CN119094341A - Method, device, equipment and storage medium for generating network management plan - Google Patents

Abstract

The present disclosure provides a method, device, equipment and storage medium for generating a network management solution, and relates to the field of computer technology. The method includes: determining a network management optimization target in response to a network management trigger; determining network data to be analyzed and a network data analysis strategy according to the network management optimization target; processing the network data to be analyzed by the network data analysis strategy to generate an analysis result; obtaining historical data corresponding to the network management optimization target, and determining a target network management solution according to the historical data and the analysis result. The method can generate a network management strategy using data-driven and optimization-target-oriented methods to improve the overall performance of the network and user experience.

Description

Method, device, equipment and storage medium for generating network management scheme

Technical Field

The disclosure relates to the field of computer technology, and in particular, to a method, a device, equipment and a storage medium for generating a network management scheme.

Background

With the development of network technology, network states need to be focused from multiple dimensions and optimization is performed in time, and network optimization is an important aspect aiming at network performance guarantee and user experience improvement.

In the related art, optimization management is required in various fields of network planning, network diagnosis, network optimization, control and the like, and decision making is usually carried out by relying on manual intervention, so that decision making is often not carried out in time, and consideration is not comprehensive enough.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The purpose of the present disclosure is to provide a method, an apparatus, a device, and a storage medium for generating a network management scheme, which can utilize data driving and take an optimization target as a guide to generate a network management policy, thereby improving the overall performance and user experience of a network.

Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.

According to one aspect of the disclosure, a method for generating a network management scheme is provided, which comprises the steps of responding to triggering of network management, determining a network management optimization target, determining network data to be analyzed and a network data analysis strategy according to the network management optimization target, processing the network data to be analyzed through the network data analysis strategy to generate an analysis result, acquiring historical data corresponding to the network management optimization target, and determining a target network management scheme according to the historical data and the analysis result.

In one embodiment of the disclosure, determining a network management optimization target in response to a trigger of network management includes determining to trigger the network management in response to a received network management request and determining a network management optimization target according to the network management request, or determining to trigger the network management in response to a network monitoring event meeting a trigger condition and determining a network management optimization target according to the trigger condition.

In one embodiment of the disclosure, determining network data to be analyzed according to the network management optimization objective comprises determining one or more optimization factors according to the network management optimization objective, determining network data related to each optimization factor from a network element sensing dataset as the network data to be analyzed, wherein the network element sensing dataset contains network data captured by network element sensors deployed on various network components, and the types of the network data relate to at least one of network performance indexes, network service time, network real-time data and network equipment information.

In one embodiment of the disclosure, the network data analysis strategy comprises at least one network data analysis algorithm corresponding to the network management optimization target and an optimization threshold value therein, wherein the network data analysis strategy is determined according to the network management optimization target, the network data analysis strategy comprises the steps of determining one or more optimization factors according to the network management optimization target, determining network data analysis algorithms related to the optimization factors from an integrated algorithm library, and determining the optimization threshold value corresponding to the optimization factors as the optimization threshold value in the network data analysis algorithm related to the optimization factors.

In one embodiment of the disclosure, a data entry format is indicated in the network data analysis algorithm, wherein the network data to be analyzed is processed through the network data analysis strategy to generate an analysis result, the analysis result comprises preprocessing the network data to be analyzed according to the data entry format indicated in each network data analysis algorithm to obtain data to be calculated for each network data analysis algorithm, inputting the data to be calculated for each network data analysis algorithm and a corresponding optimization threshold value into each network data analysis algorithm to obtain parameter configuration data which is output by each network data analysis algorithm and aims at corresponding optimization factors, and carrying out association combination on the parameter configuration data with corresponding relations, the network data to be analyzed and the optimization threshold value to generate the analysis result.

In one embodiment of the disclosure, the integrated algorithm library comprises at least one of convolutional neural network planning, reinforcement learning network planning, deep learning network automation, K-average algorithm network planning, random forest network planning, principal component analysis network planning, decision tree network optimization, anomaly detection algorithm network security and genetic algorithm network optimization; the algorithms in the integrated algorithm library relate to at least one of the following business fields, network planning, network automation, network security and network optimization.

In one embodiment of the disclosure, parameter configuration data and an optimization threshold for the network management optimization target are indicated in the analysis result, wherein determining a target network management scheme according to the historical data and the analysis result comprises determining a historical management scheme corresponding to the network management optimization target in the historical data, determining a historical optimization effect value in each historical management scheme, determining the historical management scheme as a target network management scheme if the historical optimization effect value is superior to the optimization threshold, and determining the target network management scheme according to the parameter configuration data if the optimization threshold is superior to the historical optimization effect value.

According to another aspect of the disclosure, a generating device of a network management scheme is provided, which comprises a trigger response unit, a determining unit, an analyzing unit and a scheme generating unit, wherein the trigger response unit is used for responding to the triggering of network management and determining a network management optimization target, the determining unit is used for determining network data to be analyzed and a network data analysis strategy according to the network management optimization target, the analyzing unit is used for processing the network data to be analyzed through the network data analysis strategy to generate an analysis result, and the scheme generating unit is used for acquiring historical data corresponding to the network management optimization target and determining a target network management scheme according to the historical data and the analysis result.

In one embodiment of the disclosure, the triggering response unit is used for responding to the triggering of the network management to determine a network management optimization target, and comprises the steps of responding to a received network management request, determining to trigger the network management and determining the network management optimization target according to the network management request, or responding to a network monitoring event to meet a triggering condition, determining to trigger the network management and determining the network management optimization target according to the triggering condition.

