Network fault handling priority assessment method, system, device and storage medium

Abstract

The present disclosure provides a network fault processing priority assessment method, system, electronic device and storage medium to solve the problem that the current alarm assessment lacks evaluation of the actual impact of the network by the fault. The method comprises: collecting wireless network basic data; integrating the collected data according to different dimensions; performing single-cell single-dimension index sensitivity scoring; scoring the single-cell and single-BBU level fault processing urgency according to the index sensitivity score of each dimension; and obtaining a specific fault processing priority ranking according to the single-cell and single-BBU level fault processing urgency score and the specific alarm processing time limit urgency. The present disclosure can reduce the impact of the fault on the network and improve maintenance efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of communication network technology, specifically to a method for prioritizing network fault handling, a system for prioritizing network fault handling, an electronic device, and a computer-readable storage medium. Background Technology

[0002] In operator network operation and maintenance, the common approach is to dispatch fault handling work orders based on device alarms, with network maintenance personnel handling network faults that have occurred. Given limited human and material resources for network maintenance, improving the efficiency of wireless network fault handling to reduce the impact of faults on the network is a key issue that operations teams need to consider.

[0003] Currently, methods to improve the efficiency of wireless network fault handling fall into two main categories: First, preventing or locating faults through intelligent operation and maintenance-based fault prediction, identification, and location. Second, training on massive amounts of alarms to determine the importance of various alarms, assessing the importance of alarm items to guide alarm handling priorities. Specifically, method one reduces the number of faults through predictive prevention or improves efficiency through intelligent fault location, but it falls short in improving personnel utilization and mitigating the impact of faults when the number of faults is large and on-site fault handling personnel are limited. Method two assesses the importance of specific alarm items, but it lacks analysis of the importance of the same fault alarms across different cells and base stations, and thus lacks an assessment of the actual impact of faults on the network. Summary of the Invention

[0004] To address at least the problems in existing technologies, such as the inability to prioritize the most urgent alarms when alarm information is unavailable, the lack of analysis on the importance of the same fault alarms in different cells and base stations, and the deficiency in assessing the actual impact of faults on the network, this disclosure provides a network fault handling priority assessment method, a network fault handling priority assessment system, an electronic device, and a computer-readable storage medium, which can reduce the impact of faults on the network and improve maintenance efficiency.

[0005] In a first aspect, this disclosure provides a method for prioritizing network fault handling, the method comprising:

[0006] Perform basic data collection for the wireless network;

[0007] The collected data is integrated according to different dimensions;

[0008] Perform sensitivity scoring of each indicator in a single cell and a single dimension;

[0009] The urgency of fault handling for a single cell and a single BBU (Baseband Unit) is scored based on the sensitivity scores of each indicator in each dimension.

[0010] The priority ranking of specific fault handling is obtained based on the urgency score of single cell and single BBU level fault handling and the urgency of specific alarm handling time limits.

[0011] Furthermore, the collection of basic wireless network data includes:

[0012] Historical data for various indicators are collected from data sources based on a defined time period. These data sources include wireless network management systems, complaint handling systems, equipment technical specification documents, and wireless network resource management systems.

[0013] Furthermore, the different dimensions include: capacity, hardware, and perception;

[0014] The integration of collected data according to different dimensions includes:

[0015] For each indicator in the capacity dimension, the wireless network management data is collected at the hourly granularity of each cell, and the average value of each hour is calculated on a daily basis to serve as the daily indicator value for each cell in the capacity dimension.

[0016] For each hardware dimension indicator, based on the data obtained from professional network administrators, and supplemented by the equipment technical characteristic documents of the hardware device scenario, we obtained data for each hardware dimension indicator.

[0017] For the perception dimension indicators, the complaint handling system is used as the data source, and the specific cell is determined with the assistance of the wireless network professional network management and wireless network resource management system, which serve as the perception dimension indicators for that cell.

[0018] Furthermore, the sensitivity scoring of each indicator in a single cell and single dimension includes:

[0019] For single-cell capacity metrics:

[0020] Thresh is determined by the following formula. Ci :

[0021] Thresh Ci =min{X Ci,max E i}

[0022] When X Ci,j ≥Thresh Ci At that time, S Ci,j =0, and count the number of cells that meet the conditions as M. Ci ;

[0023] When XCi,j <Thresh Ci At that time, all eligible communities will be classified as X. Ci,j Sort X in ascending order, where X Ci,min Corresponding cell S Ci,j =T, other neighborhood scores are calculated as X Ci,j Scores are assigned based on a weighted ranking.

[0024] Among them, Thresh Ci X represents the zero threshold for capacity dimension indicator i, where j represents the cell number, and X... Ci,max E represents the maximum value of index item i in the capacity dimension of a single-system cell across the entire network. i X is the current network expansion threshold value for indicator item i. Ci , j S represents the index value of index item i in the capacity dimension of cell j. Ci , j Let be the sensitivity score of capacity dimension indicator i for community j, and T be the preset maximum score.

