Network management method, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a network management method, electronic equipment and a computer readable storage medium. The network management method comprises the following steps: detecting the residual effective duration of a license file; if the remaining effective duration reaches a first preset duration, calling historical network management data; determining network management parameters according to the historical network management data; and managing the network of the network equipment based on the network management parameters. According to the scheme of the embodiment, the network management can intelligently manage the network, so that the network capacity can be intelligently shrunk after the License fails, the intelligent management and recovery effects of the network are finally achieved, the management of the network management on the network after the License fails is enhanced, and the network management has the capability of self-regulation and self-control of the network.

Description

Technical Field

[0001] The present disclosure relates to the field of network management, and particularly to a network management method, an electronic device, and a computer-readable storage medium. Background Art

[0002] Traditional network management License expiration control method:

[0003] In a traditional network element access permission management system, all network elements accessed by the network management are controlled through a network management License file.

[0004] When the network management license expires and the user modifies the configuration parameters, when the network element detects that the modified configuration parameters belong to the services controlled by the License, the network element service module sends an authentication request to the network management License management module, and the network management License management module returns an authentication failure response because there is no valid License. When the network element service module receives the failure response, it invalidates the modified configuration parameters, so the relevant service modifications do not take effect. Summary of the Invention

[0005] Embodiments of the present disclosure provide a network management method, an electronic device, and a computer-readable storage medium.

[0006] In a first aspect, embodiments of the present disclosure provide a network management method, which may include:

[0007] Detect the remaining valid duration of the license file;

[0008] If the remaining valid duration reaches a first preset duration, call historical network management data;

[0009] Determine network management parameters according to the historical network management data;

[0010] Manage the network of the network device based on the network management parameters.

[0011] In a second aspect, embodiments of the present disclosure provide an electronic device, which includes:

[0012] One or more processors;

[0013] A memory storing one or more programs thereon, and when the one or more programs are executed by the one or more processors, the one or more processors implement the network management method;

[0014] One or more input / output I / O interfaces connected between the processor and the memory and configured to implement information interaction between the processor and the memory.

[0015] In a third aspect, embodiments of the present disclosure provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the network management method described above is implemented.

[0016] Embodiments of the present disclosure detect the remaining valid duration of a license file to facilitate timely management of a network that is about to exceed the License validity period, and minimize the impact on users caused by License expiration. When the remaining valid duration reaches a first preset duration, historical network management data is called; network management parameters are determined based on the historical network management data, and the network is managed based on the network management parameters, enabling the network management to intelligently manage the network, facilitating intelligent contraction of the network capacity after the License expires, ultimately achieving intelligent management and recovery of the network, strengthening the network management by the network management after the License expires, and enabling the network management to have the ability to self-regulate the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In the drawings of embodiments of the present disclosure:

[0018] Figure 1 is a flowchart of the network management method provided by embodiments of the present disclosure;

[0019] Figure 2 is a schematic diagram of the network management system provided by embodiments of the present disclosure;

[0020] Figure 3 is a schematic diagram of a solution for the License control module to monitor changes in the License file provided by embodiments of the present disclosure;

[0021] Figure 4 is a schematic diagram of management measures based on a preset model of License control items provided by embodiments of the present disclosure;

[0022] Figure 5 is a schematic diagram of an emergency state handling solution provided by embodiments of the present disclosure;

[0023] Figure 6 is a block diagram of the composition of an electronic device provided by embodiments of the present disclosure;

[0024] Figure 7 is a block diagram of the composition of a computer-readable storage medium provided by embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] To enable those skilled in the art to better understand the technical solutions of the present disclosure, the communication perception data processing method and computer-readable storage medium provided by embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0026] The present disclosure will be described more fully hereinafter with reference to the accompanying drawings. However, the illustrated embodiments may be embodied in different forms and the present disclosure should not be construed as limited to the embodiments set forth below. On the contrary, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0027] The accompanying drawings of the embodiments of the present disclosure are used to provide a further understanding of the embodiments of the present disclosure, and constitute a part of the specification. Together with the detailed embodiments, they are used to explain the present disclosure and do not constitute a limitation to the present disclosure. By describing the detailed embodiments with reference to the accompanying drawings, the above and other features and advantages will become more apparent to those skilled in the art.

[0028] The present disclosure may be described with reference to plan views and / or cross-sectional views by means of ideal schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances.

[0029] In the case of no conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0030] The terms used in the present disclosure are only for describing specific embodiments and are not intended to limit the present disclosure. As used in the present disclosure, the term "and / or" includes any and all combinations of one or more of the related listed items. As used in the present disclosure, the singular forms "a" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. As used in the present disclosure, the terms "comprising", "made of", specify the presence of the stated features, wholes, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their groups.

[0031] Unless otherwise defined, all terms (including technical and scientific terms) used in the present disclosure have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless the present disclosure clearly so defines.

[0032] The present disclosure is not limited to the embodiments shown in the drawings, but includes modifications to the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the drawings have schematic properties, and the shapes of the regions shown in the drawings illustrate the specific shapes of the regions of the elements, but are not intended to be restrictive.

[0033] Traditional network management License (permission, or software license) expiration control method:

[0034] In the traditional network element access permission management system, all network elements accessed by the network management are controlled through the network management License file.

