Mobile communication system operation and maintenance management method and system

Abstract

The invention discloses a mobile communication system operation and maintenance management method and system, and relates to the technical field of communication data processing, and the method comprises the steps: determining the abnormality rate corresponding to each type of equipment state data and each type of network performance data, splitting the data curve of each type of equipment state data and each type of network performance data through the abnormality rate, and obtaining the data curve of each type of equipment state data and each type of network performance data; therefore, the splitting adaptability of each type of data is ensured. According to the method, the curve characteristics of each partial data curve are analyzed, data smoothing processing is carried out on the complete data curve, smoothing processing is adaptively carried out according to the curve characteristics of different types of data curves, and therefore the data smoothing processing effect is improved. According to the method, independent analysis and correlation analysis are performed on the smoothed data curves of the equipment state data and the network performance data, the defect condition in the communication system is identified by integrating the analysis results of the two levels, and an operation and maintenance strategy is formulated according to the defect condition, so that the adaptability and safety of operation and maintenance management of the communication system are improved; and safe operation of the communication system is ensured.

Description

Technical Field

[0001] This invention relates to the field of communication data processing technology, and in particular to a method and system for operation and maintenance management of mobile communication systems. Background Technology

[0002] Mobile communication system operation and maintenance management solutions are primarily based on the rapid development and widespread application of current mobile communication networks. With the popularization of next-generation communication technologies such as 5G, the scale of mobile communication networks is constantly expanding, placing higher demands on network capacity, stability, and security. At the same time, the complexity and diversity of mobile communication networks also increase the difficulty of operation and maintenance management. To ensure the normal operation and efficient service of mobile communication networks, advanced operation and maintenance management solutions are needed, improving operational efficiency and service quality through real-time monitoring, fault early warning, and performance optimization. These technologies provide strong support for the formulation and implementation of mobile communication system operation and maintenance management solutions.

[0003] In existing technologies, a unified data smoothing method is used for different types of related data in mobile communication systems. However, different types of data have different timeliness and fluctuations, resulting in poor data smoothing effect. Furthermore, different types of related data cannot be reliably integrated to reflect the status of the communication system, leading to poor adaptability and low security in the operation and maintenance management of the communication system.

[0004] Therefore, improving the effectiveness of data smoothing, the adaptability of operation and maintenance management, and security are technical problems that need to be solved. Summary of the Invention

[0005] The purpose of this invention is to address the problems of poor data smoothing performance, poor adaptability to operation and maintenance management of communication systems, and low security in existing technologies. Therefore, this invention proposes a mobile communication system operation and maintenance management method, which includes:

[0006] Acquire device status data and network performance data of the mobile communication system over a period of time, classify the device status data and network performance data, determine the anomaly rate corresponding to each type of device status data and each type of network performance data, and construct data curves of their respective data changes over time based on each type of device status data and each type of network performance data.

[0007] By using anomaly rates to split the data curves for each type of device status data and each type of network performance data, a complete data curve is divided into multiple partial data curves. The curve characteristics of each partial data curve are analyzed, and the complete data curve is smoothed to obtain the smoothed data curves for each type of device status data and each type of network performance data.

[0008] The smoothed data curves of device status data and network performance data are analyzed separately to obtain the first analysis result. Correlation analysis is performed on the device status data and network performance data to obtain the second analysis result.

[0009] By combining the results of the first and second analyses, defects within the mobile communication system are identified, and operation and maintenance strategies are set to address these defects, thereby optimizing the operation and maintenance management of the mobile communication system.

[0010] In some embodiments of this application, the anomaly rate corresponding to each type of device status data and each type of network performance data is determined, including:

[0011] Collect historical records of each type of device status data and each type of network performance data, and identify the abnormal data corresponding to each type of device status data and each type of network performance data in the historical records;

[0012] By using the timestamps and data volumes of abnormal data, the proportion of abnormal data volume and the proportion of abnormal data time periods are determined in each type of device status data and each type of network performance data. The abnormality rate of each type of device status data and each type of network performance data is determined by combining the proportion of abnormal data volume and the proportion of abnormal data time periods.

