Risk monitoring method and device

Abstract

The invention discloses a risk monitoring method and device, and relates to the technical field of computers, and the method comprises the steps: firstly obtaining computing power grid-connected process data corresponding to node equipment, and selecting to-be-analyzed node data in a preset time period from the computing power grid-connected process data; processing the to-be-analyzed node data through a preset risk prediction model, and generating an initial risk value corresponding to the node equipment; adjusting the initial risk value according to the computing power grid-connected process data to obtain a target risk value meeting a preset risk condition; and performing risk monitoring on the node equipment based on the target risk value, and determining a corresponding risk level of the node equipment in the computing power grid connection process. Compared with the prior art, the method has the advantages that risk loss is effectively reduced, manual participation is reduced, the labor cost of risk management is reduced, the efficiency and quality of risk management are improved, and powerful guarantee is provided for safety and stability of computing power grid connection.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a risk monitoring method and device. Background Art

[0002] Computing power grid connection is an innovative technology system and service model based on key technologies such as computing power measurement, pan-computing scheduling and trusted transactions, which aims to give full play to the advantages of computing networks, widely gather computing power from multiple parties, and promote the inclusiveness of computing power and efficient services. It uses decentralized technologies such as blockchain to uniformly register and manage idle computing power resources, multi-party computing power resources and computing power services, and realize the unified operation of distributed computing power.

[0003] At present, risk monitoring of the computing power grid connection process is mainly carried out through manual experience, and appropriate risk judgments will be made at high-risk locations or times, so as to achieve the purpose of risk monitoring of the computing power grid connection process.

[0004] However, in a complex network environment with a large number of node devices, using this risk monitoring method will make it impossible to timely determine the risk status of all node devices, and thus impossible to monitor the risks of each node device, affecting the efficiency and quality of computing power grid connection. Summary of the invention

[0005] In view of this, the present application provides a risk monitoring method and device, the main purpose of which is to improve the technical problem that the current existing technology cannot timely judge the risk status of all node devices when the network environment is relatively complex and there are many node devices, and thus cannot monitor the risks of each node device, affecting the efficiency and quality of computing power grid connection.

[0006] In a first aspect, the present application provides a risk monitoring method, comprising:

[0007] Obtaining computing power grid-connected process data corresponding to the node device and selecting node data to be analyzed within a preset time period from the computing power grid-connected process data;

[0008] Processing the node data to be analyzed by using a preset risk prediction model to generate an initial risk value corresponding to the node device;

[0009] The initial risk value is adjusted according to the computing power grid connection process data to obtain a target risk value that meets the preset risk conditions;

[0010] The node device is subjected to risk monitoring based on the target risk value to determine the corresponding risk level of the node device during the computing power grid connection process.

[0011] In a second aspect, the present application provides a risk monitoring device, comprising:

[0012] An acquisition module is configured to acquire computing power grid-connected process data corresponding to the node device and select node data to be analyzed within a preset time period from the computing power grid-connected process data;

[0013] A generating module is configured to process the node data to be analyzed by using a preset risk prediction model to generate an initial risk value corresponding to the node device;

[0014] An adjustment module is configured to adjust the initial risk value according to the computing power grid connection process data to obtain a target risk value that meets a preset risk condition;

[0015] The monitoring module is configured to perform risk monitoring on the node device based on the target risk value and determine the corresponding risk level of the node device during the computing power grid connection process.

[0016] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the risk monitoring method of the first aspect when the computer program is executed by a processor.

[0017] In a fourth aspect, the present application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the risk monitoring method of the first aspect when executing the computer program.

[0018] In a fifth aspect, the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the risk monitoring method of the first aspect is implemented.

