Seismic Judgment Method, Device, Equipment and Storage Medium Based on Network Traffic

Abstract

The present invention provides a method, device, equipment and storage medium for earthquake judgment based on network traffic, which relates to the technical field of electrical digital data processing. The method includes: obtaining the traffic data corresponding to the historical station waveform data of the earthquake monitoring station, and the historical traffic data between each node on the data transmission link; establishing a traffic data vector set based on the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link; wherein, the vectors in the traffic data vector set represent the vectors composed of the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link at the same moment; inputting the traffic data vector set into a preset earthquake judgment model to judge whether an earthquake has occurred. The present invention can judge whether an earthquake event has occurred in a timely and accurate manner.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical digital data processing, and in particular, to a method, device, equipment and storage medium for earthquake judgment based on network traffic. Background Art

[0002] The multi-services and services of the existing seismic monitoring station network are deployed in a multi-cloud network environment, including heterogeneous architectures such as private clouds, public clouds, and hybrid clouds. The in-cloud network traffic analysis is mainly used to monitor the health status of devices such as networks, security, computing storage, etc., such as detecting server loads, network congestion, or identifying security threats such as DDoS attacks, malware, etc. These applications focus on the performance and security of the network itself. Traditional earthquake discrimination is based on multi-station waveform data from a seismological perspective to carry out phase identification. In the current earthquake event judgment methods, there is no consideration of realizing earthquake event judgment from other perspectives. Although the traditional method of realizing earthquake event judgment through phase identification is accurate enough, there is still a gap in how to judge earthquake events from other perspectives. The inability to judge earthquake events from multiple perspectives makes the identification of earthquake events less accurate. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, equipment and storage medium for earthquake judgment based on network traffic to supplement the existing earthquake event judgment methods and realize the judgment of earthquake events in a timely and accurate manner from another perspective, making the judgment of earthquake events more accurate.

[0004] In a first aspect, embodiments of the present invention provide a method for earthquake judgment based on network traffic, including:

[0005] Obtain the traffic data corresponding to the historical station waveform data of the seismic monitoring station, and the historical traffic data between each node on the data transmission link; wherein, each node on the data transmission link includes: a seismic monitoring station, a data processing node, an information publishing node, and a user terminal.

[0006] Based on the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link, establish a traffic data vector set; wherein, the vectors in the traffic data vector set represent the vectors composed of the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link at the same moment.

[0007] Input the traffic data vector set into a preset earthquake judgment model to judge whether an earthquake has occurred.

[0008] In a possible implementation manner, the preset earthquake judgment model is a preset long short-term memory neural network model; inputting the traffic data vector set into the preset earthquake judgment model to judge whether an earthquake has occurred includes:

[0009] Input the set of traffic data vectors into a preset long short-term memory neural network model to obtain a prediction vector.

[0010] Obtain the real-time value of the traffic data corresponding to the station waveform data of the seismic monitoring station and the real-time value of the traffic data between each node on the data transmission link, and denote them as the first real-time value and the second real-time value respectively; and establish a real-time vector based on the first real-time value and the second real-time value.

[0011] If the Euclidean distance between the prediction vector and the real-time vector is less than or equal to the first preset value, it is determined that an earthquake has not occurred.

[0012] If the Euclidean distance between the prediction vector and the real-time vector is greater than the first preset value, it is determined that an earthquake has occurred.

[0013] In a possible implementation manner, the calculation formula for the Euclidean distance between the prediction vector and the real-time vector is:

[0014]

[0015] Wherein, represents the Euclidean distance between the prediction vector and the real-time vector, represents the prediction vector, represents the real-time vector, represents the total number of the real-time value of the traffic data corresponding to the station waveform data of the seismic monitoring station and the real-time value of the traffic data between each node on the data transmission link.

[0016] In a possible implementation manner, the training process of the preset earthquake judgment model is as follows:

[0017] Divide the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link into a training set and a test set.

[0018] Input the training set into the preset earthquake judgment model to calculate the training prediction value.

[0019] Aim at minimizing the difference between the test set and the training prediction value, perform iteration, and optimize the hyperparameters of the preset earthquake judgment model until the difference between the test set and the training prediction value no longer becomes smaller or reaches the iteration number upper limit.