[0013] In some embodiments of this application, the data curves for each type of device status data and each type of network performance data are split based on the anomaly rate, thus dividing a complete data curve into multiple partial data curves, including:

[0014] Different anomaly rates correspond to different time periods. The data curves of each type of device status data and each type of network performance data are split according to the time period, thereby splitting a complete data curve into multiple time-continuous partial data curves.

[0015] In some embodiments of this application, the curve characteristics of each partial data curve are analyzed, and data smoothing processing is performed on the complete data curve, including:

[0016] Curve characteristics include slope, fluctuation range, standard deviation, and inflection point. Each part of the data curve is evenly divided into multiple curve segments, the slope of each curve segment is calculated, and the fluctuation range, standard deviation, and inflection point of the partial data curves are combined to evaluate the fluctuation value of each partial data curve.

[0017]

[0018] Where B represents the fluctuation value of a portion of the data curve, α1, α2, and α3 are the conversion coefficients corresponding to the slope, fluctuation amplitude, and standard deviation, respectively, n1 is the number of curve segments after dividing this portion of the data curve, and Z... iThe slope of the i-th curve segment after dividing the data curve is X, the fluctuation range of the data curve is C, the standard deviation of the data curve is n2, the number of inflection points of the data curve is n1, and the preset constant is k1.

[0019] The smoothing period is determined based on the fluctuation value of each part of the data curve. Smoothing is performed according to the smoothing period of each part of the data curve to obtain the smoothed value. The smoothed values ​​of each part of the data curve are connected to obtain the smoothed complete data curve.

[0020] In some embodiments of this application, the smoothed data curves of device status data and network performance data are analyzed separately to obtain a first analysis result, including:

[0021] For equipment status data, a threshold range is set for each type of equipment status data. Anomalies are detected on the smoothed data curve of the equipment status data. Trend analysis is performed on the smoothed data curve of the equipment status data to obtain the changing trend. Anomalies and changing trends of the smoothed data curve of the equipment status data are analyzed by a preset algorithm to obtain the equipment status result.

[0022] For network performance data, a threshold range is set for each type of network performance data. Anomalies are detected on the smoothed data curve of the network performance data. Trend analysis is performed on the smoothed data curve of the network performance data to obtain the changing trend. Anomalies and changing trends of the smoothed data curve of the network performance data are analyzed by a preset algorithm to obtain the network performance results.

[0023] Device status results and network performance results are used as the primary analysis results.

[0024] In some embodiments of this application, correlation analysis is performed on device status data and network performance data to obtain a second analysis result, including:

[0025] Correlation analysis is performed on each type of device status data and each type of network performance data to determine the correlation between pairs of data. Based on the correlation, the device status data and network performance data that meet the requirements are selected, and the corresponding device status data and network performance data are recorded as correlation data. The functional relationship between device status data and network performance data is obtained by fitting the correlation data, and the impact of the correlation data on the overall mobile communication system is evaluated.

[0026] Standardize the data for each type of device status and each type of network performance, sum the data for each type of device status by weight, define a device status index, sum the data for each type of network performance by weight, and define a network performance index.

[0027] The status level of the mobile communication system is generated based on the overall impact of relevant data on the mobile communication system, equipment status indicators, and network performance indicators.

[0028]

[0029] Where L is the status level of the mobile communication system, ρ1 and ρ2 are the weights of the device status index and network performance index respectively, D1 and D2 are the device status index and network performance index respectively, τ is the impact of relevant data on the overall mobile communication system, k2 and k3 are preset constants, and [] is the rounding symbol.

[0030] The functional relationship between the corresponding device status data and network performance data, as well as the status level of the mobile communication system, are used as the second analysis result.

[0031] In some embodiments of this application, defects within the mobile communication system are identified by combining the results of the first analysis and the results of the second analysis, including:

[0032] By mapping the functional relationships between device status results and network performance results with the corresponding device status data and network performance data under relevant data, and by mapping the device status results and network performance results with the status level of the mobile communication system, defect information can be identified.

