Fault analysis method and system applied to 5G base station transmission link

Abstract

The invention discloses a fault analysis method and system applied to a 5G base station transmission link, and the method comprises the following steps: obtaining alarm information of the 5G base station transmission link through integrating a real-time data stream processing mechanism and an incremental learning model; the alarm information is preprocessed; based on a time dimension, a topology dimension and a text dimension, converting the pre-processed alarm information into multi-dimensional vector representation; grouping aggregation is carried out by combining a DBSCAN algorithm; through an Incident root cause analysis algorithm, performing deep suspected root cause analysis on the grouped and aggregated alarm information, and determining suspected root cause alarms; and performing fault diagnosis through the knowledge graph and the diagnosis rule, generating a repair process and recording the whole process. According to the method, the accuracy and speed of fault positioning can be remarkably improved, the intelligence and automation level of fault analysis is enhanced, and meanwhile, the real-time performance and flexibility of fault processing are ensured, so that the operation and maintenance management of a 5G network is optimized, and a solid guarantee is provided for the stability and reliability of communication service.

Description

Technical Field

[0001] The present invention relates to the field of 5G communication networks, and more specifically to a fault analysis method and system applied to a 5G base station transmission link. Background Art

[0002] In 5G communication networks, base stations are key nodes that connect user devices to the core network, and the stability and reliability of their transmission links are crucial. With the large-scale deployment of 5G networks and the diversification of application scenarios, the data traffic on base station transmission links is growing exponentially, which places higher demands on fault detection, diagnosis, and repair.

[0003] From the perspective of the accuracy and efficiency of fault location, traditional fault analysis methods mostly rely on manual experience and step-by-step troubleshooting processes. This process is not only time-consuming, but also easily subject to the subjectivity and experience limitations of human judgment, resulting in inaccurate fault location or missing key information. It is often difficult to quickly identify and accurately locate the fault point, which prolongs the time for troubleshooting and recovery, affecting the continuity and stability of network services.

[0004] Secondly, the existing technology also has obvious deficiencies in the intelligence and automation of fault analysis. Although artificial intelligence and machine learning technologies have developed rapidly in recent years and have achieved remarkable results in many fields, their application in 5G base station fault analysis and processing still faces many challenges. On the one hand, the complexity of the algorithm model and the acquisition and labeling of training data limit the intelligence level of the existing technology; on the other hand, the consumption of computing resources and the optimization of the algorithm model also affect the automation level of fault analysis. These factors together lead to the fact that the existing technology still requires a lot of manual intervention and judgment in the fault analysis process, which reduces the efficiency and accuracy of fault handling.

[0005] Finally, from the perspective of real-time and flexibility of fault handling, traditional fault handling methods usually follow a series of fixed steps, including fault information collection, analysis, location, repair and verification, etc. The connection and conversion between these steps are often not smooth and efficient, resulting in a lengthy and inflexible fault handling process.

[0006] Therefore, how to design a fault analysis method applied to 5G base station transmission links, improve the accuracy and efficiency of fault location, and enhance the intelligence and automation of fault analysis is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0007] In view of this, the present invention provides a fault analysis method applied to 5G base station transmission links. By integrating real-time data stream processing, incremental learning, multi-dimensional vector construction and clustering, root cause analysis algorithm and knowledge graph, rapid fault location, diagnosis and repair are achieved. Compared with the existing technology, the real-time, intelligence, accuracy and operability of fault handling are significantly improved.

[0008] In order to achieve the above object, the present invention adopts the following technical solution:

[0009] In a first aspect, the present invention provides a fault analysis method applied to a 5G base station transmission link, comprising the following steps:

[0010] S1. Obtain the alarm information of 5G base station transmission link by integrating real-time data stream processing mechanism and incremental learning model;

[0011] S2. Preprocess the alarm information to obtain preprocessed alarm information;

[0012] S3, based on the time dimension, topology dimension and text dimension, convert the pre-processed warning letter into a multi-dimensional vector representation;

[0013] S4, based on multi-dimensional vector representation, combined with DBSCAN algorithm for grouping aggregation;

[0014] S5. Perform in-depth suspected root cause analysis on the grouped and aggregated alarm information through the Incident root cause analysis algorithm to determine the suspected root cause alarm.

