and historical data of a plurality of trading devices in the target trading system;
[0006] Based on the neural network prediction model, according to the historical data, determining the coordination parameters between any two of the transaction devices;
[0007] Inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain an output device task allocation strategy;
[0008] According to the device task allocation strategy, a corresponding transaction execution task is allocated to each of the transaction devices.
[0009] As an optional implementation, in the first aspect of the present invention, the historical data includes historical code execution records, historical transaction records and historical inter-device communication data.
[0010] As an optional implementation, in the first aspect of the present invention, the determining of the coordination parameters between any two of the transaction devices based on the neural network prediction model according to the historical data includes:
[0011] For any two of the transaction devices, calculate the proportion of the communication data between the two transaction devices in the historical inter-device communication data of the two transaction devices to all the communication data;
[0012] Calculating a correlation parameter between the historical transaction records of the two transaction devices;
[0013] Calculating the code similarity in the historical code execution records of the two transaction devices;
[0014] Inputting the historical data of the two transaction devices into a trained coordination degree prediction neural network to obtain coordination prediction parameters corresponding to the two transaction devices; the coordination degree prediction neural network is trained by a training data set including historical data of a plurality of training devices and corresponding annotations of coordination work between devices;
[0015] The coordination parameter between the two transaction devices is calculated according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter.
[0016] As an optional implementation, in the first aspect of the present invention, the calculating the collaborative cooperation parameter between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the collaborative prediction parameter includes:
[0017] Calculating a first weight proportional to the proportion of the data;
[0018] Calculating a second weight proportional to the association parameter; the second weight is less than the first weight;
[0019] Calculating a third weight proportional to the code similarity; the third weight is less than the second weight;
[0020] The product of the first weight, the second weight, the third weight and the collaborative prediction parameter is calculated to obtain the collaborative coordination parameter between the two transaction devices.
[0021] As an optional implementation, in the first aspect of the present invention, the inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain the output device task allocation strategy includes:
[0022] Determine the trading instructions and trading rules corresponding to the current trading strategy;
[0023] Determine the device parameters of each of the transaction devices; the device parameters include device model, device communication rate, device computing performance and device current status;
[0024] The transaction instructions, the transaction rules, the device parameters and the coordination parameters are input into the trained SAC model to obtain the output device task allocation strategy; the device task allocation strategy is used to limit the transaction devices that need to perform tasks and the transaction task parameters to be performed by each transaction device; the transaction task parameters include the transaction institution port, the transaction financial product type, the transaction trigger rules and the transaction reference rules between other devices.
[0025] As an optional embodiment, in the first aspect of the present invention, the SAC model includes a strategy network and a value network; the strategy network is used to randomly generate an equipment task allocation plan based on the input transaction instructions, the transaction rules, the equipment parameters and the coordination parameters, and the value network calculates the value of the equipment task allocation plan according to a preset state value rule, and when the value meets the preset value function requirements, the equipment task allocation plan is output as an equipment task allocation strategy; the SAC model is trained by using a training data set including multiple training transaction task equipment allocation data and corresponding transaction action annotations, transaction code annotations and transaction result annotations.
[0026] As an optional implementation, in the first aspect of the present invention, the state value rule is:
[0027] For each transaction device in the device task allocation scheme, according to the device parameters of the transaction device and the preset parameter rules, the execution efficiency and execution cost corresponding to the transaction task parameters of the transaction device are calculated;
[0028] Calculating an average value of the coordination parameters between the transaction device and all other transaction devices involved in the transaction reference rule of the transaction device to obtain a coordination value;
[0029] calculating an efficiency value proportional to the execution efficiency;
[0030] calculating a cost value inversely proportional to said execution cost;
[0031] Calculate the product of the coordination value, the efficiency value and the cost value to obtain the equipment value of the transaction equipment;
[0032] The average value of the equipment values of all the transaction equipment in the equipment task allocation plan is calculated to obtain the value of the equipment task allocation plan.
