Financial market data intelligent monitoring method, system, equipment and medium

Abstract

The invention relates to a data monitoring technology, and discloses a financial market data intelligent monitoring method, which comprises the following steps: carrying out data cleaning on multi-path price source price information of a financial market to obtain preprocessed price information, carrying out same-type data multi-price source comparison on the preprocessed price information to obtain a price difference value set, if a price difference value greater than a difference value threshold value does not exist, information is acquired again, otherwise, early warning information is sent out, latest price verification is performed on the preprocessed price information, if the latest price verification is passed, early warning information is sent out, and if the latest price verification is passed, financial market data is acquired and classified, and after financial market classification data is obtained, features are extracted to obtain financial parameter time domain features; and analyzing a risk coefficient according to the financial parameter time domain characteristics by using a financial market logistic regression model, and judging whether a risk exists or not according to the risk coefficient. The invention further provides a financial market data intelligent monitoring device, electronic equipment and a storage medium. According to the invention, timeliness and accuracy of financial market data monitoring can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data monitoring technology, and in particular to a method, system, device and medium for intelligent monitoring of financial market data. Background Art

[0002] In the current financial market environment, the security and stability of data are crucial to the operation of financial institutions. With the rapid development of financial markets and the sharp increase in trading volume, the monitoring of financial market data has become an indispensable part of financial institutions.

[0003] At present, the traditional financial market data monitoring method mainly relies on manual review and simple rule matching, and does not monitor the timeliness, accuracy, completeness and other data characteristics of the data. When the data quality is abnormal, it cannot be discovered in the first time, and the data monitoring function with added monitoring is relatively simple and cannot be reused. If a large amount of data is connected, more manpower is required to complete different types of monitoring. In addition, when the season switches or the data publisher switches, the monitoring rules need to be manually adjusted (for example, when the summer time switches to the winter time, the opening time of the European and American markets is delayed, so the data release time will also be delayed, and the start time of monitoring needs to be adjusted). If the adjustment is not timely, there will be many false alarms, resulting in the monitoring not being able to generate real value. As a result, the existing financial market data monitoring methods have low timeliness and low accuracy. Summary of the invention

[0004] The present invention provides a method, system, device and medium for intelligent monitoring of financial market data, the main purpose of which is to solve the problems of low timeliness and low accuracy of existing financial market data monitoring methods.

[0005] To achieve the above purpose, the present invention provides a method for intelligently monitoring financial market data, comprising:

[0006] Acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information;

[0007] Performing a comparison of multiple price sources of the same type of data on the preprocessed price information to obtain a price difference set;

[0008] If there is no price difference greater than the preset difference threshold in the price difference set, returning to the step of acquiring price information from multiple price sources in the financial market in real time;

[0009] If there is a price difference greater than a preset difference threshold in the price difference set, a warning message is issued;

[0010] Performing latest price verification on the pre-processed price information;

[0011] If the pre-processed price information fails to pass the latest price verification, a warning message is issued;

[0012] If the pre-processed price information passes the latest price verification, financial market data is acquired in real time, and the financial market data is classified according to the time zone to obtain financial market classification data;

[0013] Performing Fourier transformation on the financial market classification data to obtain time domain characteristics of financial parameters;

[0014] A pre-trained financial market logistic regression model is used to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and whether there is risk in the financial market is determined based on the risk coefficient.

[0015] Optionally, performing data conversion processing on the price information of the multiple price sources to obtain conversion data includes:

[0016] Convert the commodity names contained in the price information of the multiple price sources into preset codes to obtain name standardization data;

[0017] The commodity prices included in the name standardization data are converted into U.S. dollar exchange rates to obtain conversion data.

[0018] Optionally, performing missing value processing and outlier processing on the converted data to obtain pre-processed price information includes:

[0019] Traversing the conversion data, and identifying null price values ​​in the conversion data;

[0020] Calculate the average price of the same type of commodities with the empty price value, and use the average price to replace the empty price value to obtain filled price data;

[0021] Identifying abnormal price data in the filling price data that is greater than a preset abnormal value threshold;

[0022] The abnormal price data is deleted to obtain pre-processed price information.

[0023] Optionally, the comparing the pre-processed price information with multiple price sources of the same type of data includes:

[0024] Obtain the maximum price and the minimum price of each commodity type in the pre-processed price information;

[0025] Calculate the price difference between the maximum price and the minimum price of each commodity type;

[0026] Integrate the price differences of each commodity type to obtain a price difference set.

[0027] Optionally, performing the latest price verification on the pre-processed price information includes:

[0028] Obtaining the latest price in the preprocessed price information;

[0029] If the latest price does not exceed or is equal to the boundary of the preset normal distribution model or the difference between the latest price and the boundary of the normal distribution model is greater than the preset limit threshold, it is determined that the pre-processed price information passes the latest price check;

[0030] If the latest price exceeds the boundary of the normal distribution model and is less than or equal to a preset limit threshold, it is determined that the preprocessed price information has not passed the latest price verification.

