Network analysis method, apparatus, device, and storage medium

Abstract

The application discloses a network analysis method and device, equipment and a storage medium, wherein the method comprises: acquiring network equipment data; constructing equipment portraits based on the network equipment data; constructing family group portraits based on the equipment portraits and using a correlation degree algorithm, wherein the equipment in the family group serves the same target user; constructing network portraits of the family group based on group network data and home broadband service system data of the family group, so as to analyze the family group by using the network portraits.

Description

Technical Field

[0001] This application relates to the field of communication technology, and includes, but is not limited to, a network analysis method, apparatus, device, and storage medium. Background Technology

[0002] With the development of smart networking services and the diversification of networking services within users' homes, various devices and business systems will generate a large amount of network data and user data. However, existing home network analysis mainly focuses on the relationship between users and devices, and between platforms and devices. It uses real-time data to determine the current status of devices and combines historical data to locate and resolve faults. The data is relatively closed, with poor visibility and availability. Summary of the Invention

[0003] In view of this, embodiments of this application provide a network analysis method, apparatus, device, and storage medium.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] In a first aspect, embodiments of this application provide a network analysis method, the method comprising:

[0006] Obtain network device data;

[0007] A device profile is constructed based on the network device data;

[0008] Based on the device profile, a correlation algorithm is used to construct a family group profile, wherein the devices in the family group serve the same target user;

[0009] Based on the group network data and home broadband service system data of the family group, a network profile of the family group is constructed, so as to analyze the family group using the network profile.

[0010] Secondly, embodiments of this application provide a network analysis system, the system comprising:

[0011] The acquisition layer is used to collect data from network devices and broadband service systems.

[0012] The base layer is used to store the network device data and the broadband service system data;

[0013] The platform layer is used for big data processing, building machine learning and data mining engines to construct device profiles based on the network device data; constructing household group profiles based on the device profiles using correlation algorithms; and constructing network profiles of the household groups based on the group network data and broadband service system data, so as to provide algorithmic support for analyzing the household groups using the network profiles.

[0014] The functional layer, based on the storage capacity of the basic layer and the data processing capacity of the platform layer, is used to provide real-time query, statistical analysis, data mining and machine learning for the family group;

[0015] The business layer, supported by the functional layer, provides personalized recommendations, statistical reports, network behavior analysis, fault warnings, and online real-time queries.

[0016] Thirdly, embodiments of this application provide a network analysis device, the device comprising:

[0017] The acquisition module is used to acquire network device data;

[0018] The first construction module is used to construct a device profile based on the network device data;

[0019] The second construction module is used to construct a family group profile based on the device profile using a correlation algorithm, wherein the devices in the family group serve the same target user.

[0020] The third construction module is used to construct a network profile of the family group based on the group network data and home broadband service system data, so as to analyze the family group using the network profile.

[0021] Fourthly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the program to implement the above-described method.

[0022] Fifthly, embodiments of this application provide a storage medium storing executable instructions for inducing a processor to execute the above-described method.

[0023] In this embodiment, network device data is first acquired; then, a device profile is constructed based on the network device data; a household group profile is constructed based on the device profile using a correlation algorithm; finally, a network profile of the household group is constructed based on the group network data and home broadband service system data, so as to analyze the household group using the network profile. In this way, by constructing a network profile, pain points and difficulties in home networks can be identified in advance, providing strong support for operation and maintenance, optimization, and marketing departments, and enabling refined operations. Attached Figure Description

[0024] Figure 1 A schematic diagram of a network analysis system architecture provided in an embodiment of this application;

[0025] Figure 2 A schematic diagram illustrating the implementation process of a network analysis method provided in this application embodiment;

[0026] Figure 3 A schematic diagram illustrating the construction of group profiles and network profiles provided in this application embodiment;

[0027] Figure 4 A schematic diagram illustrating a homegroup networking method provided in an embodiment of this application;

[0028] Figure 5 A schematic diagram illustrating the construction of a network profile as provided in an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of the composition structure of a network analysis device provided in an embodiment of this application;

[0030] Figure 7 This is a schematic diagram of a hardware entity of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of the embodiments will be further described in detail below with reference to the accompanying drawings. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0032] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0033] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit the scope of this application.

