Network optimization method, device, equipment, medium and product

Abstract

The invention relates to the technical field of communication, and particularly provides a network optimization method and device, equipment, a medium and a product, and the method comprises the steps: obtaining network data in a to-be-optimized network region; wherein the network data comprises at least one of user equipment data, network flow data, network state data and user behavior data; performing evaluation processing on the network data through an evaluation model to obtain an evaluation result; wherein the evaluation result is used for indicating the credibility of the network data in each stage of a data life cycle; and determining target network data of which the evaluation result meets a preset evaluation requirement in the network data, and optimizing the network topology structure of the to-be-optimized network region according to the target network data, so that the data quality of the network data in each stage of a data life cycle can be effectively ensured, and the user experience is improved. And the accuracy of network optimization based on the network data is further improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular, to a network optimization method, device, apparatus, medium and product. BACKGROUND

[0002] In a home network environment, a plurality of network devices can be generally supported to connect to a broadband network, and different network devices need to run different application programs with appropriate network bandwidth. However, some devices may excessively occupy network bandwidth, causing the network devices to fail to normally run their application programs, thereby affecting the network experience of users.

[0003] In the related art, network bandwidth is flexibly allocated on demand by periodically monitoring network data of network devices, but errors are easily introduced in the collection and transmission of network data, causing the problem that bandwidth resources cannot be reasonably allocated, thereby affecting the accuracy of network optimization. SUMMARY

[0004] The present disclosure is proposed in view of the above problems. The present disclosure provides a network optimization method, device, apparatus, medium and product.

[0005] According to one aspect of the present disclosure, a network optimization method is provided, comprising:

[0006] obtaining network data in a network area to be optimized; wherein the network data comprises at least one of the following: user device data, network traffic data, network state data and user behavior data;

[0007] performing evaluation processing on the network data by an evaluation model to obtain an evaluation result; wherein the evaluation result is used to indicate the credibility of the network data at each stage of a data life cycle;

[0008] determining target network data in which the evaluation result meets a preset evaluation requirement in the network data, and optimizing a network topology structure of the network area to be optimized according to the target network data.

[0009] In addition, the evaluation processing on the network data by the evaluation model to obtain the evaluation result according to one aspect of the present disclosure further comprises:

[0010] determining a multi-dimensional evaluation index of the network data for each stage of the data life cycle;

[0011] calculating the evaluation result of the network data at the corresponding stage based on the multi-dimensional evaluation index;

[0012] determining the evaluation result according to the evaluation result of each stage.

[0013] In addition, when the data lifecycle is in the data processing stage according to an aspect of the present disclosure, the calculation of the evaluation result of the network data in the corresponding stage based on the multi-dimensional evaluation index further includes:

[0014] determining a preprocessing category of the network data, and preprocessing the network data according to the preprocessing category to obtain preprocessed network data;

[0015] checking data integrity of the preprocessed network data;

[0016] weighting the preprocessing category and the data integrity to obtain a weighting result, and determining data processing reliability of the network data according to the weighting result.

[0017] In addition, when the data lifecycle is in the data transmission stage according to an aspect of the present disclosure, the calculation of the evaluation result of the network data in the corresponding stage based on the multi-dimensional evaluation index further includes:

[0018] obtaining encryption complexity of an encryption algorithm of the network data;

[0019] obtaining a transmission path of the network data in the data transmission stage;

[0020] calculating data transmission complexity of the network data based on the transmission path of the network data and the encryption complexity.

[0021] In addition, according to an aspect of the present disclosure, the data lifecycle includes a data source stage, a data processing stage, and a data transmission stage; and the evaluation processing of the network data by the evaluation model to obtain an evaluation result further includes:

[0022] performing evaluation processing on the network data in the data source stage by the evaluation model to obtain data source credibility;

[0023] performing evaluation processing on the network data in the data processing stage by the evaluation model to obtain data processing reliability;

[0024] performing evaluation processing on the network data in the data transmission stage by the evaluation model to obtain data transmission complexity.

[0025] In addition, according to an aspect of the present disclosure, the target network data in which the evaluation result meets the preset evaluation requirement in the network data further includes:

[0026] determining a highest evaluation result of network data in a same data source;

[0027] If the highest evaluation result is greater than or equal to a preset evaluation threshold, the network data corresponding to the highest evaluation result is determined as the target network data.

[0028] In addition, the method for optimizing the network topology structure of the network area to be optimized according to the target network data according to an aspect of the present disclosure further comprises:

[0029] selecting network topology metadata in the target network data; wherein the network topology metadata is used to describe attribute information of network devices corresponding to the target network data in the network area to be optimized and connection relationships between the network devices;

[0030] constructing a network topology structure of the network area to be optimized based on the network topology metadata;

[0031] optimizing the connection relationships between the network devices in the network topology structure through a genetic algorithm to obtain an optimized network topology structure.

[0032] In addition, the method for optimizing the connection relationships between the network devices in the network topology structure through a genetic algorithm to obtain an optimized network topology structure according to an aspect of the present disclosure further comprises:

[0033] randomly encoding the network topology structure to obtain a plurality of groups of candidate network topologies; wherein the candidate network topologies are used to indicate candidate connection relationships between the network devices;

[0034] calculating an adaptability of each of the candidate network topologies based on an adaptability function; wherein the adaptability is used to indicate stability of each candidate network topology;

[0035] determining a candidate network topology corresponding to a highest adaptability to obtain a target network topology;

[0036] processing the target network topology through a genetic algorithm to obtain an optimized network topology structure.