[0033] As an optional implementation, in the first aspect of the present invention, allocating a corresponding transaction execution task to each of the transaction devices according to the device task allocation strategy includes:
[0034] Determine a plurality of transaction devices to be allocated corresponding to the device task allocation strategy;
[0035] Sending a request to the transaction device to be allocated to obtain new transaction device parameters;
[0036] Calculating the parameter difference between the new transaction device parameters of all the transaction devices to be allocated and the device parameters used to calculate the device task allocation strategy;
[0037] Determine whether the parameter difference is greater than a preset difference threshold, and if not, assign a corresponding transaction execution task to each of the transaction devices to be assigned;
[0038] If so, the new transaction device parameters are used as update data, and the step of inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain the output device task allocation strategy is re-executed to obtain a new device task allocation strategy.
[0039] A second aspect of an embodiment of the present invention discloses a transaction device data processing system based on SAC, the system comprising:
[0040] An acquisition module, used to acquire a current trading strategy of a target trading system and historical data of a plurality of trading devices in the target trading system;
[0041] A determination module, configured to determine the coordination parameters between any two of the transaction devices based on the neural network prediction model and the historical data;
[0042] A prediction module, used for inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain an output device task allocation strategy;
[0043] The allocation module is used to allocate a corresponding transaction execution task to each of the transaction devices according to the device task allocation strategy.
[0044] As an optional implementation, in the second aspect of the present invention, the historical data includes historical code execution records, historical transaction records and historical inter-device communication data.
[0045] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the coordination parameters between any two of the transaction devices based on the neural network prediction model and the historical data includes:
[0046] For any two of the transaction devices, calculate the proportion of the communication data between the two transaction devices in the historical inter-device communication data of the two transaction devices to all the communication data;
[0047] Calculating a correlation parameter between the historical transaction records of the two transaction devices;
[0048] Calculating the code similarity in the historical code execution records of the two transaction devices;
[0049] Inputting the historical data of the two transaction devices into a trained coordination degree prediction neural network to obtain coordination prediction parameters corresponding to the two transaction devices; the coordination degree prediction neural network is trained by a training data set including historical data of a plurality of training devices and corresponding annotations of coordination work between devices;
[0050] The coordination parameter between the two transaction devices is calculated according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter.
[0051] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module calculates the collaborative cooperation parameter between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the collaborative prediction parameter includes:
[0052] Calculating a first weight proportional to the proportion of the data;
[0053] Calculating a second weight proportional to the association parameter; the second weight is less than the first weight;
[0054] Calculating a third weight proportional to the code similarity; the third weight is less than the second weight;
[0055] The product of the first weight, the second weight, the third weight and the collaborative prediction parameter is calculated to obtain the collaborative coordination parameter between the two transaction devices.
[0056] As an optional implementation, in the second aspect of the present invention, the prediction module inputs the current transaction strategy and the coordination parameters into the trained SAC model to obtain the specific manner of the output device task allocation strategy, including:
[0057] Determine the trading instructions and trading rules corresponding to the current trading strategy;
[0058] Determine the device parameters of each of the transaction devices; the device parameters include device model, device communication rate, device computing performance and device current status;
[0059] The transaction instructions, the transaction rules, the device parameters and the coordination parameters are input into the trained SAC model to obtain the output device task allocation strategy; the device task allocation strategy is used to limit the transaction devices that need to perform tasks and the transaction task parameters to be performed by each transaction device; the transaction task parameters include the transaction institution port, the transaction financial product type, the transaction trigger rules and the transaction reference rules between other devices.
[0060] As an optional embodiment, in the second aspect of the present invention, the SAC model includes a strategy network and a value network; the strategy network is used to randomly generate an equipment task allocation plan based on the input transaction instructions, the transaction rules, the equipment parameters and the coordination parameters, and the value network calculates the value of the equipment task allocation plan according to a preset state value rule, and when the value meets the preset value function requirements, the equipment task allocation plan is output as an equipment task allocation strategy; the SAC model is trained by using a training data set including multiple training transaction task equipment allocation data and corresponding transaction action annotations, transaction code annotations and transaction result annotations.