[0015] S6. Use knowledge graphs and diagnostic rules to diagnose suspected root cause alarms, generate repair processes, and record the entire process.

[0016] Preferably, the S1 comprises:

[0017] Receive the alarm information of each node on the 5G base station transmission link through the Kafka message queue model; wherein, multiple consumer groups are set in the Kafka message queue model, and each consumer group processes the corresponding type of alarm information respectively;

[0018] Combined with online learning algorithms, an incremental learning model is constructed to dynamically adjust the internal parameters of the alarm information received based on the Kafka message queue model;

[0019] Apply timestamps to dynamically adjusted alarm information, record the exact time of occurrence and arrival of each alarm information at the system, and classify and store the alarm information with timestamps by type.

[0020] Preferably, the dynamic adjustment of internal parameters of the alarm information received based on the Kafka message queue model includes:

[0021] Monitor the alarm information flow of the Kafka message queue in real time, and dynamically adjust the number of consumer groups according to the flow changes; and analyze the type distribution of alarm information, and dynamically adjust the number of consumer instances in each consumer group according to the number of different types of alarm information.

[0022] Preferably, said S2 comprises:

[0023] Read alarm information with timestamps and perform standardization and normalization;

[0024] Based on the standardized and normalized alarm information, the pre-trained NLP model is used to parse the text alarm content, extract key information and convert it into structured data;

[0025] Based on structured data, construct alarm time series and network topology diagrams.

[0026] Preferably, the S3 comprises:

[0027] Converting the timestamp into a relative time value relative to a reference time, and normalizing the relative time value to a preset interval to form a time dimension vector;

[0028] Determine the network node position corresponding to the alarm information by using the network topology relationship diagram, and encode the network node position into a topology dimension vector;

[0029] Parse the text alarm content, extract key information and convert it into word vectors or sentence vectors to form text dimension vectors;

[0030] The time dimension vector, topology dimension vector and text dimension vector are combined, and linear dimensionality reduction is performed in conjunction with the PCA algorithm to generate a multi-dimensional vector representation of the alarm information.

[0031] Preferably, the generating of the multi-dimensional vector representation of the warning information further includes: performing vector similarity calculation; the vector similarity calculation includes:

[0032] Calculate the cosine similarity between the multidimensional vector representation of each warning information and the multidimensional vector representation of all other warning information;

[0033] Based on a preset similarity threshold, when the cosine similarity calculation result of any two alarm information exceeds the threshold, the two alarm information are determined to be duplicate or highly similar;

[0034] After repeated or highly similar alarm information is identified, one of the pieces of alarm information is selected as representative alarm information, and the remaining repeated or highly similar alarm information is deduplicated.

[0035] Preferably, the S4 comprises:

[0036] loading the multidimensional vector representation;

[0037] Based on the distribution characteristics of the alarm information and the clustering requirements, the neighborhood size in the DBSCAN algorithm and the minimum number of points required to form a dense area are set;

[0038] Conduct cluster analysis and obtain cluster analysis results;

[0039] Based on the cluster analysis results, the alarm information belonging to the same group is merged into one alarm group, and a unique identifier is assigned to each alarm group.

[0040] Preferably, the S5 comprises:

[0041] Load the alarm group and its identifier into the Incident root cause analysis algorithm;

[0042] Extract key features related to root cause analysis from each alarm and convert them into numerical vectors; the key features include: alarm type, severity, occurrence time, impact scope, and associated network elements;

[0043] Combine the pre-trained gradient boosting tree model to perform root cause analysis, predict the suspected root cause alarms of each alarm group, and generate a ranked list of suspected root cause alarms;

[0044] Based on the ranked list of suspected root cause alarms, a final suspected root cause alarm and a corresponding alarm group identifier are determined.