[0020] In a possible implementation manner, optimizing the hyperparameters of the preset earthquake judgment model includes:

[0021] Optimize the hyperparameters of the preset earthquake judgment model through a particle swarm algorithm or an annealing algorithm.

[0022] In a possible implementation, the historical traffic data between each node on the data transmission link includes: the historical traffic data between the seismic monitoring station and the data processing node, the historical traffic data between the data processing node and the information publishing node, and the historical traffic data between the information publishing node and the user terminal.

[0023] In a possible implementation, obtain the traffic data corresponding to the historical station waveform data of the seismic monitoring station, and the historical traffic data between each node on the data transmission link, including:

[0024] Obtain the initial data of the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link.

[0025] Perform noise removal, outlier removal, and missing value filling on the initial data to obtain the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link.

[0026] In a second aspect, an embodiment of the present invention provides a seismic judgment device based on network traffic, including:

[0027] A data acquisition module, configured to acquire the traffic data corresponding to the historical station waveform data of the seismic monitoring station, and the historical traffic data between each node on the data transmission link; wherein, each node on the data transmission link includes: a seismic monitoring station, a data processing node, an information publishing node, and a user terminal.

[0028] A data processing module, configured to establish a traffic data vector set based on the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link; wherein, the vectors in the traffic data vector set represent the vectors composed of the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link at the same moment.

[0029] A result output module, configured to input the traffic data vector set into a preset seismic judgment model to determine whether an earthquake has occurred.

[0030] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method in the first aspect or any possible implementation manner of the first aspect above is implemented.

[0031] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method in the first aspect or any possible implementation manner of the first aspect above is implemented.

[0032] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program which, when executed by a processor, implements the method in the first aspect above or any possible implementation manner of the first aspect.

[0033] In the embodiment of the present invention, the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link are input into the seismic judgment model to obtain a predicted value, and the predicted value is compared with the real-time acquisition value, so as to determine whether an earthquake has occurred. The judgment of whether an earthquake event occurs is carried out from the network traffic level. By using the method of machine learning, the accuracy of the judgment result can be greatly improved. Furthermore, the method of combining the seismic phase recognition based on the waveform data of multiple stations to judge the earthquake event can be used to judge the earthquake event from multiple angles, avoiding false alarms and making the judgment of the earthquake event more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a flowchart of the implementation of the seismic judgment method based on network traffic provided by an embodiment of the present invention;

[0035] Figure 2 is a schematic structural diagram of the seismic judgment device based on network traffic provided by an embodiment of the present invention;

[0036] Figure 3 is a schematic diagram of the electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0038] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0039] It should also be understood that the term " / and" as used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0040] As used in the specification of this application and the appended claims, the term "if" may be construed, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrases "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0041] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for differentiating descriptions and cannot be construed as indicating or implying relative importance.

[0042] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0043] The following will be combined with the attached Figure 1 to the attached Figure 3 to describe the embodiments of the present invention in detail.

[0044] See Figure 1 , which shows the implementation flowchart of the earthquake judgment method based on network traffic provided by the embodiments of the present invention, and is described in detail as follows:

[0045] Step 101, obtain the traffic data corresponding to the historical station waveform data of the earthquake monitoring station, as well as the historical traffic data between each node on the data transmission link; wherein, each node on the data transmission link includes: an earthquake monitoring station, a data processing node, an information publishing node, and a user terminal.

[0046] Exemplarily, the historical traffic data between each node on the data transmission link includes: the historical traffic data between the earthquake monitoring station and the data processing node, the historical traffic data between the data processing node and the information publishing node, and the historical traffic data between the information publishing node and the user terminal.

[0047] Exemplarily, step 101 may include:

[0048] Obtain the initial data of the flow data corresponding to the historical station waveform data of the seismic monitoring station and the historical flow data between each node on the data transmission link.

[0049] Perform noise removal, outlier removal, and missing value filling on the initial data to obtain the flow data corresponding to the historical station waveform data of the seismic monitoring station and the historical flow data between each node on the data transmission link.

[0050] Exemplarily, by means such as noise removal, outlier removal, and missing value filling on the initial data, the flow data corresponding to the historical station waveform data of the seismic monitoring station and the historical flow data between each node on the data transmission link can be improved, ensuring the accuracy of subsequent earthquake judgment.

[0051] Step 102: Based on the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link, establish a flow data vector set; where the vectors in the flow data vector set represent the vectors composed of the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link at the same moment.

