SAS-based high-frequency data processing method

Abstract

The invention discloses an SAS-based high-frequency data processing method, which comprises the following steps of: acquiring high-frequency data through an SAS system, preprocessing the acquired high-frequency data, extracting data characteristics in the preprocessed high-frequency data by adopting a statistical analysis function of the SAS system, and displaying the data characteristics corresponding to the high-frequency data to a worker. Data analysis labels input by workers are obtained, a data analysis label corresponding to each piece of high-frequency data is obtained, data relation learning is carried out by adopting a deep learning algorithm according to the data characteristics corresponding to the high-frequency data and the data analysis labels corresponding to the high-frequency data, and a high-frequency data processing model is obtained; and finally, the high-frequency data can be processed according to the high-frequency data processing model, so that the processing efficiency and accuracy of the high-frequency data are effectively improved, and the technical problem caused by manual processing in the prior art is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a method for processing high-frequency data based on SAS. Background Art

[0002] With the rapid development of the financial market, high-frequency data has become an important basis for financial analysis and decision-making. However, the processing and analysis of high-frequency data face challenges such as large data volume, high real-time requirements, and complex features. Traditional data processing methods mainly use manual analysis and processing to handle data, which are difficult to meet the requirements of efficient and accurate analysis. Therefore, how to effectively process and analyze high-frequency data has become an urgent problem to be solved. Summary of the Invention

[0003] The present invention provides a method for processing high-frequency data based on SAS to solve the problems of low efficiency and inaccurate analysis caused by manual data processing in the prior art.

[0004] A method for processing high-frequency data based on SAS includes:

[0005] Collect high-frequency data through the SAS system, and preprocess the collected high-frequency data to obtain the preprocessed high-frequency data; wherein, the data types of the high-frequency data are specified by the staff;

[0006] Use the statistical analysis function of the SAS system to extract the data features in the preprocessed high-frequency data to obtain the data features corresponding to the high-frequency data;

[0007] Display the data features corresponding to the high-frequency data to the staff, and obtain the data analysis labels input by the staff to obtain the data analysis labels corresponding to each high-frequency data;

[0008] According to the data features corresponding to the high-frequency data and the data analysis labels corresponding to the high-frequency data, use a deep learning algorithm to learn the data relationship and obtain a high-frequency data processing model;

[0009] Deploy the high-frequency data processing model in the cloud computing center, and after collecting the data features of real-time high-frequency data through the SAS system, transmit them to the cloud computing center for processing, identify the data analysis labels corresponding to the data features of the real-time high-frequency data, and obtain the high-frequency data processing result.

[0010] Further, it further includes:

[0011] When the high-frequency data processing result meets the preset alarm condition, a data warning message is generated and transmitted to the device designated by the staff.

[0012] Further, high-frequency data is collected through the SAS system, and the collected high-frequency data is preprocessed to obtain the preprocessed high-frequency data, including:

[0013] Based on the data types specified by the staff, high-frequency data is collected through the SAS system;

[0014] The collected high-frequency data is cleaned, denoised, and standardized to obtain the preprocessed high-frequency data.

[0015] Further, according to the data characteristics corresponding to the high-frequency data and the data analysis labels corresponding to the high-frequency data, a deep learning algorithm is used for data relationship learning to obtain a high-frequency data processing model, including:

[0016] A convolutional neural network or a recurrent neural network is constructed to obtain a neural network to be trained;

[0017] Based on the hyperparameters of the neural network to be trained, the population is initialized;

[0018] For each individual in the population, using the data characteristics corresponding to the high-frequency data as the input and the data analysis labels corresponding to the high-frequency data as the expected output, the fitness corresponding to the individual is obtained;

[0019] Determine the individual with the maximum fitness as the optimal individual and the individual with the minimum fitness as the worst individual;

[0020] According to the optimal individual, an adaptive learning strategy is used to select the initial position for each individual to determine the individuals after the initial position selection;

[0021] According to the worst individual, a neighborhood diffusion search strategy is used to perform neighborhood search on each individual after the initial position selection to obtain the individuals after the neighborhood search;

[0022] A position influence search strategy is used to perform adaptive information interaction on each individual after the neighborhood search to obtain the individuals after the adaptive information interaction;

[0023] A position mutation search strategy is used to perform global mutation search on each individual after the adaptive information interaction to obtain the individuals after the global mutation search;

[0024] When the individuals after the global mutation search or the current number of training times meet the training end condition, the optimal individual is re-determined, and the parameters in the optimal individual are used as the final parameters of the neural network to be trained to obtain the high-frequency data processing model.