[0033] In some embodiments of this application, operational and maintenance strategies are set to address defects within the mobile communication system, including:

[0034] Analyze defect information to set the range of each type of operation and maintenance parameter, and use the combination of operation and maintenance parameter ranges under all types as operation and maintenance strategies to achieve operation and maintenance management of mobile communication systems.

[0035] Correspondingly, this application also provides a mobile communication system operation and maintenance management system, including,

[0036] The module is used to acquire device status data and network performance data of the mobile communication system over a period of time, classify the device status data and network performance data, determine the anomaly rate corresponding to each type of device status data and each type of network performance data, and construct data curves of their respective data changes over time based on each type of device status data and each type of network performance data.

[0037] The smoothing module is used to split the data curves of each type of device status data and each type of network performance data based on the anomaly rate. It splits a complete data curve into multiple partial data curves, analyzes the curve characteristics of each partial data curve, and performs data smoothing on the complete data curve to obtain the smoothed data curves of each type of device status data and each type of network performance data.

[0038] The analysis module is used to analyze the smoothed data curves of device status data and network performance data separately to obtain the first analysis result, and to perform correlation analysis on the device status data and network performance data to obtain the second analysis result.

[0039] The operation and maintenance module is used to identify defects in the mobile communication system by combining the results of the first and second analyses, and to set operation and maintenance strategies for the defects in the mobile communication system, thereby optimizing the operation and maintenance management of the mobile communication system.

[0040] Compared with the prior art, the beneficial effects of this invention are as follows:

[0041] 1. Determine the anomaly rate for each type of device status data and each type of network performance data. Based on the anomaly rate, segment the data curves for each type of device status data and each type of network performance data to ensure the adaptability of the segmentation for each data type. Analyze the curve characteristics of each data segment, and perform data smoothing on the complete data curve. Adaptive smoothing is applied to the curve characteristics of different types of data curves, thereby improving the effectiveness of data smoothing and providing a reliable foundation for subsequent data analysis.

[0042] 2. The smoothed data curves of equipment status data and network performance data are analyzed separately and with correlation to obtain the first and second analysis results. By combining the two levels of analysis results, defects in the communication system are identified, and operation and maintenance strategies are formulated to address these defects. This improves the adaptability and security of communication system operation and maintenance management and ensures the safe operation of the communication system. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating a mobile communication system operation and maintenance management method proposed in this invention.

[0044] Figure 2 This is a schematic diagram of the structure of a mobile communication system operation and maintenance management system proposed in this invention. Detailed Implementation

[0045] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0046] Reference Figure 1 A method for operation and maintenance management of a mobile communication system includes the following steps:

[0047] Step S101: Obtain device status data and network performance data of the mobile communication system over a period of time, classify the device status data and network performance data, determine the anomaly rate corresponding to each type of device status data and each type of network performance data, and construct data curves for the data changes over time based on each type of device status data and each type of network performance data.

[0048] In this embodiment, device status data includes CPU utilization, memory usage, disk space, etc., while network performance data includes throughput, latency, packet loss rate, etc. The real-time nature of these different types of data varies, and the anomaly rate is an indicator describing data anomalies.

[0049] In some embodiments of this application, the anomaly rate corresponding to each type of device status data and each type of network performance data is determined, including:

[0050] Collect historical records of each type of device status data and each type of network performance data, and identify the abnormal data corresponding to each type of device status data and each type of network performance data in the historical records;

[0051] By using the timestamps and data volumes of abnormal data, the proportion of abnormal data volume and the proportion of abnormal data time periods are determined in each type of device status data and each type of network performance data. The abnormality rate of each type of device status data and each type of network performance data is determined by combining the proportion of abnormal data volume and the proportion of abnormal data time periods.

[0052] In this embodiment, an anomaly rate is determined by combining the proportion of abnormal data volume and the proportion of abnormal data time periods.

[0053] Step S102: The data curves of each type of device status data and each type of network performance data are split according to the anomaly rate. A complete data curve is split into multiple partial data curves, and the curve characteristics of each partial data curve are analyzed. The complete data curve is then smoothed to obtain the smoothed data curves of each type of device status data and each type of network performance data.