[0035] Existing home network solutions focus on remote management and configuration of network devices, and troubleshooting and resolving device malfunctions. However, with the development of smart networking services and the diversification of home networking services, various devices and service systems will generate large amounts of network data (network device data) and user data (home broadband service system data).

[0036] Existing home network analytics focuses on the relationships between users and devices, and between platforms and devices. It uses real-time data to determine the current status of devices and combines this with historical data to locate and resolve faults. However, it suffers from problems such as relatively closed data and poor visibility and usability.

[0037] The existing technology has the following three problems:

[0038] Problem 1: Existing systems analyze the relationship between users and devices or platforms and devices, without delving into the connections between devices and groups, or between groups and networks.

[0039] Question 2: The existing system only considers the network situation of a single device, without considering the network environment of the entire group as a family unit, and lacks analysis of the relationship between the group and the network.

[0040] Question 3: Existing systems fail to provide family group profiles through big data analytics, remaining only at the level of individual device network profiles, and thus cannot offer effective solutions at the family level to improve users' perceived network quality.

[0041] This application provides a schematic diagram of a network analysis system architecture, as shown in the embodiments below. Figure 1 As shown in the diagram, the architecture includes: a data acquisition layer 11, a foundation layer 12, a platform layer 13, a functional layer 14, and a business layer 15.

[0042] A network analytics system is a home information system that integrates home networks and big data analytics. It enables the management of various smart network devices within the home, integrates home broadband services, collects and processes massive amounts of home network data, and analyzes the usage, needs, and pain points of family groups through big data analysis. This makes home network use more convenient, efficient, and intelligent, and provides strong support for home network construction.

[0043] Data acquisition layer 11 is used to collect data from network devices and broadband service systems;

[0044] Here, the acquisition layer 11 is used to collect data from multiple channels, including probe data, device management data, preprocessing data, and work order systems. This enables the acquisition of data sources from multiple broadband service systems and network devices.

[0045] Base layer 12 is used to store the network device data and the home broadband service system data;

[0046] Here, the base layer 12 includes the Hadoop Distributed File System (HDFS), the distributed, column-oriented open-source database HBase, and the distributed application coordination service software Zookeeper. It can realize distributed storage in the base layer using Hadoop HDFS, HBase, and Zookeeper. The stored content includes, but is not limited to, basic device information, device uplink information, downstream device information, device surrounding WiFi status, terminal operating status, user information, work order information, complaint information, business status, etc.

[0047] Platform layer 13 is used for big data processing, building machine learning and data mining engines to construct device profiles based on the network device data; constructing household group profiles based on the device profiles using correlation algorithms; and constructing network profiles of the household groups based on the group network data and broadband service system data, so as to provide algorithmic support for analyzing the household groups using the network profiles.

[0048] Here, platform layer 13 includes Apache Hive, Apache Pig, the ETL tool Flume / Sqoop, the parallel computing engine MapReduce, and the algorithm / learning engine Hadoop ML / Mahout. During implementation, platform layer 13, addressing the different analytical needs of functional layer 14, uses the MapReduce parallel computing engine as its core, employing Flume / Sqoop to extract, clean, transform, and load data from multiple data sources into an HBase-based data storage model. A parallel machine learning and data mining engine is built based on Hadoop ML / Mahout, providing discriminant analysis, clustering, decision trees, association algorithms, recommendation algorithms, and more.

[0049] Functional layer 14, based on the storage capacity of the basic layer and the data processing capacity of the platform layer, is used to provide real-time query, statistical analysis, data mining and machine learning for the family group;

[0050] Here, functional layer 14 includes real-time query, statistical analysis, data mining, and machine learning to analyze and mine the data processed by platform layer 13, establish device profile module, group profile module, and network profile module, establish group concept by analyzing device characteristics, and derive the relationship between devices, groups, and networks based on the usage of network devices and home groups, thereby providing a more intuitive understanding of the home network situation and providing effective support for the development of subsequent home networking services.