[0061] As an optional implementation, in the second aspect of the present invention, the state value rule is:
[0062] For each transaction device in the device task allocation scheme, according to the device parameters of the transaction device and the preset parameter rules, the execution efficiency and execution cost corresponding to the transaction task parameters of the transaction device are calculated;
[0063] Calculating an average value of the coordination parameters between the transaction device and all other transaction devices involved in the transaction reference rule of the transaction device to obtain a coordination value;
[0064] calculating an efficiency value proportional to the execution efficiency;
[0065] calculating a cost value inversely proportional to said execution cost;
[0066] Calculate the product of the coordination value, the efficiency value and the cost value to obtain the equipment value of the transaction equipment;
[0067] The average value of the equipment values of all the transaction equipment in the equipment task allocation plan is calculated to obtain the value of the equipment task allocation plan.
[0068] As an optional implementation, in the second aspect of the present invention, allocating a corresponding transaction execution task to each of the transaction devices according to the device task allocation strategy includes:
[0069] Determine a plurality of transaction devices to be allocated corresponding to the device task allocation strategy;
[0070] Sending a request to the transaction device to be allocated to obtain new transaction device parameters;
[0071] Calculating the parameter difference between the new transaction device parameters of all the transaction devices to be allocated and the device parameters used to calculate the device task allocation strategy;
[0072] Determine whether the parameter difference is greater than a preset difference threshold, and if not, assign a corresponding transaction execution task to each of the transaction devices to be assigned;
[0073] If so, the new transaction device parameters are used as update data, and the step of inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain the output device task allocation strategy is re-executed to obtain a new device task allocation strategy.
[0074] The third aspect of the present invention discloses another SAC-based transaction device data processing system, the system comprising:
[0075] A memory storing executable program code;
[0076] a processor coupled to the memory;
[0077] The processor calls the executable program code stored in the memory to execute part or all of the steps in the SAC-based transaction device data processing method disclosed in the first aspect of the present invention.
[0078] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the SAC-based transaction device data processing method disclosed in the first aspect of the present invention.
[0079] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0080] The present invention can determine the degree of coordination and cooperation between different devices based on historical data through a neural network model, and then combine the SAC model to predict the device task allocation strategy corresponding to the current trading strategy, so as to assign more reasonable execution tasks to each device, thereby effectively improving the operating efficiency and effect of device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors. BRIEF DESCRIPTION OF THE DRAWINGS
[0081] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.
[0082] Figure 1 It is a flow chart of a transaction device data processing method based on SAC disclosed in an embodiment of the present invention.
[0083] Figure 2 It is a structural schematic diagram of a SAC-based transaction device data processing system disclosed in an embodiment of the present invention.
[0084] Figure 3 It is a structural schematic diagram of another SAC-based transaction device data processing system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0085] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0086] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.
[0087] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0088] The present invention discloses a transaction equipment data processing method and system based on SAC, which can determine the degree of coordination between different devices according to historical data through a neural network model, and then combine the SAC model to predict the device task allocation strategy corresponding to the current transaction strategy, so as to allocate more reasonable execution tasks to each device, thereby effectively improving the operating efficiency and effect of the device execution transaction strategy in a multi-device scenario, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors. The following are detailed descriptions.
[0089] Embodiment 1
[0090] See also Figure 1 , Figure 1 : is a flow chart of a transaction device data processing method based on SAC disclosed in an embodiment of the present invention. Figure 1 The described SAC-based transaction device data processing method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the SAC-based transaction device data processing method may include the following operations:
[0091] 101. Obtain the current trading strategy of the target trading system and the historical data of multiple trading devices in the target trading system.
[0092] 102. Based on the neural network prediction model and historical data, determine the coordination parameters between any two trading devices.
[0093] 103. Input the current transaction strategy and coordination parameters into the trained SAC model to obtain the output device task allocation strategy.
[0094] 104. According to the device task allocation strategy, a corresponding transaction execution task is allocated to each transaction device.
[0095] It can be seen that the above-mentioned embodiment of the invention can determine the degree of coordination and cooperation between different devices based on historical data through a neural network model, and then combine the SAC model to predict the device task allocation strategy corresponding to the current trading strategy, so as to assign more reasonable execution tasks to each device, thereby effectively improving the operating efficiency and effect of the device execution trading strategy in a multi-device scenario, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0096] As an optional embodiment, in the above steps, the historical data includes historical code execution records, historical transaction records and historical inter-device communication data.