[0025] For single-cell hardware metrics:

[0026] By combining hardware information with the available time of the community managed by professional network administrators, and using AI classification algorithms, the threshold for a perfect score (Thresh) is determined. THi Thresh with a zero score 0Hi :

[0027] When X Hi , j ≥min{D i Thresh 0Hi When S Hi , j =0, where D i Recommended equipment-related threshold values ​​for the product manual;

[0028] When X Hi , j ≤Thresh THi At that time, S Hi , j =T;

[0029] Other neighborhood scores, based on indicator X Hi , j Proportional scoring;

[0030] Among them, X Hi , j Let i be the indicator value of hardware dimension indicator item i in community j.

[0031] Furthermore, regarding the sensing dimension indicators for a single cell:

[0032] Based on the complaint data of each community, the number of complaints corresponding to each community's perception dimension indicator is determined, thereby obtaining the sensitivity score of that perception dimension indicator.

[0033] Furthermore, the scoring of the urgency of single-cell and single-BBU level fault handling based on the sensitivity scores of various indicators across different dimensions includes:

[0034] The urgency score for fault handling in a single cell is calculated using the following formula:

[0035]

[0036] Among them, S Cj S represents the capacity dimension scores of cell j. Hj S represents the scores of all hardware dimensions of cell j. Pj For all perception dimensions of cell j, N C N is the number of metrics included in the capacity dimension scoring. H To account for the number of metrics included in the hardware dimension scoring, N P The number of indicators included in the perception dimension score; α is the weight of the capacity dimension in the cell indicator sensitivity scoring system, β is the weight of the hardware dimension in the cell indicator sensitivity scoring system, and γ is the weight of the perception dimension in the cell indicator sensitivity scoring system; S cellj Let α+β+γ be the fault handling urgency score for cell j, where α+β+γ=1;

[0037] For the urgency score of single BBU-level fault handling, it is calculated by using the full index scores of all cells under the single BBU:

[0038]

[0039] Among them, S BB This is the fault handling urgency score of BBU with serial number k, S cellj It is the fault handling urgency score of cell j in BBU k, where N is the total number of cells in BBU k.

[0040] Furthermore, the method also includes:

[0041] For mobile networks of different standards, the urgency of fault handling at the single cell and single BBU levels is scored and sorted for processing.

[0042] Furthermore, the process of obtaining the specific fault handling priority ranking based on the urgency score of single cell and single BBU-level fault handling and the urgency of specific alarm handling time limits includes:

[0043] Calculate the urgency score for handling the fault in the cell or BBU where the alarm occurred;

[0044] Compare the fault handling urgency scores of the cells or BBUs involved in the cell-level or BBU-level pending alarm list. The lower the score, the higher the processing priority. The item with the lowest current score, i.e. the highest processing priority, is taken as the first item in the list.

[0045] Arrange other alarms according to their corresponding processing time limits and urgency levels.

[0046] The list order is dynamically updated based on alarm changes.

[0047] Secondly, this disclosure provides a network fault handling priority assessment system, the system comprising:

[0048] The data acquisition module is configured to collect basic data from the wireless network.

[0049] The processing module is configured to integrate the collected data based on different dimensions;

[0050] The scoring module is configured to perform sensitivity scoring of various indicators for a single cell in a single dimension; and,

[0051] The urgency of handling faults at the single cell and single BBU level is scored based on the sensitivity scores of each indicator in each dimension.

[0052] The sorting module is configured to prioritize specific fault handling based on the urgency score of a single cell and a single BBU-level fault handling and the urgency of the specific alarm handling time limit.

[0053] Thirdly, this disclosure provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes a network fault handling priority assessment method as described in any of the first aspects.

[0054] Fourthly, this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the network fault handling priority assessment method described in any of the first aspects above.

[0055] Beneficial effects:

[0056] The network fault handling priority assessment method, system, electronic equipment, and storage medium disclosed herein acquire basic data, integrate the collected data according to different dimensions, and differentiate the scoring of indicators for each dimension to obtain a single-cell and single-BBU level fault handling urgency score. The fault handling urgency score is then comprehensively considered in conjunction with the urgency of specific alarm handling time limits to obtain a specific fault handling priority ranking method. By comprehensively assessing the fault handling urgency of a cell or base station from multiple dimensions and combining it with the urgency of specific alarm handling time limits, the processing priority of alarms in the currently pending cells or base stations is ranked to guide maintenance personnel in determining which alarms require priority handling. This aims to minimize the impact of network faults and improve the efficiency of wireless network fault handling under limited manpower. Attached Figure Description

[0057] Figure 1 A flowchart illustrating a network fault handling priority assessment method provided in Embodiment 1 of this disclosure;

[0058] Figure 2 This is a schematic diagram of a fault handling priority ranking method provided in an embodiment of the present disclosure;

[0059] Figure 3 This is a schematic diagram of an apparatus for implementing a method for prioritizing fault handling in a mobile wireless network, as provided in Embodiment 2 of this disclosure.

[0060] Figure 4 This is an architecture diagram of a network fault handling priority assessment system provided in Embodiment 3 of this disclosure;

[0061] Figure 5 This is an architectural diagram of an electronic device provided in Embodiment 4 of this disclosure. Detailed Implementation

[0062] To enable those skilled in the art to better understand the technical solutions of this disclosure, the disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments and drawings described herein are merely for explaining the invention and are not intended to limit the invention.