[0054] In this embodiment, for data with a high anomaly rate, the number of data curves after curve splitting is greater, in order to accurately capture fluctuations; conversely, for data with a low anomaly rate, the number of data curves after curve splitting is smaller.

[0055] In some embodiments of this application, the data curves for each type of device status data and each type of network performance data are split based on the anomaly rate, thus dividing a complete data curve into multiple partial data curves, including:

[0056] Different anomaly rates correspond to different time periods. The data curves of each type of device status data and each type of network performance data are split according to the time period, thereby splitting a complete data curve into multiple time-continuous partial data curves.

[0057] In some embodiments of this application, the curve characteristics of each partial data curve are analyzed, and data smoothing processing is performed on the complete data curve, including:

[0058] Curve characteristics include slope, fluctuation range, standard deviation, and inflection point. Each part of the data curve is evenly divided into multiple curve segments, the slope of each curve segment is calculated, and the fluctuation range, standard deviation, and inflection point of the partial data curves are combined to evaluate the fluctuation value of each partial data curve.

[0059]

[0060] Where B represents the fluctuation value of a portion of the data curve, α1, α2, and α3 are the conversion coefficients corresponding to the slope, fluctuation amplitude, and standard deviation, respectively, n1 is the number of curve segments after dividing this portion of the data curve, and Z... i The slope of the i-th curve segment after dividing the data curve is X, the fluctuation range of the data curve is C, the standard deviation of the data curve is n2, the number of inflection points of the data curve is n1, and the preset constant is k1.

[0061] The smoothing period is determined based on the fluctuation value of each part of the data curve. Smoothing is performed according to the smoothing period of each part of the data curve to obtain the smoothed value. The smoothed values ​​of each part of the data curve are connected to obtain the smoothed complete data curve.

[0062] In this embodiment, the slope is the slope of the tangent line to the curve at a certain point or segment, reflecting the trend of data change. The fluctuation range refers to the difference between the maximum and minimum values ​​of the curve within a certain time period, reflecting the range of data fluctuation. An inflection point is a point on the curve where the concavity / convexity changes, i.e., a turning point in the curve's trend. It reflects the point of change in the data trend. The calculation of inflection points typically involves the second derivative. At a point on the curve, if the second derivative changes from positive to negative or from negative to positive, that point is an inflection point. The fluctuations represented by the slope, fluctuation range, and standard deviation are summed, and the sum of the fluctuations of the three is corrected by the number of inflection points. Then, the average of the three values ​​is taken as the fluctuation value of a portion of the data curve.

[0063] In this embodiment, different fluctuation values ​​correspond to different smoothing periods (durations). Each part of the data curve is split according to the smoothing period, and the smoothing value is calculated to obtain the smoothed data curve. The smoothing process includes moving average and exponential smoothing. Moving average: This method takes the average value of data over a certain period of time (smoothing period) to eliminate short-term fluctuations. For example, the average value of the past 5 or 10 data points can be calculated as the current smoothing value. Exponential smoothing is similar; it calculates the smoothing value by assigning weights to data at different time points within the smoothing period.

[0064] As we can understand, a smoothing value represents the average level or trend of data over a specific time period. This value is calculated by averaging all data points within that period, thus reflecting the overall state of the data over that time period, rather than the instantaneous state of a single data point. Smoothing values ​​help us better understand the long-term behavior of data and reduce misunderstandings caused by short-term fluctuations.

[0065] Differences in data curves before and after smoothing device status data:

[0066] 1. The trend is becoming more obvious:

[0067] Before smoothing, the data curve may be less obvious due to noise interference, making the long-term trend and change pattern less obvious.

[0068] The smoothed data curves more clearly show the long-term trends and patterns of equipment status, helping us to more accurately predict the future status of the equipment.

[0069] 2. Anomaly identification:

[0070] In the data curve before smoothing, outliers may be difficult to identify due to noise masking them.

[0071] In the smoothed data curve, outliers will be more prominent because they deviate significantly from the smoothed data trend. This helps us to promptly detect and address anomalies in the device status.