[0035] When the network management license expires and the user modifies the configuration parameters, when the network element detects that the modified configuration parameters belong to the services controlled by the License, the network element service module sends an authentication request to the network management License management module, and the network management License management module returns an authentication failure response because there is no valid License. After receiving the failure response, the network element service module invalidates the modified configuration parameters, and the relevant service modifications do not take effect.

[0036] During this period, if the user does not modify the configuration parameters, the existing network data can still be used and the existing network services can be retained.

[0037] Therefore, at present, there are cases where operator users apply for short-term Licenses and refuse to fulfill the contract terms after expiration, and equipment manufacturers have no effective measures to recover network management capabilities in such situations.

[0038] In the embodiments of the present disclosure, by detecting the remaining valid duration of the license file, it is convenient to manage the network that is about to exceed the License validity period in a timely manner, and minimize the impact of License expiration on users. When the remaining valid duration reaches the first preset duration, historical network management data is called; network management parameters are determined based on the historical network management data, and the network is managed based on the network management parameters, enabling the network management to intelligently manage the network, so as to intelligently shrink the network capacity after the License expires, and finally achieve the intelligent management and recovery of the network, strengthening the network management by the network management after the License expires, and enabling the network management to have the ability to self-regulate the network.

[0039] The network management method in the embodiments of the present disclosure can be executed by any electronic device such as a terminal device or a server that needs to implement corresponding functions based on the license file. The terminal device may include, but is not limited to: in-vehicle devices, user equipment (UE), mobile devices, computing devices, wearable devices, etc. For example, it includes, but is not limited to, cellular phones, cordless phones, personal digital assistants (PDAs), portable computers, etc. The network management method can be implemented by the processor calling computer-readable program instructions stored in the memory, or can be implemented by the server.

[0040] The embodiments of the present disclosure are applicable to all network management systems for network element license management. By combining the License file and the network management, the network management can intelligently manage the network elements and shrink the network capacity, and finally achieve the intelligent recovery of network capacity management.

[0041] The embodiments of the present disclosure can be applied to the centralized License control of a wireless communication network. For scenarios where there is an explosive growth in the population in certain areas during a specific period, such as concerts, tourism, etc., this License management measure can be used. When the License expires, the power consumption of network elements is gradually reduced, and the network management capabilities are recycled.

[0042] The solutions of the embodiments of the present disclosure will be introduced in detail below.

[0043] The embodiments of the present disclosure provide a network management method, which is applied to the network management side, such as Figure 1 shown, the method may include steps S11 - S14:

[0044] S11. Detect the remaining valid duration of the license file.

[0045] S12. When the remaining valid duration reaches the first preset duration, call the historical network management data.

[0046] S13. Determine the network management parameters according to the historical network management data.

[0047] S14. Manage the network of the network device based on the network management parameters.

[0048] In the embodiments of the present disclosure, as Figure 2 shown, the solutions of the embodiments of the present disclosure can be implemented based on a preset network management system 100. The network management system 100 includes four major modules: the License management module 101, the intelligent computing module 102, the alarm management module 103, and the network device 104 in the network management system.

[0049] In the embodiments of the present disclosure, the License management module 101 may include: a License file expiration detection module 1011, a License control module 1012, and a License storage module 1013, which are respectively used for detecting the remaining valid duration of the License file, controlling and managing the system License file, and storing License - related data. The License management module 101 can also collect historical network management data and use it for in - depth data operation and analysis by the intelligent computing module. As Figure 3As shown in the figure, after the License file is imported into the License storage module 1013 through a normal data stream, the License storage module 1013 decrypts the License data, stores the License data, and reads the License data. The License control module 1012 can listen for file changes in the License storage module 1013 through Kafka (Kafka is a high-throughput distributed publish-subscribe messaging system that can process all action stream data of consumers in a website), calibrate and update the monitored License file, read the License data of the changed License file, and store the License data in the License storage module 1013.

[0050] Intelligent operation module 102: It is used to deeply analyze and calculate historical network management data, and calculate the required network management parameters, so as to manage the network of the entire network device before and after the License file expires based on the network management parameters.

[0051] Alarm management module 103: Notify users of various License alarms generated by License management, so that users can timely know the License problems existing in the network management system.

[0052] Network device 104: A network device connected to the network management system.

[0053] In the embodiment of the present disclosure, obtaining historical network management data includes, but is not limited to: obtaining the change N in the number of historical network devices accessed in the network management system and / or historical license authentication flow data;

[0054] The historical license authentication flow data includes any one or more of the following: the change Q in the increase of license authentication data, the number F of control items participating in control in license authentication, and the function G of control items participating in control in license authentication.

[0055] In the embodiment of the present disclosure, the historical license authentication flow data can be obtained alone, and the network management parameters are calculated based on the historical license authentication flow data. The change N in the number of historical network devices accessed in the network management system added in the solution of the embodiment of the present disclosure can assist the historical license authentication flow data to improve the prediction accuracy of network management parameters.

[0056] In the embodiment of the present disclosure, the License file failure detection module 1011 can detect the failure information of the license file, and the failure information can include, but is not limited to: whether it fails and the remaining valid duration.

[0057] In an embodiment of the present disclosure, the License file failure detection module 1011 may obtain network management related data in the current network management system, and call the License control module 1012 of the network management to extract key data such as the activation time and expiration time of the License for each network product (for example, including but not limited to: 2G / 3G / 4G / 5G products). Based on these data, the intelligent operation module 102 can calculate the remaining valid duration of the license file. In order to manage network elements whose License expiration is approaching in a timely manner and minimize the impact of License failure on users, the alarm module may be notified to report License alarms within a certain period before the expiration.