[0031] Optionally, performing Fourier transform on the financial market classification data to obtain the time domain characteristics of financial parameters includes:

[0032] Sampling the financial market classification data at preset time intervals to obtain discretized financial data;

[0033] Performing fast Fourier transform on the discretized financial data to obtain frequency domain information;

[0034] Extracting key features from the frequency domain information to obtain frequency domain features;

[0035] Perform inverse Fourier transform on the frequency domain features to obtain time domain features.

[0036] Optionally, the using of a pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient includes:

[0037] Normalizing the time series characteristics of the financial parameters to obtain normalized time series characteristics;

[0038] Calculating a linear output value based on the normalized time series characteristics using the financial market logistic regression model;

[0039] The risk coefficient is calculated according to the linear output value using the activation function preset in the financial market logistic regression model.

[0040] In order to solve the above problems, the present invention further provides a financial market data intelligent monitoring device, the device comprising:

[0041] A data acquisition module is used to acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information;

[0042] A price comparison module, for comparing the pre-processed price information with multiple price sources of the same type of data to obtain a price difference set, and if there is no price difference greater than a preset difference threshold in the price difference set, returning to the step of obtaining the price information of multiple price sources in the financial market in real time, and if there is a price difference greater than a preset difference threshold in the price difference set, issuing a warning message;

[0043] A price verification module performs a latest price verification on the pre-processed price information, and issues a warning message if the pre-processed price information fails the latest price verification;

[0044] A feature extraction module, if the pre-processed price information passes the latest price verification, acquires financial market data in real time, classifies the financial market data according to time zones to obtain financial market classification data, performs Fourier transformation on the financial market classification data to obtain time domain features of financial parameters;

[0045] The risk analysis module uses a pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and determines whether there is risk in the financial market based on the risk coefficient.

[0046] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0047] at least one processor;

[0048] and, a memory communicatively coupled to the at least one processor;

[0049] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned method for intelligent monitoring of financial market data.

[0050] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned financial market data intelligent monitoring method.

[0051] The embodiment of the present invention obtains price information from multiple price sources in the financial market in real time, performs data conversion processing on the price information from multiple price sources to obtain converted data, performs missing value processing and abnormal value processing on the converted data to obtain pre-processed price information, performs multi-price source comparison of the same type of data on the pre-processed price information to obtain a price difference set, and if there is no price difference greater than a preset difference threshold in the price difference set, returns to the step of obtaining price information from multiple price sources in the financial market in real time, and if there is a price difference greater than a preset difference threshold in the price difference set, issues a warning message, and performs a warning on the price difference set. The pre-processed price information is subjected to the latest price verification. If the pre-processed price information fails the latest price verification, a warning message is issued. If the pre-processed price information passes the latest price verification, financial market data is acquired in real time, the financial market data is classified according to the time zone, and the financial market classification data is obtained. The financial market classification data is subjected to Fourier transformation to obtain the time domain characteristics of the financial parameters. The pre-trained financial market logistic regression model is used to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain the risk coefficient, and the risk coefficient is used to determine whether there is a risk in the financial market. Therefore, the intelligent monitoring method, device, electronic device and computer-readable storage medium for financial market data proposed in the present invention can solve the problem of low accuracy when making product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of a flow chart of a method for intelligently monitoring financial market data provided by an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of a process for processing missing values ​​and outliers provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of a process for extracting time domain features provided by an embodiment of the present invention;

[0055] Figure 4 A functional module diagram of a financial market data intelligent monitoring device provided by an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of the structure of an electronic device for implementing the method for intelligently monitoring financial market data provided by one embodiment of the present invention.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0059] The embodiment of the present application provides a method for intelligent monitoring of financial market data. The execution subject of the method for intelligent monitoring of financial market data includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for intelligent monitoring of financial market data can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0060] Reference Figure 1 FIG. 1 is a flow chart of a method for intelligently monitoring financial market data provided by an embodiment of the present invention. In this embodiment, the method for intelligently monitoring financial market data includes:

[0061] S1. Acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information;

[0062] In the embodiment of the present invention, the multi-source price information is a set of price information including multiple sources and multiple types of commodities.

[0063] In the embodiment of the present invention, the real-time acquisition of price information from multiple price sources in the financial market is to obtain price information of different types of commodities around the world in real time.

[0064] In an embodiment of the present invention, the data conversion processing of the price information from multiple price sources is to convert the format of the price information from multiple price sources, including converting the commodity names in the price information from multiple price sources into preset numbers, and converting the commodity prices in the price information from multiple price sources into US dollars according to the exchange rate.