In one embodiment of the disclosure, the determining unit determines network data to be analyzed according to the network management optimization objective, and the determining unit determines one or more optimization factors according to the network management optimization objective, determines network data related to each optimization factor from a network element sensing data set as the network data to be analyzed, wherein the network element sensing data set contains network data captured by network element sensors deployed on various network components, and the types of the network data relate to at least one of network performance indexes, network service time, network real-time data and network equipment information.

In one embodiment of the disclosure, the network data analysis strategy comprises at least one network data analysis algorithm corresponding to the network management optimization target and an optimization threshold value therein, wherein the determining unit determines the network data analysis strategy according to the network management optimization target, and the determining unit comprises determining one or more optimization factors according to the network management optimization target, determining the network data analysis algorithm related to each optimization factor from an integrated algorithm library, and determining the optimization threshold value corresponding to each optimization factor as the optimization threshold value in the network data analysis algorithm related to each optimization factor.

In one embodiment of the disclosure, a data entry format is indicated in the network data analysis algorithm, wherein an analysis unit processes the network data to be analyzed through the network data analysis strategy to generate an analysis result, the analysis unit comprises preprocessing the network data to be analyzed according to the data entry format indicated in each network data analysis algorithm to obtain data to be calculated for each network data analysis algorithm, inputting the data to be calculated for each network data analysis algorithm and a corresponding optimization threshold value into each network data analysis algorithm to obtain parameter configuration data which is output by each network data analysis algorithm and aims at corresponding optimization factors, and performing association combination on the parameter configuration data with corresponding relations, the network data to be analyzed and the optimization threshold value to generate the analysis result.

In one embodiment of the disclosure, the integrated algorithm library comprises at least one of convolutional neural network planning, reinforcement learning network planning, deep learning network automation, K-average algorithm network planning, random forest network planning, principal component analysis network planning, decision tree network optimization, anomaly detection algorithm network security and genetic algorithm network optimization; the algorithms in the integrated algorithm library relate to at least one of the following business fields, network planning, network automation, network security and network optimization.

In one embodiment of the disclosure, parameter configuration data and an optimization threshold for the network management optimization target are indicated in the analysis result, wherein a scheme generating unit determines a target network management scheme according to the historical data and the analysis result, the scheme generating unit comprises determining historical management schemes corresponding to the network management optimization target in the historical data, determining historical optimization effect values in each historical management scheme, determining the historical management scheme as the target network management scheme if the historical optimization effect values are superior to the optimization threshold, and determining the target network management scheme according to the parameter configuration data if the optimization threshold is superior to the historical optimization effect values.

According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of generating a network management scheme as described above.

According to yet another aspect of the present disclosure, there is provided an electronic device including a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to perform the method of generating a network management scheme described above via execution of the executable instructions.

According to yet another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of generating a network management scheme as described above.

The method for generating the network management scheme provided by the embodiment of the disclosure can realize a data-driven network management mode, automatically determine relevant network data to be analyzed based on a network management optimization target, determine network data analysis strategies which correspond to the optimization target and can be used for processing the network data to be analyzed, and ensure the scientificity and the effectiveness of network management through a systematic flow. The method not only can help a network manager to quickly respond to the triggering of network management, but also can continuously optimize the management strategy based on historical data to improve the overall performance and user experience of the network and ensure the scientificity and effectiveness of network management.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.

Fig. 1 shows a schematic diagram of an exemplary system architecture to which a generation method of a network management scheme of an embodiment of the present disclosure may be applied.

Fig. 2 shows a flowchart of a method of generating a network management scheme of one embodiment of the present disclosure.

Fig. 3 shows a flowchart of a method of generating a network management scheme of one embodiment of the present disclosure.

Fig. 4 illustrates a flowchart of determining network data to be analyzed in a method of generating a network management scheme according to an embodiment of the present disclosure.

Fig. 5 illustrates a flowchart of determining a network data analysis policy in a method of generating a network management scheme according to one embodiment of the present disclosure.

Fig. 6 shows a flowchart of generating an analysis result in the generation method of the network management scheme of one embodiment of the present disclosure.

Fig. 7 shows a block diagram of a generation apparatus of a network management scheme of one embodiment of the present disclosure.

Fig. 8 shows a block diagram of a network management scheme generating computer device in an embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein, but rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present disclosure, the meaning of "a plurality" is at least two, such as two, three, etc., unless explicitly specified otherwise.

Fig. 1 shows a schematic diagram of an exemplary system architecture to which a generation method of a network management scheme of an embodiment of the present disclosure may be applied.

As shown in fig. 1, the system architecture may include a server 101, a network 102, and a client 103. Network 102 is the medium used to provide communication links between clients 103 and server 101. Network 102 may include various connection types such as wired, wireless communication links, or fiber optic cables, among others.

In an exemplary embodiment, the client 103 in data transmission with the server 101 may include, but is not limited to, a smart phone, a desktop computer, a tablet computer, a notebook computer, a smart speaker, a digital assistant, an AR (Augmented Reality) device, a VR (Virtual Reality) device, a smart wearable device, and the like. Alternatively, the operating system running on the electronic device may include, but is not limited to, an android system, an IOS system, a linux system, a windows system, and the like.

The server 101 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligent platforms, and the like. In some practical applications, the server 101 may also be a server of a network platform, and the network platform may be, for example, a transaction platform, a live broadcast platform, a social platform, or a music platform, which is not limited in the embodiments of the present disclosure. The server may be one server or may be a cluster formed by a plurality of servers, and the specific architecture of the server is not limited in this disclosure.