[0072] Difference between network performance data curves before and after smoothing:

[0073] 1. Reduced volatility:

[0074] Network performance data is often affected by a variety of factors, such as network congestion, equipment failure, and user behavior, resulting in significant fluctuations in the data curve.

[0075] The smoothed data curves can effectively reduce these fluctuations, making the trend of network performance changes clearer.

[0076] 2. More accurate bottleneck identification:

[0077] Before smoothing, network performance bottlenecks may be difficult to identify accurately due to data fluctuations in the data curve.

[0078] Smoothed data curves can more accurately reflect changes in network performance, helping us to pinpoint bottlenecks in the network and providing a basis for optimizing network performance.

[0079] 3. More sensitive anomaly detection:

[0080] Smoothed data curves are more sensitive to abnormal changes in network performance. This is because smoothing reduces the impact of normal fluctuations, making abnormal changes more prominent on the data curve.

[0081] This helps us to detect network faults or attacks in a timely manner and take appropriate measures to deal with them.

[0082] Step S103: Analyze the smoothed data curves of device status data and network performance data separately to obtain the first analysis result; perform correlation analysis on the device status data and network performance data to obtain the second analysis result.

[0083] In this embodiment, the smoothed data curves of device status data and network performance data are analyzed separately. Each type of data is analyzed completely independently without any correlation. The first analysis result provides a relatively specific data situation. The second analysis result provides the overall communication system status and the functional relationships between correlated device status data and network performance data.

[0084] In some embodiments of this application, the smoothed data curves of device status data and network performance data are analyzed separately to obtain a first analysis result, including:

[0085] For equipment status data, a threshold range is set for each type of equipment status data. Anomalies are detected on the smoothed data curve of the equipment status data. Trend analysis is performed on the smoothed data curve of the equipment status data to obtain the changing trend. Anomalies and changing trends of the smoothed data curve of the equipment status data are analyzed by a preset algorithm to obtain the equipment status result.

[0086] For network performance data, a threshold range is set for each type of network performance data. Anomalies are detected on the smoothed data curve of the network performance data. Trend analysis is performed on the smoothed data curve of the network performance data to obtain the changing trend. Anomalies and changing trends of the smoothed data curve of the network performance data are analyzed by a preset algorithm to obtain the network performance results.

[0087] Device status results and network performance results are used as the primary analysis results.

[0088] In this embodiment, statistical methods (such as the 3σ principle, box plots, etc.) or machine learning algorithms (such as isolated forests, LOF, etc.) are used to detect outliers in the data. Device status results and network performance results are data content containing outliers or trends, or data content containing points or trends with potential anomaly risks.

[0089] In some embodiments of this application, correlation analysis is performed on device status data and network performance data to obtain a second analysis result, including:

[0090] Correlation analysis is performed on each type of device status data and each type of network performance data to determine the correlation between pairs of data. Based on the correlation, the device status data and network performance data that meet the requirements are selected, and the corresponding device status data and network performance data are recorded as correlation data. The functional relationship between device status data and network performance data is obtained by fitting the correlation data, and the impact of the correlation data on the overall mobile communication system is evaluated.

[0091] Standardize the data for each type of device status and each type of network performance, sum the data for each type of device status by weight, define a device status index, sum the data for each type of network performance by weight, and define a network performance index.

[0092] The status level of the mobile communication system is generated based on the overall impact of relevant data on the mobile communication system, equipment status indicators, and network performance indicators.

[0093]

[0094] Where L is the status level of the mobile communication system, ρ1 and ρ2 are the weights of the device status index and network performance index respectively, D1 and D2 are the device status index and network performance index respectively, τ is the impact of relevant data on the overall mobile communication system, k2 and k3 are preset constants, and [] is the rounding symbol.

[0095] The functional relationship between the corresponding device status data and network performance data, as well as the status level of the mobile communication system, are used as the second analysis result.