[0065] In the embodiment of the present invention, the step of performing data conversion processing on the price information of the multiple price sources to obtain converted data includes:

[0066] Convert the commodity names contained in the price information of the multiple price sources into preset codes to obtain name standardization data;

[0067] The commodity prices included in the name standardization data are converted into U.S. dollar exchange rates to obtain conversion data.

[0068] In detail, converting the product names contained in the multiple price source price information into preset codes means that each product has a preset code. For example, the code of apple may be 001, then all product names of apple in the multiple price source price information are converted into 001.

[0069] In detail, the commodity prices contained in the name standardization data are converted into the US dollar exchange rate to obtain the conversion data, which is converted according to the currency corresponding to the commodity price and the exchange rate with the US dollar.

[0070] In the embodiment of the present invention, refer to Figure 2 As shown, a schematic diagram of a process for processing missing values ​​and outliers is provided in an embodiment of the present invention. The process of processing missing values ​​and outliers on the converted data to obtain preprocessed price information includes:

[0071] S21, traversing the conversion data, and identifying null price values ​​in the conversion data;

[0072] S22, calculating the average price of the same type of commodities with the empty price value, and replacing the empty price value with the average price to obtain filled price data;

[0073] S23, identifying abnormal price data in the filling price data that is greater than a preset abnormal value threshold;

[0074] S24. Deleting the abnormal price data to obtain pre-processed price information.

[0075] In detail, the identifying of empty price values ​​in the conversion data is to identify commodities without price marking or with a price marking of 0.

[0076] In detail, the abnormal price data in the filled price data that is greater than the preset abnormal value threshold is to identify the obviously abnormal commodity price. For example, if the price of a basketball is 999 US dollars, it can be determined that the price is abnormal. The abnormal value threshold can be set according to the multiple of the mean of the commodity price. For example, if the mean price of a basketball is 20 US dollars, the abnormal value threshold of the basketball price can be set to 100 US dollars (five times the mean).

[0077] In an embodiment of the present invention, price information from multiple price sources in the financial market is acquired in real time, data conversion processing is performed on the multiple price source price information to obtain converted data, thereby improving the efficiency of subsequent data processing. Pre-processed price information is obtained by performing missing value processing and outlier processing on the converted data, thereby improving the accuracy of subsequent data analysis.

[0078] S2. Compare the pre-processed price information with multiple price sources of the same type of data to obtain a set of price differences.

[0079] In the embodiment of the present invention, the comparing the pre-processed price information with multiple price sources of the same type of data includes:

[0080] Obtain the maximum price and the minimum price of each commodity type in the pre-processed price information;

[0081] Calculate the price difference between the maximum price and the minimum price of each commodity type;

[0082] Integrate the price differences of each commodity type to obtain a price difference set.

[0083] In an embodiment of the present invention, by comparing the pre-processed price information with multiple price sources of the same type of data, a price difference set is obtained, which improves the efficiency of subsequent determination of whether there is a price difference greater than a preset difference threshold in the price difference set.

[0084] S3, determining whether there is a price difference greater than a preset difference threshold in the price difference set;

[0085] If there is no price difference greater than the preset difference threshold in the price difference set, return to S1, obtain price information from multiple price sources in the financial market in real time, perform data conversion processing on the multiple price source price information to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information.

[0086] If there is a price difference greater than a preset difference threshold in the price difference set, S4 is executed to issue a warning message.

[0087] In the embodiment of the present invention, when there is a price difference greater than a preset difference threshold in the price difference set, it means that the price difference of a certain type of commodity at this time exceeds expectations, and therefore an early warning is required.

[0088] In the embodiment of the present invention, when there is a price difference greater than a preset difference threshold value in the price difference set, the efficiency of monitoring the price data in the financial market is improved by issuing an early warning message.

[0089] S5. Perform the latest price verification on the pre-processed price information.

[0090] In the embodiment of the present invention, since the price information of the multiple price sources is acquired in real time, the pre-processed price information obtained after processing the price information of the multiple price sources is updated in real time.

[0091] In the embodiment of the present invention, the step of performing the latest price verification on the pre-processed price information includes:

[0092] Obtaining the latest price in the preprocessed price information;

[0093] If the latest price does not exceed or is equal to the boundary of the preset normal distribution model or the difference between the latest price and the boundary of the normal distribution model is greater than the preset limit threshold, it is determined that the pre-processed price information passes the latest price check;

[0094] If the latest price exceeds the boundary of the normal distribution model and is less than or equal to a preset limit threshold, it is determined that the preprocessed price information has not passed the latest price verification.

[0095] In detail, the curve of the normal distribution model is determined by the mean and standard deviation of the preprocessed price information. The mean determines the center position of the normal curve, that is, the symmetry axis of the distribution; the standard deviation determines the shape of the normal curve, especially the degree of dispersion or width of the distribution. The larger the standard deviation, the more dispersed the distribution and the flatter the curve; the smaller the standard deviation, the more concentrated the distribution and the steeper the curve.