[0019] By means of the above technical scheme, a risk monitoring method and device provided in the present application first obtain the computing power grid-connected process data corresponding to the node device and select the node data to be analyzed within a preset time period from the computing power grid-connected process data; process the node data to be analyzed by a preset risk prediction model to generate an initial risk value corresponding to the node device; adjust the initial risk value according to the computing power grid-connected process data to obtain a target risk value that meets the preset risk conditions; perform risk monitoring on the node device based on the target risk value to determine the corresponding risk level of the node device during the computing power grid-connected process. Compared with the current existing technology, this application uses a preset risk prediction model to obtain the initial risk value corresponding to the node device for the node data to be analyzed within a preset time period of the node device, and then adjusts the initial risk value based on the computing power grid-connected process data corresponding to the node device to obtain a target risk value that meets the preset risk conditions. The node device is monitored for risk based on the target risk value, which can more accurately identify and evaluate various risks in the computing power grid-connected process, and can also accurately monitor the risks of each node device involved in the computing power grid-connected process, so that the risk loss in the computing power grid-connected process can be effectively reduced, and manual participation can be reduced, reducing the manpower cost of risk management, while improving the efficiency and quality of risk management, and providing a strong guarantee for the safety and stability of computing power grid-connected.

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0023] Figure 1 A schematic diagram of a risk monitoring method provided in an embodiment of the present application is shown;

[0024] Figure 2 A schematic diagram of a risk monitoring method provided in an embodiment of the present application is shown;

[0025] Figure 3A schematic structural diagram of a risk monitoring device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0027] In order to improve the technical problem that the existing technology cannot timely judge the risk status of all node devices when the network environment is relatively complex and there are many node devices, and thus cannot monitor the risk of each node device, which affects the efficiency and quality of computing power grid connection. This embodiment provides a risk monitoring method, such as Figure 1 As shown, the method includes:

[0028] Step 101: Obtain computing power grid-connected process data corresponding to the node device and select node data to be analyzed within a preset time period from the computing power grid-connected process data.

[0029] In the embodiment of the present application, node devices are basic components in network communication and distributed computing systems. They can be any form of physical or virtual devices, with certain computing, storage and network communication capabilities, used to perform specific tasks or services. In different application scenarios, node devices play different roles. Specifically, node devices can include server nodes, client nodes, edge nodes, storage nodes, computing nodes, blockchain nodes and sensor nodes, etc. Correspondingly, server nodes are high-performance computing devices within data centers or enterprises, responsible for processing large amounts of data, running complex applications or providing services, such as database servers, Web servers, mail servers, etc. Client nodes are devices used by end users, such as personal computers, smart phones, tablet computers, etc., which are usually used to access network resources, run applications or interact with servers. Edge nodes are devices located at the edge of the network, such as routers, switches, Internet of Things (IoT) devices, etc., which are responsible for processing local data, performing preliminary data processing and filtering, reducing the pressure on the central server, and improving response speed. Storage nodes are devices specifically used to store data, such as network attached storage (NAS), storage servers in storage area networks (SAN), or storage nodes in distributed file systems. Computing nodes are devices that focus on computing tasks. They are commonly found in high-performance computing (HPC) clusters and virtual machines in cloud computing environments. They are used to perform parallel computing tasks, scientific computing, big data analysis, etc. Blockchain nodes are node devices in blockchain networks that are responsible for verifying transactions, maintaining the consistency of blockchain ledgers, and participating in consensus mechanisms to ensure the security and stability of the network. Sensor nodes are small sensor devices that act as nodes in the Internet of Things (IoT) system and are responsible for collecting environmental data, monitoring the state of the physical world, and sending data to a central node or cloud platform.

[0030] In some examples, Computing Power Grid is a concept that connects computing resources scattered around the world through the network to form a unified, dispatchable computing resource pool. This practice is similar to power grid connection, which connects the power grids of multiple power producers to form a larger power network to improve resource utilization efficiency and system stability. In computing power grid connection, computing resources such as personal computers, data centers, and edge computing nodes can all become "power stations", contributing their computing power through the Internet to jointly complete large-scale computing tasks.