[0025] Further, using the data characteristics corresponding to the high-frequency data as the input and the data analysis labels corresponding to the high-frequency data as the expected output, the fitness corresponding to the individual is obtained, including:

[0026] After applying the parameters included in the individual to the neural network to be trained, using the data features corresponding to the high-frequency data as the input, obtain the actual output in the neural network to be trained;

[0027] Using the data analysis label corresponding to the high-frequency data as the expected output, and according to the expected output and the actual output, obtain the loss function value corresponding to the individual;

[0028] Take the negative of the loss function value corresponding to the individual to obtain the fitness corresponding to the individual.

[0029] Furthermore, according to the optimal individual, adopt an adaptive learning strategy to select the initial position for each individual, and determine the individual after the initial position selection, including:

[0030]

[0031] Among them, represents the i-th individual in the t-th training process, i = 1, 2, …, N, and N represents the total number of individuals in the population, represents the individual after the initial position selection represents the optimal individual, c 1 represents the first learning factor, c 2 represents the second learning factor, r 1 represents the first random number between (0, 1), r 2 represents the second random number between (0, 1), represents the k-th individual in the t-th training process.

[0032] Furthermore, according to the worst individual, adopt a neighborhood diffusion search strategy to perform neighborhood search on each individual after the initial position selection, and obtain the individual after the neighborhood search, including:

[0033]

[0034] Among them, represents the m-th individual after the initial position selection in the t-th training process, represents the m-th individual after the initial position selection in the (t - 1)-th training process, represents the individual after the neighborhood search β 1 represents the reverse search coefficient located in the middle of (0, 1), β 2 represents the position memory coefficient between (0, 0.2), r 3 represents the third random number between (0, 1), represents the worst individual.

[0035] Furthermore, the position influence search strategy is used to perform adaptive information interaction on each individual after the neighborhood search, and the individuals after the adaptive information interaction are obtained, including:

[0036]

[0037] in, represents the individual after the nth neighborhood search during the tth training process The d-th dimension parameter, d = 1, 2, ..., D, D represents the total dimension of the parameter, represents the d-th dimension parameter of the individual after the n-th adaptive information interaction, r 4 Represents the fourth random number between (0,1), r 5 represents the fifth random number between (0,1), Represents the individual after the nth neighborhood search Randomly matched other individuals The d-th dimension parameter, T represents the preset maximum number of training times, γ nc Represents an individual With other individuals The position between the parameters, dist nc Represents an individual With other individuals The Euclidean distance between nmax Represents an individual The maximum Euclidean distance to all other individuals, dist nmin Represents an individual Minimum Euclidean distance to all other individuals.

[0038] Furthermore, a positional variation search strategy is used to perform a global variation search on each individual after adaptive information interaction, and the individuals after the global variation search are obtained, including:

[0039]

[0040] in, represents the individual after the sth adaptive information interaction during the tth training process, Represents the individual after global mutation search Levy represents the random Levy flight factor, α represents the position variation search control factor, Indicates that except for individual Random individuals other than represents a newly generated random individual, e represents a natural constant, π represents the circumference of a circle, and r 6 represents the sixth random number between (0,1), sin represents the sine function, and T represents the preset maximum number of training times.

[0041] Further, after deploying the high-frequency data processing model in the cloud computing center and collecting the data features of real-time high-frequency data through the SAS system, the data features are transmitted to the cloud computing center for processing to identify the data analysis tags corresponding to the data features of the real-time high-frequency data, and the high-frequency data processing result is obtained, including:

[0042] Deploy the high-frequency data processing model in the cloud computing center;

[0043] Collect real-time high-frequency data through the SAS system and extract the data features of the real-time high-frequency data through the SAS system;

[0044] Transmit the data features of the real-time high-frequency data to the cloud computing center, and the cloud computing center schedules the deployed high-frequency data processing model to identify the received data features to obtain the output of the high-frequency data processing model;

[0045] Determine the high-frequency data processing result according to the output of the high-frequency data processing model.