[0051] The business layer 15 is used to provide personalized recommendations, statistical reports, network behavior analysis, fault warnings, and online real-time queries, supported by the functional layer.

[0052] Here, with the support of the functional layer 14, the business layer 15 provides users with personalized recommendations, statistical reports, network behavior analysis, fault warnings, and online real-time queries.

[0053] In this embodiment, a big data analysis system (network analysis system) can be used to analyze the relationships between groups and between groups and networks. By constructing a profile of family groups, pain points and difficulties of family networks can be identified in advance, providing strong support for departments such as operation and maintenance, optimization, and marketing, and enabling refined operation.

[0054] This application provides a network analysis method, such as... Figure 2 As shown, the method includes:

[0055] Step S210: Obtain network device data;

[0056] Here, network devices can refer to communication devices used in a home network, including but not limited to wireless routers, modems / optical modems, switches, home computers, and mobile phones. Smart networking technology for home networks is a product of the continuous development of network communication and information technologies.

[0057] Routers, also known as gateway devices, can be used to connect multiple logically separate networks. A logical network can represent a single network or a subnet. When data is transmitted from one subnet to another, it can be accomplished through the router's routing function.

[0058] When home broadband is accessed via telephone line, a modem is used; when home broadband is accessed via fiber optic cable, an optical modem is used.

[0059] A switch is a network device used for forwarding electrical (optical) signals, which can provide a dedicated electrical signal path for any two network nodes connected to the switch.

[0060] Here, network device data includes at least: basic device information, device uplink information, downstream device information, surrounding WiFi status, and terminal operating status.

[0061] In some embodiments, network device data may refer to data reported by the network device through a probe, wherein the probe may be a data acquisition module integrated into the device for collecting device data.

[0062] In some embodiments, network device data can be transmitted via, for example, Figure 1 The probes in the acquisition layer 11 shown report network device data.

[0063] In some embodiments, network device data can be transmitted via, for example, Figure 1 The data collection layer 11 shown above is used to report network device data through device management.

[0064] In some embodiments, network device data can be transmitted via, for example, Figure 1 The data acquisition layer 11 shown is preprocessed and reported network device data. The preprocessing layer can be a platform that includes home user network information and device information.

[0065] During implementation, no restrictions are placed on the platform from which network devices report network device data.

[0066] Step S220: Construct a device profile based on the network device data;

[0067] Here, the characteristic data of the device can be determined based on the network device data, including at least the device's uplink status, downstream device information, WIFI status, surrounding WIFI information, network information, parameter configuration, and service monitoring information.

[0068] During implementation, device profiles can be built based on the feature data of the above devices.

[0069] Step S230: Based on the device profile, construct a family group profile using a correlation algorithm, wherein the devices in the family group serve the same target user;

[0070] In some embodiments, the uplink element of the network device can be determined based on the uplink status in the device profile.

[0071] During implementation, network devices with consistent characteristic data can be grouped into one category based on device profiles using discriminant analysis and clustering algorithms. The relationships between network devices within the same group can then be analyzed using correlation algorithms and the network devices' uplink elements. If network devices share the same downstream network devices based on these relationships, then these network devices belong to the same home group. For example, if the same mobile phone appears on two different network devices using the same broadband account, then these two different network devices belong to the same home group. Here, the devices within the home group serve the same target user.

[0072] Step S240: Construct a network profile of the family group based on the group network data and home broadband service system data, and use the network profile to analyze the family group.

[0073] Here, the broadband service system data includes at least: user information, work order information, complaint information, and service status. In some embodiments, network device data can be obtained through methods such as... Figure 1The data collection layer 11 shown is where the work order system reports data to the broadband service system.

[0074] During implementation, the group network data of the family group and the home broadband service system data of the family group can be obtained first, and then a network profile of the family group can be constructed based on the above two types of data.

[0075] In some embodiments, a network profile of a household group can be presented through a unified and easy-to-understand visual view. Based on this network profile, the network status, usage preferences, and abnormal household groups of the group can be analyzed. Then, in combination with business needs, personalized recommendations, visualizations, and fault warnings can be provided.