In an exemplary embodiment, a user may perform an operation on the client 103, for example, may input a network management instruction, so that a network management request is generated on the client 103 and sent to the server 101, and the server 101 determines that network management is triggered, so as to execute a method for generating a network management scheme provided in the present disclosure.

In an exemplary embodiment, the process of the server 101 for implementing the method for generating the network management scheme may be that the server 101 determines a network management optimization target in response to a trigger of network management, the server 101 determines network data to be analyzed and a network data analysis policy according to the network management optimization target, the server 101 processes the network data to be analyzed through the network data analysis policy to generate an analysis result, the server 101 obtains historical data corresponding to the network management optimization target, and determines a target network management scheme according to the historical data and the analysis result.

In addition, it should be noted that, fig. 1 is only one application environment of the method for generating the network management scheme provided in the present disclosure. The number of servers 101, networks 102, and clients 103 in FIG. 1 is merely illustrative, and any number of clients, networks, and servers may be provided as desired.

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the following describes in more detail each step of the method for generating a network management scheme in the exemplary embodiment of the present disclosure with reference to the accompanying drawings and embodiments.

Fig. 2 shows a flowchart of a method of generating a network management scheme of one embodiment of the present disclosure. The method provided by the embodiments of the present disclosure may be performed by the server 101 or the client 103 as shown in fig. 1, but the present disclosure is not limited thereto.

In the following explanation, the server 101 is exemplified as an execution subject.

As shown in fig. 2, the method for generating a network management scheme according to an embodiment of the present disclosure may include the following steps.

Step S201, in response to the triggering of the network management, determining a network management optimization target.

In this embodiment, network management is a data-driven management activity aimed at optimizing network performance and improving user experience. The triggering mechanism for network management may include various means such as the occurrence of specific events (e.g., system performance degradation, increased user complaints, security event occurrence), periodic maintenance planning, network management instructions with targeted optimization effects, etc.

Network management optimization objectives may be determined based on the trigger patterns, and these objectives may include improving network performance, reducing latency, enhancing security, optimizing resource allocation, improving user satisfaction, etc.

Step S203, determining the network data to be analyzed and the network data analysis policy according to the network management optimization target.

In this embodiment, relevant network data may be automatically selected for collection according to a network management optimization objective, so as to serve as network data to be analyzed. Such data may include network traffic data, device performance data, user behavior data, multimedia content data uploaded to the cloud by the user, security logs, and the like.

In an exemplary embodiment, the collected network data to be analyzed can be subjected to preprocessing work such as cleaning, conversion, aggregation and the like, so that the data quality is ensured.

In this embodiment, an appropriate network data analysis policy may be formulated according to a network management optimization objective, for example, a policy of which analysis tool (such as a big data platform and a machine learning model), an analysis dimension (such as time, geographic location and user type), an analysis method (such as statistical analysis, trend prediction and anomaly detection) is adopted. The network data analysis strategy is corresponding to the network management optimization target and can provide analysis algorithms and related information for processing the network data to be analyzed.

In an exemplary embodiment, a plurality of network data analysis policies corresponding to different network management optimization objectives may be formulated in advance, and when the network management optimization objectives are determined, the network data analysis policies corresponding thereto may be automatically associated for use.

Step S205, processing the network data to be analyzed through the network data analysis policy, and generating an analysis result.

In this embodiment, the determined network data analysis policy may be used to perform deep analysis on the network data to be analyzed, mine a potential mode, trend or problem, and then determine an analysis result based on the mined result.

Step S207, obtaining historical data corresponding to the network management optimization target, and determining a target network management scheme according to the historical data and the analysis result.

In the present embodiment, in the history data corresponding to the network management optimization target, the network management policy and the effect in the similar case in the past may be included, and thus the history data may be acquired as a reference. The specific network management scheme can be prepared by combining historical data and current analysis results and comprehensively considering factors such as technical feasibility, cost effectiveness, user influence and the like.

In an exemplary embodiment, the formulated solution may also be subjected to simulation tests or small-scale trial-and-error to evaluate its actual effectiveness and potential risk. After the evaluation is passed, the network management scheme can be formally implemented, and the effect of the network management scheme can be continuously monitored so as to adjust and optimize in time.

According to the method for generating the network management scheme, the network management optimization target can be automatically determined in response to the triggering of the network management, the network data to be analyzed and the required network data analysis strategy are automatically determined according to the network management optimization target, then the network data to be analyzed are processed by using the network data analysis strategy to generate an analysis result, and finally the target network management scheme is generated according to the historical data and the analysis result under the same network management optimization target. Therefore, the generation method of the network management scheme provided by the disclosure is a data-driven network management mode, can automatically determine relevant network data to be analyzed based on a network management optimization target, and determine network data analysis strategies which correspond to the optimization target and can be used for processing the network data to be analyzed, and ensures the scientificity and the effectiveness of network management through a systematic flow. The method not only can help a network manager to quickly respond to the triggering of network management, but also can continuously optimize the management strategy based on historical data to improve the overall performance and user experience of the network and ensure the scientificity and effectiveness of network management.

Fig. 3 shows a flowchart of a method of generating a network management scheme of one embodiment of the present disclosure. As shown in fig. 3, in the embodiment of the present disclosure, steps S305, S307, S309 in the method for generating the network management scheme shown in fig. 3 correspond to steps S203, S205, S207, respectively, in the method for generating the network management scheme shown in fig. 2, and are not repeated here.

In some embodiments, the method for generating the network management scheme shown in fig. 3 may further include the following steps based on the method for generating the network management scheme shown in fig. 2.

Step S301, in response to the received network management request, determines to trigger the network management, and determines a network management optimization objective according to the network management request.