[0031] For this embodiment, the computing power grid connection process data may include: device status data, network status data, data status data and user behavior data of the node device; specifically, the device status data may include the operating status, performance parameters, load conditions, etc. of hardware facilities such as servers, network devices, and storage devices. Based on this, it can be judged whether the equipment is operating normally and whether there are risks such as overload and failure. The network status data mainly includes key indicators such as network traffic, bandwidth utilization, network delay, and packet loss rate. The network is the skeleton of the computing power grid connection. Any network anomaly may affect the stability and performance of the entire system. Based on this, the stability and performance of the device can be judged. The data status data includes the integrity, confidentiality and availability of the data. The system monitors the transmission, storage and access process of the data; based on this, it can detect whether there is a risk of data leakage, tampering or illegal access. User behavior data includes the user's operating behavior, and abnormal behavior patterns include frequent login failures, illegal access attempts, etc. These behaviors may be potential security threats; based on this, potential risks can be evaluated.

[0032] It should be noted that, during the process of computing power grid connection, the time of computing power grid connection can be divided into multiple time periods. Accordingly, the preset time period can be the time period that needs to be monitored during the current computing power grid connection process.

[0033] In some examples, the node data to be analyzed is node process data selected from computing power grid-connected process data that can be subsequently analyzed.

[0034] Step 102: Process the node data to be analyzed using a preset risk prediction model to generate an initial risk value corresponding to the node device.

[0035] In the embodiment of the present application, the preset risk prediction model can be a convolutional neural network (CNN) for the prediction model. It is a type of feedforward neural network that includes convolution calculations and has a deep structure, and is one of the representative algorithms of deep learning. Specifically, the convolutional neural network has the ability to represent learning, and can classify the input information according to the hierarchical structure in a translation-invariant manner, which is why it is called a "translation-invariant artificial neural network". The convolutional neural network is constructed based on the visual mechanism of organisms, and performs supervised learning and unsupervised learning. It was first applied to computer vision and is now widely used in fields such as natural language processing. The convolutional neural network is mainly divided into a three-layer architecture of input layer, hidden layer and output layer. By adjusting the network structure, increasing the amount of training data, and using more effective optimization algorithms, the output accuracy of the convolutional neural network can be significantly improved. In addition, the preprocessing of the input data, the generalization ability of the model, etc. will also affect the output accuracy.

[0036] In some examples, the initial risk value may be a risk value obtained after the data to be analyzed passes through a preset risk prediction model. It should be noted that the risk values ​​in the embodiments of the present application are all percentage values, that is, the risk value values ​​are all less than 1.

[0037] Step 103: Adjust the initial risk value according to the computing power grid connection process data to obtain a target risk value that meets the preset risk conditions.

[0038] For this embodiment, the initial risk value obtained by the preset risk prediction model needs to be further adjusted to obtain a more accurate target risk value, and the current computing power grid-connected risk of the node device is judged by the target risk value.

[0039] Step 104: Perform risk monitoring on the node device based on the target risk value to determine the corresponding risk level of the node device during the computing power grid connection process.

[0040] Compared with the current existing technology, this embodiment uses a preset risk prediction model to obtain the initial risk value corresponding to the node device for the node data to be analyzed within a preset time period of the node device, and then adjusts the initial risk value based on the computing power grid-connected process data corresponding to the node device to obtain a target risk value that meets the preset risk conditions. The node device is monitored for risk based on the target risk value, which can more accurately identify and evaluate various risks in the computing power grid-connected process, and can also accurately monitor the risks of each node device involved in the computing power grid-connected process, so that the risk loss in the computing power grid-connected process can be effectively reduced, and manual participation can be reduced, reducing the manpower cost of risk management, while improving the efficiency and quality of risk management, and providing a strong guarantee for the safety and stability of computing power grid-connected.

[0041] In order to further illustrate the specific implementation process of the method of this embodiment, this embodiment provides the following Figure 2 The specific method shown includes:

[0042] Step 201: Obtain computing power grid-connected process data corresponding to the node device and classify the computing power grid-connected process data according to preset categories to obtain multiple computing power grid-connected process sub-data.