[0096] In the embodiment of the present invention, when the difference between the latest price and the boundary of the normal distribution model is greater than a preset limit threshold, it may be that an abnormal commodity price and an abnormal exchange rate are caused by an emergency.

[0097] In the embodiment of the present invention, by performing the latest price check on the pre-processed price information, the efficiency of determining whether it is necessary to issue early warning information is improved.

[0098] S6. Determine whether the pre-processed price information passes the latest price verification.

[0099] If the pre-processed price information fails to pass the latest price verification, S4 is executed to issue a warning message.

[0100] In the embodiment of the present invention, when the pre-processed price information fails to pass the latest price verification, it means that the latest price in the pre-processed price information exceeds expectations and there may be an abnormality, so it is necessary to issue an early warning message.

[0101] If the pre-processed price information passes the latest price verification, S7 is executed to obtain financial market data in real time, and the financial market data is classified according to the time zone to obtain financial market classification data.

[0102] In the embodiment of the present invention, the financial market data contains various types of data, including exchange rates, bank interest rates, volatility and other data, and covers financial market data of various countries.

[0103] In the embodiment of the present invention, since different countries have different time zones, the time for releasing financial market data is also different, so the financial market data needs to be classified.

[0104] In the embodiment of the present invention, financial market data is acquired in real time and classified according to time zones to obtain financial market classification data, thereby improving the accuracy of subsequent data analysis.

[0105] S8. Perform Fourier transform on the financial market classification data to obtain time domain characteristics of financial parameters.

[0106] In the embodiment of the present invention, the financial market classification data is a label with a time attribute, and its time information corresponds to the time zone when the data is obtained.

[0107] In the embodiment of the present invention, refer to Figure 3 As shown, a schematic diagram of a process for extracting time domain features is provided in an embodiment of the present invention, wherein the financial market classification data is subjected to Fourier transform to obtain the time domain features of financial parameters, including:

[0108] S31, sampling the financial market classification data at preset time intervals to obtain discretized financial data;

[0109] S32, performing fast Fourier transform on the discretized financial data to obtain frequency domain information;

[0110] S33, extracting key features from the frequency domain information to obtain frequency domain features;

[0111] S34. Perform inverse Fourier transform on the frequency domain features to obtain time domain features.

[0112] In detail, the Fast Fourier Transform is used to calculate the Fourier Transform of discrete signals, which can convert time domain signals into frequency domain representations.

[0113] In detail, the key feature extraction of the frequency domain information includes extracting characteristic data such as frequency peak value and amplitude of the frequency domain information to reflect the periodicity of the frequency domain information.

[0114] In detail, the inverse Fourier transform is the inverse process of Fourier transform, which is used to convert the frequency domain signal back into the time domain signal.

[0115] In the embodiment of the present invention, by performing Fourier transform on the financial market classification data, the time domain characteristics of the financial parameters are obtained, which improves the information expression capability of the time domain characteristics of the financial parameters of Sohu and improves the efficiency of subsequent financial market risk analysis.

[0116] S9. Use a pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and determine whether there is risk in the financial market according to the risk coefficient.

[0117] In the embodiment of the present invention, the financial market logistic regression model is a logistic regression model used to process binary classification problems and can be used to predict the probability of an event occurring, such as whether it will rain tomorrow.

[0118] In the embodiment of the present invention, the financial market logistic regression model is constructed by constructing a linear function to represent the relationship between the independent variable and the dependent variable, and then defining a logistic function (usually a Sigmoid function) to map the output result to between 0 and 1. Then, the hyperparameters of the financial market logistic regression model are optimized by gradient descent and other methods using training data until a preset number of iterations is reached. The training data can be market financial data before and after the financial crisis in history.

[0119] In an embodiment of the present invention, the financial market logistic regression model is a model that takes whether there is a risk of financial crisis as its analysis target. The risk coefficient can reflect the volatility of the financial market at that time, and its value is between 0 and 1. The closer the risk coefficient is to 1, the higher the volatility of the financial market and the greater the probability of a financial crisis.

[0120] In the embodiment of the present invention, the risk analysis of the financial market is performed based on the time domain characteristics of the financial parameters using the pre-trained financial market logistic regression model to obtain the risk coefficient, including:

[0121] Normalizing the time series characteristics of the financial parameters to obtain normalized time series characteristics;

[0122] Calculating a linear output value based on the normalized time series characteristics using the financial market logistic regression model;

[0123] The risk coefficient is calculated according to the linear output value using the activation function preset in the financial market logistic regression model.

[0124] In detail, the normalization processing of the financial parameter time series characteristics is to map the data in the financial parameter time series characteristics to between 0 and 1, unify the scale of the data, and improve the efficiency of data processing.