[0046] A method for processing high-frequency data based on SAS provided by the present invention collects high-frequency data through the SAS system, preprocesses the collected high-frequency data, then uses the statistical analysis function of the SAS system to extract the data features in the preprocessed high-frequency data, displays the data features corresponding to the high-frequency data to the staff, and obtains the data analysis tags input by the staff to obtain the data analysis tags corresponding to each high-frequency data. According to the data features corresponding to the high-frequency data and the data analysis tags corresponding to the high-frequency data, a deep learning algorithm is used to learn the data relationship to obtain a high-frequency data processing model. Finally, the high-frequency data can be processed based on the high-frequency data processing model, effectively improving the processing efficiency and accuracy of the high-frequency data, and solving the technical problems caused by manual processing in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0048] Figure 1 It is a flowchart of a method for processing high-frequency data based on SAS provided by an embodiment of the present invention.

[0049] Through the above accompanying drawings, specific embodiments of the present invention have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the inventive concept in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0051] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0052] As Figure 1 shown, an SAS-based high-frequency data processing method provided by an embodiment of the present invention includes:

[0053] S1. Collect high-frequency data through an SAS (Statistics Analysis System) system, and preprocess the collected high-frequency data to obtain preprocessed high-frequency data; wherein, the data types of the high-frequency data are specified by the staff;

[0054] The purpose of preprocessing the collected high-frequency data is to make the data more regular and easier to be recognized. Therefore, various existing technologies can be used to preprocess the collected high-frequency data to improve the recognizability and regularity of the data. The data types of the high-frequency data are specified by the staff, which can assist the staff in realizing self-defined high-frequency data processing tasks, thereby improving the processing efficiency and accuracy of the high-frequency data.

[0055] S2. Use the statistical analysis function of the SAS system to extract the data features in the preprocessed high-frequency data to obtain the data features corresponding to the high-frequency data;

[0056] The statistical analysis function of the SAS system can extract the data features in the high-frequency data, making the data easier to be recognized, thereby improving the data recognition effect.

[0057] S3. Display the data features corresponding to the high-frequency data to the staff, and obtain the data analysis labels input by the staff to obtain the data analysis labels corresponding to each high-frequency data;

[0058] The data types of the high-frequency data are specified by the staff (for example, the staff can determine various market high-frequency data, or the high-frequency operation data corresponding to a certain device). After determining the data features, the high-frequency data and the corresponding data features can be displayed to the staff. The staff only needs to process the data once at the beginning (i.e., the high-frequency data), and then automated processing can be realized, improving the processing efficiency of the staff for the high-frequency data and reducing the misprocessing caused by manual processing.

[0059] S4. Based on the data characteristics corresponding to the high-frequency data and the data analysis labels corresponding to the high-frequency data, use a deep learning algorithm to perform data relationship learning to obtain a high-frequency data processing model;

[0060] The deep learning algorithm has the ability to learn data relationships. After performing data relationship learning through the deep learning algorithm, a high-frequency data processing model with data processing capabilities can be obtained. This high-frequency data processing model can complete the data recognition tasks specified by the staff (i.e., the recognition tasks between high-frequency data and data analysis labels).

[0061] S5. Deploy the high-frequency data processing model in the cloud computing center, and after collecting the data characteristics of real-time high-frequency data through the SAS system, transmit them to the cloud computing center for processing, identify the data analysis labels corresponding to the data characteristics of the real-time high-frequency data, and obtain the high-frequency data processing result.

[0062] Deploying the high-frequency data processing model in the cloud computing center can utilize the powerful computing power of the cloud computing center to achieve rapid data recognition, and at the same time cooperate with the SAS system to assist workers in improving data recognition efficiency.

[0063] In the embodiment of the present invention, it further includes:

[0064] When the high-frequency data processing result meets the preset alarm condition, a data warning message is generated and the data warning message is transmitted to the device specified by the staff.