[0045] Preferably, the S6 comprises:

[0046] Load the knowledge graph and diagnostic rule base; the knowledge graph includes base station equipment, transmission links, alarm types and their correlations in the 5G base station transmission link; the diagnostic rule base includes preset rules and logical reasoning rules for different alarm types, equipment status and historical fault handling experience;

[0047] Match the suspected root cause alarm information with the nodes and relationships in the loaded knowledge graph, and analyze the associated nodes and relationships to determine the possible fault propagation path and impact range;

[0048] Combined with the diagnostic rule base, logical reasoning is performed to analyze the relevance, time sequence, and equipment status of alarm information, predict the cause of the fault, and generate a preliminary fault diagnosis report;

[0049] Generate a repair process for the fault based on the fault diagnosis report and pre-defined repair strategy;

[0050] Perform the corresponding repair operations, record the operation results, timestamps and possible abnormal conditions of each step in real time, and obtain a complete fault handling log.

[0051] In a second aspect, the present invention provides a fault analysis system applied to a 5G base station transmission link, comprising:

[0052] Data acquisition module: used to obtain the alarm information of 5G base station transmission links by integrating real-time data stream processing mechanism and incremental learning model;

[0053] Preprocessing module: used to preprocess the alarm information to obtain the preprocessed alarm information;

[0054] Multi-dimensional vector representation generation module: used to convert the pre-processed warning message into a multi-dimensional vector representation based on the time dimension, topology dimension and text dimension;

[0055] Grouping aggregation module: used for grouping aggregation based on multi-dimensional vector representation combined with DBSCAN algorithm;

[0056] Root cause analysis module: used to perform in-depth suspected root cause analysis on grouped and aggregated alarm information through the Incident root cause analysis algorithm to determine the suspected root cause alarm;

[0057] Fault diagnosis and repair module: used to diagnose suspected root cause alarms through knowledge graphs and diagnostic rules, generate repair processes and record the entire process.

[0058] It can be seen from the above technical solution that compared with the prior art, the technical solution of the present invention has the following advantages:

[0059] Beneficial effects:

[0060] 1. By using the Kafka message queue model and online learning algorithm, internal parameters can be dynamically adjusted to adapt to the changes in different types of alarm information flow, ensuring that the system can still maintain efficient processing capabilities and response speed when facing large-scale data. And through timestamp marking and classified storage, the time attribute of the alarm information can be preserved, which helps to more accurately locate the time point when the fault occurs, thereby improving the accuracy of fault analysis.

[0061] 2. By converting the alarm information into multi-dimensional vectors and combining PCA dimensionality reduction technology with vector similarity calculation, the correlation analysis between alarm information is enhanced, and data redundancy is effectively reduced, improving the efficiency and quality of cluster analysis. In particular, duplicate or highly similar alarm information is deduplicated to avoid unnecessary waste of resources and improve the speed and accuracy of fault diagnosis.

[0062] 3. With the support of knowledge graph and diagnostic rule base, we can deeply explore the complex relationship behind the alarm, predict the possible fault propagation path and its impact range, and then generate a more scientific and reasonable repair process. The whole process emphasizes the characteristics of automation and intelligence. Every link from alarm reception to fault repair has been optimized, ensuring the timeliness and effectiveness of fault handling and improving the efficiency and reliability of operation and maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0064] Figure 1 A flow chart of a fault analysis method applied to a 5G base station transmission link provided in an embodiment of the present invention;

[0065] Figure 2 A schematic diagram of a specific implementation process of the fault analysis method provided by an embodiment of the present invention;

[0066] Figure 3 A structural framework diagram of a fault analysis system applied to a 5G base station transmission link provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Embodiment 1;

[0069] like Figure 1 As shown, this embodiment provides a fault analysis method applied to a 5G base station transmission link, comprising the following steps:

[0070] S1. Obtain the alarm information of 5G base station transmission link by integrating real-time data stream processing mechanism and incremental learning model;

[0071] S2. Preprocess the alarm information to obtain preprocessed alarm information;

[0072] S3, based on the time dimension, topology dimension and text dimension, convert the pre-processed warning letter into a multi-dimensional vector representation;

[0073] S4, based on multi-dimensional vector representation, combined with DBSCAN algorithm for grouping aggregation;

[0074] S5. Perform in-depth suspected root cause analysis on the grouped and aggregated alarm information through the Incident root cause analysis algorithm to determine the suspected root cause alarm.

