A network signal intelligent monitoring method and system based on satellite Internet

Abstract

The present invention relates to the field of communications technology and proposes a method for intelligent network signal monitoring based on satellite internet. The method comprises: first obtaining the network coverage area corresponding to the satellite internet and collecting raw signal data; parsing parameters including strength, frequency, and delay; constructing a multi-dimensional network sequence based on this data and extracting features; locating interference sources by combining satellite orbits, ground topography, and meteorological data; calculating interference strength to delineate signal-weak areas and enhance the signal; then monitoring the network to determine key optimization areas; querying the current network usage status to analyze optimization directions; extracting optimized signal points to calculate signal balance values; and finally generating network signal indicators; analyzing fluctuation trends and influencing factors; and finally generating an intelligent signal monitoring report. The present invention can improve the monitoring efficiency of satellite network signal monitoring.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and system for intelligently monitoring network signals based on satellite Internet. Background Art

[0002] In today's digital age, the Internet has been deeply integrated into every aspect of people's lives. With the vigorous development of satellite Internet technology, it has become an indispensable part of the modern communication system by providing network access services to special scenarios around the world, especially in remote areas, oceans, and air, with its advantages of wide coverage and freedom from geographical restrictions.

[0003] At present, traditional network signal monitoring methods have exposed many shortcomings when facing the complex application scenarios of satellite Internet. On the one hand, ground network signal monitoring mainly focuses on the base station coverage area, and lacks consideration for the characteristics of satellite signal long transmission path and susceptibility to interference from the space environment. It is difficult to accurately capture the fluctuations and attenuation of satellite Internet signals. On the other hand, conventional monitoring is mostly based on fixed-time sampling detection, and cannot track the dynamically changing signal conditions of satellite Internet in real time and continuously. In the face of sudden space weather changes, satellite attitude adjustments or temporary failures of ground stations, it is difficult to provide timely warnings, which in turn affects the normal operation of various services that rely on satellite networks, resulting in the current monitoring efficiency of satellite Internet network signals. Therefore, a network signal intelligent monitoring method based on satellite Internet is needed to improve the monitoring efficiency of satellite network signal monitoring. Summary of the Invention

[0004] The present invention provides a method and system for intelligently monitoring network signals based on satellite Internet, the main purpose of which is to improve the monitoring efficiency of satellite network signals.

[0005] To achieve the above objectives, the present invention provides a method for intelligently monitoring network signals based on satellite Internet, comprising:

[0006] Obtaining a network coverage area corresponding to the satellite internet, collecting raw signal data within the network coverage area, parsing detailed signal parameters corresponding to the raw signal data, the detailed signal parameters including signal strength information, signal frequency information, and delay parameter information; constructing a multidimensional network sequence corresponding to the satellite internet based on the detailed signal parameters, and extracting sequence dimension features from the multidimensional network sequence;

[0007] Based on the sequence dimension features and in combination with the satellite orbit data, ground terrain data, and meteorological data corresponding to the satellite Internet, the interference source is located in the network coverage area to obtain the located interference source, the main interference source type corresponding to the located interference source is identified, and based on the main interference source type, the interference intensity value corresponding to the located interference source is calculated;

[0008] Based on the interference intensity value, delineate signal-weak areas within the network coverage area, perform signal enhancement on the signal-weak areas to obtain signal-enhanced areas, perform real-time network monitoring on the signal-enhanced areas to obtain real-time network data, and determine key optimization areas required for the satellite Internet based on the real-time network data;

[0009] querying the current network usage status corresponding to the key optimization area, analyzing the network optimization direction corresponding to the key optimization area based on the current network usage status, extracting optimized signal points in the network optimization direction, and calculating the signal equalization value corresponding to the key optimization area based on the optimized signal points;

[0010] Based on the signal balance value, a network signal index corresponding to the key optimization area is generated, the signal fluctuation trend corresponding to the network signal index is analyzed, the fluctuation influencing factors in the signal fluctuation trend are identified, and based on the fluctuation influencing factors, a signal intelligent monitoring report corresponding to the satellite Internet is generated.

[0011] Optionally, constructing a multi-dimensional network sequence corresponding to the satellite Internet based on the detailed signal parameters includes:

[0012] Identifying key characteristic indicators in the signal detailed parameters;

[0013] Classifying the signal detailed parameters according to the key characteristic indicators to obtain a parameter classification set;

[0014] Mapping the parameters in the parameter classification set to their corresponding network dimensions to obtain an initial dimensional network;

[0015] Extracting an initial network subsequence from the initial dimensional network;

[0016] Analyzing association rules between subsequences in the initial network subsequence;

[0017] Based on the association rules, the initial network subsequences are sequence-integrated to obtain a multi-dimensional network sequence.

[0018] Optionally, locating the interference source in the network coverage area based on the sequence dimension feature in combination with satellite orbit data, ground terrain data, and meteorological data corresponding to the satellite Internet to obtain the located interference source includes:

[0019] Extracting abnormal feature information corresponding to the sequence dimension feature;

[0020] Identify orbital parameter characteristics in satellite orbit data;

[0021] Based on the abnormal characteristic information and the orbital parameter characteristics, constructing an interference source positioning framework corresponding to the network coverage area;

[0022] Extract meteorological influencing factors from meteorological data;

[0023] Based on the meteorological impact factor and the interference source positioning framework, performing regional identification on the network coverage area to obtain a candidate interference area;

[0024] Perform feature analysis on ground terrain data to obtain a terrain feature set;

[0025] Based on the terrain feature set, interference sources are located in the candidate interference area to obtain located interference sources.

[0026] Optionally, the calculating, based on the main interference source type, the interference intensity value corresponding to the positioning interference source includes:

[0027] The interference intensity value corresponding to the positioning interference source is calculated using the following formula:

[0028]

[0029] in, Indicates the interference intensity value corresponding to the positioning interference source, Indicates the number of types corresponding to the main interference source type, Indicates the quantity index corresponding to the main interference source type, Indicates the The interference frequency factor corresponding to each main interference source type, Indicates the The interference amplitude factor corresponding to each main interference source type, represents the interference influence function.

[0030] Optionally, demarcating a signal-weak area in the network coverage area based on the interference intensity value includes:

[0031] Identifying an interference intensity level corresponding to the interference intensity value;

[0032] Performing partition processing on the interference intensity level to obtain a partition intensity level;

[0033] determining, based on the partition strength level, a network coverage unit corresponding to the network coverage area;

[0034] Performing actual signal measurement on the network coverage unit to obtain actual signal data;

[0035] Based on the measured signal data, a signal weak area in the network coverage area is delineated.

[0036] Optionally, determining the key optimization area required for the satellite Internet based on the real-time network data includes:

[0037] identifying performance data clusters in the real-time network data;

[0038] Setting thresholds for indicators in the network data cluster to obtain a data threshold range;

[0039] Based on the indicator threshold range, screening the core data subset in the performance data cluster;

[0040] Analyzing subset weights corresponding to the core data subsets;

[0041] Based on the subset weights, determine the key optimization areas required for the satellite Internet

[0042] Optionally, querying the current network usage status corresponding to the key optimization area includes:

[0043] Identify the topological identification code of the key optimization area in the satellite Internet;

[0044] Parsing the encoding rules corresponding to the topology identification code;

[0045] Based on the coding rules, construct a regional basic framework corresponding to the key optimization area;

[0046] Based on the regional basic framework, query the regional limited data corresponding to the key optimization area;

[0047] Based on the area-limited data, extracting the regional traffic records corresponding to the key optimization area;

[0048] Based on the regional traffic records, query the network usage status corresponding to the key optimization area.

[0049] Optionally, analyzing the network optimization direction corresponding to the key optimization area according to the current network usage status includes:

[0050] Collecting real-time usage data corresponding to each node in the network usage status;

[0051] Based on the real-time usage data, a network status matrix corresponding to the key optimization interval is constructed;

[0052] Dividing the network unit groups corresponding to the grid units in the network state matrix;

[0053] analyzing the degree of network association between the groups of network units;

[0054] Based on the network correlation degree, analyze the network optimization direction corresponding to the key optimization area

[0055] Optionally, the calculating, based on the optimized signal point, the signal equalization value corresponding to the key optimization area includes:

[0056] The signal equalization value corresponding to the key optimization area is calculated using the following formula:

[0057]

[0058] in, Indicates the signal equalization value corresponding to the key optimization area, Indicates the total number of optimized signal points in the key optimization area, Indicates the number index of optimized signal points, Indicates the The signal strength value corresponding to the optimized signal point, Indicates the average value of the signal strength corresponding to the optimized signal point, Indicates the standard deviation of the signal strength corresponding to the optimized signal point.