[0043] In an embodiment of the present application, the multiple computing power grid-connected process sub-data obtained by classification according to preset categories may include: device status data, network status data, data status data and user behavior data.

[0044] For example, for risk monitoring of node device A during the computing power grid-connected process, it is first necessary to obtain the computing power grid-connected process data A corresponding to the node device A, and then classify and process the computing power grid-connected process data A according to preset categories to obtain device status data A, network status data A, data status data A and user behavior data A.

[0045] Step 202: Generate fitting curves corresponding to a plurality of computing power grid-connected process sub-data, and determine the node data to be analyzed based on the fitting curves.

[0046] Among them, the fitting curve changes with the time of the computing power grid connection process.

[0047] Optionally, step 202 may specifically include: selecting a target fitting curve within a preset time period from the fitting curves, merging the target fitting curves to obtain target image data corresponding to the node device; marking the target image data with a device sequence identifier corresponding to the node device, and determining the marked target image data as the node data to be analyzed.

[0048] In the embodiment of the present application, the association sequence identifier (Association Sequence Identifier) ​​may be a unique identifier used to identify and track a series of related events, actions or data in data mining, sequence pattern recognition or a specific business process.

[0049] Exemplarily, based on step 201, a fitting curve 1 corresponding to the device status data A, a fitting curve 2 corresponding to the network status data A, a fitting curve 3 corresponding to the data status data A, and a fitting curve 4 corresponding to the user behavior data A are generated, and the fitting curve 1, the fitting curve 2, the fitting curve 3, and the fitting curve 4 are intercepted and merged into the same blank picture according to a preset time length, and an associated sequence identification mark A is configured in the blank picture to obtain the data A to be analyzed corresponding to the node device A.

[0050] Step 203: Process the node data to be analyzed by using a preset risk prediction model to generate an initial risk value corresponding to the node device.

[0051] Exemplarily, based on step 202, the data A to be analyzed is subjected to a preset risk prediction model to obtain an initial risk value A corresponding to the node device A.

[0052] Step 204: adjust the initial risk value according to the computing power grid connection process data to obtain a target risk value that meets the preset risk conditions.

[0053] Optionally, multiple computing power grid-connected process sub-data include: device status data, network status data, data status data and user behavior data; accordingly, step 204 may specifically include: adjusting the initial risk value according to the device status data, network status data, data status data and user behavior data to obtain a target risk value that meets the preset risk conditions.

[0054] Furthermore, step 204 specifically also includes: generating a device status risk value, a network status risk value, a data security risk value and a user behavior risk value corresponding to the node device based on the device status data, the network status data, the data status data and the user behavior data; adjusting the initial risk value according to the device status risk value, the network status risk value, the data security risk value and the user behavior risk value to obtain a target risk value that meets the preset risk conditions.

[0055] In the embodiment of the present application, the device status risk value corresponding to the node device can be determined by Formula 1, which is specifically as follows:

[0056]

[0057] In formula 1, Ld j t is the real-time power load occupancy of the jth node device, Lc j t is the rated power load of the jth node device, Lc j is the real-time cooling equipment load of the j-th node device, Lct is the rated cooling equipment load of the i-th node device, and pT is the number of failures.

[0058] It should be noted that using the number of failures as an exponential magnification factor can significantly increase f in the first place when the failure frequency increases. M (S j *W j ) value, thereby significantly increasing the final risk value F j The calculated value of (T) helps to quickly respond to fault maintenance and eliminate risks quickly.

[0059] Correspondingly, the network status risk value corresponding to the node device can be determined by Formula 2, which is specifically as follows:

[0060]

[0061] In Formula 2, Kt is the real-time bandwidth utilization within the preset time length T, ws is the real-time network traffic, Uk is the network delay fluctuation discreteness, fv is the average packet loss rate, and K is the minimum threshold of bandwidth utilization.