[0076] In this embodiment, network device data is first acquired; then, a device profile is constructed based on the network device data; a household group profile is constructed based on the device profile using a correlation algorithm; finally, a network profile of the household group is constructed based on the group network data and home broadband service system data, so as to analyze the household group using the network profile. In this way, by constructing a network profile, pain points and difficulties in home networks can be identified in advance, providing strong support for operation and maintenance, optimization, and marketing departments, and enabling refined operations.

[0077] Figure 3 This application provides a schematic diagram illustrating the construction of group profiles and network profiles, as shown in the embodiments. Figure 3 As shown, the diagram includes: device (network device) profile 31, device group relationship 32, group profile 33, network group relationship 34, network profile 35, and network device relationship 36.

[0078] Device profiles can be built based on device feature data.31 Here, device feature data mainly includes uplink status, downstream device information, WIFI status, surrounding WIFI information, network information, parameter configuration, service monitoring information, etc.

[0079] Based on the device profile 31, the device group relationship 32 is analyzed. The device group relationship 32 identifies whether devices belong to the same group and the relationship between devices in the group network. Discriminant analysis and clustering algorithms group devices with unified characteristic data into one category. The correlation algorithm analyzes the association relationship between devices in the same group. For example, if devices have the same downstream devices, then these devices belong to the same home group. The uplink status of the devices indicates their uplink network element. Based on the group network data and home broadband service system data in the constructed home group, a network profile 33 for that home group is constructed.

[0080] Based on the above group profile 33, the group network relationship 34 is analyzed, and the network characteristics of the devices in the home group are extracted, including WiFi parameters, WiFi power, weak signal threshold, channel noise floor, signal strength, receiving rate, sending rate, and message statistics, to describe the network profile of the devices 35.

[0081] Based on the network profile 35, the relationship between network devices 36 is analyzed to obtain the relationship between devices in the network.

[0082] For example, such as Figure 4 As shown, classification algorithms can be used to distinguish several network conditions within a group, including:

[0083] Figure 4 The mesh network on the left has no parent-child relationship between nodes. As long as they are within the range of wireless transmission power, they can communicate directly. If one node fails, it will only affect the wireless links related to it, while other links can continue to communicate normally. This type of network has very high reliability.

[0084] Figure 4 In a tree-like network, nodes have parent-child relationships. Each node only communicates with nodes that have a direct parent-child relationship with it. If a parent node fails, all its child nodes will become unusable.

[0085] Figure 4 The AC+AP networking method on the right refers to AC being the controller and AP being the WIFI router. AC acts as a dedicated control device to control user terminals to switch between different APs, enabling automatic switching and seamless coverage.

[0086] In this embodiment, a group network identification model is established based on a multi-dimensional analysis of the relationship between devices, groups, and networks. By deeply mining device information and establishing an identification model of device group relationships based on the associations between devices, it determines whether devices belong to the same group and their relationships within the group, thereby deriving the distribution of the group network. By mining the relationships between devices, groups, and networks in a home network, a home group characteristic model is constructed to analyze and discover users' core needs, addressing network pain points and challenges.

[0087] Figure 5 This is a schematic diagram illustrating the construction of a network profile as provided in an embodiment of this application, such as... Figure 5 As shown, the network profile includes first-order labels 51, second-order labels 52, and third-order labels 53, among which,

[0088] First-order label 51: Extract basic data from six dimensions: user perception, location attributes, network quality, device attributes, business behavior, and complaint characteristics, and generate first-order labels through numerical transformation and statistics;

[0089] Second-order labels 52: Second-order labels are generated through similarity algorithms, location algorithms, recognition algorithms, etc.

[0090] Third-order label 53: Using prediction algorithms such as time series and regression to analyze trend changes, discover the changing patterns of user group network behavior, and derive third-order labels such as locked-in users, high-risk users, game users, and network anomalies.