[0059] Optionally, generating a network signal indicator corresponding to the key optimization area based on the signal balance value includes:

[0060] Identifying a signal value interval in which the signal equalization value lies;

[0061] Determining a signal fluctuation standard corresponding to the signal value interval;

[0062] According to the signal fluctuation standard, the fluctuation level corresponding to the signal balance value is divided;

[0063] Extracting features of the fluctuation level to obtain fluctuation level features;

[0064] Based on the fluctuation level characteristics, a network signal index corresponding to the key optimization area is generated.

[0065] First, the present invention obtains the network coverage area corresponding to the satellite Internet and collects the original signal data in the network coverage area, which helps to fully understand the distribution of satellite network signals in specific areas, lays the foundation for accurate analysis of signal characteristics, and can timely detect the source of abnormal signal changes, effectively ensuring the stability and reliability of satellite Internet services in special scenarios such as remote areas, oceans, and air, and greatly improving the accuracy and efficiency of satellite network signal monitoring. At the same time, the present invention locates the interference source in the network coverage area based on the sequence dimension characteristics combined with the satellite orbit data, ground terrain data and meteorological data corresponding to the satellite Internet, and obtains the located interference source, which can reflect the interference of factors such as the atmosphere, and then accurately determines the location of the interference source in combination with the sequence dimension characteristics, effectively shortening the time for troubleshooting interference problems, improving the stability and reliability of satellite Internet signals, and ensuring service quality and continuity. The present invention demarcates the signal in the network coverage area based on the interference intensity value. Weak areas can help network operators identify areas prone to signal problems in advance, allowing them to perform targeted network optimization and equipment upgrades. When planning new network infrastructure layouts, base stations and other equipment can be rationally configured based on the distribution of signal-weak areas, improving resource allocation efficiency. By querying the network usage status corresponding to the key optimization areas, the present invention can accurately understand the actual network problems faced by users in the area, such as frequent disconnections and lags, allowing optimization measures to directly address pain points. By understanding the real-time demand for data traffic and peak and trough periods, network resources can be rationally allocated and resource utilization improved. Furthermore, based on the signal balance value, the present invention generates network signal indicators corresponding to the key optimization areas, objectively quantifying the network signal conditions within the area and providing an accurate basis for evaluating network performance. These indicators can serve as an important reference for network optimization, facilitating the targeted formulation and adjustment of optimization strategies, such as focusing on improving areas with poor signal balance, and facilitating long-term monitoring of network quality. Therefore, the present invention proposes a satellite internet-based network signal intelligent monitoring method and system that can improve the monitoring efficiency of satellite network signal monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic diagram of a flow chart of a method for intelligently monitoring network signals based on satellite Internet provided in one embodiment of the present invention;

[0067] Figure 2 A schematic diagram of modules for implementing a satellite Internet-based network signal intelligent monitoring system provided in one embodiment of the present invention.

[0068] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0069] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0070] The present invention provides a method for intelligently monitoring network signals based on satellite internet. The method can be executed by at least one of electronic devices, such as a server or a terminal, that can be configured to execute the method provided by the present invention. In other words, the method can be executed by software or hardware installed on a terminal or server. The server can include, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0071] Example 1:

[0072] Reference Figure 1 FIG. 1 is a flow chart of a method for intelligently monitoring network signals based on satellite internet according to an embodiment of the present invention. In this embodiment, the method for intelligently monitoring network signals based on satellite internet includes:

[0073] S1. Obtain a network coverage area corresponding to the satellite internet, collect raw signal data within the network coverage area, analyze detailed signal parameters corresponding to the raw signal data, wherein the detailed signal parameters include signal strength information, signal frequency information, and delay parameter information; construct a multi-dimensional network sequence corresponding to the satellite internet based on the detailed signal parameters, and extract sequence dimension features from the multi-dimensional network sequence.

[0074] The present invention obtains the network coverage area corresponding to the satellite Internet and collects the original signal data within the network coverage area, which helps to fully understand the distribution of satellite network signals in specific areas, lays the foundation for accurate analysis of signal characteristics, and can promptly detect the source of abnormal signal changes. It can effectively ensure the stability and reliability of satellite Internet services in special scenarios such as remote areas, oceans, and air, and greatly improve the accuracy and efficiency of satellite network signal monitoring.

[0075] The satellite internet refers to a global communication network system constructed using a satellite constellation. Through a network architecture composed of multiple satellites, it realizes functions such as data transmission and communication interaction between different locations on the earth's surface, breaking geographical restrictions and providing network access services to global users. The network coverage area refers to the geographical range in which satellite internet signals can be effectively transmitted and available for user connection, including different areas such as land, ocean, and specific airspace in the air. The range depends on multiple factors such as satellite orbit, transmission power, and antenna design. The raw signal data refers to satellite network signal-related data directly collected within the network coverage area without deep processing, such as the initial signal strength value, original frequency value, initial measurement value of transmission delay, and basic information such as signal waveform. Optionally, obtaining the network coverage area corresponding to the satellite internet can be achieved through satellite orbit simulation tools, such as STK, GMAT, etc.; collecting the raw signal data within the network coverage area can be achieved through SDR platforms, such as GNU Radio, HackRF, etc.

[0076] Furthermore, the present invention analyzes the detailed signal parameters corresponding to the original signal data, which include signal strength information, signal frequency information, and delay parameter information. This can accurately determine the strength distribution of the signal, promptly discover the signal attenuation area, and optimize it in a targeted manner. This helps to grasp the timeliness of data transmission, reduce the risk of business jams or interruptions due to excessive delays, and overall improve the communication efficiency and reliability of satellite Internet.

[0077] Among them, the signal detailed parameters refer to a key data set for comprehensively characterizing and evaluating satellite Internet signals; the signal strength information refers to a quantitative indicator of the power or amplitude of the satellite signal when it propagates to the receiving end, usually measured in decibels (dB). It reflects the attenuation or enhancement of the signal during space transmission due to factors such as distance, obstacles, and interference, which directly affects the signal receivability and communication quality; the signal frequency information refers to the oscillation frequency of the electromagnetic wave carried by the satellite signal, measured in Hertz (Hz). Different satellite communication systems or services use specific frequency ranges. Accurate frequency information is crucial for signal reception, demodulation, and avoiding frequency conflicts; the delay parameter information refers to the transmission time delay experienced by the signal from the satellite transmitter to the ground receiver, including the signal propagation delay in space, satellite processing delay, and ground equipment processing delay. Optionally, the analysis of the signal detailed parameters corresponding to the raw signal data can be implemented using data analysis tools, such as MATLAB, Python, etc.

[0078] Furthermore, based on the detailed signal parameters, the present invention constructs a multi-dimensional network sequence corresponding to the satellite Internet, which can integrate various information such as signal strength, frequency, and delay to form a comprehensive and orderly network data system, which helps to analyze the signal characteristic change trends in different areas and time periods of the satellite network from a macro perspective, and provide a strong basis for accurately locating network fault points or weak links, thereby effectively improving the operation and maintenance management efficiency of the satellite Internet.

[0079] Among them, the multi-dimensional network sequence refers to the organic integration of the scattered initial network sub-sequences based on the association rules determined above, so as to form a comprehensive network sequence that covers all key dimensions of the satellite Internet, fully reflects the overall picture of the signal, and the various parts are interconnected.

[0080] As an embodiment of the present invention, constructing a multi-dimensional network sequence corresponding to the satellite Internet based on the detailed signal parameters includes: identifying key characteristic indicators in the detailed signal parameters; classifying the detailed signal parameters according to the key characteristic indicators to obtain a parameter classification set; mapping the parameters in the parameter classification set to their corresponding network dimensions to obtain an initial dimensional network; extracting an initial network subsequence in the initial dimensional network; analyzing association rules between subsequences in the initial network subsequences; and performing sequence integration on the initial network subsequences based on the association rules to obtain a multi-dimensional network sequence.