[0058] In an embodiment of the present disclosure, historical network management data may be called when it is detected that the remaining valid duration reaches a first preset duration; network management parameters may be determined according to the historical network management data. The first preset duration can be defined according to requirements, and the specific value of the first preset duration is not limited here. For example, the first preset duration may include but not limited to: two weeks before the License file expires, because this duration is a certain time away from the License file expiration, which can ensure that users have sufficient time to update the License file, and this duration makes the historical license authentication flow data generated during the use of the License file rich enough, which is beneficial to the accurate calculation of network management parameters.

[0059] In an embodiment of the present disclosure, when it is detected that the remaining valid duration reaches the first preset duration, the historical network management data in the current network management system before the License failure may be collected through the License control module 1012, and the alarm module may be notified to report License alarms.

[0060] In an embodiment of the present disclosure, the historical network management data includes but not limited to at least one of the following: the change N in the historical access quantity of network devices and the historical license authentication flow data.

[0061] In an embodiment of the present disclosure, the historical license authentication flow data includes but not limited to at least one of the following: the change Q in the increase of License authentication data, the number F of control items participating in control in License authentication, and the control item function G.

[0062] In an embodiment of the present disclosure, the intelligent operation module 102 may determine network management parameters according to the historical network management data.

[0063] In an embodiment of the present disclosure, the network management parameters may include but not limited to at least one of the following:

[0064] Grace period T, noise reduction step size X per unit time, and access failure probability K per unit time.

[0065] In an embodiment of the present disclosure, determining network management parameters according to historical network management data includes:

[0066] Inputting the historical network management data into a licensed network management model to output network management parameters;

[0067] The licensed network management model can be obtained by training a preset neural network with preset network management sample data and when the loss value of the neural network meets the preset requirements; the neural network can include, but is not limited to, a convolutional neural network and a long short-term memory recurrent neural network, that is, the licensed network management model includes, but is not limited to, a convolutional neural network and a long short-term memory recurrent neural network.

[0068] In an embodiment of the present disclosure, in order to predict network management parameters (such as grace period T, noise reduction step X, and access failure probability K, etc.) required for network management, a convolutional neural network (CNN) and a long short-term memory (LSTM) recurrent neural network can be combined to analyze historical data such as the historical change N of the number of network device accesses, the increase rate change Q of the whole network License authentication data, the number F of control items participating in control in License authentication, and the control item function G, etc., to achieve the prediction of the required network management parameters.

[0069] In an embodiment of the present disclosure, inputting the historical network management data into the licensed network management model to output the network management parameters includes:

[0070] Inputting the historical network management data into a convolutional neural network to obtain the correlation characteristics of the licensed authentication data stream within the area of control items with the same function;

[0071] Inputting the correlation characteristics of the licensed authentication data stream and the historical change N of the number of network device accesses into a long short-term memory recurrent neural network, and the long short-term memory recurrent neural network fuses the correlation characteristics of the licensed authentication data stream and the historical change of the number of network device accesses to obtain the change trend of the authentication request and the time period characteristics of the authentication request; calculating the grace period T according to the time period characteristics of the authentication request, and obtaining the noise reduction step X and the probability K of network access failure according to the change trend of the authentication request.

[0072] In the embodiments of the present disclosure, the historical license authentication flow data (or License authentication flow data) includes control items participating in authentication. The control item information includes a control item id (identity identifier) and a control item function G, as well as an authorized quantity a and a configured quantity b. Among them, the increase or decrease of the license authentication data is judged according to the value of b - a. The License authentication data increase amplitude change Q refers to the data change of b - a. The License control item quantity F is the number of License control items included in an authentication request. The control item function G is defined according to the functions of the License control items. Among them, parameters such as Q, F, and M are unique features of License on the network management. Based on these features, the prediction accuracy can be improved. With the change N of the number of existing network device accesses as an auxiliary, a machine learning model (i.e., a license network management model) is established to predict parameters such as the grace period T, noise reduction step size X, or failure probability K required for the management network.

[0073] In the embodiments of the present disclosure, the convolutional neural network uses convolutional kernels to extract features, and the fitting ability of the overall license network management model can be controlled by using different convolutions, poolings, and the size of the finally output feature vectors. When overfitting, the dimension of the feature vector can be reduced, and when underfitting, the output dimension of the convolutional layer can be increased. It is more flexible than other feature extraction methods.

[0074] In the embodiments of the present disclosure, for the License authentication flow data set of the target detection point and its adjacent points collected, the License authentication flow data of the points in the area with the same number of devices can be mapped to a one-dimensional vector. Taking the prediction point as the reference point, the License authentication flow data of the prediction point is placed in the center of the vector. Taking the device access flow size as the measurement standard, the vector is filled according to the distance from the reference point, and the vector is subjected to convolutional processing. For example, a convolutional kernel size of 3 and a sliding step size of 1 can be used to extract the License authentication flow correlation within the area of control items with the same function, and a License authentication flow data convolutional feature vector is generated.

[0075] In the embodiments of the present disclosure, convolution can be understood as local weighted summation: g(i) = f(Aw + B), where A represents the input of the convolutional kernel, W represents the weight of the convolutional kernel for processing the input, B represents the bias term, and i represents the number of steps of convolutional sliding, that is, the i-th element in the generated convolutional feature vector, the average convolutional feature vector, to perform average pooling processing on the convolutional feature vector generated in the previous step.