[0063] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence; furthermore, in the absence of conflict, the embodiments and features in the embodiments of this disclosure can be arbitrarily combined with each other.

[0064] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. The singular forms “a,” “the,” and “the” as used in the embodiments of this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0065] In the following description, the use of suffixes such as “module,” “part,” or “unit” to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, “module,” “part,” or “unit” may be used interchangeably.

[0066] The following detailed embodiments illustrate the technical solutions of this disclosure and how they solve the aforementioned technical problems in the prior art. It is understood that in the embodiments of this application, the executing entity may perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the steps may be executed in different orders as presented in the embodiments of this application, and it is not necessary to execute all the operations in the embodiments of this application. Moreover, the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0067] Figure 1 This is a flowchart illustrating a network fault handling priority assessment method provided in Embodiment 1 of this disclosure, as shown below. Figure 1 As shown, the method includes:

[0068] Step S101: Collect basic wireless network data;

[0069] Step S102: Integrate the collected data according to different dimensions;

[0070] Step S103: Perform sensitivity scoring for each indicator in a single cell and single dimension;

[0071] Step S104: Score the urgency of single cell and single BBU level fault handling based on the sensitivity scores of each indicator in each dimension;

[0072] Step S105: Obtain the specific fault handling priority ranking based on the urgency score of single cell and single BBU level fault handling and the urgency of specific alarm handling time limits.

[0073] Due to differences in the service volume and location of each cell and BBU, the consequences of faults in different cells or BBUs may vary. Determining which cell or BBU alarms should be prioritized for handling, in order to maximize personnel efficiency and minimize the impact of faults with limited personnel, is crucial. To address this, this embodiment of the disclosure collects and processes basic wireless network data, integrates data based on different dimensions affecting cell sensitivity, and performs sensitivity scoring for each indicator of each dimension for each cell. Then, based on each dimension, a single-cell and single-BBU level fault handling urgency score is calculated. This urgency score is then combined with the urgency of the specific alarm handling time limit to obtain a specific fault handling priority ranking. Alarms are then processed according to the ranking, prioritizing alarms from the cells or BBUs with the greatest impact.

[0074] In general, a base station consists of a BBU (Base Station Unit), an RRU (Remote Radio Unit), and antennas. One BBU connects to three RRUs, one RRU corresponds to one antenna, one antenna corresponds to one sector, and one sector can correspond to multiple cells depending on the frequency band. Therefore, BBU alarms and cell alarms are at different levels. Consequently, cell-level and BBU-level alarms need to be assessed and prioritized based on their urgency.

[0075] The embodiments disclosed herein can prioritize the processing of alarms in currently pending cells or base stations, guiding maintenance personnel to determine which alarms need to be processed first. This enables the network to minimize its impact under limited manpower conditions and improve the efficiency of wireless network fault handling.

[0076] Furthermore, the collection of basic wireless network data includes:

[0077] Historical data for various indicators are collected from data sources based on a defined time period. These data sources include wireless network management systems, complaint handling systems, equipment technical specification documents, and wireless network resource management systems.

[0078] By collecting historical data over a predefined time period, we can obtain information about the business volume, complaint data, and hardware status of each community over a certain period of time. The defined time period for data collection can vary for each dimension of indicators and can be set according to the actual situation. For example, complaint indicators can be collected over six months or one year. Business volume indicators can be collected over one month, one quarter, or one year.

[0079] Furthermore, the different dimensions include: capacity, hardware, and perception;

[0080] The integration of collected data according to different dimensions includes:

[0081] For each indicator in the capacity dimension, the wireless network management data is collected at the hourly granularity of each cell, and the average value of each hour is calculated on a daily basis to serve as the daily indicator value for each cell in the capacity dimension.

[0082] For each hardware dimension indicator, based on the data obtained from professional network administrators, and supplemented by the equipment technical characteristic documents of the hardware device scenario, we obtained data for each hardware dimension indicator.

[0083] For the perception dimension indicators, the complaint handling system is used as the data source, and the specific cell is determined with the assistance of the wireless network professional network management and wireless network resource management system, which serve as the perception dimension indicators for that cell.

[0084] Assessing a cell's sensitivity across three dimensions—capacity, hardware, and sensing—allows for a balanced consideration of various factors. For instance, higher cell capacity load, a higher probability of hardware failure, or more sensitive sensing capabilities result in greater impact from alarms in that cell, necessitating priority handling. Data sources for each dimension are as follows:

[0085] Capacity: Source: Professional wireless network administrator;

[0086] Hardware: Sourced from professional wireless network management and equipment technical specification documents;

[0087] Perception: Complaint handling system, professional wireless network management system, wireless network resource management system;

[0088] After collecting data on indicators from various dimensions, data processing is required, such as outlier removal and missing value filling. Then, the data is classified and statistically processed according to the specific indicators.

[0089] Furthermore, the sensitivity scoring of each indicator in a single cell and single dimension includes:

[0090] For single-cell capacity metrics:

[0091] Thresh is determined by the following formula. Ci :

[0092] Thresh Ci =min{X Ci,max E i}

[0093] When X Ci,j ≥Thresh Ci At that time, S Ci,j =0, and count the number of cells that meet the conditions as M. Ci ;

[0094] When X Ci,j <Thresh Ci At that time, all eligible communities will be classified as X. Ci,j Sort X in ascending order, where X Ci,min Corresponding cell S Ci,j =T, other neighborhood scores are calculated as X Ci,j Scores are assigned based on a weighted ranking.