[0081] Among them, the key characteristic indicators refer to those parameter characteristics in the signal detailed parameters that play a decisive role in reflecting the satellite Internet signal status, change trends and potential problems, such as extreme points in signal strength, specific frequency bands of signal frequency and abnormal delay periods in delay parameters; the parameter classification set refers to a set that classifies the signal detailed parameters into different categories according to different characteristics based on the identified key characteristic indicators, for example, parameters related to signal strength fluctuations are classified into one category, parameters related to signal frequency stability are classified into one category, and parameters related to delay anomalies are classified into one category; the initial dimensional network refers to the various parameters in the parameter classification set, which are mapped to satellite Internet through a specific algorithm or model. The network prototype that is initially constructed in different network dimensions involved in networking and can reflect the signal characteristics of each dimension; the initial network subsequence refers to a subset of signal sequences with relative independence and coherence extracted from the initial dimensional network according to certain rules (such as time segments, spatial regions, frequency intervals, etc.); the association rule refers to the inherent connection rules between subsequences discovered in the analysis of the initial network subsequences in terms of time sequence, spatial proximity, frequency response, etc., such as the gradient relationship between the signal strength changes of subsequences in adjacent areas, or the pattern of alternating appearance of subsequences with similar frequencies in time.

[0082] Furthermore, identifying key characteristic indicators from the detailed signal parameters can be achieved using a principal component analysis (PCA) algorithm. For example, PCA can be used to identify principal components with large variance contributions from numerous detailed signal parameters. These principal components are key characteristic indicators. Classifying the detailed signal parameters can be achieved using a clustering analysis algorithm, such as K-means clustering. Mapping the parameters in the parameter classification set to their corresponding network dimensions can be achieved using a feature mapping algorithm, such as KPCA and LDA. Extracting initial network subsequences from the initial dimensional network can be achieved using a time series segmentation tool, such as Pandas and NumPy. Analyzing association rules between subsequences in the initial network subsequences can be achieved using an association rule algorithm, such as Apriori and FP-Growth. Sequence integration of the initial network subsequences can be achieved using a sequence merging algorithm, such as organically integrating the dispersed initial network subsequences based on the association rules determined above to form a comprehensive network sequence covering all key dimensions of satellite internet.

[0083] By extracting the sequence dimension features in the multi-dimensional network sequence, the present invention can accurately refine the key characteristics of network signals in different dimensions, deeply explore the regular patterns hidden in complex network sequences, and help to quickly locate the root dimension of abnormal signal changes. It provides precise guidance for targeted optimization of network performance and greatly improves the efficiency of satellite Internet troubleshooting and performance improvement.

[0084] Among them, the sequence dimension features refer to the key characterization information extracted from the constructed multi-dimensional network sequence, which can reflect the unique properties and change laws of satellite Internet signals in various dimensions (such as spatial dimension, time dimension, frequency dimension, etc.). For example, in the spatial dimension, it is reflected as the distribution characteristics of signal coverage strength in different regions; in the time dimension, it is the trend characteristics of signal strength, frequency, etc. fluctuating over time; in the frequency dimension, it is related to the stability and proportion of signals in each frequency band. Optionally, the extraction of sequence dimension features in the multi-dimensional network sequence can be achieved through spectrum analysis algorithms, such as: FFT, PSD and other algorithms.

[0085] S2. Based on the sequence dimension features and combined with the satellite orbit data, ground terrain data and meteorological data corresponding to the satellite Internet, the interference source is located in the network coverage area to obtain the located interference source, the main interference source type corresponding to the located interference source is identified, and based on the main interference source type, the interference intensity value corresponding to the located interference source is calculated.

[0086] The present invention locates interference sources in the network coverage area based on the sequence dimension features in combination with the satellite orbit data, ground terrain data and meteorological data corresponding to the satellite Internet, and obtains the located interference sources, which can reflect the interference of factors such as the atmosphere. The sequence dimension features are then combined to accurately determine the location of the interference source, effectively shortening the time for troubleshooting interference problems, improving the stability and reliability of satellite Internet signals, and ensuring service quality and continuity.

[0087] Among them, the satellite orbit data refers to a series of parameter information related to the satellite's orbit in space, including the satellite's orbital altitude, orbital inclination, orbital period, perigee and apogee coordinates, etc. These data can be used to accurately calculate the satellite's position relative to the earth's surface at different times, thereby analyzing the impact of satellite position changes on signal transmission paths, signal strength, signal delay, etc.; the ground terrain data refers to the geographical morphological information of the earth's surface, such as the altitude, slope, terrain undulations of mountains, hills, plains, rivers, oceans, etc. These data are obtained through technical means such as geographic information systems (GIS) Acquisition and storage, in satellite Internet signal analysis, is used to evaluate the effects of ground terrain on satellite signal propagation, such as blocking, reflection, and diffraction. For example, high mountains may block the signal propagation path, resulting in signal shadow areas, and large areas of water may cause signal reflections and multipath effects. The meteorological data refers to various data reflecting the state and changes of the atmosphere, including temperature, air pressure, humidity, wind speed, wind direction, precipitation, cloud thickness, ionosphere conditions, etc. Meteorological factors can have various effects on satellite signals. For example, precipitation can absorb and scatter signals, resulting in signal attenuation, and changes in the electron density of the ionosphere can cause signal refraction, delay, and flicker.

[0088] As an embodiment of the present invention, the interference source is located in the network coverage area based on the sequence dimension feature in combination with the satellite orbit data, ground terrain data and meteorological data corresponding to the satellite Internet to obtain the located interference source, including: extracting abnormal feature information corresponding to the sequence dimension feature; identifying orbital parameter features in the satellite orbit data; constructing an interference source positioning framework corresponding to the network coverage area based on the abnormal feature information and the orbital parameter features; extracting meteorological impact factors in meteorological data; based on the meteorological impact factors and the interference source positioning framework, performing regional identification on the network coverage area to obtain candidate interference areas; performing feature analysis on the ground terrain data to obtain a terrain feature set; based on the terrain feature set, performing interference source positioning on the candidate interference area to obtain a located interference source.

[0089] Among them, the abnormal characteristic information refers to the key information that deviates from the normal signal pattern screened out from the sequence dimension characteristics, such as the period of sudden drop in signal strength in the time dimension, and the unknown abnormal frequency fluctuations in the frequency dimension; the orbital parameter characteristics refer to the parameter set in the satellite orbit data that plays a key role in describing the satellite's operating attitude and position changes. For example, the satellite's orbital eccentricity determines the degree of its orbital ellipse, which in turn affects the signal coverage range and intensity change law; the orbital inclination is related to the satellite's inclination angle relative to the earth's equatorial plane, and is closely related to the signal receiving characteristics in different latitudes; the interference source positioning framework refers to a structured system constructed by integrating abnormal characteristic information and orbital parameter characteristics, which defines the direction, scope and key focus areas of interference source investigation, and stipulates from which angles to combine satellite operation dynamics and signal abnormality performance to search for interference sources. For example, based on the satellite position range corresponding to the signal abnormality period, the affected ground area is preliminarily identified as the starting point for investigation; the meteorological influencing factor refers to the key factor in meteorological data that can significantly affect satellite signal transmission. The candidate interference area refers to the geographical range within the network coverage area where interference sources may be hidden, preliminarily delineated based on meteorological influencing factors and the interference source positioning framework. These areas are suspected of signal fluctuations caused by meteorological anomalies and are consistent with the approximate range corresponding to the satellite's operating position and signal anomaly characteristics. The terrain feature set refers to a collection of key characteristics of the surface morphology obtained through in-depth analysis of ground terrain data, including the altitude and slope direction of mountains, the depth and width of valleys, and the distribution of plains, water bodies and other landforms. The located interference source refers to the specific source that is ultimately determined to have a negative impact on satellite signals within the satellite Internet network coverage area. It can be a specific mountain location that causes signal reflection and obstruction due to terrain, an area covered by strong convective clouds that causes signal attenuation due to meteorological factors, or the location of an illegal signal transmitter set up on the ground.