[0065] The high-frequency data processing result refers to a data classification label. Therefore, the preset alarm condition can be set as a specific data classification label (set by the staff according to the actual situation). When the data classification label corresponding to the identified real-time high-frequency data is the same as any label in the preset alarm condition, a data warning message can be generated.

[0066] In the embodiment of the present invention, high-frequency data is collected through the SAS system, and the collected high-frequency data is preprocessed to obtain the preprocessed high-frequency data, including:

[0067] Based on the data types specified by the staff, collect high-frequency data through the SAS system;

[0068] Clean the collected high-frequency data (such as removing missing values), denoise (such as removing outliers), and perform standardization processing (such as numerical processing and normalization processing) to obtain the preprocessed high-frequency data.

[0069] In the embodiment of the present invention, based on the data characteristics corresponding to the high-frequency data and the data analysis labels corresponding to the high-frequency data, use a deep learning algorithm to perform data relationship learning to obtain a high-frequency data processing model, including:

[0070] Construct a convolutional neural network or a recurrent neural network to obtain a neural network to be trained. It should be noted that the above neural network is only a preferred example of the embodiments of the present invention, and other neural networks can also be used as the neural network to be trained. When different neural networks are selected, the data features need to be processed into corresponding input forms.

[0071] Based on the hyperparameters of the neural network to be trained, initialize the population. For example, the data can be initialized by using a random initialization method, so as to obtain a population. Each individual in the population includes all the hyperparameters to be trained of the neural network to be trained. The hyperparameters to be trained can be all or part of the hyperparameters of the neural network to be trained.

[0072] For each individual in the population, use the data features corresponding to the high-frequency data as the input and the data analysis label corresponding to the high-frequency data as the expected output to obtain the fitness corresponding to the individual.

[0073] Determine the individual with the maximum fitness as the optimal individual and the individual with the minimum fitness as the worst individual.

[0074] According to the optimal individual, use an adaptive learning strategy to select the initial position for each individual to determine the individual after the initial position selection.

[0075] According to the worst individual, use a neighborhood diffusion search strategy to perform neighborhood search on each individual after the initial position selection to obtain the individual after the neighborhood search.

[0076] Use a position influence search strategy to perform adaptive information interaction on each individual after the neighborhood search to obtain the individual after the adaptive information interaction.

[0077] Use a position mutation search strategy to perform global mutation search on each individual after the adaptive information interaction to obtain the individual after the global mutation search.

[0078] When the individual after the global mutation search or the current number of training times meets the training end condition (for example, according to the individual after the global mutation search, re-determine the optimal individual. When the fitness of the optimal individual converges, the training end condition is met; or when the current number of training times is greater than or equal to the preset maximum number of training times, the training end condition is met), re-determine the optimal individual, and use the parameters in the optimal individual as the final parameters of the neural network to be trained to obtain a high-frequency data processing model.

[0079] Optionally, out-of-bounds processing can also be performed on the individual after each search to ensure data validity.

[0080] When learning data relationships in the prior art, there are often problems with poor learning effects of data relationships, resulting in the inability to accurately complete the data processing tasks specified by the staff. Therefore, the embodiments of the present invention provide a deep learning algorithm to improve the accuracy of data processing and ultimately improve the accuracy of completing the data processing tasks specified by the staff.

[0081] In the embodiments of the present invention, taking the data features corresponding to high-frequency data as the input and the data analysis labels corresponding to high-frequency data as the expected output, obtaining the fitness corresponding to an individual includes:

[0082] After applying the parameters included in the individual to the neural network to be trained, taking the data features corresponding to high-frequency data as the input, and obtaining the actual output in the neural network to be trained;

[0083] Taking the data analysis labels corresponding to high-frequency data as the expected output, and obtaining the loss function value corresponding to the individual according to the expected output and the actual output;

[0084] Taking the negative value of the loss function value corresponding to the individual to obtain the fitness corresponding to the individual.

[0085] In the embodiments of the present invention, according to the optimal individual, an adaptive learning strategy is adopted to select the initial position for each individual, and the individual after the initial position selection is determined, including:

[0086]

[0087] Wherein, represents the i-th individual in the t-th training process, i = 1, 2,..., N, and N represents the total number of individuals in the population, represents the individual after the initial position selection represents the optimal individual, c 1 represents the first learning factor, c 2 represents the second learning factor, r 1 represents the first random number between (0, 1), r 2 represents the second random number between (0, 1), represents the k-th individual in the t-th training process.