[0091] During implementation, it can be based on Figure 3 The network relationship 31 shown is based on device feature attributes. The third-order label attributes of the group are analyzed by data mining algorithms to construct a network profile, obtain the network status, usage preferences and abnormal family groups of the group, and then combine with business needs to provide personalized recommendations, visualization and fault warnings.

[0092] In some embodiments, the identification of network labels in the third-order labels can be performed by clustering and classification based on the KMeans algorithm of the partitioning method, and then the family groups are classified according to performance characteristics.

[0093] First, the characteristic attributes of household groups can be determined, including wireless coverage, number of terminal users, number of abnormal dropped calls, signal strength, uplink and downlink traffic, etc. Cluster analysis is performed on the characteristic attributes of multiple household groups. According to the clustering results, if the distance between the characteristic attribute of a certain household group in a class (a certain characteristic attribute) and the cluster center of that characteristic attribute meets the distance threshold, it indicates that the characteristic attribute of that household group is an outlier. Then, the vector characteristics of the cluster center of the outlier point are analyzed to determine whether the key indicators of the household group are indeed abnormal.

[0094] Based on this, a classification model for family groups is constructed, which ultimately forms an identification model for abnormal network groups. By using the key performance indicators of family groups, it is possible to determine whether a family group is experiencing network anomalies, thus achieving intelligent identification of abnormal family groups.

[0095] By using the characteristic attributes of household groups, the KMeans algorithm is used to cluster and classify household groups, forming an identification model for abnormal network groups. This model predicts abnormal network groups, enabling proactive inspection and repair, and enhancing network robustness and users' perception of network quality.

[0096] In this way, based on the data mining results of the family group network, the network profile of the group is presented through a unified and easy-to-understand visualization view. Users can combine their own needs to make personalized recommendations for services, troubleshoot network problems, and display data, thereby improving operation and maintenance efficiency, optimizing user experience, and reducing user complaint rate.

[0097] In some embodiments, step S240 above, "constructing a network profile of the family group based on the group network data and broadband service system data, and using the network profile to analyze the family group," can be achieved through the following steps:

[0098] Step 241: Based on the group network data and home broadband service system data of the aforementioned family groups, extract data from six dimensions: user perception, network quality, service behavior, location attributes, device performance attributes, and complaint characteristics.

[0099] Step 242: Generate first-order labels for the family groups based on the data from the six dimensions;

[0100] like Figure 5 As shown, the first-order label of this household group can be identified by data from six dimensions: user perception, network quality, business behavior, location attributes, device performance attributes, and complaint characteristics.

[0101] Step 243: Based on the first-order label, generate a second-order label using a similarity algorithm, a location algorithm, and a recognition algorithm. The second-order label includes at least high stability, network locking frequency, gigabit cell, high bandwidth, complaint frequency, and low latency.

[0102] like Figure 5 As shown, second-order labels can be generated based on first-order labels using big data mining algorithms, including but not limited to similarity algorithms, location algorithms, and recognition algorithms.

[0103] During implementation, second-order labels should include at least high stability, frequency of network locking, gigabit cells, high bandwidth, frequency of complaints, and low latency.

[0104] Step 244: Based on the first-order labels and the second-order labels, use a time series algorithm to determine the network behavior change patterns of the family groups;

[0105] Here, time series analysis is a statistical analysis method that can predict future development trends based on data sequences over a certain period of time; it is also known as time series trend extrapolation.

[0106] In some embodiments, the time series algorithm includes correlation aggregation, time series accumulation, and label fixation.

[0107] like Figure 5 As shown, the network behavior change patterns of the family groups can be determined using time series algorithms based on first-order and second-order labels.

[0108] Step 245: Generate third-order labels for the family group network based on the network behavior change patterns, wherein the third-order labels include at least locked users, high-risk users, game users, and abnormal network users.