[0037] In addition, the method for calculating the adaptability of each of the candidate network topologies based on an adaptability function according to an aspect of the present disclosure further comprises:

[0038] determining multi-dimensional network state data in the target network data that matches network devices corresponding to the candidate network topology;

[0039] performing weighted processing on the multi-dimensional network state data to obtain the adaptability.

[0040] According to another aspect of the present disclosure, a network optimization device is provided, comprising:

[0041] The acquisition unit is configured to acquire network data in a network area to be optimized, wherein the network data comprises at least one of the following: user equipment data, network traffic data, network status data, and user behavior data.

[0042] The processing unit is configured to perform evaluation processing on the network data by using an evaluation model to obtain an evaluation result, wherein the evaluation result is used to indicate a degree of credibility of the network data at each stage of a data life cycle.

[0043] The network optimization unit is configured to determine target network data in the network data, wherein the evaluation result of the target network data meets preset evaluation requirements, and to optimize a network topology of the network area to be optimized according to the target network data.

[0044] According to yet another aspect of the present disclosure, an electronic device is provided, comprising a processor, a memory, and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, and the machine-readable instructions being executed by the processor to perform the steps of the network optimization method described above.

[0045] According to yet another aspect of the present disclosure, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, the computer program being executed by a processor to perform the steps of the network optimization method described above.

[0046] According to yet another aspect of the present disclosure, a computer program product is provided, the computer program product being stored in a storage medium, the program product being executed by at least one processor to perform the steps of the network optimization method described above.

[0047] As will be described in detail below, according to the network optimization method, device, equipment, medium, and product of the embodiments of the present disclosure, the network data is evaluated by using an evaluation model to obtain an evaluation result, wherein the network data comprises at least one of the following: user equipment data, network traffic data, network status data, and user behavior data, and the evaluation result is used to indicate a degree of credibility of the network data at each stage of a data life cycle, so as to determine target network data in the network data, wherein the evaluation result of the target network data meets preset evaluation requirements, thereby effectively ensuring the data quality of the network data at each stage of the data life cycle and further improving the accuracy of network optimization based on the network data.

[0048] It is to be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further explanation of the subject technology. BRIEF DESCRIPTION OF DRAWINGS

[0049] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0050] Figure 1 is a flow chart illustrating a network optimization method according to an embodiment of the present disclosure.

[0051] Figure 2 is a flow chart further illustrating a network topology analysis process in the network optimization method according to an embodiment of the present disclosure.

[0052] Figure 3 is a flow chart further illustrating a network optimization process in the network optimization method according to an embodiment of the present disclosure.

[0053] Figure 4 is a block diagram illustrating a network optimization apparatus according to an embodiment of the present disclosure.

[0054] Figure 5 is a hardware block diagram of an electronic device according to an embodiment of the present disclosure.

[0055] Figure 6 is a schematic diagram of a computer program product according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present disclosure more apparent, the following will describe the example embodiments according to the present disclosure in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, and are not all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the example embodiments described herein.

[0057] For the convenience of understanding the present embodiments, first, a network optimization method disclosed by the present embodiments will be described in detail, and the execution subject of the network optimization method provided by the present embodiments is generally an electronic device with certain computing capability, which for example includes a terminal device or a server or other processing device. In some possible implementation manners, the network optimization method can be realized by a processor calling computer readable instructions stored in a memory.

[0058] Referring to Figure 1 , a flow chart of a network optimization method provided by the present embodiments is shown, and the method includes steps S101-S103, wherein:

[0059] Step S101: Obtain network data within the network area to be optimized; wherein the network data includes at least one of the following: user equipment data, network traffic data, network status data, and user behavior data;

[0060] Here, the network area to be optimized can be selected as needed based on the actual application scenario, such as a home network, enterprise network, or data center network. The type of network data can also be adjusted as needed depending on the actual application scenario; this application does not provide further examples. In this embodiment, only the application scenario of a home network is taken as an example. To optimize its network topology, it is necessary to obtain network data within the network area to be optimized; this network data is the data required in the home network scenario.

[0061] Specifically, network data may include at least one of the following categories: user device data, network traffic data, network status data, and user behavior data.

[0062] User device data refers to device attribute data related to various network devices in the network area to be optimized, such as device type, device model, and device status. This information can be obtained through the user management system. In addition, user device data may also include application types, such as video applications, game applications, and office applications. The type of application used by the user can be identified by combining user device data and application traffic data.

[0063] Network traffic data is used to describe the traffic characteristics of network data during data transmission, such as traffic size, traffic type, and traffic time. This network traffic data can be obtained through a traffic management system.

[0064] Network status data refers to the real-time operating status of the communication network within the network area to be optimized, such as network bandwidth, network latency, and network congestion. This network status data can be obtained through the Data Switched Services Network (DSSN).

[0065] User behavior data refers to a user's network usage behavior in the area to be optimized, such as user internet browsing habits, usage time, and user preferences. This user behavior data can also be obtained through data networks.

[0066] In this embodiment of the application, the service platform can obtain network data within the network area to be optimized to understand the actual usage and overall performance of the communication network within the network area to be optimized, and use the network data as the basis for subsequent data evaluation and network optimization.

[0067] Step S102: The network data is evaluated using an evaluation model to obtain an evaluation result; wherein the evaluation result is used to indicate the reliability of the network data at each stage of the data lifecycle;

[0068] Here, different model types for evaluation can be selected according to specific evaluation needs and application scenarios, such as machine learning models, deep learning models, and statistical models. This application does not limit this.