[0052] Exemplarily, for the convenience of understanding the flow data vector set, assume that the flow data corresponding to the historical station waveform data is A, and the historical flow data between each node on the data transmission link is B, C, and D, where A, B, C, and D are the flow data at the same moment. Then the flow data vector is (A, B, C, D). It is not difficult to understand that the flow data vectors at multiple moments form the flow data vector set.

[0053] Step 103: Input the flow data vector set into a preset earthquake judgment model to determine whether an earthquake has occurred.

[0054] Exemplarily, the preset earthquake judgment model is a preset long short-term memory neural network model.

[0055] Exemplarily, step 103 may include:

[0056] Input the flow data vector set into a preset long short-term memory neural network model to obtain a prediction vector.

[0057] Obtain the real-time values of the flow data corresponding to the station waveform data of the seismic monitoring station and the real-time values of the flow data between each node on the data transmission link, which are respectively denoted as the first real-time value and the second real-time value; and establish a real-time vector based on the first real-time value and the second real-time value.

[0058] If the Euclidean distance between the prediction vector and the real-time vector is less than or equal to the first preset value, it is determined that no earthquake has occurred.

[0059] If the Euclidean distance between the predicted vector and the real-time vector is greater than the first preset value, it is determined that an earthquake has occurred.

[0060] Exemplarily, the predicted vector is calculated using historical data. In this way, the final result can be obtained through a simple Euclidean distance judgment at the first time after obtaining the real-time vector, avoiding a large amount of data operations and improving the real-time performance of earthquake judgment. In addition, it can also ensure the timeliness of combining with traditional methods (methods for identifying earthquake phases based on waveform data of multiple stations to judge earthquake events), and realize multi-angle and rapid judgment of earthquake events.

[0061] Exemplarily, the calculation formula for the Euclidean distance between the predicted vector and the real-time vector can be:

[0062]

[0063] Where, represents the Euclidean distance between the predicted vector and the real-time vector, represents the predicted vector, represents the real-time vector, represents the total number of real-time values of the flow data corresponding to the station waveform data of the earthquake monitoring station and the real-time values of the flow data between each node on the data transmission link.

[0064] Exemplarily, the training process of the preset earthquake judgment model can be:

[0065] Divide the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link into a training set and a test set.

[0066] Input the training set into the preset earthquake judgment model to calculate the training prediction value.

[0067] With the goal of minimizing the difference between the test set and the training prediction value, perform iteration to optimize the hyperparameters of the preset earthquake judgment model until the difference between the test set and the training prediction value no longer decreases or reaches the iteration number limit.

[0068] Exemplarily, optimizing the hyperparameters of the preset earthquake judgment model can include:

[0069] Optimize the hyperparameters of the preset earthquake judgment model through the particle swarm algorithm or the annealing algorithm.

[0070] Exemplarily, through the particle swarm algorithm or the annealing algorithm, the iteration speed of the earthquake judgment model can be accelerated, the convergence speed of the earthquake judgment model can be accelerated, and the processing efficiency can be improved.

[0071] Specifically, this method can also comprehensively judge seismic events by combining the results of this method with the seismic phase results obtained from real-time data, identify the same event from multiple perspectives, and further improve the accuracy of the event identification results.

[0072] The above-mentioned earthquake judgment method based on network traffic inputs the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link into the earthquake judgment model to obtain a predicted value, and compares the predicted value with the real-time acquisition value, then it can be determined whether an earthquake has occurred. This method judges whether an earthquake event has occurred from the network traffic layer, adopts the method of machine learning, can greatly improve the accuracy of the judgment result, and then can combine the method of identifying and judging seismic events based on multi-station waveform data to judge seismic events from multiple perspectives, avoid false alarms, and make the judgment of seismic events more accurate.

[0073] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0074] The following is an apparatus embodiment of the present invention. For the details not described in detail therein, reference can be made to the corresponding method embodiments above.

[0075] Figure 2 The structural schematic diagram of the earthquake judgment apparatus based on network traffic provided by the embodiments of the present invention is shown. For the convenience of description, only the parts related to the embodiments of the present invention are shown and are described in detail as follows:

[0076] As Figure 2 shown, the earthquake judgment apparatus based on network traffic includes:

[0077] A data acquisition module 201, configured to acquire the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link; wherein, each node on the data transmission link includes: a seismic monitoring station, a data processing node, an information publishing node, and a user terminal.