[0062] It should be noted that when the real-time bandwidth utilization is high, but the actual network traffic is very low, there is a high possibility that there is a problem with the power-saving device.

[0063] Furthermore, the data security risk value and user behavior risk value corresponding to the node device can be determined by Formula 3 and Formula 4, which are specifically as follows:

[0064]

[0065]

[0066] In Formula 3 and Formula 4, s is a preset coefficient (which can be set based on experience), Dw is the data integrity rate, Dm is the data encryption level, Cl is the number of login failures, Cn is the number of illegal attempts, cp is the frequency of illegal attempts, and ct is the average interval between illegal attempts.

[0067] It should be noted that in the present embodiment, Cn cp It is an exponential amplification item, which can respond quickly to sudden attacks. Accordingly, encryption level 1 is the highest. If the data integrity rate decreases, the probability of abnormality is high. Therefore, the higher the encryption level, the higher the D j The greater the risk calculation fluctuation, the stronger the reaction, which improves the flexibility and agility of risk calculation and can reduce the number of risk alarms when the encryption level is low, thereby reducing unnecessary risk warning actions and reducing costs.

[0068] Furthermore, the initial risk value can be adjusted according to the device status risk value, the network status risk value, the data security risk value and the user behavior risk value by using Formula 5, which is specifically as follows:

[0069] F j (T) = Z j (T)*ln(e+f M (S j *W j )+D j *C j ) (Formula 5)

[0070] In Formula 5, F j (T) is the final risk value of the j-th node device within the preset time length T, which is the target risk value, Z j (T) is the risk probability value of the jth node device within the preset time length T, f M (x) is the target logistic function.

[0071] It should be noted that F j (T) The coefficient is calculated by multiplying the risk probability value by the coefficient, and the coefficient is obtained by weighting the device status risk, network status risk, data security risk, and user behavior risk.

[0072] In an embodiment of the present application, step 204 specifically also includes: determining the target logic function corresponding to the node device based on the device status risk value and the network status risk value; adjusting the initial risk value based on the device status risk value, the network status risk value, the data security risk value, the user behavior risk value and the target logic function to obtain a target risk value that meets the preset risk conditions.

[0073] Correspondingly, step 204 specifically also includes: when it is determined that the product of the device status risk value and the network status risk value is greater than the preset risk threshold, the first preset logic function is determined as the target logic function; when it is determined that the product of the device status risk value and the network status risk value is less than or equal to the preset risk threshold, the second preset logic function is determined as the target logic function.

[0074] The first preset logic function is different from the second preset logic function.

[0075] In the embodiment of the present application, when S j *W j When the value of is greater than or equal to the preset risk threshold, it indicates that the device status risk and the network status risk are relatively large, then the first preset logic function is determined as the target logic function. Specifically, the first preset logic function is shown in the following formula 6:

[0076]

[0077] It should be noted that when the product of the device status risk value and the network status risk value exceeds the rated value, it means that the risk is relatively high. j (T) rises by M (x) Enlarged times)

[0078] Accordingly, when S j *W j When the value of is less than the preset risk threshold, it indicates that both the device status risk and the network status risk are within a controllable range, and the second preset logic function is determined as the target logic function, wherein the preset risk threshold is obtained through experience.

[0079] Specifically, the second preset logic function is shown in the following formula 7:

[0080] fM(x)=0(Formula 7)

[0081] Step 205: Perform risk monitoring on the node device based on the target risk value to determine the corresponding risk level of the node device during the computing power grid connection process.

[0082] Optionally, after step 205, the method of this embodiment further includes: when it is determined that the risk level is greater than a preset risk level threshold, determining the impact range information corresponding to the risk level, and generating alarm information corresponding to the node device.

[0083] The warning information includes risk level and impact scope information.