[0095] Among them, Thresh Ci X represents the zero threshold for capacity dimension indicator i, where j represents the cell number, and X... Ci,max E represents the maximum value of index item i in the capacity dimension of a single-system cell across the entire network. i X is the current network expansion threshold value for indicator item i. Ci,j S represents the index value of index item i in the capacity dimension of cell j. Ci,j Let be the sensitivity score of capacity dimension indicator i for community j, and T be the preset maximum score.

[0096] For single-cell hardware metrics:

[0097] By combining hardware information with the available time of the community managed by professional network administrators, and using AI classification algorithms, the threshold for a perfect score (Thresh) is determined. THi Thresh with a zero score 0H :

[0098] When X Hi , j ≥min{D i Thresh 0Hi When S Hi , j =0, where D i Recommended equipment-related threshold values ​​for the product manual;

[0099] When X Hi,j ≤Thresh THi At that time, S Hi,j =T;

[0100] Other neighborhood scores, based on indicator X Hi , j Proportional scoring;

[0101] Among them, X Hi,j S represents the indicator value of indicator item i in the hardware dimension of community j. Hi,j Let i be the sensitivity score of hardware dimension indicator item i for community j.

[0102] The capacity dimension is generally used to measure the busyness of community services. Therefore, the higher the value of each indicator, the busier the community services are and the lower the score. The preset maximum score T can be set by the user. For ease of calculation, it can be set to 10.

[0103] The capacity dimension metrics include CPU load, PRB (Physical Resource Block) utilization, and RRC (Radio Resource Control) connected users, which can be set according to actual conditions, and the sensitivity score of each dimension is calculated separately.

[0104] The scores of the other cells are calculated as X. Ci,j The scoring is based on a ranking ratio, including:

[0105] Set T to 10 points

[0106] When X Ci,j If the sorted value is within the interval (((x-1)*1 / 999),(x*1 / 999)], then S Ci,j =10-0.01*x, where x∈{1,999}.

[0107] For example, the RRC connection user count metric for a community is X. Ci =80, based on the previous Thresh calculation Ci =100, X is the number taken from the current network. Ci,min That is, the minimum number of RRC connected users in a single cell is 0; the value range is 0-100, then X Ci =80 points are ranked in the range That is, x = 800, and the score S for the RRC connected user count indicator of this cell is obtained. Ci =2.00, if X Ci =70, and similarly, x = 700, S Ci =3.00.

[0108] Hardware dimensions typically describe device hardware information using hardware type, hardware model, and hardware lifespan. Each indicator is calculated separately. For example, hardware lifespan is calculated using AI classification algorithms after determining relevant information such as the device's current usage time and recommended replacement threshold. These AI classification algorithms include, but are not limited to, kmedoids, CURE, CLIQUE, and FCM.

[0109] Furthermore, regarding the sensing dimension indicators for a single cell:

[0110] Based on the complaint data of each community, the number of complaints corresponding to each community's perception dimension indicator is determined, thereby obtaining the sensitivity score of that perception dimension indicator.

[0111] Perception dimension is generally used to measure the sensitivity of users in a wireless network coverage area to service quality. Metrics include historical complaint counts, complaint counts in the past six months, and complaint counts in a quarter. Based on the current operator's sensitivity to complaint issues, S is recommended. Pi,j (The sensitivity score of perception dimension indicator i for community j) is shown in the table below:

[0112] Table 1: Recommended S Pi,j Score

[0113] 0 5 and above 2 and above 2 4 4 3 5 1 6 2 8 1 10 0 0

[0114] It is known that the lower the score of each dimension indicator, the higher the capacity load of the community, the higher the probability of hardware failure, or the more sensitive the perception.

[0115] Furthermore, the scoring of the urgency of single-cell and single-BBU level fault handling based on the sensitivity scores of various indicators across different dimensions includes:

[0116] The urgency score for fault handling in a single cell is calculated using the following formula:

[0117]

[0118] Among them, S Cj S represents the capacity dimension scores of cell j. Hj S represents the scores of all hardware dimensions of cell j. Pj For all perception dimensions of cell j, N C N is the number of metrics included in the capacity dimension scoring. H To account for the number of metrics included in the hardware dimension scoring, N P The number of indicators included in the perception dimension score; α is the weight of the capacity dimension in the cell indicator sensitivity scoring system, β is the weight of the hardware dimension in the cell indicator sensitivity scoring system, and γ is the weight of the perception dimension in the cell indicator sensitivity scoring system; S cellj Let α+β+γ be the fault handling urgency score for cell j, where α+β+γ=1;

[0119] For the urgency score of single BBU-level fault handling, it is calculated by using the full index scores of all cells under the single BBU:

[0120]

[0121] Among them, S BBUk This is the fault handling urgency score of BBU with serial number k, S celljIt is the fault handling urgency score of cell j in BBU k, where N is the total number of cells in BBU k.