[0125] In the embodiment of the present invention, judging whether there is a risk in the financial market based on the risk coefficient is performed by judging whether the risk coefficient is greater than a preset risk coefficient threshold. If the risk coefficient is greater than the risk coefficient threshold, it is judged that the current financial market is highly volatile and there is a risk, and an early warning message needs to be issued. Otherwise, it is judged that the current financial market is stable and there is no risk.

[0126] In an embodiment of the present invention, a pre-trained financial market logistic regression model is used to perform risk analysis on the financial market based on the time domain characteristics of the financial parameters to obtain a risk coefficient. Based on the risk coefficient, it is determined whether there is risk in the financial market, thereby improving the efficiency and accuracy of financial market data monitoring.

[0127] like Figure 4 , which is a functional module diagram of a financial market data intelligent monitoring device provided by an embodiment of the present invention.

[0128] The financial market data intelligent monitoring device 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the financial market data intelligent monitoring device 100 may include a data acquisition module 101, a price comparison module 102, a price verification module 103, a feature extraction module 104 and a risk analysis module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0129] In this embodiment, the functions of each module / unit are as follows:

[0130] The data acquisition module 101 is used to acquire the price information of multiple price sources in the financial market in real time, perform data conversion processing on the price information of multiple price sources to obtain converted data, perform missing value processing and abnormal value processing on the converted data to obtain pre-processed price information;

[0131] The price comparison module 102 is used to compare the pre-processed price information with multiple price sources of the same type of data to obtain a price difference set. If there is no price difference greater than a preset difference threshold in the price difference set, the step of obtaining the price information of multiple price sources in the financial market in real time is returned. If there is a price difference greater than a preset difference threshold in the price difference set, a warning message is issued;

[0132] The price verification module 103 performs a latest price verification on the pre-processed price information, and issues a warning message if the pre-processed price information fails the latest price verification;

[0133] The feature extraction module 104 acquires financial market data in real time if the pre-processed price information passes the latest price verification, classifies the financial market data according to time zones to obtain financial market classification data, and performs Fourier transformation on the financial market classification data to obtain time domain features of financial parameters;

[0134] The risk analysis module 105 uses a pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and determines whether there is risk in the financial market according to the risk coefficient.

[0135] The data acquisition module 101 is used to acquire the price information of multiple price sources in the financial market in real time, perform data conversion processing on the price information of multiple price sources to obtain converted data, perform missing value processing and abnormal value processing on the converted data to obtain pre-processed price information;

[0136] In the embodiment of the present invention, the multi-source price information is a set of price information including multiple sources and multiple types of commodities.

[0137] In the embodiment of the present invention, the real-time acquisition of price information from multiple price sources in the financial market is to obtain price information of different types of commodities around the world in real time.

[0138] In an embodiment of the present invention, the data conversion processing of the price information from multiple price sources is to convert the format of the price information from multiple price sources, including converting the commodity names in the price information from multiple price sources into preset numbers, and converting the commodity prices in the price information from multiple price sources into US dollars according to the exchange rate.

[0139] In the embodiment of the present invention, the data acquisition module 101 is specifically used to perform data conversion processing on the price information of the multiple price sources to obtain conversion data, including:

[0140] Convert the commodity names contained in the price information of the multiple price sources into preset codes to obtain name standardization data;

[0141] The commodity prices included in the name standardization data are converted into U.S. dollar exchange rates to obtain conversion data.

[0142] In detail, converting the product names contained in the multiple price source price information into preset codes means that each product has a preset code. For example, the code of apple may be 001, then all product names of apple in the multiple price source price information are converted into 001.

[0143] In detail, the commodity prices contained in the name standardization data are converted into the US dollar exchange rate to obtain the conversion data, which is converted according to the currency corresponding to the commodity price and the exchange rate with the US dollar.

[0144] In the embodiment of the present invention, the data acquisition module 101 is specifically used to process missing values ​​and outliers on the converted data to obtain pre-processed price information, including:

[0145] Traversing the conversion data, and identifying null price values ​​in the conversion data;

[0146] Calculate the average price of the same type of commodities with the empty price value, and use the average price to replace the empty price value to obtain filled price data;

[0147] Identifying abnormal price data in the filling price data that is greater than a preset abnormal value threshold;

[0148] The abnormal price data is deleted to obtain pre-processed price information.

[0149] In detail, the identifying of empty price values ​​in the conversion data is to identify commodities without price marking or with a price marking of 0.

[0150] In detail, the abnormal price data in the filled price data that is greater than the preset abnormal value threshold is to identify the obviously abnormal commodity price. For example, if the price of a basketball is 999 US dollars, it can be determined that the price is abnormal. The abnormal value threshold can be set according to the multiple of the mean of the commodity price. For example, if the mean price of a basketball is 20 US dollars, the abnormal value threshold of the basketball price can be set to 100 US dollars (five times the mean).