In this embodiment, when a network administrator or system actively initiates a network management request, this indicates that there is a specific need or problem in the network, and management and optimization is required.

In an exemplary embodiment, the system is able to determine the optimization objective for network management based on the specifics of this request. For example, if the request is to optimize network speed for a particular region, the optimization goal may be to increase network bandwidth utilization for that region or decrease latency.

Step S303, responding to the network monitoring event to meet the triggering condition, determining to trigger the network management, and determining a network management optimization target according to the triggering condition.

In this embodiment, the network monitoring is performed continuously to monitor the state and performance of the network in real time. When it is monitored that one or more events (such as network congestion, equipment failure, security event, etc.) meet a preset trigger condition, the system automatically triggers a network management process. The trigger condition may be, for example, threshold-based (e.g., bandwidth usage exceeding 80%), pattern-based (e.g., network jitter that occurs frequently), or complex logic-based (e.g., multi-factor comprehensive judgment).

In an exemplary embodiment, the system may determine the corresponding network management optimization objective based on the specifics of the trigger condition. For example, if the CPU usage of a network device (e.g., a switch, a router) abnormally increases, reaches an early warning threshold, and is accompanied by signs of performance degradation (e.g., a longer response time), then it may be determined that its corresponding network management optimization objective is to deeply analyze the root cause of the device failure (e.g., software defect, hardware aging, etc.).

In either of the ways of step S301 and step S303, the server may determine that the network management is triggered, and determine the network management optimization target.

The two triggering modes in the embodiment ensure that the system can flexibly cope with different network management requirements. By the two modes, the system can perform network management more actively and intelligently, so that the stability and performance of the network are improved.

Fig. 4 illustrates a flowchart of determining network data to be analyzed in a method of generating a network management scheme according to an embodiment of the present disclosure. As shown in fig. 4, in some embodiments, determining the network data to be analyzed according to the network management optimization objective may include the following steps.

Step S401, determining one or more optimization factors according to the network management optimization objective.

In this embodiment, based on a determined network management optimization objective, the system may first identify one or more key optimization factors that affect achievement of the objective. These factors may be specific network performance metrics (e.g., bandwidth utilization, delay, packet loss), reliability or efficiency of network services (e.g., service time, failure recovery time), processing power of real-time data (e.g., real-time transmission delay, data integrity), or performance and status of the network device itself (e.g., device load, CPU utilization, memory usage).

Step S403, determining network data related to each optimization factor from the network element sensing data set as the network data to be analyzed.

Wherein the network element sensing dataset comprises network data captured by network element sensors deployed on a variety of network components, the type of network data relating to at least one of network performance metrics, network service time, network real-time data, and network device information.

In this embodiment, a correspondence between the optimization factor and the network data type may be preset, and then network data to be analyzed may be found out from the network element sensing data set according to the optimization factor. Network sensing data acquired by the network component corresponding to the corresponding network data type can also be directly acquired to serve as network data to be analyzed.

In an exemplary embodiment, the optimized scenarios may include wireless networks, user social behavior, multimedia content, based on which the network element sensing dataset may include large datasets related to these optimized scenarios. Specifically, it may include:

a wireless data set corresponding to the wireless network, wherein the wireless data set may include infrastructure data, key index data (such as data, data traffic, data throughput, end-to-end delay, etc.), call Detail Records (CDRs), radio information data, etc.;

A social data set corresponding to social behavior of the user, which may include an interactive data set of social media preferences of individuals and social groups;

The cloud data set corresponding to the multimedia content may include the multimedia content stored in the cloud server.

In this embodiment, when the optimization factors are determined, the system may screen out network data directly related to the optimization factors from the network element sensing dataset. The network element sensing dataset is a huge data warehouse containing various types of network data captured by network element sensors deployed on various components in the network (such as routers, switches, servers, base stations, etc.).

The types of such network data may be very broad, including but not limited to network performance metrics (e.g., throughput, bandwidth utilization), network service time (e.g., service response time, mean time to failure), network real-time data (e.g., data packets that are actually transmitted, status information for the data flows), and network device information (e.g., device model, configuration parameters, hardware health), etc.

In an exemplary embodiment, the network data associated with each optimization factor may also be consolidated into a data set to be analyzed. This dataset is the basis for the subsequent analysis effort that will provide data support for evaluating current network conditions, identifying potential problems, and formulating optimization strategies.

By the embodiment, high pertinence and efficiency can be ensured to be maintained when network data are analyzed, and submerged interference caused by massive and irrelevant data is avoided.

In some embodiments, the network data analysis policy includes at least one network data analysis algorithm corresponding to the network management optimization objective and an optimization threshold therein.

Fig. 5 illustrates a flowchart of determining a network data analysis policy in a method of generating a network management scheme according to one embodiment of the present disclosure. As shown in fig. 5, in some embodiments, determining a network data analysis policy based on the network management optimization objective may include the following steps.

Step S501, determining one or more optimization factors according to the network management optimization objective.

In this embodiment, the network management optimization objective may be understood as a macroscopic and abstract guiding direction, and the optimization factor is a specific aspect that needs to be focused on to achieve the network management objective. For example, if the network management optimization goal is to reduce network latency, the optimization factors may include route optimization, congestion control, protocol efficiency, and the like.

In step S503, a network data analysis algorithm related to each optimization factor is determined from the integrated algorithm library.

In this embodiment, after the optimization factors are specified, a network data analysis algorithm matching with these factors may be selected from a pre-integrated algorithm library. The network data analysis algorithms may include traffic analysis algorithms, performance assessment algorithms, fault prediction algorithms, etc., which enable in-depth analysis for specific optimization factors.