[0075] S6. Use knowledge graphs and diagnostic rules to diagnose suspected root cause alarms, generate repair processes, and record the entire process.

[0076] This method obtains alarm information by integrating real-time data stream processing mechanism and incremental learning model, and finally generates repair process and records the whole process after preprocessing, multi-dimensional vector representation conversion, group aggregation based on DBSCAN algorithm, deep suspected root cause analysis and knowledge graph-assisted fault diagnosis. This method significantly improves the accuracy and speed of fault location, reduces the dependence on manual intervention, enhances the automation and intelligence level of fault handling, ensures the continuity and stability of network services, and thus provides an efficient, intelligent and flexible operation and maintenance management solution for 5G base station transmission links.

[0077] The above steps and related technical features are further described in detail below:

[0078] In this embodiment S1, alarm information of a 5G base station transmission link is obtained by integrating a real-time data stream processing mechanism and an incremental learning model; specifically, the following steps are included:

[0079] The alarm information of each node on the 5G base station transmission link is received through the Kafka message queue model. Multiple consumer groups are set in the Kafka message queue model, and each consumer group processes the corresponding type of alarm information respectively. This design not only improves the processing efficiency, but also ensures the isolation between different types of alarm information and avoids mutual interference.

[0080] An incremental learning model is constructed in combination with an online learning algorithm to dynamically adjust the internal parameters of the alarm information received based on the Kafka message queue model; this includes: real-time monitoring of the alarm information flow of the Kafka message queue, and dynamically adjusting the number of consumer groups according to traffic changes; for example, increasing the number of consumer groups during peak traffic periods to disperse the load, and reducing the number of consumer groups during trough periods to save resources.

[0081] In addition, the type distribution of alarm information is analyzed, and the number of consumer instances in each consumer group is dynamically adjusted according to the number of different types of alarm information. If a certain type of alarm information suddenly increases, the system will automatically increase the number of consumer instances corresponding to this type of alarm to speed up processing; otherwise, the number of instances will be reduced to avoid resource waste.

[0082] Apply timestamps to dynamically adjusted alarm information, record the exact time of occurrence and arrival of each alarm information at the system, and classify and store the alarm information with timestamps by type.

[0083] This step achieves efficient collection and preliminary processing of 5G base station transmission link alarm information, laying a solid data foundation for subsequent fault analysis and diagnosis. This process emphasizes the characteristics of real-time, automation, and intelligence, aiming to improve the speed and accuracy of fault handling while reducing operation and maintenance costs and complexity. In particular, the combination of the Kafka message queue model and the incremental learning model ensures that the system can flexibly respond to changes in different types of alarm information traffic, and further optimizes the system's performance and resource utilization by dynamically adjusting the number of consumer groups and consumer instances.

[0084] In this embodiment S2, the alarm information is preprocessed to obtain the preprocessed alarm information; specifically, it includes:

[0085] Read the alarm information with timestamps and perform standardization and normalization. Standardization converts the data into a form with zero mean and unit variance, while normalization scales the data to a specific interval (such as [0,1]). This can eliminate the impact of dimensions, enable different types of alarm information to be compared on the same scale, and improve the accuracy of data analysis.

[0086] Based on the standardized and normalized alarm information, the pre-trained NLP model is used to parse the text alarm content, extract key information and convert it into structured data; after being trained with a large amount of text data, the NLP model can effectively understand and extract key elements in the alarm information, such as fault type, affected equipment or components, possible causes, etc.

[0087] Based on structured data, we build alarm time series and network topology diagrams. Time series analysis helps identify alarm patterns and trends, which is important for predicting future failures. The network topology diagram not only shows the connection between network nodes, but also annotates alarm-related information, such as the specific location of the alarm and its impact range.