[0151] The price comparison module 102 compares the pre-processed price information with multiple price sources of the same type of data to obtain a price difference set. If the price difference set does not contain a price difference greater than a preset difference threshold, the module returns to the step of obtaining real-time price information from multiple price sources in the financial market. If the price difference set contains a price difference greater than a preset difference threshold, a warning message is issued.

[0152] In the embodiment of the present invention, the price comparison module 102 is specifically used to compare multiple price sources of the same type of data on the pre-processed price information, including:

[0153] Obtain the maximum price and the minimum price of each commodity type in the pre-processed price information;

[0154] Calculate the price difference between the maximum price and the minimum price of each commodity type;

[0155] Integrate the price differences of each commodity type to obtain a price difference set.

[0156] In an embodiment of the present invention, by comparing the pre-processed price information with multiple price sources of the same type of data, a price difference set is obtained, which improves the efficiency of subsequent determination of whether there is a price difference greater than a preset difference threshold in the price difference set.

[0157] In the embodiment of the present invention, when there is a price difference greater than a preset difference threshold in the price difference set, it means that the price difference of a certain type of commodity at this time exceeds expectations, and therefore an early warning is required.

[0158] The price verification module 103 is used to perform the latest price verification on the pre-processed price information, and if the pre-processed price information fails the latest price verification, an early warning message is issued.

[0159] In the embodiment of the present invention, since the price information of the multiple price sources is acquired in real time, the pre-processed price information obtained after processing the price information of the multiple price sources is updated in real time.

[0160] In the embodiment of the present invention, the price verification module 103 is specifically used to perform the latest price verification on the pre-processed price information, including:

[0161] Obtaining the latest price in the preprocessed price information;

[0162] If the latest price does not exceed or is equal to the boundary of the preset normal distribution model or the difference between the latest price and the boundary of the normal distribution model is greater than the preset limit threshold, it is determined that the pre-processed price information passes the latest price check;

[0163] If the latest price exceeds the boundary of the normal distribution model and is less than or equal to a preset limit threshold, it is determined that the preprocessed price information has not passed the latest price verification.

[0164] In detail, the curve of the normal distribution model is determined by the mean and standard deviation of the preprocessed price information. The mean determines the center position of the normal curve, that is, the symmetry axis of the distribution; the standard deviation determines the shape of the normal curve, especially the degree of dispersion or width of the distribution. The larger the standard deviation, the more dispersed the distribution and the flatter the curve; the smaller the standard deviation, the more concentrated the distribution and the steeper the curve.

[0165] In the embodiment of the present invention, when the difference between the latest price and the boundary of the normal distribution model is greater than a preset limit threshold, it may be that an abnormal commodity price and an abnormal exchange rate are caused by an emergency.

[0166] In the embodiment of the present invention, when the pre-processed price information fails to pass the latest price verification, it means that the latest price in the pre-processed price information exceeds expectations and there may be an abnormality, so it is necessary to issue an early warning message.

[0167] The feature extraction module 104 is used to determine whether the pre-processed price information passes the latest price verification. If the pre-processed price information passes the latest price verification, financial market data is obtained in real time, the financial market data is classified according to the time zone to obtain financial market classification data, and the financial market classification data is Fourier transformed to obtain the time domain characteristics of financial parameters.

[0168] In the embodiment of the present invention, the financial market data contains various types of data, including exchange rates, bank interest rates, volatility and other data, and covers financial market data of various countries.

[0169] In the embodiment of the present invention, since different countries have different time zones, the time for releasing financial market data is also different, so the financial market data needs to be classified.

[0170] In the embodiment of the present invention, financial market data is acquired in real time and classified according to time zones to obtain financial market classification data, thereby improving the accuracy of subsequent data analysis.

[0171] In the embodiment of the present invention, the financial market classification data is a label with a time attribute, and its time information corresponds to the time zone when the data is obtained.

[0172] In the embodiment of the present invention, the feature extraction module 104 is specifically used to perform Fourier transform on the financial market classification data to obtain the time domain features of financial parameters, including:

[0173] Sampling the financial market classification data at preset time intervals to obtain discretized financial data;

[0174] Performing fast Fourier transform on the discretized financial data to obtain frequency domain information;

[0175] Extracting key features from the frequency domain information to obtain frequency domain features;

[0176] Perform inverse Fourier transform on the frequency domain features to obtain time domain features.

[0177] In detail, the Fast Fourier Transform is used to calculate the Fourier Transform of discrete signals, which can convert time domain signals into frequency domain representations.

[0178] In detail, the key feature extraction of the frequency domain information includes extracting characteristic data such as frequency peak value and amplitude of the frequency domain information to reflect the periodicity of the frequency domain information.

[0179] In detail, the inverse Fourier transform is the inverse process of Fourier transform, which is used to convert the frequency domain signal back into the time domain signal.