[0069] The data lifecycle refers to the entire process of network data from creation to destruction, covering various stages such as data source, data acquisition, data storage, data processing, data transmission, data usage, data archiving, and data destruction. Each stage has its specific tasks and requirements, which will be further described later.

[0070] Since the data requirements for network data differ at each stage of the data lifecycle, the dimensions for evaluating network data also differ for each stage, as will be described exemplarily later. Furthermore, due to the different types of network data, different evaluation dimensions can be set for the same type of network data at the same stage of the data lifecycle; this application does not require this.

[0071] In this embodiment of the application, the service platform can use an evaluation model to evaluate network data at each stage of the data lifecycle, so as to assess the credibility of the network data at each stage, comprehensively measure the quality of the network data from multiple evaluation perspectives, facilitate subsequent data screening, and lay the foundation for improving the accuracy of network optimization.

[0072] Step S103: Determine the target network data in the network data whose evaluation results meet the preset evaluation requirements, and optimize the network topology of the network area to be optimized based on the target network data.

[0073] Here, the preset evaluation requirements are key criteria used to screen and select target network data. They can be flexibly set according to specific optimization goals, application scenarios and network environments. No further examples will be given here, but an exemplary solution will be provided later.

[0074] Here, network topology refers to the geometric arrangement and connection of various network devices and transmission links in the network area to be optimized. It describes the physical or logical relationship between network devices in the network area to be optimized and determines the transmission path of network data in the network area to be optimized and the overall performance of the communication network in the network area to be optimized.

[0075] In this embodiment, data whose evaluation results meet preset evaluation requirements can be selected from the network data and used as target network data to ensure that the network data meets the requirements at each stage.

[0076] Based on this, the network topology of the network area to be optimized can be optimized, bandwidth resources can be allocated reasonably, and further, the optimal transmission path of network data can be selected based on the network topology to improve the network performance of the network area to be optimized.

[0077] In the above embodiments, by evaluating network data through an evaluation model to obtain evaluation results, and then identifying target network data whose evaluation results meet preset evaluation requirements, the data quality of network data at each stage of the data lifecycle can be effectively ensured. This allows for improved accuracy of network optimization based on highly reliable data.

[0078] In an optional implementation, the above steps evaluate the network data using an evaluation model to obtain an evaluation result, specifically including the following steps:

[0079] For each stage of the data lifecycle, determine multi-dimensional evaluation indicators for the network data;

[0080] The evaluation results of the network data at the corresponding stage are calculated based on the multi-dimensional evaluation indicators.

[0081] The evaluation results are determined based on the evaluation results of each of the aforementioned stages.

[0082] As mentioned above, the data lifecycle includes multiple stages. For each stage, multi-dimensional evaluation indicators can be determined. Depending on the evaluation dimensions set for different stages, the multi-dimensional evaluation indicators will also be different between different stages.

[0083] For example, multi-dimensional evaluation metrics at the data sourcing stage can be set as data source integrity and data provider reliability; multi-dimensional evaluation metrics at the data processing stage can be set as preprocessing category and data integrity; and multi-dimensional evaluation metrics at the data transmission stage can be set as the encryption complexity of the network data encryption algorithm and the transmission path for network data transmission. This application will not provide further examples here.

[0084] The evaluation dimensions and multi-dimensional evaluation indicators can be flexibly adjusted according to different actual application scenarios.

[0085] In the above implementation, by setting multi-dimensional evaluation indicators for each stage, the quality of network data at each stage can be comprehensively evaluated, which can reduce optimization errors and deviations caused by data quality issues to a certain extent. Furthermore, by using the evaluation results of each stage as the data basis, the data quality of network data throughout the entire data lifecycle can be comprehensively evaluated, providing more accurate input data for the network optimization process.

[0086] In an optional implementation, when the data lifecycle is in the data processing stage, the step of calculating the evaluation result of the network data at the corresponding stage based on the multi-dimensional evaluation indicators specifically includes the following steps:

[0087] Determine the preprocessing category of the network data, and preprocess the network data according to the preprocessing category to obtain preprocessed network data;

[0088] Check the data integrity of the preprocessed network data;

[0089] The preprocessing category and the data integrity are weighted to obtain a weighted processing result, and the data processing reliability of the network data is determined based on the weighted processing result.

[0090] Following on from the above, when the data lifecycle is in the data processing stage, the corresponding multi-dimensional evaluation indicators can be set as preprocessing category and data integrity.

[0091] The preprocessing category represents the type of data processing method, such as data cleaning, data fusion, and data transformation. Different preprocessing methods can be represented using one-hot encoding or other categorical encoding methods. Data integrity includes: data missingness, data duplication, data anomalies, and data consistency. Data integrity of the network data can be determined based on at least one aspect. A value of 1 can represent data integrity after preprocessing, and a value of 0 can represent data loss after preprocessing.

[0092] In addition, since the reliability of data processing varies across different networks and the emphasis differs in different application scenarios, an adjustment parameter is introduced. This parameter is used to control the impact of preprocessing type and data integrity on the reliability of data processing. This parameter can be flexibly adjusted as needed, and this application does not require it.

[0093] The reliability of network data processing can be calculated using the following formula:

[0094] Where MethodType is the preprocessing category of network data, DataLoss is the data integrity of network data, k is an adjustment parameter, and Reliability is the data processing reliability of network data, which is used to measure the reliability of network data in the preprocessing process.