[0076] In an embodiment of the present disclosure, an LSTM recurrent neural network is used to process the sequence data of the increase in License authentication data, analyze the change in the correlation characteristics of the license authentication data stream at different times (or the correlation characteristics of the License authentication stream), fuse the change characteristics of the number of device accesses (i.e., the characteristics obtained based on the change in the historical access number of network devices) and the correlation characteristics of the License authentication stream, and obtain the change trend and time period characteristics of the authentication request, specifically: the correlation characteristics of the License authentication stream extracted at the same time are aggregated into a time series, and the time series is input into the LSTM recurrent neural network to generate an increase change feature vector of the License authentication stream (i.e., the change trend of the authentication request). The time periodic characteristics of the License authentication stream are obtained by collecting the License authentication stream data at the same time within the first preset period (e.g., the previous day) before the License expires and the License authentication stream data at the same time within the second preset period (e.g., the previous week), and inputting the data into the LSTM recurrent neural network respectively, so as to extract the daily cycle characteristics and weekly cycle characteristics.

[0077] In an embodiment of the present disclosure, a fully connected network in the neural network can be used to fuse the time period characteristics extracted from the License authentication stream of the relevant function control items collected and the change characteristics of the number of device accesses, compare the predicted value output by the neural network with the actual value of the License authentication stream, calculate the loss value, continuously optimize the neural network, use the mean square error as the loss function, calculate the characteristics between the predicted value output by the neural network and the actual License authentication stream data, and then use the backpropagation algorithm to continuously optimize the parameters of the neural network. Calculate the parameter gradient in the backpropagation algorithm, and use RMSprop (root mean square propagation) to continuously adapt the learning rate. RMSprop can update the learning rate according to the previous gradient change. The RMSprop algorithm uses the variable MeanSquare(w,t) to save the average value of the gradient squares of each weight for a period of time at the t-th (t is a positive integer) update of the learning rate, and adapt the learning rate according to this variable to continuously optimize the parameters, so that the structure of the neural network reaches the optimal solution.

[0078] In an embodiment of the present disclosure, managing the network of network devices based on network management parameters may include:

[0079] During the grace period T, issue a failure warning to the network device;

[0080] After the grace period has elapsed, at each preset unit of time, the network management calculates the service set and / or the number of network elements that need to be shrunk across the network based on the duration beyond the grace period, and manages the network of network devices based on the service set and / or the number of network elements that need to be shrunk across the network.

[0081] In the embodiments of the present disclosure, after calculating the grace period T based on historical network management data and the licensed network management model, the network of network devices can be managed based on the grace period T. This management includes early warnings and a gradual reduction in network capacity in the later stage.

[0082] In the embodiments of the present disclosure, for example, if the grace period is calculated to be 15 days 10 days before the License file expires, then starting from the current moment, within the first 10 days of these 15 days, the existing network management capabilities can be maintained unchanged, and an alarm message indicating the expiration of the License file can be sent to the alarm management module 103 every day. In the later 5 days of these 15 days (when the License file has expired), a License alarm indicating the lack of a valid license file can be sent to the alarm management module 103 every day and forwarded to the user in the form of a text message or an email. Because this management measure is relatively rigorous, through the daily alarm reports during the grace period, not only can the user be friendly reminded, but also the user experience can be enhanced.

[0083] In the embodiments of the present disclosure, after exceeding the grace period T, warnings can be stopped, and specific management of the network capacity can be started, and as the duration beyond the grace period gradually increases, the management intensity can be gradually strengthened.

[0084] In the embodiments of the present disclosure, for example, the network management can calculate the service set and / or the number of network elements that need to be shrunk across the network based on the duration beyond the grace period, and manage the network of network devices based on the service set and / or the number of network elements that need to be shrunk across the network.

[0085] In the embodiments of the present disclosure, a service set may refer to a set formed by the control of the same network function or different network functions participating in authentication control in order to implement a certain service. The control items of the License are sold by the business according to the contract for different sites and network functions. A preset model of License control items can be established based on the network functions of the control items. Assume that in this preset model of License control items, the set of control items for the China Telecom and China Unicom network usage is 1, the set of control items for the China Mobile network usage is 2, and the set of control items for other international network usage is 3. Based on these data, the network environment of the current network can be known through the preset model of License control items, as well as the corresponding management measures (such as the service set and / or the number of network elements that need to be shrunk across the network) that should be selected for the network after the License file expires. Thus, the network can be managed accordingly based on the corresponding management measures. Moreover, this preset model of License control items can be customized, and sets 4, 5... etc. can continue to be established according to the control item functions.

[0086] In the embodiments of the present disclosure, a preset model of License control items can be flexible. For example, the management measure for the China Telecom and China Unicom network is to reduce power, and the management measure for the China Mobile network can be to reduce the number of RRC (Radio Resource Control) connections.

[0087] In the embodiments of the present disclosure, by analyzing data such as the number of control items F and the control item function G participating in the control in the License authentication through the preset model of License control items, management measures can be obtained, such as Figure 4 As shown, in this preset model of License control items, the set of control items for the China Telecom and China Unicom network usage is 1, the set of control items for the China Mobile network usage is 2, and the set of control items for other international network usage is 3. According to the number of control items F and the control item function G participating in the authentication in the current network, the management measure M can be inferred as 1, 2, or 3. If there is an intersection, the combined management is 1, 2, or 1, 3, or 2, 3. If all are involved, it is 0, indicating that the most stringent management measures 1, 2, and 3 are to be carried out.