[0090] Furthermore, the extraction of abnormal feature information corresponding to the sequence dimension features can be implemented by a time series anomaly detection algorithm, such as Z-score, IQR, and other algorithms; the identification of orbital parameter features in satellite orbit data can be implemented by an orbital parameter extraction method, such as obtaining satellite orbit information by parsing satellite orbit data files (such as TLE data) to obtain orbital parameter features; the construction of the interference source positioning framework corresponding to the network coverage area can be implemented by a data fusion method, such as Kalman filtering, weighted averaging, and other methods; the extraction of meteorological influencing factors from meteorological data can be implemented by a data extraction tool, such as Pandas, Beautiful Soup, and other tools; the regional identification of the network coverage area can be implemented by a regional identification tool, such as QGIS, GEE, and other tools; the feature analysis of ground terrain data can be implemented by a feature analysis tool, such as MATLAB, Scikit-learn, and other tools; the interference source positioning in the candidate interference area can be implemented by a signal strength-based positioning method, such as analyzing the signal strength distribution around the interference source and combining it with the propagation characteristics of satellite or wireless signals to locate the interference source.

[0091] By identifying the main interference source type corresponding to the located interference source, the present invention can accurately distinguish the essential attributes of the interference source, and can formulate highly targeted response strategies based on this, quickly and effectively weaken or eliminate the interference impact, greatly reducing the time and resource consumption for troubleshooting and solving interference problems, and improving the quality of signal transmission in various complex environments and scenarios.

[0092] Among them, the main interference source type refers to the category of the source of interference to the satellite Internet signal divided according to the main cause, covering natural factors such as meteorological changes (such as precipitation, ionospheric anomalies, cloud activity, etc.) and geographical terrain (such as mountain obstruction, canyon diffraction, etc.), as well as human factors such as illegal radio transmission, electromagnetic equipment interference and other categories of different nature. Optionally, the identification of the main interference source type corresponding to the positioning interference source can be achieved through a classification algorithm, such as: SVM, KNN and other algorithms.

[0093] Furthermore, the present invention calculates the interference intensity value corresponding to the positioning interference source based on the main interference source type, which can accurately quantify the severity of the interference, providing a key basis for evaluating the impact of satellite Internet signals. The intensity value is calculated according to the respective characteristics and related data of different main interference source types (such as meteorological, terrain or human interference), and the resource investment and technical means to deal with interference can be planned in a targeted manner, effectively improving the efficiency and accuracy of interference elimination work.

[0094] The interference intensity value refers to a quantitative indicator of the degree of interference caused to the positioning interference source, which comprehensively considers the impact of different main interference source types on the positioning interference source.

[0095] As an embodiment of the present invention, the calculating, based on the main interference source type, the interference intensity value corresponding to the positioning interference source includes:

[0096] The interference intensity value corresponding to the positioning interference source is calculated using the following formula:

[0097]

[0098] in, Indicates the interference intensity value corresponding to the positioning interference source, Indicates the number of types corresponding to the main interference source type, Indicates the quantity index corresponding to the main interference source type, Indicates the The interference frequency factor corresponding to each main interference source type, Indicates the The interference amplitude factor corresponding to each main interference source type, represents the interference influence function.

[0099] In detail, the interference frequency factor refers to the The degree of influence of the frequency of occurrence of each main interference source type on the interference intensity. For example, if a certain type of interference source (such as electromagnetic interference) appears frequently, its corresponding interference frequency factor will be larger, thus having a greater impact on the overall interference intensity when calculating the interference intensity value; the interference amplitude factor refers to the The degree of influence of the interference amplitude of each main interference source type on the interference intensity. For example, the interference amplitude generated by a high-power illegal signal transmission source is large, and its corresponding interference amplitude factor is It will be larger, and thus make a greater contribution to the overall interference intensity when calculating the interference intensity value; the interference influence function refers to a function that describes the influence of interference on the positioning interference source and certain variables ( ) is a function of the relationship between variables It can be factors related to interference, such as distance, time, and frequency. For example, as the distance increases, the interference influence function It will gradually decrease, indicating that the interference intensity decreases with increasing distance.

[0100] S3. Based on the interference intensity value, define the signal weak area in the network coverage area, enhance the signal of the signal weak area to obtain the signal enhanced area, perform real-time network monitoring on the signal enhanced area to obtain real-time network data, and determine the key optimization area required for the satellite Internet based on the real-time network data.

[0101] The present invention delineates signal-weak areas within the network coverage area based on the interference intensity value, thereby helping network operators to identify areas prone to signal problems in advance and perform targeted network optimization and equipment upgrades. When planning a new network facility layout, base stations and other equipment can be reasonably configured based on the distribution of signal-weak areas, thereby improving resource allocation efficiency.

[0102] Among them, the signal weak area refers to the area in the network coverage area where the signal strength is low and the signal quality is poor, determined according to the measured signal data. These areas may be unable to meet the requirements of normal use of the network signal in the area due to high interference intensity, terrain obstruction, equipment failure, etc., such as weak mobile phone signals and unstable network connections.

[0103] As an embodiment of the present invention, delineating the signal-weak area in the network coverage area based on the interference intensity value includes: identifying the interference intensity level corresponding to the interference intensity value; partitioning the interference intensity level to obtain a partition intensity level; determining the network coverage unit corresponding to the network coverage area based on the partition intensity level; performing actual signal measurement on the network coverage unit to obtain measured signal data; and delineating the signal-weak area in the network coverage area based on the measured signal data.

[0104] Among them, the interference intensity level refers to different levels classified according to the size of the interference intensity value. For example, the interference intensity value can be divided into three levels: high, medium and low, or more finely divided into multiple levels (such as very low, low, medium-low, medium, medium-high, high, and very high); the partition intensity level refers to the result obtained after partitioning the interference intensity level. It is to divide the area into sub-areas with different interference intensity characteristics within the network coverage area according to different interference intensity levels. For example, the high interference intensity level area may be further subdivided into several different partition intensity levels. These partition intensity levels reflect the subtle differences in interference intensity in different sub-areas under the same interference intensity level; the network coverage unit refers to the subdivision unit of the network coverage area determined based on the partition intensity level. These units can be geographical blocks, such as grids divided by longitude and latitude, or areas divided according to the coverage range of actual network coverage equipment (such as base stations); the measured signal data refers to the data obtained when performing actual signal measurement on the network coverage unit. These data include signal strength, signal quality (such as bit error rate, signal-to-noise ratio, etc.), signal frequency and other related parameters.

[0105] Furthermore, the identification of the interference intensity level corresponding to the interference intensity value can be achieved through a threshold partitioning method, such as setting several specific interference intensity thresholds, when the interference intensity value is less than threshold 1, it is a low intensity level, between threshold 1 and threshold 2, it is a medium intensity level, and greater than threshold 2, it is a high intensity level; the zoning processing of the interference intensity level can be achieved through a spatial clustering algorithm, such as the DBSCAN algorithm, which can divide the area according to the density of the interference intensity level data points, and the areas with similar density are divided into the same partition intensity level; the determination of the network coverage unit corresponding to the network coverage area can be achieved through a grid partitioning method, such as dividing the network coverage area into grids according to certain longitude and latitude intervals, and each grid is a network coverage unit; the actual signal measurement of the network coverage unit can be achieved by deploying a sensor network, such as arranging multiple fixed signal sensors in the network coverage unit, and collecting and transmitting signal data in real time through the sensors; the demarcation of the signal-weak area in the network coverage area can be achieved through a threshold judgment method, such as setting thresholds for parameters such as signal strength and signal quality, and when the measured data is lower than these thresholds, the corresponding network coverage unit is demarcated as a signal-weak area.

[0106] The present invention enhances the signal in the weak signal area to obtain a signal enhancement area, which can effectively improve the signal quality of the satellite Internet in a specific area, so that the areas that originally had poor signals can stably connect to the network, improve data transmission speed and efficiency, enhance the user's network experience in these areas, and reduce service interruptions and delays caused by signal problems.