[0096] In this embodiment, correlation analysis is performed using methods such as the Pearson correlation coefficient or the Spearman rank correlation coefficient to analyze the correlation between device status data and network performance data. Note that this correlation analysis focuses on the relationship between the device status data and the network performance data. The impact of the correlated data on the overall mobile communication system is assessed through regression analysis, analysis of variance, and machine learning (for machine learning models, methods such as TracIn can be used to evaluate the influence of training data on the mobile communication system). Correlated data includes, for example, CPU utilization and throughput, memory usage and latency. Excessive memory usage can lead to slower device response, thereby increasing network latency. The trends of device status data and network performance data over time can also be analyzed. If both show similar trends (e.g., rising or falling simultaneously) within a certain period, this may indicate a causal relationship or mutual influence between them.

[0097] In this embodiment, This indicates the correction of the sum of device status indicators and network performance indicators to the overall impact of relevant data on the mobile communication system.

[0098] Step S104: Based on the combined results of the first and second analyses, identify defects within the mobile communication system, set up operation and maintenance strategies to address these defects, and optimize the operation and maintenance management of the mobile communication system.

[0099] In this embodiment, the first analysis result and the second analysis result are combined. The first analysis result is the specific numerical value and trend of each type of data, and the second analysis result is the overall situation of the communication system. The first analysis result and the second analysis result are compared, verified and integrated.

[0100] In some embodiments of this application, defects within the mobile communication system are identified by combining the results of the first analysis and the results of the second analysis, including:

[0101] By mapping the functional relationships between device status results and network performance results with the corresponding device status data and network performance data under relevant data, and by mapping the device status results and network performance results with the status level of the mobile communication system, defect information can be identified.

[0102] In this embodiment, the functional relationships between device status results and network performance results are mapped to the corresponding device status data and network performance data under relevant data. This allows for the matching of anomalies in the device status results and network performance results under relevant data. Anomalies (such as sudden changes, abnormal peaks, etc.) are identified in the device status data and network performance data, and the matching of these anomalies is analyzed. Furthermore, by analyzing these functional relationships, it is possible to understand how different data influence each other and the degree of their impact on the overall state of the mobile communication system. The device status results and network performance results are mapped to the state level of the mobile communication system. The device status results and network performance results are input into a preset defect identification model to identify faults, defects, etc. The specific faults, anomalies, and defects identified in the first analysis result are mapped to the overall state level of the mobile communication system determined in the second analysis result. Defect information includes defect type, location, and impact.

[0103] In some embodiments of this application, operational and maintenance strategies are set to address defects within the mobile communication system, including:

[0104] Analyze defect information to set the range of each type of operation and maintenance parameter, and use the combination of operation and maintenance parameter ranges under all types as operation and maintenance strategies to achieve operation and maintenance management of mobile communication systems.

[0105] In this embodiment, the operation and maintenance parameters include monitoring parameter frequency, performance baseline, threshold parameters, etc. Setting operation and maintenance strategies for defects within a mobile communication system requires comprehensive consideration of various factors such as defect type, location, and impact. By refining the operation and maintenance strategy into a combination of specific parameters, the stable operation and high-efficiency performance of the mobile communication system can be more effectively guaranteed.

[0106] Compared with the prior art, the beneficial effects of this invention are as follows:

[0107] 1. Determine the anomaly rate for each type of device status data and each type of network performance data. Based on the anomaly rate, segment the data curves for each type of device status data and each type of network performance data to ensure the adaptability of the segmentation for each data type. Analyze the curve characteristics of each data segment, and perform data smoothing on the complete data curve. Adaptive smoothing is applied to the curve characteristics of different types of data curves, thereby improving the effectiveness of data smoothing and providing a reliable foundation for subsequent data analysis.

[0108] 2. The smoothed data curves of equipment status data and network performance data are analyzed separately and with correlation to obtain the first and second analysis results. By combining the two levels of analysis results, defects in the communication system are identified, and operation and maintenance strategies are formulated to address these defects. This improves the adaptability and security of communication system operation and maintenance management and ensures the safe operation of the communication system.

[0109] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented in hardware or by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0110] Correspondingly, this application also provides a mobile communication system operation and maintenance management system, such as... Figure 2 As shown, including,

[0111] The module is used to acquire device status data and network performance data of the mobile communication system over a period of time, classify the device status data and network performance data, determine the anomaly rate corresponding to each type of device status data and each type of network performance data, and construct data curves of their respective data changes over time based on each type of device status data and each type of network performance data.