[0095] In this embodiment, the preprocessing category of the network data can be determined during the data processing stage, and corresponding preprocessing operations can be performed on the network data. After preprocessing is completed, the data integrity of the preprocessed network data is checked, thereby determining the reliability of the network data processing based on the preprocessing category and data integrity.

[0096] In the above embodiments, by preprocessing the network data during the data processing stage, noise and abnormal data can be filtered out, making the preprocessed network data more accurate and reliable. Furthermore, by checking the data integrity of the preprocessed network data, it can be ensured that there are no missing or erroneous values, thereby effectively improving the data quality of the network data during the data processing stage, and consequently improving the accuracy of the evaluation of the network data during this stage.

[0097] In an optional implementation, when the data lifecycle is in the data transmission phase, the step of calculating the evaluation result of the network data at the corresponding phase based on the multi-dimensional evaluation indicators specifically includes the following steps:

[0098] Obtain the encryption complexity of the encryption algorithm used to obtain the network data;

[0099] Obtain the transmission path for transmitting the network data during the data transmission phase;

[0100] The data transmission complexity of the network data is calculated based on the transmission path of the network data and the encryption complexity.

[0101] Here, when the data lifecycle is in the data processing stage, the corresponding multi-dimensional evaluation indicators can be set as the encryption complexity of the encryption algorithm of the network data and the transmission path of the network data.

[0102] The complexity of an encryption algorithm affects the security and transmission efficiency of network data. Depending on the type of network data, different encryption algorithms will be used, such as asymmetric encryption algorithms, symmetric encryption algorithms, and hash algorithms.

[0103] Based on this, the complexity of different encryption algorithms can be evaluated according to their encryption characteristics. Complexity can include the key length, computational complexity, and security of the encryption algorithm. The evaluation dimensions for encryption complexity can also be adjusted as needed; this application does not require such adjustment.

[0104] Here, the network data transmission path refers to the path taken by network data from the source network device to the target network device. Evaluation dimensions for the network data transmission path can be selected as needed, such as the number of nodes the network data passes through, transmission path latency, and transmission path bandwidth.

[0105] In this embodiment, the data transmission complexity of network data can be calculated using the formula for calculating the reliability of data processing, or the data transmission complexity can be determined based on a preset threshold. This application does not require this.

[0106] In this embodiment, network data can be encrypted during the data transmission phase to evaluate the encryption complexity of the encryption algorithm. After encryption, the transmission path of the network data is known, and the data transmission complexity can be calculated based on the encryption complexity and the transmission path.

[0107] In the above embodiments, encrypting network data during the data transmission phase ensures the security of network data during transmission, making the encrypted network data more secure and reliable. Furthermore, knowing the transmission path of the encrypted network data facilitates the evaluation of the path's characteristics, thereby effectively improving the data quality during the data transmission phase and ultimately enhancing the accuracy of the evaluation of network data during this phase.

[0108] In an optional implementation, the data lifecycle described above includes: a data source stage, a data processing stage, and a data transmission stage; the step of evaluating the network data using an evaluation model to obtain an evaluation result specifically includes the following steps:

[0109] The network data at the data source stage is evaluated and processed using the evaluation model to obtain the data source credibility.

[0110] The network data during the data processing stage is evaluated and processed using the evaluation model to obtain the data processing reliability.

[0111] The network data during the data transmission phase is evaluated and processed using the evaluation model to obtain the data transmission complexity.

[0112] As mentioned earlier, the credibility of a data source can be assessed using two metrics: data source integrity and data provider reliability. Data source integrity describes whether there are missing values ​​in the online data and whether the online data covers all the necessary information; data provider reliability describes the data provider's historical reputation and operational stability.

[0113] Here, the evaluation result can be calculated using the following formula:

[0114] Where L represents the evaluation result, Credibility represents the credibility of the data source, Reliability represents the reliability of data processing, Complexity represents the complexity of data transmission, and Hops represents the number of nodes that the network data passes through during transmission.

[0115] In this embodiment of the application, multi-dimensional evaluation indicators and evaluation results are set for each of the data source stage, data processing stage and data transmission stage of the data lifecycle. This allows for the evaluation of network data throughout the entire data lifecycle from multiple evaluation dimensions, thereby comprehensively assessing the credibility of the network data and using it as the data foundation for subsequent network optimization.

[0116] In an optional implementation, the above steps, which determine the target network data in the network data whose evaluation results meet preset evaluation requirements, specifically include the following steps:

[0117] Determine the highest evaluation result for network data within the same data source;

[0118] If the highest evaluation result is greater than or equal to the preset evaluation threshold, then the network data corresponding to the highest evaluation result is determined as the target network data.

[0119] Here, the geographical location information of the network data can also be obtained and encoded. The encoded data is then classified according to the geographical location information, and the network data with the highest evaluation result not less than the preset evaluation threshold in the same geographical location information is selected as the target network data.

[0120] If the highest evaluation result in the same data source is less than the preset evaluation threshold, then the network data of that data source will be filtered.

[0121] In addition, the preset evaluation requirements can be set to select only network data that is not less than the preset evaluation threshold as target network data. That is, there can be multiple target network data from the same data source or the same geographic location information.

[0122] In this embodiment of the application, the data source to which the network data belongs can be obtained, and the network data from the same data source can be counted and sorted according to the evaluation results. The network data with the highest evaluation result is taken as the target network data of the data source.