[0084] In the embodiments of the present application, with the rapid development of technologies such as cloud computing and big data, computing power grid connection has become an important means to improve computing resource utilization and reduce operating costs. Computing power grid connection is a key technology based on computing power measurement, pan-computing scheduling and trusted transactions, which aims to give full play to the advantages of computing networks, widely gather computing power from multiple parties, and promote innovative technology systems and service models for universal computing power and efficient services. It uses decentralized technologies such as blockchain to uniformly register and manage idle computing power resources, multi-party computing power resources and computing power services, and realize the unified operation of distributed computing power.

[0085] Correspondingly, the goal of computing power grid connection is to promote the realization of social computing power integration supply, build a new computing network service capability system, support integrated services, and gradually promote computing power to become a social-level service that can be "accessed at one point and used immediately" like water and electricity. At present, when conducting risk management and control, computing power grid connection reduces risks from the encryption technology, secure communication and operation levels. In specific implementation, advanced encryption technology can be used to ensure the security of data during transmission, and secure communication protocols such as TLS / SSL can be introduced to improve the security of network transmission; at the same time, identity authentication and access control need to be adopted, and a strict identity authentication mechanism needs to be implemented to ensure that only authorized users can access and use computing power resources, and different levels of access rights are set to perform access control according to user needs and security levels.

[0086] Optionally, in terms of resource scheduling and load balancing during operation, intelligent resource scheduling algorithms are introduced to ensure efficient use of computing resources and load balancing. Dynamic adjustments are made according to task requirements and resource status to avoid resource waste and overload. A sound log management mechanism is established to record all key operations and security events, provide a basis for risk tracing, formulate detailed emergency response plans, and quickly respond to and deal with possible security incidents. At the same time, a backup and recovery mechanism is established to ensure that the normal operation of the computing network can be quickly restored when a failure or attack occurs. However, various risk issues in the process of computing power grid connection have gradually become prominent, such as equipment failure, network congestion, data leakage, etc. Traditional risk management methods often rely on manual experience and rule judgment, and are difficult to cope with complex and changing network environments.

[0087] Compared with the current existing technology, this embodiment uses a preset risk prediction model to obtain the initial risk value corresponding to the node device for the node data to be analyzed within a preset time period of the node device, and then adjusts the initial risk value based on the computing power grid-connected process data corresponding to the node device to obtain a target risk value that meets the preset risk conditions. The node device is monitored for risk based on the target risk value, which can more accurately identify and evaluate various risks in the computing power grid-connected process, and can also accurately monitor the risks of each node device involved in the computing power grid-connected process, so that the risk loss in the computing power grid-connected process can be effectively reduced, and manual participation can be reduced, reducing the manpower cost of risk management, while improving the efficiency and quality of risk management, and providing a strong guarantee for the safety and stability of computing power grid-connected.

[0088] Further, as Figure 1 and Figure 2 The specific implementation of the method shown in this embodiment provides a risk monitoring device, such as Figure 3 As shown, the device includes: an acquisition module 31, a generation module 32, an adjustment module 33, and a monitoring module 34.

[0089] An acquisition module 31 is configured to acquire computing power grid-connected process data corresponding to a node device and select node data to be analyzed within a preset time period from the computing power grid-connected process data;

[0090] A generating module 32 is configured to process the node data to be analyzed by using a preset risk prediction model to generate an initial risk value corresponding to the node device;

[0091] An adjustment module 33 is configured to adjust the initial risk value according to the computing power grid connection process data to obtain a target risk value that meets a preset risk condition;

[0092] The monitoring module 34 is configured to perform risk monitoring on the node device based on the target risk value, and determine the corresponding risk level of the node device during the computing power grid connection process.

[0093] In some examples of this embodiment, the acquisition module 31 is specifically configured to acquire the computing power grid-connected process data corresponding to the node device and classify the computing power grid-connected process data according to preset categories to obtain multiple computing power grid-connected process sub-data; generate fitting curves corresponding to the multiple computing power grid-connected process sub-data respectively, and determine the node data to be analyzed based on the fitting curves, and the fitting curves change with the time of the computing power grid-connected process.