[0122] S can be obtained by summing the sensitivity scores of all indicators in the capacity dimension. Cj S was obtained by calculating in the same way. jj and S Pj The urgency score for fault handling in each cell can be calculated using the above-mentioned methods. [α, β, γ] is used to adjust the proportions of capacity, hardware, and perception dimensions in the cell's sensitivity assessment. This can be adjusted based on current network concerns. For example, if the current focus is on resolving easily complained or highly sensitive site faults, the weight β needs to be increased, ensuring α + β + γ = 1. The initial ratio of [α, β, γ] is α:β:γ = N. C :N H :N P .

[0123] The urgency score for single-cell fault handling is the overall score for a single cell, while the urgency score for single-BBU-level fault handling is the overall score for all cells under a single BBU. By using indicators and weights across all dimensions, the urgency of fault handling for single cells and single-BBU-level cells can be scored.

[0124] Furthermore, the method also includes:

[0125] For mobile networks of different standards, the urgency of fault handling at the single cell and single BBU levels is scored and sorted for processing.

[0126] Since the current mobile wireless network operates on multiple standards, including 3G, 4G, and 5G, to avoid the inherent differences in capacity, hardware, and perception dimensions between different wireless networks, the evaluation system of this disclosure embodiment is based on a single standard. That is, 3G cells and BBUs are scored and ranked uniformly, 4G cells and BBUs are ranked uniformly, and if 6G networks are commercially available in the future, 6G cells and BBUs will also be scored and ranked in comparison with other 6G cells and BBUs.

[0127] Furthermore, the process of obtaining the specific fault handling priority ranking based on the urgency score of single cell and single BBU-level fault handling and the urgency of specific alarm handling time limits includes:

[0128] Calculate the urgency score for handling the fault in the cell or BBU where the alarm occurred;

[0129] Compare the fault handling urgency scores of the cells or BBUs involved in the cell-level or BBU-level pending alarm list. The lower the score, the higher the processing priority. The item with the lowest current score, i.e. the highest processing priority, is taken as the first item in the list.

[0130] Arrange other alarms according to their corresponding processing time limits and urgency levels.

[0131] The list order is dynamically updated based on alarm changes.

[0132] Base station fault handling is dispatched based on alarms, divided into cell-level alarms and BBU-level alarms. The alarm handling sorting method is as follows: Figure 2 As shown, it includes:

[0133] When a new alarm is detected, calculate the urgency score for handling the fault.

[0134] Compare the urgency scores of fault handling to obtain the top alarm in the list, and compare the urgency of other alarm handling time limits to rank the other alarms.

[0135] If an alarm is cleared after being processed, and a new alarm occurs, the urgency score for fault handling will be recalculated.

[0136] In urgent situations requiring time-sensitive responses, the remaining processing time for an alarm is calculated as: Alarm occurrence time - Current time - T. alarmi , among which, T alarmi The remaining processing time for alarm i is the time limit. The shorter the remaining processing time, the higher the urgency ranking. If the remaining processing time is negative, that is, the alarm has exceeded the processing time limit and has not been processed, the higher the ranking.

[0137] For example, given a current cell-level alarm list (already sorted), where alarm A has the highest priority based on its rating, and alarm B has less time remaining before its processing deadline than alarm C, the sorting table would be as follows:

[0138]

[0139]

[0140] Now, a new alarm D has occurred. The fault handling urgency score of the cell corresponding to this alarm is lower than that of the cells corresponding to alarms A, B, and C, meaning this alarm has the highest priority for handling. Alarms A, B, and C are ranked according to their urgency and time limit. If the remaining time is: Alarm B < Alarm A < Alarm C, then the list of alarms to be handled will be updated as follows:

[0141] 1. Alarm D 2. Alarm B 3. Alarm A 4. Alarm C

[0142] Wireless network maintenance personnel prioritize alarms with the highest priority based on the actual number of maintenance personnel and the location of the fault, that is, they prioritize alarms with the highest urgency and the most urgent time limit for handling the fault.

[0143] After an alarm is cleared or added, the alarm list will be recalculated and sorted according to the established principles.

[0144] This embodiment utilizes network management data, resource data, complaint data, and basic equipment data, combined with weighted optimization, to differentiate the scoring of indicators for each dimension, thereby obtaining a single-cell and single-BBU level fault handling urgency score. The fault handling urgency score is then comprehensively considered in conjunction with the urgency of specific alarm handling time limits to obtain a specific fault handling priority ranking. The fault handling priority is continuously calculated iteratively based on changes in the list of pending alarms, and the list order is updated accordingly. This guides maintenance personnel to prioritize handling pending alarms with high cell capacity load, high hardware failure probability, and high sensor sensitivity, thereby minimizing the impact of network faults and improving the efficiency of wireless network fault handling under limited manpower.

[0145] Embodiment 2 of this disclosure also provides an apparatus for implementing a method for prioritizing fault handling in mobile wireless networks, such as... Figure 3 As shown, the device consists of a data acquisition module, a data processing module, a weight management module, a fault handling urgency scoring module, a fault handling remaining time calculation module, and a fault handling priority ranking module.