[0088] In the embodiments of the present disclosure, the network management calculates the service set and / or the number of network elements that need to be shrunk across the network based on the duration exceeding the grace period according to the network management parameters, which may include:

[0089] When the duration exceeding the grace period is less than or equal to the first duration, calculate the service set and the number of network elements that need to be shrunk across the network according to the network management parameters;

[0090] When the duration exceeding the grace period is greater than the first duration, calculate the service set that needs to be shrunk across the network according to the network management parameters.

[0091] In an embodiment of the present disclosure, when the duration exceeding the grace period is less than or equal to the first duration, the network management capability is managed based on the service set and / or the number of network elements that need to be shrunk across the network, including: managing the network of network devices based on the service set and the number of network elements that need to be shrunk across the network;

[0092] Managing the network of network devices based on the service set and the number of network elements that need to be shrunk across the network may include:

[0093] Selecting target network elements across the network based on the number of network elements;

[0094] Sending a first shrinkage instruction regarding the service set that needs to be shrunk to each target network element, so that the network element calculates a target value of the first configuration data associated with the first shrinkage instruction according to the first shrinkage instruction, and modifies the target value of the first configuration data, and makes the modified target value of the first configuration data take effect.

[0095] In an embodiment of the present disclosure, the data of the first duration can be determined according to requirements, and the detailed value of the first duration is not limited herein. For example, the first duration can be 3 - 5 days.

[0096] In an embodiment of the present disclosure, within the first duration after the grace period, if the network management does not import a valid License, then at each interval duration t1 (for example, every day) without interruption, the network management calculates the service set S that needs to be shrunk across the network and the number of network elements A, intelligently selects a set of target network elements based on the number of network elements A, and sends a shrinkage instruction (i.e., the first shrinkage instruction) to the target network elements respectively. After receiving the shrinkage instruction, the network element intelligently calculates the target value of the first configuration data associated therewith, modifies the target value of the first configuration data and makes it take effect.

[0097] In an embodiment of the present disclosure, when the duration exceeding the grace period is greater than the first duration, the network management capability is managed based on the service set and / or the number of network elements that need to be shrunk across the network, including: managing the network of network devices based on the service set that needs to be shrunk across the network;

[0098] Managing the network of network devices based on the service set that needs to be shrunk across the network includes:

[0099] Sending a second shrinkage instruction regarding the service set that needs to be shrunk to all network elements, so that the network element calculates a target value of the second configuration data associated with the second shrinkage instruction according to the second shrinkage instruction, and modifies the target value of the second configuration data, and makes the modified target value of the second configuration data take effect.

[0100] In an embodiment of the present disclosure, when the duration exceeding the grace period is greater than the first duration, if the network management still fails to import a valid License, the network management can calculate the service set S that needs to be shrunk for the entire network at each interval duration t1 (for example, every day) without interruption, and issue a shrinkage instruction (i.e., the second shrinkage instruction) to all network elements respectively. After receiving the shrinkage instruction, the network element intelligently calculates the target value of the second configuration data associated with it, modifies the target value of the second configuration data, and makes it effective.

[0101] In an embodiment of the present disclosure, the service set may include, but is not limited to, at least one of the following services: network batch configuration ability, performance northbound reporting ability, network access success rate, and network coverage ability.

[0102] In an embodiment of the present disclosure, the service set S can be selected as one or more, and any one or more of the above services can be shrunk.

[0103] In an embodiment of the present disclosure, during the shrinkage of network management capabilities, if a new License file is imported into the network management system, the shrinkage of network management capabilities is immediately interrupted, and all restricted services are restored.

[0104] In an embodiment of the present disclosure, the network management parameters may include: the grace period T and the noise reduction step size X per unit time; the network management calculates the service set and / or the number of network elements that need to be shrunk for the entire network based on the duration exceeding the grace period according to the network management parameters, including:

[0105] The network management calculates the power consumption that needs to be maintained for the current network based on the duration exceeding the grace period and the noise reduction step size;

[0106] Based on the power consumption that needs to be maintained for the current network, calculate the service set and / or the number of network elements that need to be shrunk for the entire network.

[0107] In an embodiment of the present disclosure, the following parameters can be obtained through the read historical network management data:

[0108] T: Grace period;

[0109] X: Noise reduction step size: dB (decibel) / day.

[0110] In an embodiment of the present disclosure, the number of failure days Td after the grace period can be statistically calculated based on the grace period, and the noise reduction lower limit Y (dB), or the power consumption threshold, can be preset.

[0111] In the embodiments of the present disclosure, starting from the T+1 day after the expiration of the validity period of the License file, the actual power consumption value P = 100 - X*Td per day is used to illustrate the relationship between the above parameters. It should be noted that the power consumption of the network devices connected to the network management decreases at a rate of X dB per day. Based on the above data, the service set and / or the number of network elements that need to be shrunk in the whole network can be obtained. Among them, when Td is within the first duration, the service set and the number of network elements that need to be shrunk in the whole network need to be obtained; when T1 exceeds the first duration, the service set that needs to be shrunk in the whole network needs to be obtained.