[0180] In the embodiment of the present invention, by performing Fourier transform on the financial market classification data, the time domain characteristics of the financial parameters are obtained, which improves the information expression capability of the time domain characteristics of the financial parameters of Sohu and improves the efficiency of subsequent financial market risk analysis.

[0181] The risk analysis module 105 is used to use a pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and determine whether there is risk in the financial market according to the risk coefficient.

[0182] In the embodiment of the present invention, the financial market logistic regression model is a logistic regression model used to process binary classification problems and can be used to predict the probability of an event occurring, such as whether it will rain tomorrow.

[0183] In the embodiment of the present invention, the financial market logistic regression model is constructed by constructing a linear function to represent the relationship between the independent variable and the dependent variable, and then defining a logistic function (usually a Sigmoid function) to map the output result to between 0 and 1. Then, the hyperparameters of the financial market logistic regression model are optimized by gradient descent and other methods using training data until a preset number of iterations is reached. The training data can be market financial data before and after the financial crisis in history.

[0184] In an embodiment of the present invention, the financial market logistic regression model is a model that takes whether there is a risk of financial crisis as its analysis target. The risk coefficient can reflect the volatility of the financial market at that time, and its value is between 0 and 1. The closer the risk coefficient is to 1, the higher the volatility of the financial market and the greater the probability of a financial crisis.

[0185] In the embodiment of the present invention, the risk analysis module 105 is specifically used to use the pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, including:

[0186] Normalizing the time series characteristics of the financial parameters to obtain normalized time series characteristics;

[0187] Calculating a linear output value based on the normalized time series characteristics using the financial market logistic regression model;

[0188] The risk coefficient is calculated according to the linear output value using the activation function preset in the financial market logistic regression model.

[0189] In detail, the normalization processing of the financial parameter time series characteristics is to map the data in the financial parameter time series characteristics to between 0 and 1, unify the scale of the data, and improve the efficiency of data processing.

[0190] In the embodiment of the present invention, judging whether there is a risk in the financial market based on the risk coefficient is performed by judging whether the risk coefficient is greater than a preset risk coefficient threshold. If the risk coefficient is greater than the risk coefficient threshold, it is judged that the current financial market is highly volatile and there is a risk, and an early warning message needs to be issued. Otherwise, it is judged that the current financial market is stable and there is no risk.

[0191] like Figure 5 , which is a schematic diagram of the structure of an electronic device of the financial market data intelligent monitoring method provided by an embodiment of the present invention.

[0192] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a financial market data intelligent monitoring program.

[0193] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules (such as financial market data intelligent monitoring programs, etc.) stored in the memory 11, and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0194] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can be used not only to store application software and various types of data installed in the electronic device, such as the code of the intelligent monitoring program for financial market data, but also to temporarily store data that has been output or is to be output.

[0195] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0196] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in this embodiment, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0197] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0198] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0199] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0200] The financial market data intelligent monitoring program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0201] Acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information;

[0202] Performing a comparison of multiple price sources of the same type of data on the preprocessed price information to obtain a price difference set;

[0203] If there is no price difference greater than the preset difference threshold in the price difference set, returning to the step of acquiring price information from multiple price sources in the financial market in real time;

[0204] If there is a price difference greater than a preset difference threshold in the price difference set, a warning message is issued;

[0205] Performing latest price verification on the pre-processed price information;

[0206] If the pre-processed price information fails to pass the latest price verification, a warning message is issued;

[0207] If the pre-processed price information passes the latest price verification, financial market data is acquired in real time, and the financial market data is classified according to the time zone to obtain financial market classification data;

[0208] Performing Fourier transformation on the financial market classification data to obtain time domain characteristics of financial parameters;

[0209] Use the pre-trained financial market logistic regression model to perform risk analysis on the financial market based on the time domain characteristics of the financial parameters to obtain a risk coefficient, and determine whether there is risk in the financial market based on the risk coefficient

[0210] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0211] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0212] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0213] Acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information;

[0214] Performing a comparison of multiple price sources of the same type of data on the preprocessed price information to obtain a price difference set;

[0215] If there is no price difference greater than the preset difference threshold in the price difference set, returning to the step of acquiring price information from multiple price sources in the financial market in real time;

[0216] If there is a price difference greater than a preset difference threshold in the price difference set, a warning message is issued;

[0217] Performing latest price verification on the pre-processed price information;

[0218] If the pre-processed price information fails to pass the latest price verification, a warning message is issued;

[0219] If the pre-processed price information passes the latest price verification, financial market data is acquired in real time, and the financial market data is classified according to the time zone to obtain financial market classification data;

[0220] Performing Fourier transformation on the financial market classification data to obtain time domain characteristics of financial parameters;