[0094] In some examples of the present embodiment, the acquisition module 31 is further specifically configured to select a target fitting curve within the preset time period from the fitting curves, merge the target fitting curves to obtain target image data corresponding to the node device; mark the target image data with a device sequence identifier corresponding to the node device, and determine the marked target image data as the node data to be analyzed.

[0095] In some examples of this embodiment, the multiple computing power grid-connected process sub-data include: device status data, network status data, data status data and user behavior data; accordingly, the adjustment module 33 is specifically configured to adjust the initial risk value based on the device status data, the network status data, the data status data and the user behavior data to obtain a target risk value that meets the preset risk conditions.

[0096] In some examples of this embodiment, the adjustment module 33 is further specifically configured to generate a device status risk value, a network status risk value, a data security risk value and a user behavior risk value corresponding to the node device based on the device status data, the network status data, the data status data and the user behavior data; and adjust the initial risk value according to the device status risk value, the network status risk value, the data security risk value and the user behavior risk value to obtain a target risk value that meets the preset risk conditions.

[0097] In some examples of this embodiment, the adjustment module 33 is further configured to determine the target logic function corresponding to the node device based on the device status risk value and the network status risk value; adjust the initial risk value based on the device status risk value, the network status risk value, the data security risk value, the user behavior risk value and the target logic function to obtain a target risk value that meets the preset risk conditions.

[0098] In some examples of this embodiment, the adjustment module 33 is further configured to, when it is determined that the product of the device status risk value and the network status risk value is greater than a preset risk threshold, determine the first preset logic function as the target logic function; when it is determined that the product of the device status risk value and the network status risk value is less than or equal to the preset risk threshold, determine the second preset logic function as the target logic function, wherein the first preset logic function is different from the second preset logic function.

[0099] In some examples of this embodiment, the monitoring module 34 is also configured to determine the impact range information corresponding to the risk level when it is determined that the risk level is greater than a preset risk level threshold, and generate alarm information corresponding to the node device, wherein the alarm information includes the risk level and the impact range information.

[0100] It should be noted that for other corresponding descriptions of the functional units involved in the risk monitoring device provided in this embodiment, please refer to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0101] Based on the above Figure 1 to Figure 2 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 to Figure 2 The method shown.

[0102] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0103] Based on the above Figure 1 to Figure 2 The method shown, and Figure 3 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device, such as a personal computer, a server, a laptop computer, a smart phone, an intelligent robot or other intelligent terminal, which includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 to Figure 2 The method shown.

[0104] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0105] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0106] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0107] Based on the above Figure 1 to Figure 2 The present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned Figure 1 to Figure 2 The method shown, the method implemented when the computer program is executed by the processor can refer to the various embodiments of the present application, and will not be described in detail here.

[0108] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. Compared with the current prior art, this embodiment uses a preset risk prediction model to obtain the initial risk value corresponding to the node device through the node data to be analyzed within the preset time period of the node device, and then adjusts the initial risk value based on the computing power grid connection process data corresponding to the node device to obtain the target risk value that meets the preset risk conditions. Based on the target risk value, the node device is monitored for risk, which can more accurately identify and evaluate various risks in the computing power grid connection process, and can also accurately monitor the risks of each node device involved in the computing power grid connection process, so that the risk loss in the computing power grid connection process can be effectively reduced, and it can also reduce manual participation and reduce the human cost of risk management. At the same time, it improves the efficiency and quality of risk management, and provides a strong guarantee for the safety and stability of computing power grid connection.

[0109] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0110] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

Claims

1. A risk monitoring method, characterized in that: include: Obtaining computing power grid-connected process data corresponding to the node device and selecting node data to be analyzed within a preset time period from the computing power grid-connected process data; Processing the node data to be analyzed by using a preset risk prediction model to generate an initial risk value corresponding to the node device; The initial risk value is adjusted according to the computing power grid connection process data to obtain a target risk value that meets the preset risk conditions; The node device is subjected to risk monitoring based on the target risk value to determine the corresponding risk level of the node device during the computing power grid connection process.