[0109] In this embodiment, firstly, based on the group network data and broadband service system data of the family group, data from six dimensions—user perception, network quality, service behavior, location attributes, device performance attributes, and complaint characteristics—are extracted. First-order labels for the family group are generated based on these six dimensions. Then, based on the first-order labels, second-order labels are generated using similarity algorithms, location algorithms, and recognition algorithms. Finally, based on the first-order and second-order labels, time-series algorithms are used to determine the network behavior change patterns of the family group. Third-order labels for the family group network are generated based on these network behavior change patterns, wherein the third-order labels include at least locked-network users, high-risk users, gaming users, and users with abnormal network activity. In this way, by constructing third-order labels for the group network through location algorithms, recognition algorithms, and time-series algorithms, the network status and usage preferences of the family group are obtained. A unified and easily understandable visual view is then used to present the network profile of the third-order group, enabling targeted personalized recommendations.

[0110] In some embodiments, the cluster network data includes at least wireless coverage, number of terminal users, number of abnormal disconnections, signal strength, and uplink / downlink traffic. Step S240, "Constructing a network profile of the home group based on the cluster network data and broadband service system data, and using the network profile to analyze the home group," further includes the following steps:

[0111] Step 246: Based on the wireless coverage, the number of terminal users, the number of abnormal disconnections, the signal strength, and the uplink and downlink traffic, use cluster analysis to determine whether the home group has a network anomaly.

[0112] Here, the identification of network labels in the third-order label can be performed by clustering and classification based on the KMeans algorithm of the partitioning method, and then the family groups are classified according to performance characteristics.

[0113] First, the characteristic attributes of household groups can be determined, including wireless coverage, number of terminal users, number of abnormal dropped calls, signal strength, uplink and downlink traffic, etc. Cluster analysis is performed on the characteristic attributes of multiple household groups. According to the clustering results, if the distance between the characteristic attribute of a certain household group in a class (a certain characteristic attribute) and the cluster center of that characteristic attribute meets the distance threshold, it indicates that the characteristic attribute of that household group is an outlier. Then, the vector characteristics of the cluster center of the outlier point are analyzed to determine whether the key indicators of the household group are indeed abnormal.

[0114] Based on this, a classification model for family groups is constructed, which ultimately forms an identification model for abnormal network groups. By using the key performance indicators of family groups, it is possible to determine whether a family group is experiencing network anomalies, thus achieving intelligent identification of family network anomalies.

[0115] In this embodiment, clustering analysis algorithms are used to classify family groups based on their characteristic attributes, forming a family group anomaly identification model. This model predicts family groups with network anomalies, enabling pre-inspection and proactive maintenance, thereby improving network robustness and users' perception of network quality.

[0116] In some embodiments, step S240 above, "constructing a network profile of the family group based on the group network data and broadband service system data, and using the network profile to analyze the family group," further includes the following steps:

[0117] Step 247: Based on the group network data of the family group, use a classification algorithm to determine the network structure of the family group, wherein the network structure includes at least a mesh structure, a tree structure, and a controller plus router structure;

[0118] During implementation, classification algorithms can be used to determine, for example... Figure 4 The diagram shows a mesh structure, a tree structure, and a controller plus router structure.

[0119] Step 248: Determine the relationships between devices in the network profile based on the network structure, so as to analyze the household groups using the relationships between the devices.

[0120] In this embodiment, a classification algorithm is used to determine the network structure of the family group; thus, the relationships between devices in the network profile can be determined based on the network structure, so as to effectively analyze the family group by utilizing the relationships between devices.

[0121] Based on the foregoing embodiments, this application provides a network analysis device, which includes various modules, each module including sub-modules, which can be implemented by a processor in an electronic device; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be a central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA), etc.

[0122] Figure 6 This is a schematic diagram of the composition structure of the network analysis device provided in the embodiments of this application, as shown below. Figure 6 As shown, the device 600 includes:

[0123] Module 610 is used to acquire network device data;

[0124] The first construction module 620 is used to construct a device profile based on the network device data;

[0125] The second construction module 630 is used to construct a family group profile based on the device profile using a correlation algorithm, wherein the devices in the family group serve the same target user.

[0126] The third construction module 640 is used to construct a network profile of the family group based on the group network data and home broadband service system data of the family group, so as to analyze the family group using the network profile.