[0088] The above preprocessing steps improve the quality and consistency of alarm information, and lay a solid foundation for subsequent multi-dimensional analysis and fault diagnosis. In particular, the NLP model is used to parse the text alarm content, realizing the transformation from unstructured to structured data, which greatly facilitates the further processing and mining of data.

[0089] In this embodiment S3, based on the time dimension, the topology dimension and the text dimension, the pre-processed warning message is converted into a multi-dimensional vector representation; specifically, it includes:

[0090] The timestamp is converted into a relative time value relative to a reference time, and the relative time value is normalized to a preset interval to form a time dimension vector; the time dimension vector is generated by converting the timestamp in the alarm information into a relative time value relative to a reference time (such as the system startup time or a fixed reference point), and then normalizing this relative time value to a preset interval to ensure that the time attributes of different alarms are compared on the same scale.

[0091] The network topology relationship diagram is used to determine the network node position corresponding to the alarm information, and the network node position is encoded into a topology dimension vector; the topology dimension vector is used to determine the network node position associated with each alarm information, and these positions are encoded into a vector form. The encoding method can be based on the specific position, connectivity or other topological features of the network node in the network structure, and can be implemented using One-Hot encoding or embedded encoding.

[0092] Parse the text alarm content, extract key information and convert it into word vectors or sentence vectors to form text dimension vectors; the generated text dimension vectors can quantitatively describe the specific content and nature of the alarm.

[0093] The time dimension vector, topology dimension vector and text dimension vector are combined, and linear dimension reduction is performed in combination with the PCA algorithm to generate a multi-dimensional vector representation of the alarm information. In order to reduce data redundancy and improve computational efficiency, the principal component analysis algorithm PCA is used to perform linear dimension reduction on the multi-dimensional vector. PCA identifies the main direction of change in the data, retains the most important feature information, and reduces the dimension at the same time, simplifying the complexity of subsequent analysis.

[0094] Furthermore, generating a multi-dimensional vector representation of the warning information further includes: performing vector similarity calculation; the vector similarity calculation includes:

[0095] Calculate the cosine similarity between the multidimensional vector representation of each warning information and the multidimensional vector representation of all other warning information;

[0096] Based on a preset similarity threshold, when the cosine similarity calculation result of any two alarm information exceeds the threshold, the two alarm information are determined to be duplicate or highly similar;

[0097] After repeated or highly similar alarm information is identified, one of the pieces of alarm information is selected as representative alarm information, and the remaining repeated or highly similar alarm information is deduplicated.

[0098] This step combines information from three dimensions: time, topology, and text, making alarm analysis more comprehensive and in-depth. It enhances the intelligence level of fault diagnosis and lays a solid foundation for subsequent advanced functions such as cluster analysis and root cause analysis.

[0099] In this embodiment S4, grouping and aggregation are performed based on multidimensional vector representation and combined with the DBSCAN algorithm; specifically, the following steps are included:

[0100] loading the multidimensional vector representation;

[0101] Based on the distribution characteristics of the alarm information and the clustering requirements, the neighborhood size in the DBSCAN algorithm and the minimum number of points required to form a dense area are set; the neighborhood size determines the local density range considered by the algorithm during the clustering process, while the minimum number of points is used to determine whether an area is dense enough to form a cluster. The setting of these two parameters needs to comprehensively consider the actual situation of the alarm information and the clustering target to ensure the accuracy and effectiveness of the clustering results.

[0102] Perform cluster analysis to obtain cluster analysis results; the DBSCAN algorithm clusters closely connected points in space together, while points far away from any dense area are marked as noise. After the cluster analysis is completed, the system generates cluster results, including the cluster label to which each alarm information belongs. If an alarm information does not belong to any cluster, it is marked as a noise point.

[0103] Based on the cluster analysis results, the alarm information belonging to the same group is merged into one alarm group, and a unique identifier is assigned to each alarm group. Based on the cluster analysis results, the alarm information belonging to the same group (the same cluster) is merged into one alarm group. Alarms that are adjacent in time and space and have similar semantics are aggregated together, simplifying the complexity of fault analysis. A unique identifier is assigned to each alarm group. It is used for subsequent tracking and management to facilitate the rapid location and processing of specific alarm sets.