[0078] A data processing module 202, configured to establish a traffic data vector set based on the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link; wherein, the vectors in the traffic data vector set represent the vectors composed of the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link at the same moment.

[0079] The result output module 203 is configured to input the set of traffic data vectors into a preset earthquake judgment model to determine whether an earthquake has occurred.

[0080] In a possible implementation manner, the preset earthquake judgment model is a preset long short-term memory neural network model.

[0081] In a possible implementation manner, the result output module 203 can be used for:

[0082] Input the set of traffic data vectors into a preset long short-term memory neural network model to obtain a prediction vector.

[0083] Obtain the real-time value of the traffic data corresponding to the station waveform data of the earthquake monitoring station and the real-time value of the traffic data between each node on the data transmission link, which are respectively denoted as the first real-time value and the second real-time value; and establish a real-time vector based on the first real-time value and the second real-time value.

[0084] If the Euclidean distance between the prediction vector and the real-time vector is less than or equal to the first preset value, it is determined that no earthquake has occurred.

[0085] If the Euclidean distance between the prediction vector and the real-time vector is greater than the first preset value, it is determined that an earthquake has occurred.

[0086] In a possible implementation manner, the calculation formula for the Euclidean distance between the prediction vector and the real-time vector can be:

[0087]

[0088] Wherein, represents the Euclidean distance between the prediction vector and the real-time vector, represents the prediction vector, represents the real-time vector, represents the total number of the real-time value of the traffic data corresponding to the station waveform data of the earthquake monitoring station and the real-time value of the traffic data between each node on the data transmission link.

[0089] In a possible implementation manner, the training process of the preset earthquake judgment model can be:

[0090] Divide the traffic data corresponding to the historical station waveform data and the historical traffic data between each node on the data transmission link into a training set and a test set.

[0091] Input the training set into the preset earthquake judgment model and calculate the training prediction value.

[0092] Iterate with the goal of minimizing the difference between the test set and the training prediction values, and optimize the hyperparameters of the preset earthquake judgment model until the difference between the test set and the training prediction values no longer decreases or reaches the upper limit of the number of iterations.

[0093] In a possible implementation, optimizing the hyperparameters of the preset earthquake judgment model may include:

[0094] Optimize the hyperparameters of the preset earthquake judgment model through the particle swarm algorithm or the annealing algorithm.

[0095] In a possible implementation, the historical traffic data between each node on the data transmission link includes: the historical traffic data between the seismic monitoring station and the data processing node, the historical traffic data between the data processing node and the information publishing node, and the historical traffic data between the information publishing node and the user terminal.

[0096] In a possible implementation, the data acquisition module 201 may also be used for:

[0097] Obtain the initial data of the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link.

[0098] Perform denoising, outlier removal, and missing value filling on the initial data to obtain the traffic data corresponding to the historical station waveform data of the seismic monitoring station and the historical traffic data between each node on the data transmission link.

[0099] Figure 3 It is a schematic diagram of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, the electronic device 3 of this embodiment includes: a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor 30 executes the computer program 32, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0100] Exemplarily, the computer program 32 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the electronic device 3.

[0101] The electronic device 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art can understand, Figure 3This is only an example of the electronic device 3, which does not constitute a limitation on the electronic device 3. It may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, the electronic device 3 may also include input / output devices, network access devices, buses, etc.

[0102] The processor 30 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc.

[0103] The memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the electronic device 3. The memory 31 is used to store the computer program 32 and other programs and data required by the electronic device 3. The memory 31 may also be used to temporarily store data that has been output or will be output.

[0104] For the convenience and simplicity of description, only the above division of each functional module / unit is used as an example. In practical applications, the above functions may be allocated to different functional modules / units according to needs. The above modules / units may be implemented in the form of hardware, or in the form of software, or in the form of a combination of hardware and software.