[0123] In an optional implementation, the above steps, based on the target network data, optimize the network topology of the network area to be optimized, specifically including the following steps:

[0124] Select network topology metadata from the target network data; wherein, the network topology metadata is used to describe the attribute information of network devices corresponding to the target network data in the network area to be optimized and the connection relationships between the network devices;

[0125] Construct the network topology structure of the network area to be optimized based on the network topology metadata;

[0126] The connection relationships between network devices in the network topology are optimized using a genetic algorithm to obtain an optimized network topology.

[0127] Reference Figure 2 The diagram illustrates a network topology analysis process according to an embodiment of this disclosure. The network topology metadata comes from multiple data sources, such as historical home network devices, passive optical networks, optical line terminals, and broadband access servers. The network topology metadata can be collected and calculated using routers or gateway devices within the home network.

[0128] Specifically, network topology metadata may include attribute information of network devices, such as device type, device model, device status and device location, as well as data representing the connection relationships between network devices, such as the number of network nodes, the number of network connections, node degree and network diameter, and may also include data on transmission rate, transmission traffic and network bandwidth.

[0129] Among them, the number of network nodes refers to the total number of network devices in the network area to be optimized; the number of network connections refers to the number of connections between all network devices in the network area to be optimized; the node degree can be expressed as the number of connections between a network device and other network devices in the network area to be optimized; and the network diameter can be expressed as the shortest transmission path length between any two network devices in the network area to be optimized.

[0130] In this regard, a home network can be represented as a graph G = (V, E), where V represents the set of network devices and E represents the set of connections. Based on this, network devices can be represented as nodes in the graph, and the connections between network devices can be represented as edges in the graph. This allows us to construct the network topology using graph theory, thereby representing the network devices and their connections through the network topology.

[0131] As mentioned above, network topology metadata also includes data on transmission rate, transmission traffic, and network bandwidth. By collecting information such as the size and transmission rate of network data packets, the load on the home network can be analyzed and adjusted in real time, enabling network load analysis of the network area to be optimized.

[0132] Among them, transmission rate can be expressed as the speed at which network data is transmitted between network devices; transmission traffic can be expressed as the total amount of network data transmitted between network devices; and network bandwidth can be expressed as the total amount of available bandwidth resources in the network area to be optimized.

[0133] In this embodiment, network topology metadata can be collected from the target network data selected by the evaluation model to construct the network topology structure of the network area to be optimized. The connection relationship in the network topology structure can be optimized by the genetic algorithm, thereby effectively improving the network performance of the network area to be optimized.

[0134] In an optional implementation, the above steps optimize the connection relationships between network devices in the network topology using a genetic algorithm to obtain an optimized network topology, specifically including the following steps:

[0135] The network topology is randomly encoded to obtain multiple candidate network topologies; wherein, the candidate network topologies are used to indicate candidate connection relationships between the network devices;

[0136] The fitness degree of each candidate network topology is calculated based on the fitness function; wherein the fitness degree is used to indicate the stability of each candidate network topology;

[0137] Determine the candidate network topology corresponding to the highest adaptivity to obtain the target network topology;

[0138] The target network topology is processed using a genetic algorithm to obtain an optimized network topology.

[0139] Since the network topology of a home network is similar to a graph, the information of nodes, edges, etc., in the graph needs to be encoded, generally using binary encoding. Based on this, the encoded network topology is called a chromosome, or candidate network topology, and one chromosome represents one possible home network topology.

[0140] For a home network containing n network devices, assuming each device has a unique identifier, each node can be represented by a binary code, and each node can be described by a binary string. For a chromosome, a set of strings is used to describe the topology of the home network. For example, a chromosome: C = {x1, x2, ..., xn}, where xi is the i-th node represented by a binary string, and each gene...

[0141] The length of the string can be determined based on the complexity of the network topology.

[0142] Here, the fitness function measures the quality of each chromosome and can be set according to the performance indicators of the home network, such as network speed, number of connected network devices, and network data transmission volume. This will be described in detail later; further examples are not provided here.

[0143] In this embodiment, besides selecting the candidate network topology with the highest adaptability, other methods can also be used to select the target network topology, and this application does not limit this method. Based on this, a genetic algorithm is used to optimize the target network topology to obtain the optimized network topology structure.

[0144] Among them, the genetic algorithm is an optimization algorithm based on the principles of natural selection and genetics. In the iterative process of the genetic algorithm, the fitness function will be repeatedly calculated and a sequence of good and bad will be determined in each iteration, which will facilitate the subsequent selection of network topology.

[0145] Crossover and mutation operations are the core operations in the iterative process of genetic algorithms. Crossover is used to preserve good gene sequences, while mutation is used to increase new evolutionary possibilities.

[0146] Crossover can be performed to exchange or partially exchange two chromosomes. By randomly selecting two parent chromosomes and exchanging their genes with a certain probability, offspring chromosomes are obtained.

[0147] Mutation operations can introduce new possibilities during the iterative process of a genetic algorithm by randomly changing the values ​​of certain gene sequences. For example, by randomly selecting some node strings in a chromosome and changing the binary values ​​of these node strings with a certain probability, a mutated chromosome can be obtained.

[0148] In this embodiment, the network topology can be encoded, and each encoded network topology can be calculated based on the fitness function. Thus, through crossover and mutation operations of the genetic algorithm, chromosomes can be optimized and evolved in a continuous iterative process to obtain an optimized network topology.