[0104] It not only achieves effective grouping and aggregation of alarm information, but also improves the accuracy and efficiency of fault analysis. In particular, the combination of multidimensional vector representation and DBSCAN algorithm can automatically identify alarm sets with similar characteristics, thereby helping operation and maintenance personnel to find potential problems more quickly and improve the speed and accuracy of fault handling.

[0105] In this embodiment S5, the Incident root cause analysis algorithm is used to perform in-depth suspected root cause analysis on the grouped and aggregated alarm information to determine the suspected root cause alarm, specifically including:

[0106] Load the alarm group and its identifier into the Incident root cause analysis algorithm;

[0107] Extract key features related to root cause analysis from each alarm and convert them into numerical vectors; the key features include: alarm type, severity, occurrence time, impact scope, and associated network elements; specifically, alarm type: describes the specific category or nature of the fault. Severity: reflects the importance and urgency of the alarm, usually divided into different levels. Occurrence time: records the exact time of occurrence of the alarm for time series analysis. Impact scope: evaluates the impact of the alarm on the network and services, such as how many users or services are affected. Associated network elements: identifies the network devices or components involved and understands the possible propagation paths of the fault.

[0108] Combined with the pre-trained gradient boosting tree model, root cause analysis is performed to predict the suspected root cause alarms for each alarm group and generate a ranked list of suspected root cause alarms; the gradient boosting tree model can effectively handle nonlinear relationships and complex feature interactions, and is suitable for classification and regression tasks. For each alarm group, the gradient boosting tree model is used to predict the suspected root cause alarms and generate a ranked list containing the probability scores of each alarm. The higher the score, the greater the possibility that the alarm is the root cause.

[0109] Based on the ranked list of suspected root cause alarms, a final suspected root cause alarm and a corresponding alarm group identifier are determined.

[0110] This step realizes in-depth suspected root cause analysis of grouped and aggregated alarm information, significantly improving the accuracy and efficiency of fault diagnosis. In particular, the combination of the Incident root cause analysis algorithm and the pre-trained gradient boosting tree model enables the system to automatically identify the most likely root cause alarm, reducing the need for manual intervention and improving the automation level of operation and maintenance management.

[0111] In this embodiment S6, the suspected root cause alarm is diagnosed through the knowledge graph and the diagnosis rules, a repair process is generated and the whole process is recorded, which specifically includes:

[0112] Load the knowledge graph and diagnostic rule base; the knowledge graph includes base station equipment, transmission links, alarm types and their correlations in the 5G base station transmission link; the diagnostic rule base includes preset rules and logical reasoning rules for different alarm types, equipment status and historical fault handling experience;

[0113] Match the suspected root cause alarm information with the nodes and relationships in the loaded knowledge graph, and analyze the associated nodes and relationships to determine the possible fault propagation path and impact range;

[0114] Combined with the diagnostic rule base, logical reasoning is performed to analyze the relevance, time sequence, and equipment status of alarm information, predict the cause of the fault, and generate a preliminary fault diagnosis report;

[0115] Generate a repair process for the fault based on the fault diagnosis report and pre-defined repair strategy;

[0116] Perform the corresponding repair operations, record the operation results, timestamps and possible abnormal conditions of each step in real time, and obtain a complete fault handling log.

[0117] This step, combined with the application of knowledge graph and diagnostic rule base, can intelligently analyze the root cause of the fault and provide a scientific and reasonable repair plan. It enhances the automation and intelligence level of fault handling, improves the efficiency and reliability of operation and maintenance management, and ensures the stable operation of 5G base station transmission links.

[0118] This embodiment provides a fault analysis method applied to 5G base station transmission links, which obtains alarm information by integrating real-time data stream processing mechanism and incremental learning model, and finally generates a repair process and records the whole process after preprocessing, multi-dimensional vector representation conversion, group aggregation based on DBSCAN algorithm, deep suspected root cause analysis and knowledge graph-assisted fault diagnosis. This method significantly improves the accuracy and speed of fault location, reduces the dependence on manual intervention, enhances the automation and intelligence level of fault handling, ensures the continuity and stability of network services, and provides an efficient, intelligent and flexible operation and maintenance management solution for 5G base station transmission links.