[0112] In the embodiments of the present disclosure, after the network management calculates the power consumption that the current network needs to maintain according to the duration exceeding the grace period and the noise reduction step size, the method may further include:

[0113] When the power consumption that the current network needs to maintain is lower than the preset power consumption threshold, stop the process of the network management calculating the power consumption that the current network needs to maintain according to the duration exceeding the grace period and the noise reduction step size, and set the power consumption that the subsequent network needs to maintain as the power consumption threshold.

[0114] In the embodiments of the present disclosure, if after noise reduction at a rate of X db per day, when the actual power consumption P < Y, the power consumption of the network devices connected to the network management is less than the set threshold Y, then keep the power consumption of the network devices connected to the network management at Y, that is, P = Y, and no longer reduce the power consumption of the network devices connected to the network management to ensure the most basic usage ability of the network.

[0115] Table 1

[0116]

[0117] In the embodiments of the present disclosure, as shown in Table 1 above, the License storage module 1013 has product files of 3 formats, and the times for importing and activating the License files are different (2023-07-11, 2023-07-12, 2023-07-13 respectively). According to the daily full-network detection of the License control module 101, when the system time reaches 2023-09-10, that is, the first 30 days, the user will be reminded through alarm messages that the License files of 2G, 3G, 4G, and 5G are about to expire; when the system time reaches 2023-10-03, the user can be reminded through an alarm that the Licenses of 2G, 3G, 4G, and 5G are about to exceed the limit and the functions will be restricted, and the user will not be able to shield the alarms in the last 7 days. When the system time reaches 2023-10-10, the countdown of the last grace period T days starts, and within the grace period T days, after the daily full-network detection, an alarm message will be updated at a certain moment to notify the user that the network will be restricted soon.

[0118] In an embodiment of the present disclosure, when the grace period T ends, the functions of all network devices with 2G, 3G, 4G, and 5G related standards in the network environment will immediately start to be restricted. Starting from the day after the grace period T ends, the power consumption of all network devices with 2G, 3G, 4G, and 5G related standards connected to the network management will be gradually reduced at a rate of X dB per day, and the network usage capacity will start to decrease. According to the expression: P = 100 - X * Td, the power consumption of the network devices is reduced, and the network usage capacity is decreased.

[0119] Table 2

[0120] License Expiration Days Current Network Power Consumption dB Network Noise Reduction Lower Limit dB T X dB Y dB T + T1 100 - X * T1 dB Y dB ... ... Y dB T + T16 100 - X * T16 dB Y dB T + T17 Y dB Y dB T + T18 Y dB Y dB

[0121] In an embodiment of the present disclosure, as shown in Table 2, if on the T17th day after the grace period T has passed, such that Y < 100 - X * T17, then this time the current network power consumption can be set to the lower limit value of Y dB.

[0122] In an embodiment of the present disclosure, the network management parameters may include: the grace period T and the probability K of access network failure per unit time; based on the duration exceeding the grace period, the network management calculates the service set and / or the number of network elements that need to be contracted for the entire network according to the network management parameters, including:

[0123] The network management calculates the total failure rate of the access network that the current network needs to maintain according to the duration exceeding the grace period, the access network failure probability A, and the number of network device accesses;

[0124] According to the total failure rate of the access network, the service set and / or the number of network elements that need to be contracted for the entire network are calculated.

[0125] In an embodiment of the present disclosure, the following parameters can be obtained through the read historical network management data:

[0126] T: Grace period;

[0127] K: Failure probability: % / day.

[0128] In an embodiment of the present disclosure, the number of days of failure Td after the grace period can be statistically counted based on the grace period, and the upper limit of the failure probability Kd (or failure rate threshold, unit: %) and the initial value K1 of the current failure probability are preset to 0%; and the number N of devices currently accessing the network is obtained.

[0129] In an embodiment of the present disclosure, starting from the (T + 1)-th day after the expiration of the validity period of the License file, the actual access failure probability Zi per day = K1 + K * Td (where i is a positive integer). It should be noted that the network management system increases the access failure probability of network devices accessing the network at a rate of K% per day, and the number of network devices accessing the network management system will randomly decrease by a certain proportion every day. Based on the above data, the service set and / or the number of network elements that need to be shrunk across the network can be obtained. Among them, when Td is within the first time period, the service set and the number of network elements that need to be shrunk across the network need to be obtained; when Td exceeds the first time period, the service set that needs to be shrunk across the network needs to be obtained.

[0130] In an embodiment of the present disclosure, after the network management system calculates the total access failure rate that the current network needs to maintain based on the duration exceeding the grace period, the access network failure probability A, and the number of network devices accessing the network, the method may further include:

[0131] When the total access failure rate that the current network needs to maintain is higher than the preset failure rate threshold, stop the process of the network management system calculating the total access failure rate that the current network needs to maintain based on the duration exceeding the grace period, the access network failure probability, and the number of network devices accessing the network, and set the total access failure rate that the subsequent network needs to maintain to the failure rate threshold.

[0132] Table 3

[0133] License Expiration Days Current Network Access Failure Probability Upper Limit of Failure Probability Number of Network Access Devices T Z = K1% Kd% N T + T1 Z1 = Z + K * T1% Kd% N1 = N - N·Z1 ... ... Kd% ... T + T16 Z16 = Z15 + K * T16% Kd% N16 = N15 - N15·Z16 T + T17 Kd% Kd% N17 = N16 - N16·Kd% T + T18 Kd% Kd% N18 = N17 - N17·Kd%

[0134] In an embodiment of the present disclosure, as Td increases, if the actual failure probability Zi > K1 + K * Td, then the access failure probability of the network devices accessing the network management system will be greater than the set threshold Kd. At this time, set the access failure probability of the network devices accessing the network to Kd, and no longer increase the access failure probability of the network devices accessing the network management system to ensure the most basic network usage ability.