[0088] The adaptive learning strategy provided by the embodiments of the present invention enables the individual to learn the information of the optimal individual, enables the algorithm to always search for the optimum, ensures the speed of the algorithm, and at the same time conducts information interaction with other individuals, enabling the individuals farther away from the population to have a larger search step size, which not only helps to improve the speed of the algorithm but also helps to improve the ability to jump out of the local optimum.

[0089] In the embodiment of the present invention, according to the worst individual, a neighborhood diffusion search strategy is adopted to perform neighborhood search on the individuals after each initial position selection, and the individuals after neighborhood search are obtained, including:

[0090]

[0091] Among them, represents the individual after the m-th initial position selection in the t-th training process, represents the individual after the m-th initial position selection in the (t - 1)-th training process, represents the individual after neighborhood search β 1 represents the reverse search coefficient located between (0, 1), β 2 represents the position memory coefficient between (0, 0.2), r 3 represents the third random number between (0, 1), represents the worst individual.

[0092] The neighborhood diffusion search strategy provided by the embodiment of the present invention enables the individual to remember the historical position for neighborhood search, and at the same time, takes the worst individual as a reference for reverse search, improving the search ability of the algorithm for local areas.

[0093] In the embodiment of the present invention, a position influence search strategy is adopted to perform adaptive information interaction on each individual after neighborhood search, and the individuals after adaptive information interaction are obtained, including:

[0094]

[0095] Among them, represents the d-th dimension parameter of the n-th individual after neighborhood search in the t-th training process, d = 1, 2,..., D, where D represents the total dimension of the parameters, represents the d-th dimension parameter of the n-th individual after adaptive information interaction, r represents the fourth random number between (0, 1), r 4 represents the fifth random number between (0, 1), 5 represents the d-th dimension parameter of the other individual randomly matched with the n-th individual after neighborhood search T represents the preset maximum number of training times, γ represents the position influence parameter between the individual nc and the other individual dist represents the Euclidean distance between the individual nc and the other individual dist represents the Euclidean distance between the individual nmaxRepresents an individual The maximum Euclidean distance dist between this individual and all other individuals nmin Represents an individual The minimum Euclidean distance between this individual and all other individuals.

[0096] The position influence search strategy provided by the embodiments of the present invention can adjust the search step size according to the distance between two individuals. For the middle and early stages of the algorithm, it can not only improve the search speed of the algorithm, but also enhance the ability to jump out of the local optimum to a certain extent. In the later stage of the algorithm, the search accuracy gradually increases, ensuring the convergence of the algorithm.

[0097] In the embodiments of the present invention, a position mutation search strategy is adopted to perform global mutation search on each individual after adaptive information interaction, and the individual after global mutation search is obtained, including:[[]]

[0098]

[0099] Among them, Represents the s-th individual after adaptive information interaction in the t-th training process, Represents the individual after global mutation search Levy represents the random Levy flight factor, and α represents the position mutation search control factor, Represents a random individual other than the individual Represents the newly generated random individual, e represents the natural constant, π represents the pi, r 6 Represents the sixth random number between (0, 1), sin represents the sine function, and T represents the preset maximum number of training times.

[0100] The position mutation search strategy provided by the embodiments of the present invention can effectively provide the global search ability of the algorithm, and is provided with a position mutation search control factor. It provides a strong global search ability in the middle and early stages of the algorithm, and quickly reduces the global search ability in the later stage of the algorithm, ensuring the convergence of the algorithm.

[0101] The training algorithm provided by the embodiments of the present invention can effectively improve the learning ability of the algorithm for data, so as to more accurately and efficiently complete the data processing tasks specified by the staff.