[0107] Among them, the signal enhancement area refers to a specific geographical area where, after targeted processing of the originally weak signal area through a series of signal enhancement means, such as adding signal relay equipment, adjusting transmission power, optimizing antenna layout, etc., its signal strength, signal quality and other indicators are significantly improved, meeting or exceeding the network service standard requirements, and can provide users with stable and efficient network connection services. Optionally, the signal enhancement of the weak signal area can be achieved through signal enhancement tools, such as signal amplifiers, repeaters and other tools.

[0108] Furthermore, the present invention obtains real-time network data by performing real-time network monitoring on the signal enhancement area, which can accurately grasp the network operation status and promptly discover changes in signal strength, fluctuations in data transmission rate, etc., so as to quickly take adjustment measures, which helps to deeply analyze network performance and evaluate the effectiveness of signal enhancement solutions based on real-time data.

[0109] Among them, the real-time network data refers to a series of information reflecting the network operation status of the area that is continuously collected during the real-time network monitoring of the signal enhancement area, including but not limited to the signal strength values ​​in each time period, which reflects the signal propagation effect and stability in space; data transmission rate, such as upload and download speed, which is directly related to the user's network usage experience and business development efficiency; network delay data, which reflects the timeliness of data transmission; packet loss rate, which characterizes the integrity of data during transmission; and operating parameters of network equipment, such as base station transmission power, antenna gain status, etc. Optionally, the real-time network monitoring of the signal enhancement area can be achieved through network traffic monitoring tools, such as: Cacti, Zabbix and other tools.

[0110] Furthermore, the present invention determines the key optimization areas required for the satellite Internet based on the real-time network data, can accurately locate areas where network performance is poor, and enable optimization resources to be concentrated. By focusing on key areas, network bottleneck problems such as signal fluctuations and rate limitations can be efficiently resolved, thereby rapidly improving the overall network quality.

[0111] Among them, the key optimization areas refer to areas in actual space where network performance needs to be improved, based on the geographical coverage of satellite Internet, signal propagation models, and the results of core data subset weight analysis. For example, through subset weights, it is found that the core data with low transmission rates and unstable signals in certain areas accounts for a large proportion. With the help of satellite positioning and geographic information systems, these areas are accurately marked on the map. These are the key areas where resources need to be invested in subsequent optimization measures such as equipment upgrades and signal debugging.

[0112] As an embodiment of the present invention, determining the key optimization areas required for the satellite Internet based on the real-time network data includes: identifying performance data clusters in the real-time network data; setting thresholds for indicators in the network data clusters to obtain data threshold ranges; screening core data subsets in the performance data clusters based on the indicator threshold ranges; analyzing subset weights corresponding to the core data subsets; and determining the key optimization areas required for the satellite Internet based on the subset weights.

[0113] Among them, the performance data cluster refers to a data set aggregated from real-time network data based on different network performance characteristics or parameter categories. For example, data points related to signal strength are clustered into a signal strength data cluster, and those related to data transmission rate are classified into a transmission rate data cluster. These data clusters reflect the operating performance of satellite Internet in different aspects and are the basic units for subsequent analysis. They cover multivariate data such as real-time fluctuation values ​​of signal strength and measured values ​​of transmission rate in various time periods. The data threshold range refers to the numerical limits set for each indicator in the network data cluster based on past experience, network standards or pre-research models. For example, for the signal strength data cluster, according to the minimum requirements for the normal operation of satellite communications, the lower threshold is set to -90dBm and the upper threshold is set to -60dBm, which defines the signal strength. The reasonable value range of the indicator; the core data subset refers to the key data set obtained by comparing and screening with the set data threshold range in the performance data cluster. Taking the transmission rate data cluster as an example, if the threshold is set to a minimum of 1Mbps, when the transmission rate in a certain period of time is lower than this value, these transmission rate data below the threshold are screened out to form the core data subset; the subset weight refers to the value assigned based on the importance of the network performance indicator corresponding to the core data subset to the overall network operation, as well as the proportion of the subset data in the total amount, the frequency of occurrence and other factors. For example, in a scenario where the focus is on user experience, the data transmission rate core subset is directly related to the smoothness of user downloads and uploads, and is given a higher weight than other indicator subsets (such as the relatively minor device temperature data subset).

[0114] Furthermore, the identification of performance data clusters in the real-time network data can be achieved through a clustering algorithm, such as K-Means clustering, which regards real-time network data as points in a multidimensional space, where each dimension represents a type of network performance data (such as signal strength, transmission rate, delay, etc.), and divides similar data points into the same cluster; the setting of thresholds for indicators in the network data cluster can be achieved through a classification algorithm, such as decision trees, random forests, and other algorithms; the screening of core data subsets in the performance data cluster can be achieved through subset screening tools, such as Pandas, MySQL, and other tools; the analysis of subset weights corresponding to the core data subsets can be achieved through weight analysis methods, such as entropy weight method, principal component analysis method, etc.; the determination of key optimization areas required for the satellite Internet can be achieved through regional determination tools, such as QGIS, ArcGIS, and other tools.

[0115] S4. Query the network usage status corresponding to the key optimization area, analyze the network optimization direction corresponding to the key optimization area based on the network usage status, extract the optimized signal points in the network optimization direction, and calculate the signal equalization value corresponding to the key optimization area based on the optimized signal points.

[0116] By querying the network usage status corresponding to the key optimization area, the present invention can accurately understand the actual network problems faced by users in the area, such as frequent disconnections and freezes, so that optimization measures can directly hit the pain points. By understanding the real-time demand and peak and trough periods of data traffic, it is convenient to reasonably allocate network resources and improve resource utilization.

[0117] Among them, the network usage status refers to a comprehensive description and evaluation of the current network usage in the key optimization area based on regional traffic records and other relevant data, which includes the overall network load, usage frequency and traffic proportion of different applications, network stability and reliability performance, user network experience quality and other aspects.

[0118] As an embodiment of the present invention, the query of the network usage status corresponding to the key optimization area includes: identifying the topology identification code of the key optimization area in the satellite Internet; parsing the coding rules corresponding to the topology identification code; constructing the regional basic framework corresponding to the key optimization area based on the coding rules; querying the regional limitation data corresponding to the key optimization area based on the regional basic framework; extracting the regional traffic records corresponding to the key optimization area based on the regional limitation data; and querying the network usage status corresponding to the key optimization area based on the regional traffic records.

[0119] Among them, the topology identification code refers to the code used to uniquely identify the key optimization area in the satellite Internet. It is like the ID card number of a region. Through a specific character combination and digital sequence, the key optimization area can be accurately located in the entire satellite Internet system; the coding rule refers to a set of specifications and guidelines formulated for the topology identification code in the satellite Internet, which stipulates the composition structure, character meaning, digital value range and other contents of the code. For example, the code can be composed of numbers and letters, and characters or numbers in different positions represent different information, such as regional level, satellite group to which it belongs, etc.; the regional basic framework refers to the key optimization area constructed based on the topology identification code and its corresponding coding rules. The basic architecture information of the domain includes the location information of the area in the satellite Internet, the distribution of satellite nodes, ground stations, user terminals and other equipment covered, as well as the connection relationship between these devices; the regional limited data refers to specific data related to the network usage of the key optimization area within the scope defined by the regional basic framework. These data may include performance parameters, configuration information, communication protocol types, etc. of various types of equipment in the area; the regional traffic record refers to a detailed record of network data traffic within a certain time range in the key optimization area, which covers the data traffic size generated by various network applications and services, the time distribution of traffic, the data transmission volume between different user terminals or devices, and other information.

[0120] Furthermore, the identification of the topological identification code of the key optimization area in the satellite Internet can be achieved through an index search algorithm, such as: an index system constructed for regional information (such as a spatial index constructed based on geographic location information, a tree index based on regional classification, etc.), using a corresponding search algorithm to quickly locate the key optimization area in the index and obtain its associated topological identification code; the parsing of the coding rules corresponding to the topological identification code can be implemented by programming languages, such as Python, Java and other languages; the construction of the regional basic framework corresponding to the key optimization area can be implemented by graph database tools, such as Neo4j and other tools; the query of the regional limitation data corresponding to the key optimization area can be implemented by data query tools, such as SQL, NoSQL and other tools; the extraction of regional traffic records corresponding to the key optimization area can be implemented by traffic monitoring tools, such as Wireshark, NetFlow and other tools; the query of the network usage status corresponding to the key optimization area can be implemented by visualization tools, such as Tableau, Grafana and other tools.