[0135] In an embodiment of the present disclosure, the above solution of the embodiment of the present disclosure can also be extended and customized. As long as appropriate management measures are established according to the services (by imposing some restrictions on the network frequency band and bandwidth according to the usage scenario to achieve the expected network management purpose), and after being associated with the preset model of the License control item, the corresponding management measures can be obtained, and the network can be intelligently managed after the network management license expires.

[0136] In an embodiment of the present disclosure, when the user still has a need to use the current network, by importing a new License file, the network management will send an alarm recovery message of the corresponding system to the alarm management, and restore the network functions of the corresponding restricted network elements until the user imports the new unexpired License file of the corresponding system into the License storage module 1013. Then, the License control module 1012 will immediately detect a change in the product file list in the License storage module 1013, and will sequentially restore the entire network to the state before the License file expired.

[0137] In an embodiment of the present disclosure, after managing the network of a network device based on network management parameters, the method may further include:

[0138] After detecting information about a preset natural disaster, cancel the management of all networks.

[0139] In an embodiment of the present disclosure, an emergency state handling solution is provided: If natural disasters such as earthquakes, tsunamis, and typhoons occur during the intelligent energy conservation and emission reduction process of the network management, when the message monitoring module 105 detects a message about the occurrence of a natural disaster, it will immediately report an alarm to the alarm management module 103. After the License management module 101 immediately synchronizes the alarm message, it will send a message to all network devices in the network to enter the emergency state in the first time, or the network covered by the network devices in a certain area where a natural disaster occurs can be entered into the emergency state through the License control module 1012, so that these devices are no longer restricted by the License and can normally use mobile network functions within a certain period of time (for example, determined according to set parameters), as Figure 5 shown.

[0140] In an embodiment of the present disclosure, when using the network devices of 2G, 3G, 4G, and 5G in the embodiment of the present disclosure, after the License file expires, through the measure of the network management intelligent contraction of network management capabilities, the management purpose of reasonably recycling network resources without a license is achieved, reducing the unreasonable use scenarios of network resources without a license, and urging users to apply for a License in a timely manner.

[0141] An embodiment of the present disclosure also provides an electronic device 200, as Figure 6 shown, the electronic device 100 includes:

[0142] One or more processors 201;

[0143] A memory 202, on which one or more programs are stored. When the one or more programs are executed by the one or more processors 201, the one or more processors 201 implement the network management method described above;

[0144] One or more input / output I / O interfaces 203, connected between the processor 201 and the memory 202, are configured to implement information interaction between the processor 201 and the memory 202.

[0145] Among them, the processor 201 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 202 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read / write interface) 203 is connected between the processor 201 and the memory 202 and can implement information interaction between the processor 201 and the memory 202, including but not limited to a data bus (Bus), etc.

[0146] In some embodiments, the processor 201, the memory 202, and the I / O interface 203 are interconnected through a bus 104 and further connected to other components of the computing device.

[0147] The embodiments of the present disclosure also provide a computer-readable storage medium 300, as Figure 7 shown, a computer program is stored on the computer-readable storage medium 300, and when the computer program is executed by a processor, the network management method described above is implemented.

[0148] Those of ordinary skill in the art can understand that all or some of the functional modules / units disclosed above can be implemented as software, firmware, hardware, and their appropriate combinations.

[0149] In the hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be executed by several physical components in cooperation.

[0150] Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit (CPU), a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH), or other magnetic disk storage; compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical disc storage; magnetic cassettes, tapes, magnetic disk storage, or other magnetic storage; and any other medium that can be used to store the desired information and that can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery medium.

[0151] The present disclosure has disclosed example embodiments, and although specific terms have been employed, they are used only and should be construed only for general illustrative purposes and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly stated, features, characteristics, and / or elements described in connection with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in connection with other embodiments. Accordingly, those skilled in the art will understand that various forms and details may be changed without departing from the scope of the present disclosure as set forth by the appended claims.

Claims

1. A network management method, characterized in that, applied to the network management side, the method includes: detecting the remaining valid duration of the license file; if the remaining valid duration reaches a first preset duration, calling historical network management data; determining network management parameters according to the historical network management data; managing the network of network devices based on the network management parameters.

2. The network management method according to claim 1, characterized in that, the historical network management data includes at least one of the following: changes in the historical access quantity of network devices; and, historical license authentication flow data.

3. The network management method according to claim 2, characterized in that, the historical license authentication flow data includes at least one of the following: changes in the increase of license authentication data, the number of control items participating in control in license authentication, and the functions of the control items participating in control in license authentication.

4. The network management method according to claim 3, characterized in that, the determining network management parameters according to the historical network management data includes: inputting the historical network management data into a license network management model and outputting the network management parameters.

5. The network management method according to claim 4, characterized in that, the network management parameters include at least one of the following: grace period; noise reduction step size per unit time; and, probability of network access failure per unit time; the license network management model includes: a convolutional neural network and a long short-term memory recurrent neural network.