[0146] The data acquisition module is mainly responsible for collecting key data from the configuration files, performance files, and alarm files of the wireless professional network management system, as well as complaint data obtained from the complaint platform, equipment technical feature documents obtained from the equipment manufacturer's equipment introduction platform, and information on the corresponding management entity and location of the cell or BBU obtained from the wireless network resource management system, which forms the basis for subsequent statistical analysis.

[0147] The data processing module mainly integrates data sources according to different dimensions: 1) Capacity: sourced from the performance files of the professional wireless network management system, hourly indicators are sorted out, outliers are processed, and the results required for evaluation are calculated; 2) Hardware: sourced from the professional wireless network management system and equipment technical characteristic documents, hardware type, hardware model, and hardware service life are integrated, and the recommended service life of the hardware is obtained by filtering; 3) Perception: complaint handling system, professional wireless network management system, and wireless network resource management system; determine the specific cell involved in the complaint, and integrate the sensitivity of complaints in each cell;

[0148] The weight management module is mainly used for weight management in terms of capacity, hardware, and perception dimensions, and is used to score the urgency of fault handling.

[0149] The fault handling urgency scoring module is used to calculate the fault handling urgency scores at the cell and BBU levels in terms of capacity, hardware, and perception dimensions, based on the algorithm, and to serve as input for fault handling priority ranking.

[0150] The fault handling remaining time calculation module is used to calculate the remaining fault handling time for the current active alarm based on the processing time limit and occurrence time of various alarms before each re-sorting of fault handling priorities.

[0151] The fault handling priority sorting module determines the alarm with the highest priority in the list as the first alarm to be processed based on the fault handling urgency score of the cell or BBU corresponding to the current active alarm (if multiple alarms correspond to the same cell or BBU and the alarms occurred at the same time, then the multiple alarms are the first alarms to be processed). Then, it sorts the other alarms according to the remaining fault handling time of the remaining active alarms, with the alarms with the shorter remaining time appearing earlier in the list, thus outputting a list of alarms to be processed according to the fault handling priority.

[0152] Embodiment 3 of this disclosure also provides a network fault handling priority assessment system, such as Figure 4 As shown, the system includes:

[0153] The acquisition module 11 is configured to collect basic wireless network data.

[0154] Processing module 12 is configured to integrate the collected data according to different dimensions;

[0155] The scoring module 13 is configured to perform sensitivity scoring of various indicators for a single cell in a single dimension; and,

[0156] The urgency of handling faults at the single cell and single BBU level is scored based on the sensitivity scores of each indicator in each dimension.

[0157] The sorting module 14 is configured to sort the specific fault handling priorities based on the urgency score of single cell and single BBU level fault handling and the urgency of specific alarm handling time limits.

[0158] Furthermore, the acquisition module 11 is specifically configured as follows:

[0159] Historical data for various indicators are collected from data sources based on a defined time period. These data sources include wireless network management systems, complaint handling systems, equipment technical specification documents, and wireless network resource management systems.

[0160] Furthermore,

[0161] The different dimensions include: capacity, hardware, and perception;

[0162] The processing module 12 is specifically configured as follows:

[0163] For each indicator in the capacity dimension, the wireless network management data is collected at the hourly granularity of each cell, and the average value of each hour is calculated on a daily basis to serve as the daily indicator value for each cell in the capacity dimension.

[0164] For each hardware dimension indicator, based on the data obtained from professional network administrators, and supplemented by the equipment technical characteristic documents of the hardware device scenario, we obtained data for each hardware dimension indicator.

[0165] For the perception dimension indicators, the complaint handling system is used as the data source, and the specific cell is determined with the assistance of the wireless network professional network management and wireless network resource management system, which serve as the perception dimension indicators for that cell.

[0166] Furthermore, the scoring module 13 is specifically configured as follows:

[0167] For single-cell capacity metrics:

[0168] Thresh is determined by the following formula. Ci :

[0169] Thresh Ci =min{X Ci,max E i}

[0170] When X Ci,j ≥Thresh Ci At that time, S Ci,k =0, and count the number of cells that meet the conditions as M. Ci ;

[0171] When X Ci,j <Thresh Ci At that time, all eligible communities will be classified as X. Ci,j Sort X in ascending order, where X Ci,min Corresponding cell S Ci,j =T, other neighborhood scores are calculated as X Ci,j Scores are assigned based on a weighted ranking.

[0172] Among them, Thresh Ci X represents the zero threshold for capacity dimension indicator i, where j represents the cell number, and X... Ci,max E represents the maximum value of index item i in the capacity dimension of a single-system cell across the entire network. i X is the current network expansion threshold value for indicator item i. Ci,j S represents the index value of index item i in the capacity dimension of cell j. Ci,j Let be the sensitivity score of capacity dimension indicator i for community j, and T be the preset maximum score.

[0173] For single-cell hardware metrics:

[0174] By combining hardware information with the available time of the community managed by professional network administrators, and using AI classification algorithms, the threshold for a perfect score (Thresh) is determined. THi Thresh with a zero score 0Hi :

[0175] When X Hi,j ≥min{D i Thresh 0H When S Hi,j =0, where D i Recommended equipment-related threshold values ​​for the product manual;

[0176] When X Hi,j ≤Thresh THi At that time, S Hi,j =T;

[0177] Other neighborhood scores, based on indicator X Hi,j Proportional scoring;

[0178] Among them, X Hi,j S represents the indicator value of indicator item i in the hardware dimension of community j. Hi,j Let i be the sensitivity score of hardware dimension indicator item i for community j.