[0119] Embodiment 2;

[0120] An operator is operating a 5G network covering a wide area, which includes multiple base stations. Due to the large scale of the network and the dense traffic, various types of alarm information frequently appear on the base station transmission link. In order to ensure the stability of the network and the quality of service, an efficient fault analysis method is needed to quickly locate and repair the problem.

[0121] like Figure 2 As shown, the specific implementation steps include:

[0122] 1) Obtain alarm information;

[0123] The Kafka message queue model is used to receive alarm information from each base station node in real time. Each alarm information contains the following data types:

[0124] Timestamp: a time string in ISO 8601 format; Alarm ID: a unique string identifier; Alarm type: an enumeration type, specifically "transmission link interruption"; Severity: an integer ranging from 1 to 5, where 5 is the most severe; Device ID: a string identifying a specific base station device; Text description: a string describing the alarm content in detail;

[0125] In Kafka, a consumer group is set up to handle transmission link related alarms, specifically the transmission link alarm group.

[0126] And monitor the traffic of Kafka message queue in real time, add consumer groups to distribute the load during peak hours, and reduce resource consumption during low periods. The specific implementation includes: using Kafka's built-in monitoring tool to check the depth of the message queue once a minute. If the message queue depth exceeds the set threshold (such as 1000), add a consumer group; if it is lower than the threshold for 10 consecutive minutes, reduce a consumer group. Each alarm message is assigned a timestamp and stored by type. The alarm information is stored in different tables of the distributed database Cassandra, each table corresponding to an alarm type.

[0127] 2) Pre-processing alarm information;

[0128] Convert the timestamp from ISO 8601 format to Unix timestamp (seconds), normalize the severity and scale it to the [0,1] interval; and use the BERT model to parse the text description, extract key information such as fault type and affected devices, and convert it into structured data. Specifically, extract {"type":"transmission link","status":"interruption"} from "transmission link interruption".

[0129] Based on structured data, we build alarm time series and network topology diagrams to help understand the alarm occurrence patterns and potential impact scope.

[0130] 3) Multidimensional vector representation;

[0131] Time dimension vector: convert the Unix timestamp into a relative time value relative to the base time and normalize it to the interval [0,1]; Topology dimension vector: use the network topology diagram to determine the network node location corresponding to the alarm, and encode it into a One-Hot vector or an embedded vector. Text dimension vector: parse the text alarm content, extract key information and convert it into a word vector or sentence vector.

[0132] The principal component analysis algorithm is combined to perform linear dimensionality reduction on the above multidimensional vectors to simplify the data complexity and retain the first 100 principal components.

[0133] When calculating the cosine similarity between alarm information, duplicate or highly similar alarms are identified and deduplication is performed. Specifically, the similarity threshold is set to 0.9. When the cosine similarity of any two alarm information exceeds the threshold, they are determined to be duplicate alarms.

[0134] 4) Group aggregation;

[0135] Load the multidimensional vector representation after the multidimensional vector representation step 3); and according to the alarm distribution characteristics and clustering requirements, set the neighborhood size in the DBSCAN algorithm to 0.5 and the minimum number of points to 5. Perform DBSCAN clustering analysis to obtain clustering results, merge the alarm information belonging to the same group into one alarm group, and assign a unique identifier GROUP_001.

[0136] 5) Root cause analysis;

[0137] The alarm groups and their identifiers generated in the grouping and aggregation step 4) are loaded into the Incident root cause analysis algorithm; key features (such as alarm type, severity, occurrence time, etc.) are extracted from each alarm and converted into numerical vectors.

[0138] Combined with the pre-trained gradient boosting tree model, root cause analysis is performed to generate a ranked list of suspected root cause alarms, and finally the most likely root cause alarm and its corresponding alarm group identifier are determined.