In some embodiments, the algorithms in the integrated algorithm library relate to at least one of the following business domains, network planning domain, network automation domain, network security domain, and network optimization domain.

In some embodiments, the integrated algorithm library comprises at least one of convolutional neural network planning, reinforcement learning network planning, deep learning network automation, K-average algorithm network planning, random forest network planning, principal component analysis network planning, decision tree network optimization, anomaly detection algorithm network security, genetic algorithm network optimization.

In an exemplary embodiment, the specific content of each algorithm in the integrated algorithm library may be:

① The convolutional neural network planning is used for analyzing high-resolution satellite images, considering factors such as topography, population density, urban development degree and the like to determine potential positions of base stations, and analyzing images and videos captured by a network camera to detect network faults and optimize network performance.

② Reinforcement learning network planning for optimizing the location and resource allocation of the base station. The algorithm can learn from the historical data to determine the optimal position of the base station, dynamically adjust the resource allocation to optimize the network performance, and can also adjust the network parameters in real time according to the performance and feedback of the network for optimizing the 5G network and realizing the autonomous network management in the 5G network.

③ Deep learning network automation, traffic prediction, network optimization and anomaly detection. Deep learning algorithms use neural networks to process and analyze large amounts of data, learn complex patterns and relationships in the data, thereby identifying patterns in the data and predicting future performance, optimizing the 5G network.

④ And (3) K average algorithm network planning, namely identifying user groups with similar traffic patterns, and helping to optimize network resource allocation and improve network efficiency.

⑤ Random forest network planning, which predicts the demands of users on different services, such as video streaming or file downloading. This information can be used to optimize network capacity and improve user experience. The optimal network configuration is determined based on various factors, such as traffic pattern and network topology.

⑥ Principal component analysis network planning, the identification of the most important factors affecting network performance, such as signal strength or interference level. This information can be used to optimize network configuration and improve network efficiency.

⑦ And (3) optimizing the decision tree network, namely assisting in identifying the optimal network configuration according to the traffic mode, the network topology and other factors. Security threats may also be identified and classified based on network traffic patterns and other characteristics.

⑧ Anomaly detection algorithm network security anomaly detection can be used for detecting and relieving security threats such as network intrusion, denial of service attack, malicious software and the like.

⑨ Genetic Algorithm (GA) network optimization-genetic algorithm is an optimization algorithm simulating a natural selection process, and is used for finding the best solution to complex problems. Genetic algorithms can optimize 5G networks by generating and testing different network configurations to find the most efficient setup.

In step S505, an optimization threshold corresponding to each optimization factor is determined as an optimization threshold in the network data analysis algorithm related to each optimization factor.

In this embodiment, the optimization threshold is a key parameter used for judging whether the network state reaches the optimization target in the algorithm executing process. In the anomaly identification, an optimization threshold for judging whether an anomaly condition is reached or not can be set, an event corresponding to the network data meeting the anomaly condition is determined as an anomaly event, and then an anomaly device is identified based on the anomaly event for optimization management.

In an exemplary embodiment, the process of determining the optimized threshold may be comprehensively considered in combination with historical data, current network situation and business practice, so as to avoid problems that cannot be found in time due to too high threshold setting and avoid unnecessary alarms or resource waste caused by too low threshold setting.

And finally, integrating the selected network data analysis algorithm and the optimization threshold value thereof to form a complete network data analysis strategy. The strategy is used as an algorithm basis for subsequent network management and optimization, and helps a network manager to monitor network states in real time, diagnose problems and take effective measures.

Through the embodiment, multiple aspects of network management optimization targets, optimization factors, algorithm selection, optimization thresholds and the like can be comprehensively considered, and the efficiency and effect of network management are improved through scientifically and reasonably formulating and executing the strategy.

Fig. 6 shows a flowchart of generating an analysis result in the generation method of the network management scheme of one embodiment of the present disclosure. As shown in fig. 6, in some embodiments, the processing the network data to be analyzed by the network data analysis policy to generate an analysis result may include the following steps.

Step S601, preprocessing the network data to be analyzed according to the data entry format indicated in each network data analysis algorithm to obtain the data to be calculated for each network data analysis algorithm.

In some embodiments, the network data analysis algorithm indicates a data entry format.

In this embodiment, each network data analysis algorithm has its specific data input requirements, including data type, format, structure, etc., i.e., data entry format. Before executing the algorithm, the network data to be analyzed can be preprocessed based on the data entry format, so that the preprocessed data is converted into data to be calculated, which is suitable for each network data analysis algorithm, and the entry requirements of the algorithm are met.

During preprocessing, steps may be included such as data cleansing (e.g., removing invalid or outliers), data conversion (e.g., formatting date and time, unit conversion), data aggregation (e.g., grouping by time, space, or business logic), etc.

Step S603, inputting the data to be calculated and the corresponding optimization threshold value for each network data analysis algorithm into each network data analysis algorithm, and obtaining parameter configuration data for the corresponding optimization factor output by each network data analysis algorithm.

In this embodiment, the preprocessed data to be calculated and the corresponding optimization threshold may be used as inputs to be transferred to each network data analysis algorithm. Each algorithm then processes and analyzes the input data according to its internal logic and algorithm design. After the algorithm is executed, parameter configuration data aiming at corresponding optimization factors can be output, and the parameter configuration data can comprise an optimal routing path, an optimal resource allocation scheme, a performance bottleneck position, abnormal equipment information and the like.

Step S605, the parameter configuration data with the corresponding relation, the network data to be analyzed and the optimization threshold value are combined in a correlated mode, and an analysis result is generated.