[0102] In the embodiments of the present invention, after deploying the high-frequency data processing model in the cloud computing center and collecting the data characteristics of real-time high-frequency data through the SAS system, the data characteristics are transmitted to the cloud computing center for processing, and the data analysis labels corresponding to the data characteristics of the real-time high-frequency data are identified to obtain the high-frequency data processing result, including:[[]]

[0103] Deploy the high-frequency data processing model in the cloud computing center;

[0104] ​Collect real-time high-frequency data through the SAS system, and extract the data features of the real-time high-frequency data through the SAS system;

[0105] Transmit the data features of the real-time high-frequency data to the cloud computing center, and the cloud computing center schedules the deployed high-frequency data processing model to identify the received data features and obtain the output of the high-frequency data processing model;

[0106] Determine the high-frequency data processing result according to the output of the high-frequency data processing model, that is, the category with the highest probability is the high-frequency data processing result.

[0107] A method for processing high-frequency data based on SAS provided by the present invention collects high-frequency data through the SAS system, preprocesses the collected high-frequency data, then uses the statistical analysis function of the SAS system to extract the data features in the preprocessed high-frequency data, displays the data features corresponding to the high-frequency data to the staff, and obtains the data analysis labels input by the staff to get the data analysis labels corresponding to each high-frequency data. According to the data features corresponding to the high-frequency data and the data analysis labels corresponding to the high-frequency data, a deep learning algorithm is used to learn the data relationship to obtain a high-frequency data processing model. Finally, the high-frequency data can be processed based on the high-frequency data processing model, effectively improving the processing efficiency and accuracy of high-frequency data, and solving the technical problems caused by manual processing in the prior art.

[0108] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present invention. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed by the present invention. It should be understood that the present invention is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A high-frequency data processing method based on SAS, characterized in that: include: The high-frequency data is collected through the SAS system, and the collected high-frequency data is preprocessed to obtain the high-frequency data after preprocessing; wherein the data type of the high-frequency data is specified by the staff; The statistical analysis function of the SAS system is used to extract the data features of the high-frequency data after preprocessing, and obtain the data features corresponding to the high-frequency data; Display the data features corresponding to the high-frequency data to the staff, obtain the data analysis labels input by the staff, and obtain the data analysis labels corresponding to each high-frequency data; According to the data features and data analysis labels corresponding to high-frequency data, a deep learning algorithm is used to learn data relationships and obtain a high-frequency data processing model. The high-frequency data processing model is deployed in the cloud computing center. After the data features of real-time high-frequency data are collected through the SAS system, they are transmitted to the cloud computing center for processing, the data analysis labels corresponding to the data features of the real-time high-frequency data are identified, and the high-frequency data processing results are obtained.

2. The high-frequency data processing method based on SAS according to claim 1, characterized in that: Also includes: When the high-frequency data processing result meets the preset alarm condition, data warning information is generated and transmitted to the equipment designated by the staff.

3. The high-frequency data processing method based on SAS according to claim 1, characterized in that: The high-frequency data is collected through the SAS system, and the collected high-frequency data is preprocessed to obtain the high-frequency data after preprocessing, including: Based on the data types specified by the staff, high-frequency data is collected through the SAS system; The collected high-frequency data is cleaned, denoised and standardized to obtain the pre-processed high-frequency data.

4. The high-frequency data processing method based on SAS according to claim 1, characterized in that: According to the data features and data analysis labels corresponding to high-frequency data, a deep learning algorithm is used to learn data relationships and obtain a high-frequency data processing model, including: Construct a convolutional neural network or a recurrent neural network to obtain the neural network to be trained; Initializing a population based on the hyperparameters of the neural network to be trained; For each individual in the population, the data features corresponding to the high-frequency data are used as input, and the data analysis labels corresponding to the high-frequency data are used as the expected output to obtain the fitness of the individual. Determine the individual with the largest fitness as the best individual and the individual with the smallest fitness as the worst individual; According to the optimal individual, an adaptive learning strategy is used to select the initial position of each individual, and the individual after the initial position selection is determined; According to the worst individual, a neighborhood scattering search strategy is used to perform neighborhood search on each individual after the initial position selection to obtain the individual after the neighborhood search; Adopting the position influence search strategy, adaptive information interaction is performed on each individual after neighborhood search to obtain the individual after adaptive information interaction; The position variation search strategy is used to perform global variation search on each individual after adaptive information interaction to obtain the individual after global variation search; When the individual after the global variation search or the current number of training times meets the training end condition, the optimal individual is re-determined, and the parameters in the optimal individual are used as the final parameters of the neural network to be trained to obtain a high-frequency data processing model.