6. The network management method according to claim 5, characterized in that, the inputting the historical network management data into a license network management model and outputting the network management parameters includes: inputting the historical network management data into the convolutional neural network to obtain the correlation characteristics of the license authentication data stream within the area of control items with the same function; inputting the correlation characteristics of the license authentication data stream and the changes in the historical access quantity of network devices into the long short-term memory recurrent neural network, and fusing the correlation characteristics of the license authentication data stream and the changes in the historical access quantity of network devices by the long short-term memory recurrent neural network to obtain the change trend of authentication requests and the characteristics of the authentication request time period; calculating the grace period according to the characteristics of the authentication request time period, and obtaining the noise reduction step size and the probability of network access failure according to the change trend of authentication requests.

7. The network management method according to claim 1, characterized in that, the network management parameters include: grace period; the managing the network of network devices based on the network management parameters includes: giving a failure warning to the network device within the grace period; after exceeding the grace period, every preset unit time, the network management calculates the service set and / or the number of network elements that need to be shrunk in the whole network based on the duration exceeding the grace period according to the network management parameters, and manages the network of the network device based on the service set and / or the number of network elements that need to be shrunk in the whole network.

8. The network management method according to claim 7, characterized in that, the network management calculating the service set and / or the number of network elements that need to be shrunk in the whole network based on the duration exceeding the grace period according to the network management parameters includes: When the duration exceeding the grace period is less than or equal to the first duration, calculate the service set and the number of network elements that need to be shrunk in the whole network according to the network management parameters; When the duration exceeding the grace period is greater than the first duration, calculate the service set that needs to be shrunk in the whole network according to the network management parameters.

9. The network management method according to claim 8, characterized in that When the duration exceeding the grace period is less than or equal to the first duration, the management of the network management capability based on the service set and / or the number of network elements that need to be shrunk in the whole network includes: managing the network of the network device based on the service set and the number of network elements that need to be shrunk in the whole network; The management of the network of the network device based on the service set and the number of network elements that need to be shrunk in the whole network includes: Select target network elements in the whole network based on the number of network elements; Send a first shrinkage instruction regarding the service set that needs to be shrunk to each of the target network elements, so that the network element calculates a first configuration data target value associated with the first shrinkage instruction according to the first shrinkage instruction, and modifies the first configuration data target value to make the modified first configuration data target value take effect.

10. The network management method according to claim 7, characterized in that When the duration exceeding the grace period is greater than the first duration, the management of the network management capability based on the service set and / or the number of network elements that need to be shrunk in the whole network includes: managing the network of the network device based on the service set that needs to be shrunk in the whole network; The management of the network of the network device based on the service set that needs to be shrunk in the whole network includes: Send a second shrinkage instruction regarding the service set that needs to be shrunk to all network elements, so that the network element calculates a second configuration data target value associated with the second shrinkage instruction according to the second shrinkage instruction, and modifies the second configuration data target value to make the modified second configuration data target value take effect.

11. The network management method according to claim 9 or 10, characterized in that The service set includes at least one of the following services: network batch configuration capability, performance northbound reporting capability, network access success rate, and network coverage capability.

12. The network management method according to claim 7, characterized in that The network management parameters include: grace period and the noise reduction step length per unit time; the network management calculates the service set and / or the number of network elements that need to be shrunk in the whole network based on the duration exceeding the grace period according to the network management parameters, including: The network management calculates the power consumption that the current network needs to maintain according to the duration exceeding the grace period and the noise reduction step length; Calculate the service set and / or the number of network elements that need to be shrunk in the whole network according to the power consumption that the current network needs to maintain.

13. The network management method according to claim 12, characterized in that After the network management calculates the power consumption that the current network needs to maintain according to the duration exceeding the grace period and the noise reduction step length, the method further includes: When the power consumption required to be maintained by the current network is lower than a preset power consumption threshold, stop the process in which the network management device calculates the power consumption required to be maintained by the current network according to the duration exceeding the grace period and the noise reduction step size, and set the power consumption required to be maintained by the subsequent network to the power consumption threshold.

14. The network management method according to claim 7, wherein, the network management parameters include: a grace period and the probability of access network failure per unit time; the network management device calculates the service set and / or the number of network elements that the entire network needs to shrink based on the duration exceeding the grace period according to the network management parameters, including: the network management device calculates the total access network failure rate required to be maintained by the current network according to the duration exceeding the grace period, the access network failure probability, and the number of network device accesses; calculate the service set and / or the number of network elements that the entire network needs to shrink according to the total access network failure rate.

15. The network management method according to claim 14, wherein, after the network management device calculates the total access network failure rate required to be maintained by the current network according to the duration exceeding the grace period, the access network failure probability, and the number of network device accesses, the method further includes: when the total access network failure rate required to be maintained by the current network is higher than a preset failure rate threshold, stop the process in which the network management device calculates the total access network failure rate required to be maintained by the current network according to the duration exceeding the grace period, the access network failure probability, and the number of network device accesses, and set the total access network failure rate required to be maintained by the subsequent network to the failure rate threshold.

16. The network management method according to claim 1, wherein, after managing the network of the network device based on the network management parameters, the method further includes: after detecting information about a preset natural disaster, cancel the management of all networks.

17. An electronic device, wherein, the electronic device includes: one or more processors; a memory storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the network management method according to any one of claims 1-16; one or more input / output I / O interfaces connected between the processor and the memory and configured to implement information interaction between the processor and the memory.

18. A computer-readable storage medium storing a computer program, which when executed by a processor implements the network management method according to any one of claims 1-16.

Images