[0221] Use the pre-trained financial market logistic regression model to perform risk analysis on the financial market based on the time domain characteristics of the financial parameters to obtain a risk coefficient, and determine whether there is risk in the financial market based on the risk coefficient

[0222] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0223] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0224] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0225] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0226] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0227] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0228] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0229] Finally, it should be noted that the above embodiments 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 preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for intelligent monitoring of financial market data, characterized in that: The method comprises: Acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information; Performing a comparison of multiple price sources of the same type of data on the preprocessed price information to obtain a price difference set; If there is a price difference greater than a preset difference threshold value in the price difference set, a warning message is issued, and the latest price check is performed on the pre-processed price information; If the pre-processed price information passes the latest price verification, financial market data is acquired in real time, and the financial market data is classified according to the time zone to obtain financial market classification data; Performing Fourier transformation on the financial market classification data to obtain time domain characteristics of financial parameters; A pre-trained financial market logistic regression model is used to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and whether there is risk in the financial market is determined based on the risk coefficient.

2. The method for intelligent monitoring of financial market data according to claim 1, characterized in that: The step of performing data conversion processing on the price information of the multiple price sources to obtain converted data includes: Convert the commodity names contained in the price information of the multiple price sources into preset codes to obtain name standardization data; The commodity prices included in the name standardization data are converted into U.S. dollar exchange rates to obtain conversion data.

3. The method for intelligently monitoring financial market data according to claim 2, characterized in that: The performing missing value processing and outlier processing on the converted data to obtain pre-processed price information includes: Traversing the conversion data, and identifying null price values ​​in the conversion data; Calculate the average price of the same type of commodities with the empty price value, and use the average price to replace the empty price value to obtain filled price data; Identifying abnormal price data in the filling price data that is greater than a preset abnormal value threshold; The abnormal price data is deleted to obtain pre-processed price information.

4. The method for intelligently monitoring financial market data according to claim 3, characterized in that: The comparing the pre-processed price information with multiple price sources of the same type of data includes: Obtain the maximum price and the minimum price of each commodity type in the pre-processed price information; Calculate the price difference between the maximum price and the minimum price of each commodity type; Integrate the price differences of each commodity type to obtain a price difference set.

5. The method for intelligently monitoring financial market data according to claim 4, characterized in that: The performing the latest price verification on the pre-processed price information includes: Obtaining the latest price in the preprocessed price information; If the latest price does not exceed or is equal to the boundary of the preset normal distribution model or the difference between the latest price and the boundary of the normal distribution model is greater than the preset limit threshold, it is determined that the pre-processed price information passes the latest price check; If the latest price exceeds the boundary of the normal distribution model and is less than or equal to a preset limit threshold, it is determined that the pre-processed price information has not passed the latest price verification.

6. The method for intelligently monitoring financial market data according to claim 5, characterized in that: The Fourier transform of the financial market classification data is performed to obtain the time domain characteristics of financial parameters, including: Sampling the financial market classification data at preset time intervals to obtain discretized financial data; Performing fast Fourier transform on the discretized financial data to obtain frequency domain information; Extracting key features from the frequency domain information to obtain frequency domain features; Perform inverse Fourier transform on the frequency domain features to obtain time domain features.

7. The method for intelligently monitoring financial market data according to claim 6, characterized in that: The method of using the pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain the risk coefficient includes: Normalizing the time series characteristics of the financial parameters to obtain normalized time series characteristics; Calculating a linear output value based on the normalized time series characteristics using the financial market logistic regression model; The risk coefficient is calculated according to the linear output value using the activation function preset in the financial market logistic regression model.

8. A financial market data intelligent monitoring device, characterized in that: The device comprises: A data acquisition module is used to acquire price information from multiple price sources in the financial market in real time, perform data conversion processing on the price information from multiple price sources to obtain converted data, perform missing value processing and outlier processing on the converted data to obtain pre-processed price information; A price comparison module, for comparing the pre-processed price information with multiple price sources of the same type of data to obtain a price difference set, and if there is no price difference greater than a preset difference threshold in the price difference set, returning to the step of obtaining the price information of multiple price sources in the financial market in real time, and if there is a price difference greater than a preset difference threshold in the price difference set, issuing a warning message; A price verification module performs a latest price verification on the pre-processed price information, and issues a warning message if the pre-processed price information fails the latest price verification; A feature extraction module, if the pre-processed price information passes the latest price verification, acquires financial market data in real time, classifies the financial market data according to time zones to obtain financial market classification data, performs Fourier transformation on the financial market classification data to obtain time domain features of financial parameters; The risk analysis module uses a pre-trained financial market logistic regression model to perform risk analysis on the financial market according to the time domain characteristics of the financial parameters to obtain a risk coefficient, and determines whether there is risk in the financial market based on the risk coefficient.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for intelligent monitoring of financial market data as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for intelligently monitoring financial market data according to any one of claims 1 to 7 is implemented.

Images