[0097] It can be seen that through the above-mentioned optional embodiments, the content of the historical data of the device is clarified, which can better characterize the task execution characteristics of the device, so as to facilitate the subsequent determination of the coordination parameters between the devices, thereby assisting in improving the efficiency and effectiveness of the device execution transaction strategy in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0098] As an optional embodiment, in the above steps, determining the coordination parameters between any two transaction devices based on the neural network prediction model and historical data includes:
[0099] For any two transaction devices, calculate the proportion of communication data between the two transaction devices in the historical inter-device communication data of the two transaction devices to all communication data;
[0100] Calculating a correlation parameter between the historical transaction records of the two transaction devices;
[0101] Calculating code similarity in historical code execution records of the two transaction devices;
[0102] Inputting the historical data of the two transaction devices into a trained coordination degree prediction neural network to obtain coordination prediction parameters corresponding to the two transaction devices; optionally, the coordination degree prediction neural network is trained by a training data set including historical data of multiple training devices and corresponding annotations of coordination work between devices;
[0103] The coordination parameters between the two transaction devices are calculated based on the data proportion, correlation parameter, code similarity and coordination prediction parameter.
[0104] It can be seen that through the above-mentioned optional embodiments, the coordination parameters between trading devices can be calculated more accurately through the calculation of data proportion, correlation parameters and code similarity and the prediction results of the neural network, so as to facilitate the subsequent prediction of a more reasonable task allocation strategy through the SAC model, thereby assisting in improving the efficiency and effectiveness of device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0105] As an optional embodiment, in the above step, calculating the coordination parameters between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter includes:
[0106] Calculate the first weight proportional to the data proportion;
[0107] Calculating a second weight proportional to the correlation parameter; optionally, the second weight is less than the first weight;
[0108] Calculating a third weight proportional to the code similarity; optionally, the third weight is less than the second weight;
[0109] The product of the first weight, the second weight, the third weight and the collaborative prediction parameter is calculated to obtain the collaborative coordination parameter between the two transaction devices.
[0110] It can be seen that through the above-mentioned optional embodiments, the coordination parameters between trading devices can be calculated more accurately through preset weight rules and product calculations, so that a more reasonable task allocation strategy can be predicted through the SAC model later, thereby assisting in improving the efficiency and effectiveness of device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0111] As an optional embodiment, in the above steps, the current transaction strategy and coordination parameters are input into the trained SAC model to obtain the output device task allocation strategy, including:
[0112] Determine the trading instructions and trading rules corresponding to the current trading strategy;
[0113] Determine the device parameters of each transaction device; optionally, the device parameters include device model, device communication rate, device computing performance, and device current status;
[0114] The transaction instructions, transaction rules, equipment parameters and coordination parameters are input into the trained SAC model to obtain the output device task allocation strategy; optionally, the device task allocation strategy is used to limit the transaction devices that need to perform tasks and the transaction task parameters to be executed by each transaction device; the transaction task parameters include the transaction institution port, the transaction financial product type, the transaction trigger rules and the transaction reference rules between other devices.
[0115] It can be seen that through the above-mentioned optional embodiments, it is possible to determine the transaction instructions, transaction rules and device parameters, and input the determined parameters into the trained SAC model to obtain the output device task allocation strategy, so as to predict a more reasonable task allocation strategy, thereby improving the efficiency and effectiveness of device execution of transaction strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0116] As an optional embodiment, in the above steps, the SAC model includes a strategy network and a value network; the strategy network is used to randomly generate a device task allocation plan based on input transaction instructions, transaction rules, device parameters and coordination parameters, and the value network calculates the value of the device task allocation plan according to a preset state value rule, and when the value meets the preset value function requirements, the device task allocation plan is output as a device task allocation strategy; the SAC model is trained by using a training data set including multiple training transaction task device allocation data and corresponding transaction action annotations, transaction code annotations and transaction result annotations.