[0179] Furthermore, the scoring module 13 is specifically configured as follows:

[0180] The urgency score for fault handling in a single cell is calculated using the following formula:

[0181]

[0182] Among them, S Cj S represents the capacity dimension scores of cell j. Hj S represents the scores of all hardware dimensions of cell j. Pj For all perception dimensions of cell j, N C N is the number of metrics included in the capacity dimension scoring. H N is the number of metrics included in the hardware dimension scoring. P The number of indicators included in the perception dimension score; α is the weight of the capacity dimension in the cell indicator sensitivity scoring system, β is the weight of the hardware dimension in the cell indicator sensitivity scoring system, and γ is the weight of the perception dimension in the cell indicator sensitivity scoring system; S cellj Let α+β+γ be the fault handling urgency score for cell j, where α+β+γ=1;

[0183] For ease of calculation, T can be set to 10, S cellj The highest score is designed to be 100.

[0184] For the urgency score of single BBU-level fault handling, it is calculated by using the full index scores of all cells under the single BBU:

[0185]

[0186] Among them, SBBUk This is the fault handling urgency score of BBU with serial number k, S cellj It is the fault handling urgency score of cell j in BBU k, where N is the total number of cells in BBU k.

[0187] Furthermore, the scoring module 13 is also configured as follows:

[0188] For mobile networks of different standards, the urgency of fault handling at the single cell and single BBU levels is scored and sorted for processing.

[0189] Furthermore, the sorting module 14 is specifically configured as follows:

[0190] The scoring module 13 calculates the urgency score of the fault handling for the cell or BBU that triggered the alarm.

[0191] Compare the fault handling urgency scores of the cells or BBUs involved in the cell-level or BBU-level pending alarm list. The lower the score, the higher the processing priority. The item with the lowest current score, i.e. the highest processing priority, is taken as the first item in the list.

[0192] Arrange other alarms according to their corresponding processing time limits and urgency levels.

[0193] The list order is dynamically updated based on alarm changes.

[0194] The network fault handling priority assessment system of this disclosure is used to implement the network fault handling priority assessment method in the first method embodiment, so the description is relatively simple. For details, please refer to the relevant descriptions in the previous method embodiments, which will not be repeated here.

[0195] In addition, such as Figure 5 As shown, Embodiment 4 of this disclosure also provides an electronic device, including a memory 100 and a processor 200. The memory 100 stores a computer program. When the processor 200 runs the computer program stored in the memory 100, the processor 200 executes the various possible methods described above.

[0196] The memory 100 is connected to the processor 200. The memory 100 can be a flash memory, a read-only memory, or another type of memory. The processor 200 can be a central processing unit or a microcontroller.

[0197] Furthermore, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program, which is executed by a processor using the various possible methods described above.

[0198] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media includes, but is not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), Digital Video Disc (DVD) or other optical disc storage, cartridges, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer.

[0199] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this disclosure, and this disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

Claims

1. A method for prioritizing network fault handling, characterized in that, The method includes: Perform basic data collection for the wireless network; The collected data is integrated based on different dimensions, including: capacity, hardware, and perception. Sensitivity scores for various indicators in a single cell and dimension are calculated. Among them, the capacity dimension indicators include CPU load, PRB utilization, and RRC connected users; the hardware dimension indicators include hardware type, hardware model, and hardware usage years; and the perception dimension indicators include historical complaint count, complaint count in the past six months, and complaint count in a quarter. The urgency of fault handling for a single cell and a single baseband processing unit (BBU) is scored based on the sensitivity scores of each indicator in each dimension. The urgency score for fault handling of a single cell is the full indicator score of all dimensions of a single cell, and the urgency score for fault handling of a single BBU is the full indicator score of all cells under a single BBU. The priority ranking of specific fault handling is obtained based on the urgency score of single cell and single BBU level fault handling and the urgency of specific alarm handling time limit; where the urgency of alarm handling time limit is the remaining processing time of the alarm. The sensitivity scoring of each indicator in a single cell and single dimension includes: For single-cell capacity metrics: Determined by the following formula : when hour, And count the number of communities that meet the conditions. ; when At that time, all eligible communities will be classified as follows: Sort in ascending order, where Corresponding community Other neighborhoods' scores are based on... Scores are assigned based on a weighted ranking. in, Let j be the zero threshold for capacity dimension indicator i, and j represent the cell number. This represents the maximum value of index item i in the capacity dimension of single-system cells across the entire network. It is the current network expansion threshold value for indicator item i. Let i be the index value of index item i in the capacity dimension of cell j. Let be the sensitivity score of capacity dimension indicator i for community j, and T be the preset maximum score. For single-cell hardware metrics: By combining hardware information with the available time of the community managed by professional network administrators, and using AI classification algorithms, a maximum score threshold is determined. and zero score threshold : when hour, ,in, Recommended equipment-related threshold values ​​for the product manual; when hour, ; Other neighborhood scores, according to Proportional scoring; in, Let i be the indicator value of hardware dimension indicator item i in community j. Let i be the sensitivity score of hardware dimension indicator item i for community j.