5. The high-frequency data processing method based on SAS according to claim 4, characterized in that: The data features corresponding to the high-frequency data are used as input, and the data analysis labels corresponding to the high-frequency data are used as the expected output to obtain the fitness of the individual, including: After applying the parameters contained in the individual to the neural network to be trained, the data features corresponding to the high-frequency data are used as input to obtain the actual output of the neural network to be trained; The data analysis label corresponding to the high-frequency data is used as the expected output, and the loss function value corresponding to the individual is obtained according to the expected output and the actual output; The loss function value corresponding to the individual is taken as the negative number to obtain the fitness corresponding to the individual.

6. The high-frequency data processing method based on SAS according to claim 5, characterized in that: According to the optimal individual, an adaptive learning strategy is used to select the initial position of each individual, and the individual after the initial position selection is determined, including: in, represents the i-th individual in the t-th training process, i = 1, 2, ..., N, N represents the total number of individuals in the population, Represents the individual after the initial position selection represents the optimal individual, c1 represents the first learning factor, c2 represents the second learning factor, r1 represents the first random number between (0,1), and r2 represents the second random number between (0,1). represents the kth individual in the tth training process.

7. The high-frequency data processing method based on SAS according to claim 6, characterized in that: According to the worst individual, a neighborhood scattering search strategy is used to perform neighborhood search on each individual after the initial position selection, and the individuals after the neighborhood search are obtained, including: in, represents the individual after the mth initial position selection during the tth training process, represents the individual after the mth initial position selection during the t-1th training process, Represents the individual after neighborhood search β1 represents the reverse search coefficient between (0,1), β2 represents the position memory coefficient between (0,0.2), and r3 represents the third random number between (0,1). Indicates the worst individual.

8. The high-frequency data processing method based on SAS according to claim 7, characterized in that: The position influence search strategy is used to perform adaptive information interaction on the individuals after each neighborhood search, and the individuals after adaptive information interaction are obtained, including: in, represents the individual after the nth neighborhood search during the tth training process The d-th dimension parameter, d = 1, 2, ..., D, D represents the total dimension of the parameter, represents the d-th dimension parameter of the individual after the n-th adaptive information interaction, r4 represents the fourth random number between (0,1), r5 represents the fifth random number between (0,1), Represents the individual after the nth neighborhood search Randomly matched other individuals The d-th dimension parameter, T represents the preset maximum number of training times, γ nc Represents an individual With other individuals The position between the parameters, dist nc Represents individual X n t With other individuals The Euclidean distance between nmax Represents an individual The maximum Euclidean distance to all other individuals, dist nmin Represents individual X n t Minimum Euclidean distance to all other individuals.

9. The high-frequency data processing method based on SAS according to claim 8, characterized in that: The position mutation search strategy is used to perform global mutation search on each individual after adaptive information interaction, and the individuals after global mutation search are obtained, including: in, represents the individual after the sth adaptive information interaction during the tth training process, Represents the individual after global mutation search Levy represents the random Levy flight factor, α represents the position variation search control factor, Indicates that except for individual Random individuals other than Represents a newly generated random individual, e represents a natural constant, π represents the ratio of pi, r6 represents the sixth random number between (0,1), sin represents the sine function, and T represents the preset maximum number of training times.

10. The high-frequency data processing method based on SAS according to claim 1, characterized in that: The high-frequency data processing model is deployed in the cloud computing center. After the data features of real-time high-frequency data are collected through the SAS system, they are transmitted to the cloud computing center for processing, the data analysis tags corresponding to the data features of the real-time high-frequency data are identified, and the high-frequency data processing results are obtained, including: Deploy high-frequency data processing models in cloud computing centers; Collect real-time high-frequency data through the SAS system, and extract data features of the real-time high-frequency data through the SAS system; The data features of the real-time high-frequency data are transmitted to the cloud computing center, and the cloud computing center schedules the deployed high-frequency data processing model to identify the received data features and obtain the output of the high-frequency data processing model; A high-frequency data processing result is determined according to the output of the high-frequency data processing model.

Images