[0117] It can be seen that through the above optional embodiments, the structural details and training details of the SAC model are clarified, which can be used to predict a more reasonable task allocation strategy, thereby improving the efficiency and effectiveness of device execution of transaction strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0118] As an optional embodiment, in the above steps, the state value rule is:
[0119] For each trading device in the device task allocation plan, according to the device parameters of the trading device and the preset parameter rules, the execution efficiency and execution cost corresponding to the trading task parameters of the trading device are calculated;
[0120] Calculate the average value of the coordination parameters between the transaction device and all other transaction devices involved in the transaction reference rule of the transaction device to obtain the coordination value;
[0121] Calculate efficiency value proportional to execution efficiency;
[0122] Calculate the cost value which is inversely proportional to the execution cost;
[0123] Calculate the product of the coordination value, efficiency value and cost value to obtain the equipment value of the transaction equipment;
[0124] The average value of the equipment values of all the transaction equipment in the equipment task allocation plan is calculated to obtain the value of the equipment task allocation plan.
[0125] It can be seen that through the above optional embodiments, the calculation details of the state value rules in the SAC algorithm are clarified, which can be used to accurately evaluate the value of the task allocation plan and to predict a more reasonable task allocation strategy, thereby improving the efficiency and effectiveness of device execution of transaction strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0126] As an optional embodiment, in the above steps, assigning a corresponding transaction execution task to each transaction device according to the device task assignment strategy includes:
[0127] Determine a plurality of transaction devices to be allocated corresponding to the device task allocation strategy;
[0128] Send a request to the transaction device to be allocated to obtain new transaction device parameters;
[0129] Calculate the parameter difference between the new transaction device parameters of all transaction devices to be assigned and the device parameters used to calculate the device task assignment strategy;
[0130] Determine whether the parameter difference is greater than a preset difference threshold, and if not, assign a corresponding transaction execution task to each transaction device to be assigned;
[0131] If so, the new transaction device parameters are used as update data, and the step of inputting the current transaction strategy and coordination parameters into the trained SAC model to obtain the output device task allocation strategy is re-executed to obtain the new device task allocation strategy.
[0132] It can be seen that through the above-mentioned optional embodiments, it is possible to judge in advance whether there are major changes in device parameters before task allocation, and to re-predict the allocation strategy when there are changes to avoid the timeliness of the current strategy being too poor, reducing the operating efficiency of the strategy, and improving the efficiency and effectiveness of the device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0133] Embodiment 2
[0134] See also Figure 2 , Figure 2 : is a schematic diagram of a structure of a SAC-based transaction device data processing system disclosed in an embodiment of the present invention. Figure 2 The described SAC-based transaction device data processing system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the SAC-based transaction device data processing system may include:
[0135] The acquisition module 201 is used to acquire the current trading strategy of the target trading system and the historical data of multiple trading devices in the target trading system.
[0136] The determination module 202 is used to determine the coordination parameters between any two transaction devices based on the neural network prediction model and according to historical data.
[0137] The prediction module 203 is used to input the current transaction strategy and coordination parameters into the trained SAC model to obtain the output device task allocation strategy.
[0138] The allocation module 204 is used to allocate a corresponding transaction execution task to each transaction device according to the device task allocation strategy.
[0139] It can be seen that the above-mentioned embodiment of the invention can determine the degree of coordination and cooperation between different devices based on historical data through a neural network model, and then combine the SAC model to predict the device task allocation strategy corresponding to the current trading strategy, so as to assign more reasonable execution tasks to each device, thereby effectively improving the operating efficiency and effect of the device execution trading strategy in a multi-device scenario, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0140] As an optional embodiment, the historical data includes historical code execution records, historical transaction records, and historical inter-device communication data.
[0141] It can be seen that through the above-mentioned optional embodiments, the content of the historical data of the device is clarified, which can better characterize the task execution characteristics of the device, so as to facilitate the subsequent determination of the coordination parameters between the devices, thereby assisting in improving the efficiency and effectiveness of the device execution transaction strategy in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0142] As an optional embodiment, the determination module determines the specific manner of the coordination parameters between any two transaction devices based on the neural network prediction model and historical data, including:
[0143] For any two transaction devices, calculate the proportion of communication data between the two transaction devices in the historical inter-device communication data of the two transaction devices to all communication data;
[0144] Calculating a correlation parameter between the historical transaction records of the two transaction devices;
[0145] Calculating code similarity in historical code execution records of the two transaction devices;
[0146] Inputting the historical data of the two transaction devices into a trained coordination degree prediction neural network to obtain coordination prediction parameters corresponding to the two transaction devices; optionally, the coordination degree prediction neural network is trained by a training data set including historical data of multiple training devices and corresponding annotations of coordination work between devices;
[0147] The coordination parameters between the two transaction devices are calculated based on the data proportion, correlation parameter, code similarity and coordination prediction parameter.