[0149] like Figure 2 As shown, furthermore, network optimization strategies can be set for the network area to be optimized based on the optimized network topology. These strategies are based on the aforementioned network load analysis. Network optimization strategies can be set from three aspects: bandwidth optimization strategy, bypass optimization strategy, and dynamic scheduling strategy.

[0150] Bandwidth optimization strategies can establish priority queues and set corresponding thresholds for the high-speed data transmission needs of certain network devices in the optimized network topology. When the demand exceeds the threshold, the transmission rate of that network device is automatically increased. Here, the demand represents the high-speed data transmission requirement of the network device, and can be measured using the following formula: Network device transmission rate = f(demand), where demand represents related indicators such as transmission rate, transmission traffic, and network bandwidth.

[0151] Bypass optimization strategy refers to introducing bypass routers to offload network traffic when a communication network experiences a bottleneck, thereby alleviating network performance pressure. The total number of routes in the optimized network topology = n + m, where the total number of routes represents the total number of routers in the home network, n represents the number of primary routers, and m represents the number of bypass routers.

[0152] Dynamic scheduling strategies refer to optimization schemes that improve the performance and reliability of the entire home network by identifying network congestion points and peak times through real-time data collection and analysis of network load, and automatically adjusting transmission rates and caching strategies. Dynamic scheduling strategies can be adjusted and optimized based on real-time network load data. The degree of network congestion can be assessed using the following formula: Network Congestion Level = g(Network Load Data), where network congestion level represents the degree of congestion in the network, and network load data includes relevant indicators such as network traffic and latency.

[0153] In an optional implementation, the above steps calculate the adaptability of each candidate network topology based on the fitness function, specifically including the following steps:

[0154] Determine multi-dimensional network status data in the target network data that matches the network devices corresponding to the candidate network topology;

[0155] The multi-dimensional network state data is weighted to obtain the adaptive degree.

[0156] In this embodiment, the selected multi-dimensional network status data can be directly related to a specific network device in the candidate network topology. For example, if the candidate network topology includes a specific router, then the bandwidth utilization, latency, and other data related to that router are the corresponding multi-dimensional network status data.

[0157] Here, the fitness function can be: F(C) = w1S1(C) + w2S2(C).

[0158] Wherein, S1(C) represents the network performance indicators of the candidate network topology, such as a comprehensive evaluation of network speed, number of connections and transmission volume; S2(C) represents the evaluation of the congestion level or stability of the candidate network topology, such as a comprehensive evaluation of network traffic and latency indicators; w1 and w2 are weighting coefficients, which can be flexibly adjusted as needed.

[0159] Assuming there are m network devices in the candidate network topology, and they can be sorted according to the priority of each network device in using the network, we design the fitness function as follows, taking into account the needs of higher-priority network devices:

[0160] Fitness function: F(C) = w1U(C) - w2V(C) - w3Q(C).

[0161] Where U(C) represents the total number of network device connections in the candidate network topology, V(C) represents the total latency or time overhead of the communication network in the candidate network topology, and Q(C) represents the stability of the network performance of the candidate network topology. w1, w2, and w3 represent the corresponding weights, which can be adjusted according to the actual situation.

[0162] The total number of connections U(C) can be expressed as the sum of the number of connections between each network device, i.e.: U(C) = ∑c ij , where c ij This indicates whether there is a connection between the i-th network device and the j-th network device. 0 can represent no connection and 1 can represent a connection.

[0163] The total delay or time cost V(C) can be expressed as the sum of the delays on each connection path, i.e.: V(C) = ∑d ij l ij , where d ij Let l represent the latency between the i-th network device and the j-th network device. ij This represents the distance between the i-th network device and the j-th network device.

[0164] The stability of network performance, Q(C), can be expressed as the stability of bandwidth usage among various network devices, i.e.: Q(C) = ∑q i , where q i This represents the bandwidth usage stability of the i-th network device.

[0165] In the above embodiments, the adaptiveness is calculated through the above processing method. Multi-dimensional network state data can be used to comprehensively evaluate the performance of network devices, avoiding the limitations of a single indicator, and also ensuring that the optimization process is more accurate for the current candidate network topology.

[0166] The following is combined with Figure 3 The network optimization process described above is as follows:

[0167] S301: Obtain network data within the network area to be optimized.

[0168] Network data includes at least one of the following: user device data, network traffic data, network status data, and user behavior data.

[0169] S302: Determine multi-dimensional evaluation indicators for network data at each stage of the data lifecycle.

[0170] S303: Calculate the evaluation results of network data at the corresponding stage based on multi-dimensional evaluation indicators.

[0171] S304: Determine the evaluation results based on the evaluation results of each stage.

[0172] The evaluation results are used to indicate the credibility of network data at various stages of the data lifecycle.

[0173] S305: Determine the highest evaluation result for network data within the same data source.

[0174] S306: If the highest evaluation result is greater than or equal to the preset evaluation threshold, the network data corresponding to the highest evaluation result shall be determined as the target network data.

[0175] S307: Optimize the network topology of the area to be optimized based on the target network data.

[0176] As can be seen from the above description, the technical solution disclosed herein has the following advantages:

[0177] (1): Based on the architecture of genetic algorithm and adaptive neural network, intelligent allocation of home bandwidth is realized.

[0178] (2): Based on users’ historical behavior and usage habits, and relying on multi-dimensional evaluation indicators, we evaluate the credibility of network data at each stage of the data lifecycle, so as to meet the diverse needs of users on a larger scale under the premise of intelligent technology optimization.