[0112] The smoothing module is used to split the data curves of each type of device status data and each type of network performance data based on the anomaly rate. It splits a complete data curve into multiple partial data curves, analyzes the curve characteristics of each partial data curve, and performs data smoothing on the complete data curve to obtain the smoothed data curves of each type of device status data and each type of network performance data.

[0113] The analysis module is used to analyze the smoothed data curves of device status data and network performance data separately to obtain the first analysis result, and to perform correlation analysis on the device status data and network performance data to obtain the second analysis result.

[0114] The operation and maintenance module is used to identify defects in the mobile communication system by combining the results of the first and second analyses, and to set operation and maintenance strategies for the defects in the mobile communication system, thereby optimizing the operation and maintenance management of the mobile communication system.

[0115] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0116] Those skilled in the art will understand that the modules in the system of the implementation scenario can be distributed throughout the system of the implementation scenario as described, or they can be modified to reside in one or more systems different from this implementation scenario. The modules of the above-mentioned implementation scenario can be merged into one module, or they can be further divided into multiple sub-modules.

[0117] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for operation and maintenance management of a mobile communication system, characterized in that, include, Acquire device status data and network performance data of the mobile communication system over a period of time, classify the device status data and network performance data, determine the anomaly rate corresponding to each type of device status data and each type of network performance data, and construct data curves of their respective data changes over time based on each type of device status data and each type of network performance data. By using anomaly rates to split the data curves for each type of device status data and each type of network performance data, a complete data curve is divided into multiple partial data curves. The curve characteristics of each partial data curve are analyzed, and the complete data curve is smoothed to obtain the smoothed data curves for each type of device status data and each type of network performance data. The smoothed data curves of device status data and network performance data are analyzed separately to obtain the first analysis result. Correlation analysis is performed on the device status data and network performance data to obtain the second analysis result. By combining the results of the first and second analyses, defects within the mobile communication system are identified, and operation and maintenance strategies are set to address these defects, thereby optimizing the operation and maintenance management of the mobile communication system.

2. The mobile communication system operation and maintenance management method according to claim 1, characterized in that, Determine the anomaly rate for each type of device status data and each type of network performance data, including: Collect historical records of each type of device status data and each type of network performance data, and identify the abnormal data corresponding to each type of device status data and each type of network performance data in the historical records; By using the timestamps and data volumes of abnormal data, the proportion of abnormal data volume and the proportion of abnormal data time periods are determined in each type of device status data and each type of network performance data. The abnormality rate of each type of device status data and each type of network performance data is determined by combining the proportion of abnormal data volume and the proportion of abnormal data time periods.

3. The mobile communication system operation and maintenance management method according to claim 2, characterized in that, By analyzing the anomaly rate, the data curves for each type of device status data and each type of network performance data are broken down, resulting in a complete data curve being divided into multiple partial data curves, including... Different anomaly rates correspond to different time periods. The data curves of each type of device status data and each type of network performance data are split according to the time period, thereby splitting a complete data curve into multiple time-continuous partial data curves.

4. The mobile communication system operation and maintenance management method according to claim 1, characterized in that, It analyzes the curve characteristics of each part of the data curve and performs data smoothing processing on the complete data curve, including... Curve characteristics include slope, fluctuation range, standard deviation, and inflection point. Each part of the data curve is evenly divided into multiple curve segments, the slope of each curve segment is calculated, and the fluctuation range, standard deviation, and inflection point of the partial data curves are combined to evaluate the fluctuation value of each partial data curve. Where B represents the fluctuation value of a portion of the data curve, α1, α2, and α3 are the conversion coefficients corresponding to the slope, fluctuation amplitude, and standard deviation, respectively, n1 is the number of curve segments after dividing this portion of the data curve, and Z... i The slope of the i-th curve segment after dividing the data curve is X, the fluctuation range of the data curve is C, the standard deviation of the data curve is n2, the number of inflection points of the data curve is n1, and the preset constant is k1. The smoothing period is determined based on the fluctuation value of each part of the data curve. Smoothing is performed according to the smoothing period of each part of the data curve to obtain the smoothed value. The smoothed values ​​of each part of the data curve are connected to obtain the smoothed complete data curve.