[0105] The embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0106] The embodiment of the present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0107] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0108] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Without special instructions and logical conflicts, the terms and / or descriptions between different embodiments are consistent and can be mutually referred to. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0109] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for earthquake determination based on network traffic, characterized in that: include: Obtaining flow data corresponding to historical station waveform data of the seismic monitoring station and historical flow data between various nodes on the data transmission link; wherein the various nodes on the data transmission link include: seismic monitoring station, data processing node, information release node and user terminal; A flow data vector set is established based on the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link; wherein the vector in the flow data vector set represents a vector composed of the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link at the same time; Inputting the flow data vector set into a preset earthquake judgment model to judge whether an earthquake occurs; The preset earthquake judgment model is a preset long short-term memory neural network model; the flow data vector set is input into the preset earthquake judgment model to judge whether an earthquake occurs, including: Inputting the flow data vector set into a preset long short-term memory neural network model to obtain a prediction vector; Acquire the real-time value of the flow data corresponding to the station waveform data of the seismic monitoring station and the real-time value of the flow data between each node on the data transmission link, and record them as the first real-time value and the second real-time value respectively; and establish a real-time vector based on the first real-time value and the second real-time value; If the Euclidean distance between the predicted vector and the real-time vector is less than or equal to a first preset value, it is determined that the earthquake has not occurred; If the Euclidean distance between the predicted vector and the real-time vector is greater than the first preset value, it is determined that an earthquake has occurred.

2. The earthquake determination method based on network traffic according to claim 1, characterized in that: The calculation formula of the Euclidean distance between the predicted vector and the real-time vector is: in, represents the Euclidean distance between the predicted vector and the real-time vector, represents the prediction vector, represents the real-time vector, It represents the real-time value of the flow data corresponding to the station waveform data of the seismic monitoring station and the total number of real-time values ​​of the flow data between each node on the data transmission link.

3. The earthquake determination method based on network traffic according to claim 1, characterized in that: The training process of the preset earthquake judgment model is as follows: Dividing the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link into a training set and a test set; Inputting the training set into the preset earthquake judgment model to calculate the training prediction value; With the goal of minimizing the difference between the test set and the training prediction value, iterations are performed to optimize the hyperparameters of the preset earthquake judgment model until the difference between the test set and the training prediction value no longer decreases or reaches an upper limit on the number of iterations.

4. The earthquake determination method based on network traffic according to claim 3 is characterized in that: The optimizing the hyper parameters of the preset earthquake determination model includes: The hyperparameters of the preset earthquake judgment model are optimized by using a particle swarm algorithm or an annealing algorithm.

5. The earthquake determination method based on network traffic according to claim 1, characterized in that: The historical traffic data between the nodes on the data transmission link include: historical traffic data between the earthquake monitoring station and the data processing node, historical traffic data between the data processing node and the information publishing node, and historical traffic data between the information publishing node and the user terminal.

6. The earthquake determination method based on network traffic according to claim 1, characterized in that: The method of obtaining the flow data corresponding to the historical station waveform data of the seismic monitoring station and the historical flow data between each node on the data transmission link includes: Acquire the flow data corresponding to the historical station waveform data of the seismic monitoring station and the initial data of the historical flow data between each node on the data transmission link; The initial data is subjected to denoising, outlier elimination and missing value completion to obtain flow data corresponding to the historical station waveform data of the seismic monitoring station and historical flow data between each node on the data transmission link.

7. An earthquake judgment device based on network traffic, characterized in that: include: A data acquisition module, which acquires the flow data corresponding to the historical station waveform data of the seismic monitoring station, and the historical flow data between each node on the data transmission link; wherein each node on the data transmission link includes: a seismic monitoring station, a data processing node, an information release node and a user terminal; A data processing module, used to establish a flow data vector set based on the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link; wherein the vector in the flow data vector set represents a vector composed of the flow data corresponding to the historical station waveform data and the historical flow data between each node on the data transmission link at the same time; A result output module, used for inputting the flow data vector set into a preset earthquake judgment model to judge whether an earthquake occurs; The preset earthquake judgment model is a preset long short-term memory neural network model; the result output module is used to: Inputting the flow data vector set into a preset long short-term memory neural network model to obtain a prediction vector; Acquire the real-time value of the flow data corresponding to the station waveform data of the seismic monitoring station and the real-time value of the flow data between each node on the data transmission link, and record them as the first real-time value and the second real-time value respectively; and establish a real-time vector based on the first real-time value and the second real-time value; If the Euclidean distance between the predicted vector and the real-time vector is less than or equal to a first preset value, it is determined that the earthquake has not occurred; If the Euclidean distance between the predicted vector and the real-time vector is greater than the first preset value, it is determined that an earthquake has occurred.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images