[0127] In some embodiments, the third construction module 640 includes an extraction submodule, a first generation submodule, a second generation submodule, a first determination submodule, and a third generation submodule. The extraction submodule is used to extract data across six dimensions—user perception, network quality, service behavior, location attributes, device performance attributes, and complaint characteristics—based on the family group's group network data and broadband service system data. The first generation submodule is used to generate first-order labels for the family group based on the six dimensions of data. The second generation submodule is used to generate second-order labels based on the first-order labels using similarity algorithms, location algorithms, and recognition algorithms. The second-order labels include at least high stability, network locking frequency, gigabit cells, high bandwidth, complaint frequency, and low latency. The first determination submodule is used to determine the network behavior change patterns of the family group based on the first-order and second-order labels using a time series algorithm. The third generation submodule is used to generate third-order labels for the family group network based on the network behavior change patterns. The third-order labels include at least network-locked users, high-risk users, game users, and users with abnormal network activity.

[0128] In some embodiments, the group network data includes at least wireless coverage, number of terminal users, number of abnormal disconnections, signal strength, and uplink / downlink traffic. The third construction module 640 further includes a second determination submodule, used to determine whether the home group is experiencing network anomalies based on the wireless coverage, number of terminal users, number of abnormal disconnections, signal strength, and uplink / downlink traffic using cluster analysis.

[0129] In some embodiments, the third construction module 640 further includes a third determining submodule and a fourth determining submodule, used to determine the network structure of the family group based on the group network data of the family group using a classification algorithm, wherein the network structure includes at least a mesh structure, a tree structure, and a controller plus router structure; the fourth determining submodule is used to determine the relationship between devices in the network profile based on the network structure, so as to analyze the family group using the relationship between the devices.

[0130] In some embodiments, the network device data includes at least: basic device information, device uplink information, downstream device information, surrounding WiFi conditions, and terminal operating status.

[0131] In some embodiments, the home broadband service system data includes at least: user information, work order information, complaint information, and service status.

[0132] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0133] It should be noted that, in the embodiments of this application, if the above methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause electronic devices (such as mobile phones, tablets, laptops, desktop computers, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0134] Correspondingly, embodiments of this application provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps in the network analysis method provided in the above embodiments.

[0135] Correspondingly, embodiments of this application provide an electronic device, Figure 7 A schematic diagram of a hardware entity of an electronic device provided in an embodiment of this application, such as... Figure 7 As shown, the hardware entity of the device 700 includes a memory 701 and a processor 702. The memory 701 stores a computer program that can run on the processor 702. When the processor 702 executes the program, it implements the steps in the network analysis method provided in the above embodiments.

[0136] The memory 701 is configured to store instructions and applications executable by the processor 702, and can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data and video communication data) in the processor 702 and various modules in the electronic device 700. It can be implemented by flash memory or random access memory (RAM).

[0137] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0138] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0139] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0141] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0142] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0143] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0144] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a mobile phone, tablet computer, laptop computer, desktop computer, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, magnetic disks, or optical disks.

[0145] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0146] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0147] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0148] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A network analysis method, characterized in that, The method includes: Obtain network device data; A device profile is constructed based on the network device data; Based on the device profile, a correlation algorithm is used to construct a family group profile, wherein the devices in the family group serve the same target user; A network profile of the aforementioned family groups is constructed based on the group network data and broadband service system data, and the family groups are analyzed using this network profile. The network profile includes first-order labels, second-order labels, and third-order labels. The first-order labels are generated based on six dimensions of data, including extracted user perception, network quality, service behavior, location attributes, device performance attributes, and complaint characteristics. The second-order labels are generated based on the first-order labels using similarity algorithms, location algorithms, and recognition algorithms. The second-order labels include at least high stability, network locking frequency, gigabit cells, high bandwidth, complaint frequency, and low latency. The third-order labels are generated based on network behavior change patterns, which are determined using time series algorithms based on the first-order and second-order labels. The third-order labels include at least network-locked users, high-risk users, gaming users, and users with abnormal network behavior. Meanwhile, based on the group network data of the family group, a classification algorithm is used to determine the network structure of the family group, wherein the network structure includes at least a mesh structure, a tree structure, and a controller plus router structure; Based on the network structure, the relationships between devices in the network profile are determined, so as to analyze the household groups using the relationships between the devices.