2. The method according to claim 1, characterized in that, The collection of basic wireless network data includes: Historical data for various indicators are collected from data sources based on a defined time period. These data sources include wireless network management systems, complaint handling systems, equipment technical specification documents, and wireless network resource management systems.

3. The method according to claim 2, characterized in that, The integration of collected data according to different dimensions includes: For each indicator in the capacity dimension, the wireless network management data is collected at the hourly granularity of each cell, and the average value of each hour is calculated on a daily basis to serve as the daily indicator value for each cell in the capacity dimension. For each hardware dimension indicator, based on the data obtained from professional network administrators, and supplemented by the equipment technical characteristic documents of the hardware device scenario, we obtained data for each hardware dimension indicator. For the perception dimension indicators, the complaint handling system is used as the data source, and the specific cell is determined with the assistance of the wireless network professional network management and wireless network resource management system, which serve as the perception dimension indicators for that cell.

4. The method according to claim 1, characterized in that, The scoring of the urgency of single-cell and single-BBU level fault handling based on the sensitivity scores of various indicators across different dimensions includes: The urgency score for fault handling in a single cell is calculated using the following formula: in, These are the capacity dimension scores for cell j. These are the scores for all hardware dimensions of community j. For all perception dimensions of cell j, The number of metrics included in the capacity dimension score. To account for the number of metrics included in the hardware dimension scoring, The number of indicators included in the scoring of the perception dimension; The weight of capacity in the community indicator sensitivity scoring system. The weight of hardware dimensions in the community indicator sensitivity scoring system. The weight of the perception dimension in the community indicator sensitivity scoring system; The urgency score for fault handling in community j is given. ; For the urgency score of single BBU-level fault handling, it is calculated by using the full index scores of all cells under the single BBU: in, This is the fault handling urgency score for BBU with serial number k. It is the fault handling urgency score of cell j in BBU k, where N is the total number of cells in BBU k.

5. The method according to claim 1, characterized in that, The method further includes: For mobile networks of different standards, the urgency of fault handling at the single cell and single BBU levels is scored and sorted for processing.

6. The method according to claim 1, characterized in that, The method of obtaining the specific fault handling priority ranking based on the urgency score of single cell and single BBU level fault handling and the urgency of specific alarm handling time limits includes: Calculate the urgency score for handling the fault in the cell or BBU where the alarm occurred; Compare the fault handling urgency scores of the cells or BBUs involved in the cell-level or BBU-level pending alarm list. The lower the score, the higher the processing priority. The item with the lowest current score, i.e. the highest processing priority, is taken as the first item in the list. Arrange other alarms according to their corresponding processing time limits and urgency levels; The list order is dynamically updated based on alarm changes.

7. A network fault handling priority assessment system, characterized in that, The system includes: The data acquisition module is configured to collect basic data from the wireless network. The processing module is configured to integrate the collected data according to different dimensions, including: capacity, hardware, and perception. The scoring module is configured to score the sensitivity of various indicators across a single cell and dimension. These indicators include: capacity indicators (CPU load, PRB utilization, and RRC connected users); hardware indicators (hardware type, hardware model, and hardware age); and perception indicators (historical complaint count, number of complaints in the past six months, and number of complaints in one quarter). The urgency of fault handling for a single cell and a single BBU is scored based on the sensitivity scores of each indicator in each dimension. The urgency score for fault handling of a single cell is the full indicator score of all dimensions of a single cell, and the urgency score for fault handling of a single BBU is the full indicator score of all cells under a single BBU. The sorting module is configured to sort specific fault handling priorities based on the urgency score of single cell and single BBU level fault handling and the urgency of specific alarm handling time limits; where the urgency of alarm handling time limits is the remaining processing time of the alarm. The scoring module performs sensitivity scoring for each indicator in a single cell and a single dimension, specifically as follows: For single-cell capacity metrics: Determined by the following formula : when hour, And count the number of communities that meet the conditions. ; when At that time, all eligible communities will be classified as follows: Sort in ascending order, where Corresponding community Other neighborhoods' scores are based on... Scores are assigned based on a weighted ranking. in, Let j be the zero threshold for capacity dimension indicator i, and j represent the cell number. This represents the maximum value of index item i in the capacity dimension of single-system cells across the entire network. It is the current network expansion threshold value for indicator item i. Let i be the index value of index item i in the capacity dimension of cell j. Let be the sensitivity score of capacity dimension indicator i for community j, and T be the preset maximum score. For single-cell hardware metrics: By combining hardware information with the available time of the community managed by professional network administrators, and using AI classification algorithms, a maximum score threshold is determined. and zero score threshold : when hour, ,in, Recommended equipment-related threshold values ​​for the product manual; when hour, ; Other neighborhood scores, according to Proportional scoring; in, Let i be the indicator value of hardware dimension indicator item i in community j. Let i be the sensitivity score of hardware dimension indicator item i for community j.

8. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the network fault handling priority assessment method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the network fault handling priority assessment method as described in any one of claims 1-6.

Images