In this embodiment, the parameter configuration data, the network data to be analyzed (or the preprocessed version thereof), and the optimization threshold value having the correspondence relationship may be combined in an associated manner. Such correlation helps to establish a logical relationship between data, making the analysis result clearer and easier to understand. The network data to be analyzed can also comprise corresponding network components so as to better locate the equipment information to be optimized.

In an exemplary embodiment, through the association combination, a detailed analysis report or visual chart can also be generated, showing the current state of the network, the problems existing, and the optimization scheme recommended according to the algorithm. These analysis results will serve as important basis for the network manager to make decisions and take action.

According to the embodiment, a data-driven network management concept is embodied, and powerful support is provided for network management through a scientific algorithm and accurate data analysis. The network manager can quickly locate problems and evaluate risks according to analysis results and take corresponding optimization measures, so that network performance is improved, service continuity is guaranteed, and operation cost is reduced.

The following exemplifies the generation of analysis results in this embodiment.

For example, assuming that the network management optimization objective is to reduce network latency (e.g., to reduce network latency for a particular segment to less than 50ms during peak hours), the network data to be analyzed that may be selected may include network traffic data, user equipment location, base station loading conditions, transmission link quality, and the like. And then, analyzing network flow data through a network data analysis algorithm, identifying high-flow time periods and hot spot areas, predicting network load conditions of different time periods and areas by using a machine learning model, and evaluating delay and bandwidth utilization rates of different transmission paths to find an optimal routing scheme. By these algorithmic processes, the algorithm output results may be obtained by suggesting to adjust the transmission configuration of a few base stations in the area, such as increasing the transmission bandwidth, optimizing the routing path, etc., and further forming an analysis result in the form of data, such as < network component, parameter configuration > in which the network component may be, for example, "base station a, router B", the parameter configuration may be, for example, "base station a: increasing the transmission bandwidth to 10Gbps, and router B: modifying the routing table, to direct traffic to the hot spot area to the low latency path).

In some embodiments, parameter configuration data and an optimization threshold for the network management optimization objective are indicated in the analysis result, wherein determining a target network management scheme according to the historical data and the analysis result comprises determining a historical management scheme corresponding to the network management optimization objective in the historical data, determining a historical optimization effect value in each historical management scheme, determining the historical management scheme as the target network management scheme if the historical optimization effect value is superior to the optimization threshold, and determining the target network management scheme according to the parameter configuration data if the optimization threshold is superior to the historical optimization effect value.

In this embodiment, the parameter configuration data in the analysis result may provide specific configuration information required for achieving the optimization objective, and the optimization threshold in the analysis result may be used as an index value for evaluating the optimization effect.

In this embodiment, the history management scheme corresponding to the current network management optimization objective in the history data may be a management measure taken in a similar network state in the past, in which an effect after execution may be recorded, and the effect may be represented by a history optimization effect value. By comparing the effects of different historical schemes, their merits can be evaluated. The historical optimization effect values may be quantitative (e.g., percent improvement in network throughput, time delay reduction, etc.) or qualitative (e.g., improvement in user satisfaction, reduction in failure rate, etc.) for each historical management scheme. The effects of different historical schemes can be intuitively compared through quantitative or qualitative assessment.

In this embodiment, the historical optimization effect value is compared with the optimization threshold value in the current analysis result, so as to determine whether the historical scheme meets the key of the current optimization requirement.

Specifically, if the historical optimization effect value is better than the optimization threshold, it is stated that the historical approach is good enough to meet or exceed the current optimization objective. Thus, the history management scheme can be directly determined as the target network management scheme.

If the optimization threshold is better than the historical optimization effect value, the historical scheme is proved to have a certain effect, but the current optimization requirement cannot be met. At this time, a new target network management scheme needs to be formulated according to the parameter configuration data in the analysis result. These parameter configuration data are carefully calculated based on the current network state and optimization objectives, and thus are more likely to achieve better optimization results.

In an exemplary embodiment, implementation steps in the target network management scheme may also be formulated based on the history management scheme, for example, reference may be made to a parameter configuration order in the history management scheme, such as first adjusting the server, then adjusting the switch, and finally adjusting the router.

In an exemplary embodiment, the architecture for implementing the method for generating the network management scheme provided by the present disclosure may include four modules, namely, a network element sensor module, a network data middle platform module, a big data analysis module, and a knowledge center module.

For the network element sensor module, which is the input source of the method, the network element sensor can capture data from various network components where it is located.

For the network data center module, it can collect and preprocess the data collected from the network element sensor module. The data includes, but is not limited to, network performance metrics, downtime, real-time data, and device information, etc.

For the big data analysis module, an AI algorithm library can be set, and data transmitted by a network data center can be analyzed by using a context-based analysis method, and analysis results of the data are submitted to the knowledge center module. The big data analysis module can comprise 3 components of a big data set, a context-based analysis and an AI algorithm library.

Wherein the large dataset component is the basis for integrating the AI algorithm into the 5G network. The context-based analysis component can define rules and thresholds for applying the AI algorithm library to the network data. The algorithm defined by the AI algorithm library component may cover network management areas such as network planning, network automation, network security, and network optimization.

For the knowledge center module, the output result of the big data analysis module can be analyzed, and the output result is used for making an optimal scheme and implementation steps of network management. The knowledge center module can compare the historical data to the current data to select a better solution.

In an exemplary embodiment based on the above architecture, the method for generating a network management scheme provided by the present disclosure may include an initialization stage and an execution stage.

In the initialization phase, the following steps may be included:

In step 1.1, the context analysis component defines rules and thresholds for the AI algorithm library according to the optimization objective of 5G network management.