[0148] It can be seen that through the above-mentioned optional embodiments, the coordination parameters between trading devices can be calculated more accurately through the calculation of data proportion, correlation parameters and code similarity and the prediction results of the neural network, so as to facilitate the subsequent prediction of a more reasonable task allocation strategy through the SAC model, thereby assisting in improving the efficiency and effectiveness of device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0149] As an optional embodiment, the specific manner in which the determination module calculates the coordination parameters between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter includes:
[0150] Calculate the first weight proportional to the data proportion;
[0151] Calculating a second weight proportional to the correlation parameter; optionally, the second weight is less than the first weight;
[0152] Calculating a third weight proportional to the code similarity; optionally, the third weight is less than the second weight;
[0153] The product of the first weight, the second weight, the third weight and the collaborative prediction parameter is calculated to obtain the collaborative coordination parameter between the two transaction devices.
[0154] It can be seen that through the above-mentioned optional embodiments, the coordination parameters between trading devices can be calculated more accurately through preset weight rules and product calculations, so that a more reasonable task allocation strategy can be predicted through the SAC model later, thereby assisting in improving the efficiency and effectiveness of device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0155] As an optional embodiment, the prediction module inputs the current transaction strategy and coordination parameters into the trained SAC model to obtain the specific method of outputting the device task allocation strategy, including:
[0156] Determine the trading instructions and trading rules corresponding to the current trading strategy;
[0157] Determine the device parameters of each transaction device; optionally, the device parameters include device model, device communication rate, device computing performance, and device current status;
[0158] The transaction instructions, transaction rules, equipment parameters and coordination parameters are input into the trained SAC model to obtain the output device task allocation strategy; optionally, the device task allocation strategy is used to limit the transaction devices that need to perform tasks and the transaction task parameters to be executed by each transaction device; the transaction task parameters include the transaction institution port, the transaction financial product type, the transaction trigger rules and the transaction reference rules between other devices.
[0159] It can be seen that through the above-mentioned optional embodiments, it is possible to determine the transaction instructions, transaction rules and device parameters, and input the determined parameters into the trained SAC model to obtain the output device task allocation strategy, so as to predict a more reasonable task allocation strategy, thereby improving the efficiency and effectiveness of device execution of transaction strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0160] As an optional embodiment, the SAC model includes a strategy network and a value network; the strategy network is used to randomly generate a device task allocation plan based on input transaction instructions, transaction rules, device parameters and coordination parameters, and the value network calculates the value of the device task allocation plan according to a preset state value rule, and when the value meets the preset value function requirements, the device task allocation plan is output as a device task allocation strategy; the SAC model is trained by using a training data set including multiple training transaction task device allocation data and corresponding transaction action annotations, transaction code annotations and transaction result annotations.
[0161] It can be seen that through the above optional embodiments, the structural details and training details of the SAC model are clarified, which can be used to predict a more reasonable task allocation strategy, thereby improving the efficiency and effectiveness of device execution of transaction strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0162] As an optional embodiment, the state value rule is:
[0163] For each trading device in the device task allocation plan, according to the device parameters of the trading device and the preset parameter rules, the execution efficiency and execution cost corresponding to the trading task parameters of the trading device are calculated;
[0164] Calculate the average value of the coordination parameters between the transaction device and all other transaction devices involved in the transaction reference rule of the transaction device to obtain the coordination value;
[0165] Calculate efficiency value proportional to execution efficiency;
[0166] Calculate the cost value which is inversely proportional to the execution cost;
[0167] Calculate the product of the coordination value, efficiency value and cost value to obtain the equipment value of the transaction equipment;
[0168] The average value of the equipment values of all the transaction equipment in the equipment task allocation plan is calculated to obtain the value of the equipment task allocation plan.