[0179] Based on the same inventive concept, this disclosure also provides a network optimization device corresponding to the network optimization method. Since the principle of the device in this disclosure for solving the problem is similar to that of the network optimization method described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0180] Reference Figure 4 The diagram shown is a schematic representation of a network optimization device provided in an embodiment of this disclosure. The device includes: an acquisition unit 40, a processing unit 41, and a network optimization unit 42; wherein:

[0181] The acquisition unit is used to acquire network data within the network area to be optimized; wherein the network data includes at least one of the following: user equipment data, network traffic data, network status data, and user behavior data;

[0182] The processing unit is used to evaluate the network data using an evaluation model to obtain an evaluation result; wherein the evaluation result is used to indicate the reliability of the network data at various stages of the data lifecycle.

[0183] A network optimization unit is used to determine target network data in the network data whose evaluation results meet preset evaluation requirements, and to optimize the network topology of the network area to be optimized based on the target network data.

[0184] In one possible implementation, the device is also used for:

[0185] For each stage of the data lifecycle, determine multi-dimensional evaluation indicators for the network data;

[0186] The evaluation results of the network data at the corresponding stage are calculated based on the multi-dimensional evaluation indicators.

[0187] The evaluation results are determined based on the evaluation results of each of the aforementioned stages.

[0188] In one possible implementation, the device is also used for:

[0189] Determine the preprocessing category of the network data, and preprocess the network data according to the preprocessing category to obtain preprocessed network data;

[0190] Check the data integrity of the preprocessed network data;

[0191] The preprocessing category and the data integrity are weighted to obtain a weighted processing result, and the data processing reliability of the network data is determined based on the weighted processing result.

[0192] In one possible implementation, the device is also used for:

[0193] When the data lifecycle is in the data transmission phase, the evaluation result of the network data in the corresponding phase is calculated based on the multi-dimensional evaluation indicators:

[0194] Obtain the encryption complexity of the encryption algorithm used to obtain the network data;

[0195] Obtain the transmission path for transmitting the network data during the data transmission phase;

[0196] The data transmission complexity of the network data is calculated based on the transmission path of the network data and the encryption complexity.

[0197] In one possible implementation, the device is also used for:

[0198] The data lifecycle includes: the data source stage, the data processing stage, and the data transmission stage; the network data is evaluated using an evaluation model to obtain the evaluation results.

[0199] The network data at the data source stage is evaluated and processed using the evaluation model to obtain the data source credibility.

[0200] The network data during the data processing stage is evaluated and processed using the evaluation model to obtain the data processing reliability.

[0201] The network data during the data transmission phase is evaluated and processed using the evaluation model to obtain the data transmission complexity.

[0202] In one possible implementation, the device is also used for:

[0203] Determine the highest evaluation result for network data within the same data source;

[0204] If the highest evaluation result is greater than or equal to the preset evaluation threshold, then the network data corresponding to the highest evaluation result is determined as the target network data.

[0205] In one possible implementation, the device is also used for:

[0206] Select network topology metadata from the target network data; wherein, the network topology metadata is used to describe the attribute information of network devices corresponding to the target network data in the network area to be optimized and the connection relationships between the network devices;

[0207] Construct the network topology structure of the network area to be optimized based on the network topology metadata;

[0208] The connection relationships between network devices in the network topology are optimized using a genetic algorithm to obtain an optimized network topology.

[0209] In one possible implementation, the device is also used for:

[0210] The network topology is randomly encoded to obtain multiple candidate network topologies; wherein, the candidate network topologies are used to indicate candidate connection relationships between the network devices;

[0211] The fitness degree of each candidate network topology is calculated based on the fitness function; wherein the fitness degree is used to indicate the stability of each candidate network topology;

[0212] Determine the candidate network topology corresponding to the highest adaptivity to obtain the target network topology;

[0213] The target network topology is processed using a genetic algorithm to obtain an optimized network topology.

[0214] In one possible implementation, the device is also used for:

[0215] Determine multi-dimensional network status data in the target network data that matches the network devices corresponding to the candidate network topology;

[0216] The multi-dimensional network state data is weighted to obtain the adaptive degree.

[0217] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0218] Corresponding toFigure 1 In addition to the network optimization methods described in this disclosure, this embodiment also provides an electronic device 50, such as... Figure 5 The diagram shown is a structural schematic of the electronic device 50 provided in this embodiment of the present disclosure, including:

[0219] The system includes a processor 51, a memory 52, and a bus 53. The memory 52 stores execution instructions and includes main memory 521 and external memory 522. The main memory 521, also called internal memory, temporarily stores the computational data in the processor 51, as well as data exchanged with external memory such as a hard disk. The processor 51 exchanges data with the external memory 522 through the main memory 521. When the electronic device 50 is running, the processor 51 communicates with the memory 52 through the bus 53, causing the processor 51 to execute the following instructions:

[0220] Obtain network data within the network area to be optimized; wherein the network data includes at least one of the following: user equipment data, network traffic data, network status data, and user behavior data;

[0221] The network data is evaluated using an evaluation model to obtain the reliability results at each stage of the data lifecycle; wherein the evaluation results are used to indicate the reliability of the network data.

[0222] The network data is used to identify target network data whose evaluation results meet preset evaluation requirements, and the network topology of the network area to be optimized is optimized based on the target network data.