In step 1.2, the large dataset component selects several datasets according to the optimization objective of 5G network management and defines the format and content of datasets collected by the stations in the network data.

The execution sequence of step 1 and step2 is not limited.

In the execution phase, the following steps may be included:

and 2.1, collecting various data by the sensors on the network element assembly.

And 2.2, the network data center station performs preprocessing such as selecting and clustering on the data transmitted by the sensor according to the content and format of the data set defined by the big data set.

And 2.3, classifying the preprocessed data by the big data set component of the big data analysis module according to the algorithm in the AI algorithm library defined by the context analysis component, and inputting the classified data into the AI algorithm library component and the context analysis component.

And 2.4, the AI algorithm library component runs related algorithms according to the input data set and submits the algorithm operation result to the context analysis component.

And 2.5, after receiving the operation result of the AI algorithm library component, the context analysis component combines with the optimization target of 5G network management to give a big data analysis result and submits the big data analysis result to the knowledge center module.

And 2.6, the knowledge center analyzes the output result of the big data analysis module and is used for making an optimization scheme and a specific implementation step of 5G network management. The knowledge center compares the historical data with the current data to select a better scheme as the final output scheme.

By the method for generating the network management scheme, the context analysis system, the AI algorithm library and the interaction of the big data set can be utilized to quickly, accurately and automatically obtain the 5G network management optimization scheme with the optimal current performance meeting the service scene and the user requirement, so that the 5G network optimization is realized, and the key and difficult problems of the 5G network in the fields of network planning, network diagnosis, network optimization and control are solved and optimized.

It is noted that the above-described figures are only schematic illustrations of processes involved in a method according to an exemplary embodiment of the invention, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.

Fig. 7 shows a block diagram of a generating apparatus 700 of a network management scheme according to an embodiment of the present disclosure, as shown in fig. 7, including a trigger response unit 701 for determining a network management optimization target in response to a trigger of network management, a determining unit 702 for determining network data to be analyzed and a network data analysis policy according to the network management optimization target, an analyzing unit 703 for processing the network data to be analyzed through the network data analysis policy to generate an analysis result, and a scheme generating unit 704 for acquiring historical data corresponding to the network management optimization target and determining a target network management scheme according to the historical data and the analysis result.

According to the generating device of the network management scheme, the network management optimization target can be automatically determined in response to the triggering of the network management, the network data to be analyzed and the required network data analysis strategy are automatically determined according to the network management optimization target, then the network data to be analyzed are processed by using the network data analysis strategy to generate an analysis result, and finally the target network management scheme is generated according to the historical data and the analysis result under the same network management optimization target. Therefore, the generation method of the network management scheme provided by the disclosure is a data-driven network management mode, can automatically determine relevant network data to be analyzed based on a network management optimization target, and determine network data analysis strategies which correspond to the optimization target and can be used for processing the network data to be analyzed, and ensures the scientificity and the effectiveness of network management through a systematic flow. The method not only can help a network manager to quickly respond to the triggering of network management, but also can continuously optimize the management strategy based on historical data to improve the overall performance and user experience of the network and ensure the scientificity and effectiveness of network management.

In some embodiments, the trigger response unit 701 determines a network management optimization target in response to a trigger of network management, including determining to trigger the network management in response to a received network management request and determining a network management optimization target according to the network management request, or determining to trigger the network management in response to a network monitoring event meeting a trigger condition and determining a network management optimization target according to the trigger condition.

In some embodiments, the determining unit 702 determines network data to be analyzed according to the network management optimization objective, including determining one or more optimization factors according to the network management optimization objective, determining network data related to each optimization factor from a network element sensing dataset containing network data captured by network element sensors deployed on various network components as the network data to be analyzed, wherein the network data type relates to at least one of network performance index, network service time, network real-time data, and network device information.

In some embodiments, the network data analysis strategy comprises at least one network data analysis algorithm corresponding to the network management optimization objective and an optimization threshold value therein, wherein the determining unit 702 determines the network data analysis strategy according to the network management optimization objective, and the network data analysis strategy comprises determining one or more optimization factors according to the network management optimization objective, determining network data analysis algorithms related to the optimization factors from an integrated algorithm library, and determining the optimization threshold value corresponding to the optimization factors as the optimization threshold value in the network data analysis algorithm related to the optimization factors.

In some embodiments, the network data analysis algorithm indicates a data entry format, wherein the analysis unit 703 processes the network data to be analyzed through the network data analysis policy to generate an analysis result, and includes preprocessing the network data to be analyzed according to the data entry format indicated in each network data analysis algorithm to obtain data to be calculated for each network data analysis algorithm, inputting the data to be calculated for each network data analysis algorithm and a corresponding optimization threshold into each network data analysis algorithm to obtain parameter configuration data for the corresponding optimization factor output by each network data analysis algorithm, and performing association combination on the parameter configuration data, the network data to be analyzed, and the optimization threshold with corresponding relations to generate an analysis result.

In some embodiments, the integrated algorithm library comprises at least one of convolutional neural network planning, reinforcement learning network planning, deep learning network automation, K-average algorithm network planning, random forest network planning, principal component analysis network planning, decision tree network optimization, anomaly detection algorithm network security, genetic algorithm network optimization; the algorithms in the integrated algorithm library relate to at least one of the following business fields, network planning, network automation, network security and network optimization.

In some embodiments, parameter configuration data and an optimization threshold for the network management optimization objective are indicated in the analysis result, wherein the plan generation unit 704 determines a target network management plan according to the historical data and the analysis result, and the method comprises determining a historical management plan corresponding to the network management optimization objective in the historical data, determining a historical optimization effect value in each historical management plan, determining the historical management plan as a target network management plan if the historical optimization effect value is superior to the optimization threshold, and determining a target network management plan according to the parameter configuration data if the optimization threshold is superior to the historical optimization effect value.