[0121] Based on the current status of network usage, the present invention analyzes the network optimization direction corresponding to the key optimization area and extracts the optimization signal points in the network optimization direction. It can accurately focus on the root cause of network problems, for example, whether network congestion is caused by traffic concentration during peak hours or insufficient device bandwidth, and then clarify the targeted optimization direction. On the other hand, the extracted optimization signal points are like indicator lights, indicating to technical personnel where to focus their efforts, such as weak signals in specific areas, large transmission delays for certain types of applications, etc., so that resources can be efficiently allocated and network performance can be quickly improved.

[0122] Among them, the network optimization direction refers to the action direction for improving network performance and enhancing user experience based on a comprehensive analysis of the network in the key optimization area, combined with the degree of network correlation, the characteristics of network unit groups, and the current situation reflected by the network status matrix. It covers specific measures such as adjusting the network topology structure, prioritizing the optimization of network connection links for closely related groups; optimizing resource allocation strategies, and reasonably allocating bandwidth based on differences in group traffic loads; improving equipment configuration, and upgrading or replacing related equipment for groups with weak signals.

[0123] As an embodiment of the present invention, analyzing the network optimization direction corresponding to the key optimization area based on the current network usage status includes: collecting real-time usage data corresponding to each node in the current network usage status; constructing a network status matrix corresponding to the key optimization interval based on the real-time usage data; dividing the network unit groups corresponding to the grid units in the network status matrix; analyzing the network correlation degree between the network unit groups; and analyzing the network optimization direction corresponding to the key optimization area based on the network correlation degree.

[0124] Among them, the real-time usage data refers to the various parameter information reflecting the network usage that is synchronously collected at a specific time by each node (such as base station, router, terminal equipment, etc.) in the key optimization area during network operation. These data cover signal strength, transmission rate, data traffic size, number of connected users, packet loss rate, etc.; the network status matrix refers to a tool for structured presentation of the network status of the key optimization area in the form of a matrix, which divides the key optimization area into multiple grid units according to certain rules (such as geographic coordinates, network hierarchy, etc.). Each grid unit corresponds to an element position in the matrix, and the value of the element is integrated and quantified by the real-time usage data of each node in the corresponding area. For example, an urban area is divided into 10×10 grid units to construct 100×n (n is the real-time usage the network status matrix (parameter types of data used); the network unit group refers to a group formed by classifying and dividing each grid unit according to similar network characteristics or attributes on the basis of the network status matrix. For example, grid units with signal strength between -70dBm and -80dBm and medium traffic load in the network status matrix are grouped together to form a network unit group; the network correlation degree refers to the degree of mutual influence and connection between different network unit groups. For example, if the base station in one of two adjacent network unit groups often provides a large amount of data transmission services to the terminal equipment of the other group, and the signal switching between the two is frequent, then the network correlation degree between them is relatively high; conversely, if there is almost no data interaction and signal transmission between the two groups, the correlation degree is relatively low.

[0125] Furthermore, the collection of real-time usage data corresponding to each node in the current network usage status can be achieved through a network management system, such as: it can be used to centrally monitor and collect actual usage data of various types of equipment (base stations, routers, terminals, etc.) in the network; the construction of the network status matrix corresponding to the key optimization interval can be achieved through a network planning tool, such as: gridding the key optimization area according to set rules (such as coverage radius, network level, etc.), automatically matching the real-time usage data of each node to the corresponding grid element position, and generating a network status matrix; the division of the network unit groups corresponding to the grid units in the network status matrix can be achieved through rule-based classification. The method can be implemented by a class method, such as: grouping grid units with signal strength between -60dBm and -70dBm and transmission rate higher than 100Mbps into one group, and judging and classifying all grid units in the network status matrix one by one according to this rule, thereby forming different network unit groups; the analysis of the network correlation between the network unit groups can be implemented by graph theory related algorithms, such as: calculating the importance of each node (group) and the degree of correlation between them by the PageRank algorithm; the analysis of the network optimization direction corresponding to the key optimization area can be implemented by a multi-objective optimization algorithm, such as: NSGA-II and other algorithms.

[0126] The present invention calculates the signal balance value corresponding to the key optimization area based on the optimized signal points, which can intuitively present the overall balance status of the signal in the area, accurately know the degree of difference between the signals of each part, facilitate the discovery of hidden dangers of uneven signal strength, focus on weak signal links, and effectively improve the overall signal quality of the area.

[0127] Among them, the signal balance value refers to a value calculated based on the optimized signal points in the key optimization area, which is used to measure the degree of balance of signal distribution in the area and reflects the discreteness of signal strength at the optimized signal points. If the signal balance value is small, it means that the signal distribution in the key optimization area is relatively uniform; otherwise, it means that the signal distribution difference is large.

[0128] As an embodiment of the present invention, calculating the signal equalization value corresponding to the key optimization area based on the optimized signal point includes:

[0129] The signal equalization value corresponding to the key optimization area is calculated using the following formula:

[0130]

[0131] in, Indicates the signal equalization value corresponding to the key optimization area, Indicates the total number of optimized signal points in the key optimization area, Indicates the number index of optimized signal points, Indicates the The signal strength value corresponding to the optimized signal point, Indicates the average value of the signal strength corresponding to the optimized signal point, Indicates the standard deviation of the signal strength corresponding to the optimized signal point.

[0132] Furthermore, the optimized signal point refers to a specific location or node with a key indicative role in the key optimization area. These points are usually determined through analysis of the current network usage status. For example, in the network optimization process, locations with abnormal signal strength, large fluctuations in network performance, or poor user experience can be determined as optimized signal points; the signal strength value refers to the signal strength measured at the jth optimized signal point, which is used to describe the strength of the signal received by the optimized signal point; the average value refers to the arithmetic mean of the signal strength values ​​corresponding to all optimized signal points in the key optimization area, reflecting the overall level of signal strength in the key optimization area; the standard deviation refers to a measure of the degree of dispersion of the signal strength values ​​corresponding to all optimized signal points in the key optimization area relative to the average value, where the larger the standard deviation, the more dispersed the distribution of the signal strength values ​​between the optimized signal points; the smaller the standard deviation, the closer the signal strength value is to the average value and the more concentrated the distribution.

[0133] S5. Based on the signal balance value, generate a network signal index corresponding to the key optimization area, analyze the signal fluctuation trend corresponding to the network signal index, identify the fluctuation influencing factors in the signal fluctuation trend, and generate a signal intelligent monitoring report corresponding to the satellite Internet based on the fluctuation influencing factors.

[0134] Based on the signal balance value, the present invention generates network signal indicators corresponding to the key optimization area, which can objectively quantify the network signal conditions in the area and provide an accurate basis for evaluating network performance. These indicators can serve as an important reference for network optimization, facilitating the targeted formulation and adjustment of optimization strategies, such as focusing on improving areas with poor signal balance, which helps to monitor network quality in the long term.

[0135] Among them, the network signal index refers to a parameter generated after comprehensively considering the fluctuation level characteristics and used to measure the network signal quality in the key optimization area. For example, the network signal index may include a signal stability index, a network freeze probability index, a signal strength consistency index, etc.

[0136] As an embodiment of the present invention, the network signal index corresponding to the key optimization area is generated based on the signal balance value, including: identifying the signal value interval in which the signal balance value is located; determining the signal fluctuation standard corresponding to the signal value interval; dividing the fluctuation level corresponding to the signal balance value according to the signal fluctuation standard; performing feature extraction on the fluctuation level to obtain fluctuation level features; and generating the network signal index corresponding to the key optimization area based on the fluctuation level features.