2. The method according to claim 1, characterized in that The step of obtaining computing power grid-connected process data corresponding to the node device and selecting node data to be analyzed within a preset time period from the computing power grid-connected process data includes: Obtaining computing power grid-connected process data corresponding to the node device and classifying the computing power grid-connected process data according to preset categories to obtain a plurality of computing power grid-connected process sub-data; Generate fitting curves corresponding to the plurality of computing power grid-connected process sub-data respectively, and determine the node data to be analyzed based on the fitting curves, wherein the fitting curves change over time following the computing power grid-connected process.

3. The method according to claim 2, characterized in that Determining the node data to be analyzed based on the fitting curve includes: Selecting a target fitting curve within the preset time period from the fitting curves, merging the target fitting curves, and obtaining target image data corresponding to the node device; The target image data is marked with a device sequence identifier corresponding to the node device, and the marked target image data is determined as the node data to be analyzed.

4. The method according to claim 2, characterized in that: The plurality of computing power grid connection process sub-data include: device status data, network status data, data status data and user behavior data; The adjusting the initial risk value according to the computing power grid connection process data to obtain a target risk value that meets a preset risk condition includes: The initial risk value is adjusted according to the device status data, the network status data, the data status data and the user behavior data to obtain a target risk value that meets a preset risk condition.

5. The method according to claim 4, characterized in that The adjusting the initial risk value according to the device status data, the network status data, the data status data and the user behavior data to obtain a target risk value that meets a preset risk condition includes: Based on the device status data, the network status data, the data status data and the user behavior data, generate a device status risk value, a network status risk value, a data security risk value and a user behavior risk value corresponding to the node device; The initial risk value is adjusted according to the device status risk value, the network status risk value, the data security risk value and the user behavior risk value to obtain a target risk value that meets the preset risk conditions.

6. The method according to claim 5, characterized in that The adjusting the initial risk value according to the device status risk value, the network status risk value, the data security risk value and the user behavior risk value to obtain a target risk value that meets a preset risk condition includes: Determining a target logic function corresponding to the node device according to the device state risk value and the network state risk value; The initial risk value is adjusted according to the device status risk value, the network status risk value, the data security risk value, the user behavior risk value and the target logic function to obtain a target risk value that meets the preset risk conditions.

7. The method according to claim 6, characterized in that The determining, according to the device state risk value and the network state risk value, a target logic function corresponding to the node device comprises: In the case where it is determined that the product of the device state risk value and the network state risk value is greater than a preset risk threshold, determining a first preset logic function as the target logic function; When it is determined that the product of the device status risk value and the network status risk value is less than or equal to a preset risk threshold, a second preset logic function is determined as the target logic function, wherein the first preset logic function is different from the second preset logic function.

8. The method according to any one of claims 1 to 7, characterized in that After performing risk monitoring on the node device based on the target risk value and determining the corresponding risk level of the node device during the computing power grid connection process, the method further includes: When it is determined that the risk level is greater than a preset risk level threshold, the impact range information corresponding to the risk level is determined, and alarm information corresponding to the node device is generated, wherein the alarm information includes the risk level and the impact range information.

9. A risk monitoring device, characterized in that: include: An acquisition module is configured to acquire computing power grid-connected process data corresponding to the node device and select node data to be analyzed within a preset time period from the computing power grid-connected process data; A generating module is configured to process the node data to be analyzed by using a preset risk prediction model to generate an initial risk value corresponding to the node device; An adjustment module is configured to adjust the initial risk value according to the computing power grid connection process data to obtain a target risk value that meets a preset risk condition; The monitoring module is configured to perform risk monitoring on the node device based on the target risk value and determine the corresponding risk level of the node device during the computing power grid connection process.

10. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images