5. The mobile communication system operation and maintenance management method according to claim 1, characterized in that, The smoothed data curves of device status data and network performance data were analyzed separately to obtain the first analysis results, including: For equipment status data, a threshold range is set for each type of equipment status data. Anomalies are detected on the smoothed data curve of the equipment status data. Trend analysis is performed on the smoothed data curve of the equipment status data to obtain the changing trend. Anomalies and changing trends of the smoothed data curve of the equipment status data are analyzed by a preset algorithm to obtain the equipment status result. For network performance data, a threshold range is set for each type of network performance data. Anomalies are detected on the smoothed data curve of the network performance data. Trend analysis is performed on the smoothed data curve of the network performance data to obtain the changing trend. Anomalies and changing trends of the smoothed data curve of the network performance data are analyzed by a preset algorithm to obtain the network performance results. Device status results and network performance results are used as the primary analysis results.

6. The mobile communication system operation and maintenance management method according to claim 5, characterized in that, A correlation analysis was performed on device status data and network performance data to obtain the second analysis result, including: Correlation analysis is performed on each type of device status data and each type of network performance data to determine the correlation between pairs of data. Based on the correlation, the device status data and network performance data that meet the requirements are selected, and the corresponding device status data and network performance data are recorded as correlation data. The functional relationship between device status data and network performance data is obtained by fitting the correlation data, and the impact of the correlation data on the overall mobile communication system is evaluated. Standardize the data for each type of device status and each type of network performance, sum the data for each type of device status by weight, define a device status index, sum the data for each type of network performance by weight, and define a network performance index. The status level of the mobile communication system is generated based on the overall impact of relevant data on the mobile communication system, equipment status indicators, and network performance indicators. Where L is the status level of the mobile communication system, ρ1 and ρ2 are the weights of the device status index and network performance index respectively, D1 and D2 are the device status index and network performance index respectively, τ is the impact of relevant data on the overall mobile communication system, k2 and k3 are preset constants, and [] is the rounding symbol. The functional relationship between the corresponding device status data and network performance data, as well as the status level of the mobile communication system, are used as the second analysis result.

7. The mobile communication system operation and maintenance management method according to claim 6, characterized in that, Based on the combined results of the first and second analyses, defects within the mobile communication system are identified, including: By mapping the functional relationships between device status results and network performance results with the corresponding device status data and network performance data under relevant data, and by mapping the device status results and network performance results with the status level of the mobile communication system, defect information can be identified.

8. The mobile communication system operation and maintenance management method according to claim 7, characterized in that, To configure operational and maintenance strategies to address defects within mobile communication systems, including: Analyze defect information to set the range of each type of operation and maintenance parameter, and use the combination of operation and maintenance parameter ranges under all types as operation and maintenance strategy to achieve operation and maintenance management of mobile communication system.

9. A mobile communication system operation and maintenance management system, characterized in that, include, The module is used to acquire device status data and network performance data of the mobile communication system over a period of time, classify the device status data and network performance data, determine the anomaly rate corresponding to each type of device status data and each type of network performance data, and construct data curves of their respective data changes over time based on each type of device status data and each type of network performance data. The smoothing module is used to split the data curves of each type of device status data and each type of network performance data based on the anomaly rate. It splits a complete data curve into multiple partial data curves, analyzes the curve characteristics of each partial data curve, and performs data smoothing on the complete data curve to obtain the smoothed data curves of each type of device status data and each type of network performance data. The analysis module is used to analyze the smoothed data curves of device status data and network performance data separately to obtain the first analysis result, and to perform correlation analysis on the device status data and network performance data to obtain the second analysis result. The operation and maintenance module is used to identify defects in the mobile communication system by combining the results of the first and second analyses, and to set operation and maintenance strategies for the defects in the mobile communication system, thereby optimizing the operation and maintenance management of the mobile communication system.

Images