[0169] It can be seen that through the above optional embodiments, the calculation details of the state value rules in the SAC algorithm are clarified, which can be used to accurately evaluate the value of the task allocation plan and to predict a more reasonable task allocation strategy, thereby improving the efficiency and effectiveness of device execution of transaction strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall transaction system, save equipment energy consumption, and reduce errors.
[0170] As an optional embodiment, according to the device task allocation strategy, a corresponding transaction execution task is allocated to each transaction device, including:
[0171] Determine a plurality of transaction devices to be allocated corresponding to the device task allocation strategy;
[0172] Send a request to the transaction device to be allocated to obtain new transaction device parameters;
[0173] Calculate the parameter difference between the new transaction device parameters of all transaction devices to be assigned and the device parameters used to calculate the device task assignment strategy;
[0174] Determine whether the parameter difference is greater than a preset difference threshold, and if not, assign a corresponding transaction execution task to each transaction device to be assigned;
[0175] If so, the new transaction device parameters are used as update data, and the step of inputting the current transaction strategy and coordination parameters into the trained SAC model to obtain the output device task allocation strategy is re-executed to obtain the new device task allocation strategy.
[0176] It can be seen that through the above-mentioned optional embodiments, it is possible to judge in advance whether there are major changes in device parameters before task allocation, and to re-predict the allocation strategy when there are changes to avoid the timeliness of the current strategy being too poor, reducing the operating efficiency of the strategy, and improving the efficiency and effectiveness of the device execution of trading strategies in multi-device scenarios, so as to effectively improve the work efficiency of the overall trading system, save equipment energy consumption, and reduce errors.
[0177] Embodiment 3
[0178] See also Figure 3 , Figure 3 It is another SAC-based transaction device data processing system disclosed in an embodiment of the present invention. Figure 3The described SAC-based transaction device data processing system is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the SAC-based transaction device data processing system may include:
[0179] A memory 301 storing executable program codes;
[0180] a processor 302 coupled to the memory 301;
[0181] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the SAC-based transaction device data processing method described in the first embodiment.
[0182] Embodiment 4
[0183] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the SAC-based transaction device data processing method described in the first embodiment.
[0184] Embodiment 5
[0185] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the SAC-based transaction device data processing method described in the first embodiment.
[0186] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0187] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0188] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0189] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0190] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0191] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0192] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0193] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0194] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0195] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0196] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0197] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0198] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0199] Finally, it should be noted that the SAC-based transaction device data processing method and system disclosed in the embodiment of the present invention only discloses the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A transaction device data processing method based on SAC, characterized in that: The method comprises: Acquire the current trading strategy of the target trading system and the historical data of multiple trading devices in the target trading system; the historical data includes historical code execution records, historical transaction records and historical inter-device communication data; Based on the neural network prediction model and according to the historical data, determining the coordination parameters between any two of the transaction devices includes: For any two of the transaction devices, calculate the proportion of the communication data between the two transaction devices in the historical inter-device communication data of the two transaction devices to all the communication data; Calculating a correlation parameter between the historical transaction records of the two transaction devices; Calculating the code similarity in the historical code execution records of the two transaction devices; Inputting the historical data of the two transaction devices into a trained coordination degree prediction neural network to obtain coordination prediction parameters corresponding to the two transaction devices; the coordination degree prediction neural network is trained by a training data set including historical data of a plurality of training devices and corresponding annotations of coordination work between devices; Calculating the coordination parameter between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter; Inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain an output device task allocation strategy; According to the device task allocation strategy, a corresponding transaction execution task is allocated to each of the transaction devices.
2. The SAC-based transaction device data processing method according to claim 1, characterized in that: The calculating the coordination parameter between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter includes: Calculating a first weight proportional to the proportion of the data; Calculating a second weight proportional to the association parameter; the second weight is less than the first weight; Calculating a third weight proportional to the code similarity; the third weight is less than the second weight; The product of the first weight, the second weight, the third weight and the collaborative prediction parameter is calculated to obtain the collaborative coordination parameter between the two transaction devices.