[0223] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the network optimization method described in the above-described method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0224] This disclosure also provides a computer program product 60, such as... Figure 6 The diagram shown is a schematic diagram of the structure of a computer program product 60 provided in an embodiment of this disclosure. The computer program product 60 carries a computer program 61. The program included in the computer program 61 can be used to execute the steps of the network optimization method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0225] The network optimization method, apparatus, device, medium, and product according to embodiments of the present disclosure have been described above with reference to the accompanying drawings. First, network data within the network area to be optimized is acquired; wherein the network data includes at least one of the following: user equipment data, network traffic data, network status data, and user behavior data; then, the network data is evaluated using an evaluation model to obtain an evaluation result; wherein the evaluation result is used to indicate the reliability of the network data at various stages of its data lifecycle; finally, target network data whose evaluation results meet preset evaluation requirements is identified from the network data, and the network topology of the network area to be optimized is optimized based on the target network data, thereby effectively ensuring the data quality of the network data at various stages of its data lifecycle and further improving the accuracy of network optimization based on network data.

[0226] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0227] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0228] Additionally, as used herein, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.

[0229] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0230] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0231] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0232] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A network optimization method, characterized in that, include: Obtain network data within the network area to be optimized; wherein the network data includes at least one of the following: user equipment data, network traffic data, network status data, and user behavior data; The network data is evaluated using an evaluation model to obtain evaluation results; wherein, the evaluation results are used to indicate the reliability of the network data at various stages of the data lifecycle. The network data is used to identify target network data whose evaluation results meet preset evaluation requirements, and the network topology of the network area to be optimized is optimized based on the target network data.

2. The method according to claim 1, characterized in that, The evaluation process of the network data using an evaluation model to obtain evaluation results includes: For each stage of the data lifecycle, determine multi-dimensional evaluation indicators for the network data; The evaluation results of the network data at the corresponding stage are calculated based on the multi-dimensional evaluation indicators. The evaluation results are determined based on the evaluation results of each of the aforementioned stages.

3. The method according to claim 2, characterized in that, When the data lifecycle is in the data processing stage, calculating the evaluation result of the network data at the corresponding stage based on the multi-dimensional evaluation indicators includes: Determine the preprocessing category of the network data, and preprocess the network data according to the preprocessing category to obtain preprocessed network data; Check the data integrity of the preprocessed network data; The preprocessing category and the data integrity are weighted to obtain a weighted processing result, and the data processing reliability of the network data is determined based on the weighted processing result.

4. The method according to claim 2, characterized in that, When the data lifecycle is in the data transmission phase, the calculation of the evaluation result of the network data in the corresponding phase based on the multi-dimensional evaluation indicators includes: Obtain the encryption complexity of the encryption algorithm used to obtain the network data; Obtain the transmission path for transmitting the network data during the data transmission phase; The data transmission complexity of the network data is calculated based on the transmission path of the network data and the encryption complexity.

5. The method according to claim 1, characterized in that, The data lifecycle includes: a data source stage, a data processing stage, and a data transmission stage; the evaluation of the network data using an evaluation model to obtain evaluation results includes: The network data at the data source stage is evaluated and processed using the evaluation model to obtain the data source credibility. The network data during the data processing stage is evaluated and processed using the evaluation model to obtain the data processing reliability. The network data during the data transmission phase is evaluated and processed using the evaluation model to obtain the data transmission complexity.

6. The method according to claim 1, characterized in that, The step of determining the target network data in the network data whose evaluation results meet the preset evaluation requirements includes: Determine the highest evaluation result for network data within the same data source; If the highest evaluation result is greater than or equal to the preset evaluation threshold, then the network data corresponding to the highest evaluation result is determined as the target network data.

7. The method according to claim 1, characterized in that, The step of optimizing the network topology of the network region to be optimized based on the target network data includes: Select network topology metadata from the target network data; wherein, the network topology metadata is used to describe the attribute information of network devices corresponding to the target network data in the network area to be optimized and the connection relationships between the network devices; Construct the network topology structure of the network area to be optimized based on the network topology metadata; The connection relationships between network devices in the network topology are optimized using a genetic algorithm to obtain an optimized network topology.

8. The method according to claim 7, characterized in that, The optimization of the connection relationships between network devices in the network topology using a genetic algorithm to obtain an optimized network topology includes: The network topology is randomly encoded to obtain multiple candidate network topologies; wherein, the candidate network topologies are used to indicate candidate connection relationships between the network devices; The fitness degree of each candidate network topology is calculated based on the fitness function; wherein the fitness degree is used to indicate the stability of each candidate network topology; Determine the candidate network topology corresponding to the highest adaptivity to obtain the target network topology; The target network topology is processed using a genetic algorithm to obtain an optimized network topology.

9. The method according to claim 8, characterized in that, The calculation of the adaptability of each candidate network topology based on the fitness function includes: Determine multi-dimensional network status data in the target network data that matches the network devices corresponding to the candidate network topology; The multi-dimensional network state data is weighted to obtain the adaptive degree.

10. A network optimization device, characterized in that, include: The acquisition unit is used to acquire network data within the network area to be optimized; wherein the network data includes at least one of the following: user equipment data, network traffic data, network status data, and user behavior data; The processing unit is used to evaluate the network data using an evaluation model to obtain an evaluation result; wherein the evaluation result is used to indicate the reliability of the network data at various stages of the data lifecycle. A network optimization unit is used to determine target network data in the network data whose evaluation results meet preset evaluation requirements, and to optimize the network topology of the network area to be optimized based on the target network data.

11. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the network optimization method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the network optimization method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product is stored in a storage medium, and the program product is executed by at least one processor to implement the network optimization method as described in any one of claims 1 to 9.

Images