Other details of the embodiment of fig. 7 may be found in the other embodiments described above.

Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects that may be referred to herein collectively as a "circuit," module "or" system.

Fig. 8 shows a block diagram of a network management scheme generating computer device in an embodiment of the present disclosure. It should be noted that the illustrated electronic device is only an example, and should not impose any limitation on the functions and application scope of the embodiments of the present invention.

An electronic device 800 according to such an embodiment of the invention is described below with reference to fig. 8. The electronic device 800 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.

As shown in fig. 8, the electronic device 800 is embodied in the form of a general purpose computing device. The components of electronic device 800 may include, but are not limited to, at least one processing unit 810 described above, at least one memory unit 820 described above, and a bus 830 that connects the various system components, including memory unit 820 and processing unit 810.

Wherein the storage unit stores program code that is executable by the processing unit 810 such that the processing unit 810 performs steps according to various exemplary embodiments of the present invention described in the above section of the "exemplary method" of the present specification. For example, the processing unit 810 may perform the method as shown in fig. 2.

The storage unit 820 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 8201 and/or cache memory 8202, and may further include Read Only Memory (ROM) 8203.

Storage unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

Bus 830 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 800, and/or any device (e.g., router, modem, etc.) that enables the electronic device 800 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 850. Also, electronic device 800 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 over bus 830. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 800, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.

A program product for implementing the above-described method according to an embodiment of the present invention may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of a readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order, or that all illustrated steps be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

According to one aspect of the present disclosure, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the methods provided in the various alternative implementations of the above-described embodiments.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims (10)

1. A method for generating a network management scheme, comprising:

responding to the triggering of network management, and determining a network management optimization target;

determining network data to be analyzed and a network data analysis strategy according to the network management optimization target;

Processing the network data to be analyzed through the network data analysis strategy to generate an analysis result;

And acquiring historical data corresponding to the network management optimization target, and determining a target network management scheme according to the historical data and the analysis result.

2. The method of claim 1, wherein determining a network management optimization objective in response to a trigger for network management comprises:

determining to trigger the network management in response to the received network management request and determining a network management optimization objective based on the network management request, or

And responding to the network monitoring event to meet the triggering condition, determining to trigger the network management, and determining a network management optimization target according to the triggering condition.

3. The method of claim 1, wherein determining network data to be analyzed based on the network management optimization objective comprises:

determining one or more optimization factors according to the network management optimization objective;

Determining network data related to each optimization factor from a network element sensing data set to serve as the network data to be analyzed;

Wherein the network element sensing dataset comprises network data captured by network element sensors deployed on a variety of network components, the type of network data relating to at least one of network performance metrics, network service time, network real-time data, and network device information.

4. The method of claim 1, wherein the network data analysis policy includes at least one network data analysis algorithm corresponding to the network management optimization objective and an optimization threshold therein;

wherein determining a network data analysis policy according to the network management optimization objective comprises:

determining one or more optimization factors according to the network management optimization objective;

Determining a network data analysis algorithm related to each optimization factor from an integrated algorithm library;

and determining an optimization threshold value corresponding to each optimization factor to serve as the optimization threshold value in the network data analysis algorithm related to each optimization factor.

5. The method of claim 4, wherein the network data analysis algorithm indicates a data entry format;

The network data to be analyzed is processed through the network data analysis strategy, and an analysis result is generated, which comprises the following steps:

Preprocessing the network data to be analyzed according to the data entry format indicated in each network data analysis algorithm to obtain the data to be calculated for each network data analysis algorithm;

inputting the data to be calculated and the corresponding optimization threshold value for each network data analysis algorithm into each network data analysis algorithm to obtain parameter configuration data which is output by each network data analysis algorithm and aims at the corresponding optimization factors;

And carrying out association combination on the parameter configuration data with the corresponding relation, the network data to be analyzed and the optimization threshold value to generate an analysis result.

6. The method of claim 4, wherein the library of integrated algorithms comprises at least one of convolutional neural network planning, reinforcement learning network planning, deep learning network automation, K-average algorithm network planning, random forest network planning, principal component analysis network planning, decision tree network optimization, anomaly detection algorithm network security, genetic algorithm network optimization;

the algorithms in the integrated algorithm library relate to at least one of the following business fields, network planning, network automation, network security and network optimization.

7. The method according to claim 1, wherein parameter configuration data and an optimization threshold for the network management optimization objective are indicated in the analysis result;

wherein determining a target network management scheme according to the historical data and the analysis result comprises:

Determining a history management scheme corresponding to the network management optimization target in the history data, and determining a history optimization effect value in each history management scheme;

If the historical optimization effect value is better than the optimization threshold value, determining the historical management scheme as a target network management scheme;

And if the optimization threshold is better than the historical optimization effect value, determining a target network management scheme according to the parameter configuration data.

8. A network management scheme generation apparatus, comprising:

A trigger response unit for determining a network management optimization target in response to a trigger of network management;

the determining unit is used for determining network data to be analyzed and a network data analysis strategy according to the network management optimization target;

the analysis unit is used for processing the network data to be analyzed through the network data analysis strategy and generating an analysis result;

and the scheme generating unit is used for acquiring historical data corresponding to the network management optimization target and determining a target network management scheme according to the historical data and the analysis result.

9. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of generating a network management scheme as claimed in any one of claims 1 to 7.

10. An electronic device, comprising:

One or more processors;

Storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of generating a network management scheme as claimed in any one of claims 1 to 7.