[0137] Among them, the signal value interval refers to dividing the possible value range of the signal balance value into several continuous sub-ranges. For example, the signal balance value from 0 to 100 can be divided into different intervals such as 0-20, 20-40, 40-60, 60-80, and 80-100. The signal fluctuation standard refers to the rule or scale set for measuring the degree of signal fluctuation for each signal value interval. For example, in the interval of small signal balance values ​​(such as 0-20), small fluctuation changes can be considered significant; while in the interval of large signal balance values ​​(such as 80-100), small fluctuation changes can be considered significant. The fluctuation level refers to further subdividing the value interval of the signal balance value into different levels according to the signal fluctuation standard. For example, within a certain signal value interval, it can be divided into three levels according to the signal fluctuation standard: low fluctuation, medium fluctuation, and high fluctuation. The fluctuation level characteristics refer to the description of the typical attributes or characteristics of each fluctuation level. For example, a low fluctuation level may have characteristics such as smooth signal changes and stable network performance; a high fluctuation level may have characteristics such as drastic signal changes and a high risk of network lag.

[0138] Furthermore, the identification of the signal value interval in which the signal balance value is located can be achieved through an interval judgment tool, such as MATLAB, R language and other tools; the determination of the signal fluctuation standard corresponding to the signal value interval can be achieved through a statistical analysis method, such as: counting the standard deviation of the signal fluctuation in each interval, and setting a certain multiple (such as 1.5 times) of the average standard deviation of the interval as the signal fluctuation standard of the interval; the division of the fluctuation level corresponding to the signal balance value can be achieved through a fuzzy logic algorithm, such as: using fuzzy logic to process the level division of signal fluctuations, defining fuzzy sets such as "low fluctuation", "medium fluctuation" and "high fluctuation", and through membership functions To determine the degree to which the fluctuation corresponding to the signal balance value belongs to different fuzzy sets, and then determine the fluctuation level; the feature extraction of the fluctuation level can be achieved through the feature template matching method, such as: pre-defining the feature templates corresponding to low fluctuation, medium fluctuation, and high fluctuation levels, and then matching the actual fluctuation level with the feature template to obtain the fluctuation level feature; the generation of the network signal index corresponding to the key optimization area can be achieved through the weighted synthesis method, such as: giving a weight of 0.4 to the signal strength stability feature, a weight of 0.3 to the network delay stability feature, and a weight of 0.3 to the packet loss rate feature, and then calculating the comprehensive network signal index based on the actual value of each feature.

[0139] By analyzing the signal fluctuation trends corresponding to the network signal indicators and identifying the fluctuation influencing factors in the signal fluctuation trends, the present invention can accurately grasp the dynamic changes of the network, know the quality trends of the signals in advance, take the initiative in network maintenance, optimization and troubleshooting, avoid signal deterioration affecting user use, help to rationally plan network upgrades and resource allocation, tilt resources to weak links according to the fluctuation law, and maximize network efficiency.

[0140] Among them, the signal fluctuation trend refers to the tendency of network signal indicators (such as signal strength, stability, etc.) to change over time or other related factors (such as geographical location movement, change in the number of users, etc.). For example, the signal fluctuation trend can be that the signal strength gradually decreases during certain periods of the day and gradually increases during other periods, showing a periodic change; or it can be a linear trend in which the signal stability indicator continues to decrease as the number of user access increases; the fluctuation influencing factors refer to various reasons that can cause fluctuations in network signal indicators. These factors are multifaceted, including natural environmental factors, such as weather conditions (heavy rain and lightning can affect signal transmission), topography (mountainous areas, high-rise buildings, etc. can cause signal obstruction or reflection); network equipment factors themselves, such as base station power adjustment, equipment Aging or failure; user behavior factors, such as a sudden increase in the number of users leading to network congestion, and users occupying the signal by using high-bandwidth applications (such as high-definition video live broadcast); and external interference factors, such as interference from other nearby wireless signal sources, etc. Optionally, the analysis of the signal fluctuation trend corresponding to the network signal indicator can be achieved through a trend line fitting method, such as: using a fitting method such as the least squares method, the data points of the network signal indicator are fitted into a straight line or curve to intuitively show the signal fluctuation trend; the identification of fluctuation influencing factors in the signal fluctuation trend can be achieved through a feature selection algorithm, such as: the ReliefF algorithm assigns weights according to the ability of features (influencing factors) to distinguish sample classifications (different signal fluctuation states), and features with high weights are considered to be important fluctuation influencing factors.

[0141] Furthermore, the present invention generates an intelligent signal monitoring report corresponding to the satellite Internet based on the fluctuation influencing factors, which helps the operation and maintenance team to quickly understand the root cause of satellite signal fluctuations and accurately determine whether it is caused by environmental factors such as space radiation and orbital perturbations, or ground station equipment failures and sudden traffic peaks on the user side. It can timely adjust the monitoring direction and resource allocation to ensure signal stability.

[0142] Among them, the signal intelligent monitoring report refers to a comprehensive and dynamic document generated for satellite Internet signals based on advanced monitoring technology and intelligent algorithms. It covers all-round evaluation information of satellite signals, and records in detail the signal status in different time periods, different regions and various working conditions, including key indicators such as signal strength, stability, and transmission rate. What is particularly critical is that the report deeply analyzes various factors affecting signal fluctuations, whether it is the cosmic environmental factors such as solar storms and geomagnetic interference of satellites in space, or electromagnetic interference around ground stations, equipment aging and failure, as well as human and application scenario factors such as user-end usage habits and traffic tidal changes. Optionally, the generation of the signal intelligent monitoring report corresponding to the satellite Internet can be achieved through report generation tools, such as Jupyter Notebook, Tableau and other tools.

[0143] First, the present invention obtains the network coverage area corresponding to the satellite Internet and collects the original signal data in the network coverage area, which helps to fully understand the distribution of satellite network signals in specific areas, lays the foundation for accurate analysis of signal characteristics, and can timely detect the source of abnormal signal changes, effectively ensuring the stability and reliability of satellite Internet services in special scenarios such as remote areas, oceans, and air, and greatly improving the accuracy and efficiency of satellite network signal monitoring. At the same time, the present invention locates the interference source in the network coverage area based on the sequence dimension characteristics combined with the satellite orbit data, ground terrain data and meteorological data corresponding to the satellite Internet, and obtains the located interference source, which can reflect the interference of factors such as the atmosphere, and then accurately determines the location of the interference source in combination with the sequence dimension characteristics, effectively shortening the time for troubleshooting interference problems, improving the stability and reliability of satellite Internet signals, and ensuring service quality and continuity. The present invention demarcates the signal in the network coverage area based on the interference intensity value. Weak areas can help network operators identify areas prone to signal problems in advance, allowing them to perform targeted network optimization and equipment upgrades. When planning new network infrastructure layouts, base stations and other equipment can be rationally configured based on the distribution of signal-weak areas, improving resource allocation efficiency. By querying the network usage status corresponding to the key optimization areas, the present invention can accurately understand the actual network problems faced by users in the area, such as frequent disconnections and lags, allowing optimization measures to directly address pain points. By understanding the real-time demand for data traffic and peak and trough periods, network resources can be rationally allocated and resource utilization improved. Furthermore, based on the signal balance value, the present invention generates network signal indicators corresponding to the key optimization areas, objectively quantifying the network signal conditions within the area and providing an accurate basis for evaluating network performance. These indicators can serve as an important reference for network optimization, facilitating the targeted formulation and adjustment of optimization strategies, such as focusing on improving areas with poor signal balance, and facilitating long-term monitoring of network quality. Therefore, the present invention proposes a satellite internet-based network signal intelligent monitoring method and system that can improve the monitoring efficiency of satellite network signal monitoring.

[0144] Example 2:

[0145] like Figure 2 FIG. 1 is a module diagram of a satellite Internet-based network signal intelligent monitoring system provided by one embodiment of the present invention.

[0146] The satellite internet-based network signal intelligent monitoring system 200 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the satellite internet-based network signal intelligent monitoring system 200 may include a feature extraction module 201, a strength value calculation module 202, a region determination module 203, an equalization value calculation module 204, and a report generation module 205. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function. These modules are stored in the electronic device's memory.