2. The method as described in claim 1, characterized in that, The group network data includes at least wireless coverage, number of terminal users, number of abnormal disconnections, signal strength, and uplink / downlink traffic. The method further includes: Based on the wireless coverage, the number of terminal users, the number of abnormal disconnections, the signal strength, and the uplink and downlink traffic, cluster analysis is used to determine whether the home group has a network anomaly.

3. The method as described in any one of claims 1 or 2, characterized in that, The network device data includes at least: basic device information, device uplink information, downstream device information, surrounding WiFi status, and terminal operating status.

4. The method as described in any one of claims 1 or 2, characterized in that, The data in the home broadband service system includes at least: user information, work order information, complaint information, and service status.

5. A network analysis system, characterized in that, The network analysis system includes: The acquisition layer is used to collect data from network devices and broadband service systems. The base layer is used to store the network device data and the broadband service system data; The platform layer is used for big data processing, building machine learning and data mining engines to construct device profiles based on network device data; constructing household group profiles based on the device profiles using correlation algorithms; and constructing network profiles for the household groups based on group network data and broadband service system data, providing algorithmic support for analyzing the household groups using these network profiles. The network profiles include first-order labels, second-order labels, and third-order labels. The first-order labels are generated based on six dimensions of data, including extracted user perception, network quality, service behavior, location attributes, device performance attributes, and complaint characteristics. The second-order labels are generated based on the first-order labels using similarity algorithms, location algorithms, and recognition algorithms, and include at least high stability, network locking frequency, gigabit cells, high bandwidth, complaint frequency, and low latency. The third-order labels are generated based on network behavior change patterns, determined using time series algorithms based on the first-order and second-order labels, and include at least network-locked users, high-risk users, game users, and users with abnormal network activity. The platform layer is also used to determine the network structure of the family group based on the group network data of the family group using a classification algorithm, wherein the network structure includes at least a mesh structure, a tree structure, and a controller plus router structure; and to determine the relationship between devices in the network profile based on the network structure, so as to analyze the family group using the relationship between the devices; The functional layer, based on the storage capacity of the basic layer and the data processing capacity of the platform layer, is used to provide real-time query, statistical analysis, data mining and machine learning for the family group; The business layer, supported by the functional layer, provides personalized recommendations, statistical reports, network behavior analysis, fault warnings, and online real-time queries.

6. A network analysis device, characterized in that, The device includes: The acquisition module is used to acquire network device data; The first construction module is used to construct a device profile based on the network device data; The second construction module is used to construct a family group profile based on the device profile using a correlation algorithm, wherein the devices in the family group serve the same target user. The third construction module is used to construct a network profile of the family group based on the group network data and home broadband service system data, so as to analyze the family group using the network profile. The network profile includes first-order labels, second-order labels, and third-order labels. The first-order labels are generated based on six dimensions of data, including extracted user perception, network quality, service behavior, location attributes, device performance attributes, and complaint characteristics. The second-order labels are generated based on the first-order labels using similarity algorithms, location algorithms, and recognition algorithms. The second-order labels include at least high stability, network locking frequency, gigabit cells, high bandwidth, complaint frequency, and low latency. The third-order labels are generated based on network behavior change patterns, which are determined based on the first-order and second-order labels using time series algorithms. The third-order labels include at least network-locked users, high-risk users, game users, and users with abnormal network behavior. The third construction module further includes a third determining submodule and a fourth determining submodule. The third determining submodule is used to determine the network structure of the family group based on the group network data of the family group using a classification algorithm, wherein the network structure includes at least a mesh structure, a tree structure, and a controller plus router structure. The fourth determining submodule is used to determine the relationship between devices in the network profile based on the network structure, so as to analyze the family group by utilizing the relationship between the devices.

7. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, It stores executable instructions for causing a processor to execute, thereby implementing the steps of the method according to any one of claims 1 to 4.

Images