3. The SAC-based transaction device data processing method according to claim 2, characterized in that: The step of inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain an output device task allocation strategy includes: Determine the trading instructions and trading rules corresponding to the current trading strategy; Determine the device parameters of each of the transaction devices; the device parameters include device model, device communication rate, device computing performance and device current status; The transaction instructions, the transaction rules, the device parameters and the coordination parameters are input into the trained SAC model to obtain the output device task allocation strategy; the device task allocation strategy is used to limit the transaction devices that need to perform tasks and the transaction task parameters to be performed by each transaction device; the transaction task parameters include the transaction institution port, the transaction financial product type, the transaction trigger rules and the transaction reference rules between other devices.
4. The SAC-based transaction device data processing method according to claim 3, characterized in that: The SAC model includes a strategy network and a value network; the strategy network is used to randomly generate an equipment task allocation plan based on the input transaction instructions, the transaction rules, the equipment parameters and the coordination parameters; the value network calculates the value of the equipment task allocation plan according to a preset state value rule, and when the value meets the preset value function requirements, the equipment task allocation plan is output as an equipment task allocation strategy; the SAC model is trained by using a training data set including multiple training transaction task equipment allocation data and corresponding transaction action annotations, transaction code annotations and transaction result annotations.
5. The SAC-based transaction device data processing method according to claim 4, characterized in that: The state value rules are: For each transaction device in the device task allocation scheme, according to the device parameters of the transaction device and the preset parameter rules, the execution efficiency and execution cost corresponding to the transaction task parameters of the transaction device are calculated; Calculating an average value of the coordination parameters between the transaction device and all other transaction devices involved in the transaction reference rule of the transaction device to obtain a coordination value; calculating an efficiency value proportional to the execution efficiency; calculating a cost value inversely proportional to said execution cost; Calculate the product of the coordination value, the efficiency value and the cost value to obtain the equipment value of the transaction equipment; The average value of the equipment values of all the transaction equipment in the equipment task allocation plan is calculated to obtain the value of the equipment task allocation plan.
6. The SAC-based transaction device data processing method according to claim 3, characterized in that: The step of allocating a corresponding transaction execution task to each of the transaction devices according to the device task allocation strategy includes: Determine a plurality of transaction devices to be allocated corresponding to the device task allocation strategy; Sending a request to the transaction device to be allocated to obtain new transaction device parameters; Calculating the parameter difference between the new transaction device parameters of all the transaction devices to be allocated and the device parameters used to calculate the device task allocation strategy; Determine whether the parameter difference is greater than a preset difference threshold, and if not, assign a corresponding transaction execution task to each of the transaction devices to be assigned; If so, the new transaction device parameters are used as update data, and the step of inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain the output device task allocation strategy is re-executed to obtain a new device task allocation strategy.
7. A transaction equipment data processing system based on SAC, characterized in that: The system comprises: An acquisition module, used to acquire the current trading strategy of the target trading system and the historical data of multiple trading devices in the target trading system; the historical data includes historical code execution records, historical transaction records and historical inter-device communication data; A determination module, used to determine the coordination parameters between any two of the transaction devices based on the neural network prediction model and the historical data, including: For any two of the transaction devices, calculate the proportion of the communication data between the two transaction devices in the historical inter-device communication data of the two transaction devices to all the communication data; Calculating a correlation parameter between the historical transaction records of the two transaction devices; Calculating the code similarity in the historical code execution records of the two transaction devices; Inputting the historical data of the two transaction devices into a trained coordination degree prediction neural network to obtain coordination prediction parameters corresponding to the two transaction devices; the coordination degree prediction neural network is trained by a training data set including historical data of a plurality of training devices and corresponding annotations of coordination work between devices; Calculating the coordination parameter between the two transaction devices according to the data proportion, the correlation parameter, the code similarity and the coordination prediction parameter; A prediction module, used for inputting the current transaction strategy and the coordination parameters into the trained SAC model to obtain an output device task allocation strategy; The allocation module is used to allocate a corresponding transaction execution task to each of the transaction devices according to the device task allocation strategy.
8. A transaction equipment data processing system based on SAC, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the SAC-based transaction device data processing method as described in any one of claims 1-6.