[0147] In this embodiment, the functions of each module / unit are as follows:

[0148] The feature extraction module 201 is configured to obtain a network coverage area corresponding to the satellite internet, collect raw signal data within the network coverage area, analyze detailed signal parameters corresponding to the raw signal data, wherein the detailed signal parameters include signal strength information, signal frequency information, and delay parameter information; construct a multi-dimensional network sequence corresponding to the satellite internet based on the detailed signal parameters; and extract sequence dimension features from the multi-dimensional network sequence.

[0149] The intensity value calculation module 202 is used to locate the interference source in the network coverage area based on the sequence dimension feature in combination with the satellite orbit data, ground terrain data and meteorological data corresponding to the satellite Internet, obtain the located interference source, identify the main interference source type corresponding to the located interference source, and calculate the interference intensity value corresponding to the located interference source based on the main interference source type;

[0150] The area determination module 203 is configured to, based on the interference intensity value, delineate signal-weak areas within the network coverage area, perform signal enhancement on the signal-weak areas to obtain signal-enhanced areas, perform real-time network monitoring on the signal-enhanced areas to obtain real-time network data, and determine key optimization areas required for the satellite Internet based on the real-time network data;

[0151] The balance value calculation module 204 is configured to query the current network usage status corresponding to the key optimization area, analyze the network optimization direction corresponding to the key optimization area based on the current network usage status, extract optimized signal points in the network optimization direction, and calculate the signal balance value corresponding to the key optimization area based on the optimized signal points;

[0152] The report generation module 205 is used to generate network signal indicators corresponding to the key optimization area based on the signal balance value, analyze the signal fluctuation trend corresponding to the network signal indicator, identify the fluctuation influencing factors in the signal fluctuation trend, and generate a signal intelligent monitoring report corresponding to the satellite Internet based on the fluctuation influencing factors.

[0153] In detail, the modules described in the satellite Internet-based network signal intelligent monitoring system 200 described in the embodiment of the present invention adopt the same technical means as the satellite Internet-based network signal intelligent monitoring method described in the accompanying drawings when in use, and can produce the same technical effects, which will not be repeated here.

[0154] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A network signal intelligent monitoring method based on satellite Internet, characterized in that: The method comprises: Obtaining a network coverage area corresponding to the satellite internet, collecting raw signal data within the network coverage area, parsing detailed signal parameters corresponding to the raw signal data, the detailed signal parameters including signal strength information, signal frequency information, and delay parameter information; constructing a multidimensional network sequence corresponding to the satellite internet based on the detailed signal parameters, and extracting sequence dimension features from the multidimensional network sequence; Based on the sequence dimension feature and in combination with satellite orbit data, ground terrain data, and meteorological data corresponding to the satellite Internet, the interference source is located in the network coverage area to obtain a located interference source, the main interference source type corresponding to the located interference source is identified, and based on the main interference source type, the interference intensity value corresponding to the located interference source is calculated, wherein the interference intensity value corresponding to the located interference source is calculated based on the main interference source type, including: The interference intensity value corresponding to the positioning interference source is calculated using the following formula: ； in, Indicates the interference intensity value corresponding to the positioning interference source, Indicates the number of types corresponding to the main interference source type, Indicates the quantity index corresponding to the main interference source type, Indicates the The interference frequency factor corresponding to each main interference source type, Indicates the The interference amplitude factor corresponding to each main interference source type, represents the interference influence function; Based on the interference intensity value, delineate signal-weak areas within the network coverage area, perform signal enhancement on the signal-weak areas to obtain signal-enhanced areas, perform real-time network monitoring on the signal-enhanced areas to obtain real-time network data, and determine key optimization areas required for the satellite Internet based on the real-time network data; Querying the network usage status corresponding to the key optimization area, analyzing the network optimization direction corresponding to the key optimization area based on the network usage status, extracting optimized signal points in the network optimization direction, and calculating the signal equalization value corresponding to the key optimization area based on the optimized signal points. Calculating the signal equalization value corresponding to the key optimization area based on the optimized signal points includes: The signal equalization value corresponding to the key optimization area is calculated using the following formula: ； in, Indicates the signal equalization value corresponding to the key optimization area, Indicates the total number of optimized signal points in the key optimization area, Indicates the number index of optimized signal points, Indicates the The signal strength value corresponding to the optimized signal point, Indicates the average value of the signal strength corresponding to the optimized signal point, Indicates the standard deviation of the signal strength corresponding to the optimized signal point; Based on the signal balance value, a network signal index corresponding to the key optimization area is generated, the signal fluctuation trend corresponding to the network signal index is analyzed, the fluctuation influencing factors in the signal fluctuation trend are identified, and based on the fluctuation influencing factors, a signal intelligent monitoring report corresponding to the satellite Internet is generated.

2. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: The step of constructing a multi-dimensional network sequence corresponding to the satellite Internet based on the detailed signal parameters includes: Identifying key characteristic indicators in the signal detailed parameters; Classifying the signal detailed parameters according to the key characteristic indicators to obtain a parameter classification set; Mapping the parameters in the parameter classification set to their corresponding network dimensions to obtain an initial dimensional network; Extracting an initial network subsequence from the initial dimensional network; Analyzing association rules between subsequences in the initial network subsequence; Based on the association rules, the initial network subsequences are sequence-integrated to obtain a multi-dimensional network sequence.

3. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: The interference source is located in the network coverage area based on the sequence dimension feature in combination with satellite orbit data, ground terrain data, and meteorological data corresponding to the satellite Internet, to obtain the located interference source, including: Extracting abnormal feature information corresponding to the sequence dimension feature; Identify orbital parameter characteristics in satellite orbit data; Based on the abnormal characteristic information and the orbital parameter characteristics, constructing an interference source positioning framework corresponding to the network coverage area; Extract meteorological influencing factors from meteorological data; Based on the meteorological impact factor and the interference source positioning framework, performing regional identification on the network coverage area to obtain a candidate interference area; Perform feature analysis on ground terrain data to obtain a terrain feature set; Based on the terrain feature set, interference sources are located in the candidate interference area to obtain located interference sources.

4. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: Delineating a signal weak area in the network coverage area based on the interference intensity value includes: Identifying an interference intensity level corresponding to the interference intensity value; Performing partition processing on the interference intensity level to obtain a partition intensity level; determining, based on the partition strength level, a network coverage unit corresponding to the network coverage area; Performing actual signal measurement on the network coverage unit to obtain actual signal data; Based on the measured signal data, a signal weak area in the network coverage area is delineated.

5. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: Determining the key optimization areas required for the satellite Internet based on the real-time network data includes: identifying performance data clusters in the real-time network data; Setting thresholds for indicators in the performance data cluster to obtain data threshold ranges; Based on the data threshold range, screening the core data subset in the performance data cluster; Analyzing subset weights corresponding to the core data subsets; Based on the subset weights, the key optimization areas required for the satellite Internet are determined.

6. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: The querying of the current network usage status corresponding to the key optimization area includes: Identify the topological identification code of the key optimization area in the satellite Internet; Parsing the encoding rules corresponding to the topology identification code; Based on the coding rules, construct a regional basic framework corresponding to the key optimization area; Based on the regional basic framework, query the regional limited data corresponding to the key optimization area; Based on the area-limited data, extracting the regional traffic records corresponding to the key optimization area; Based on the regional traffic records, query the network usage status corresponding to the key optimization area.

7. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: Analyzing the network optimization direction corresponding to the key optimization area based on the current network usage status includes: Collecting real-time usage data corresponding to each node in the network usage status; Based on the real-time usage data, construct a network status matrix corresponding to the key optimization interval; Dividing the network unit groups corresponding to the grid units in the network state matrix; analyzing the degree of network association between the groups of network units; Based on the network association degree, the network optimization direction corresponding to the key optimization area is analyzed.

8. The method for intelligently monitoring network signals based on satellite Internet according to claim 1, wherein: Generating the network signal indicator corresponding to the key optimization area based on the signal balance value includes: Identifying a signal value interval in which the signal equalization value lies; Determining a signal fluctuation standard corresponding to the signal value interval; According to the signal fluctuation standard, the fluctuation level corresponding to the signal balance value is divided; Extracting features of the fluctuation level to obtain fluctuation level features; Based on the fluctuation level characteristics, a network signal index corresponding to the key optimization area is generated.

Images