[0139] 6) Fault diagnosis and repair;

[0140] Load the knowledge graph containing base station equipment, transmission links, alarm types and their associations in the 5G base station transmission link, as well as the diagnostic rule base for different alarm types. For example, the knowledge graph records the connection relationship between base station equipment, and the diagnostic rule base contains specific repair strategies for different types of alarms.

[0141] Match the suspected root cause alarm information with the nodes and relationships in the knowledge graph to analyze the possible fault propagation path and impact range; perform logical reasoning in conjunction with the diagnostic rule base to generate a preliminary fault diagnosis report.

[0142] Furthermore, a specific repair process is generated based on the diagnostic report and the predefined repair strategy. For the fault type of "transmission link interruption", the repair process may include the following steps:

[0143] Check the physical connection: Send a technician to the affected base station to check whether the fiber connection is loose or damaged. Test the signal strength: Use an optical power meter to measure the signal strength at both ends of the fiber to confirm whether there is attenuation. Replace the damaged fiber: If the fiber is found to be obviously damaged, replace the damaged section of fiber immediately. Restart related equipment: Restart the equipment involved in the transmission link to ensure that the configuration is correct. Verify the repair effect: Retest the transmission link performance to ensure that it has returned to normal.

[0144] Finally, when performing repair operations, the operation results, timestamps and abnormal conditions of each step are recorded in real time to form a complete fault handling log.

[0145] Through the application of the above technical solutions, especially for the specific type of alarm information such as "transmission link interruption", operators can achieve efficient and accurate fault analysis and rapid repair. This process not only reduces the need for manual intervention and improves operation and maintenance efficiency, but also ensures the continuity and stability of network services.

[0146] Embodiment 3;

[0147] like Figure 3 As shown, this embodiment provides a fault analysis system applied to a 5G base station transmission link, including:

[0148] Data acquisition module: used to obtain the alarm information of 5G base station transmission links by integrating real-time data stream processing mechanism and incremental learning model;

[0149] Preprocessing module: used to preprocess the alarm information to obtain the preprocessed alarm information;

[0150] Multi-dimensional vector representation generation module: used to convert the pre-processed warning message into a multi-dimensional vector representation based on the time dimension, topology dimension and text dimension;

[0151] Grouping aggregation module: used for grouping aggregation based on multi-dimensional vector representation combined with DBSCAN algorithm;

[0152] Root cause analysis module: used to perform in-depth suspected root cause analysis on grouped and aggregated alarm information through the Incident root cause analysis algorithm to determine the suspected root cause alarm;

[0153] Fault diagnosis and repair module: used to diagnose suspected root cause alarms through knowledge graphs and diagnostic rules, generate repair processes and record the entire process.

[0154] This embodiment provides a fault analysis system applied to 5G base station transmission links, which includes a data acquisition module, a preprocessing module, a multi-dimensional vector representation generation module, a group aggregation module, a root cause analysis module, and a fault diagnosis and repair module. It obtains alarm information by integrating a real-time data stream processing mechanism and an incremental learning model, and finally generates a repair process and records the entire process after preprocessing, multi-dimensional vector representation conversion, group aggregation based on the DBSCAN algorithm, deep suspected root cause analysis, and knowledge graph-assisted fault diagnosis. The system significantly improves the accuracy and speed of fault location, reduces the need for manual intervention, enhances the automation and intelligence level of fault handling, and ensures the stable operation and service quality of the 5G base station transmission link.

[0155] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0156] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fault analysis method applied to a 5G base station transmission link, characterized in that: The following steps are involved: S1. Obtain the alarm information of 5G base station transmission link by integrating real-time data stream processing mechanism and incremental learning model; S2. Preprocess the alarm information to obtain preprocessed alarm information; S3, based on the time dimension, topology dimension and text dimension, convert the pre-processed warning letter into a multi-dimensional vector representation; S4, based on multi-dimensional vector representation, combined with DBSCAN algorithm for grouping aggregation; S5. Perform in-depth suspected root cause analysis on the grouped and aggregated alarm information through the Incident root cause analysis algorithm to determine the suspected root cause alarm. S6. Use knowledge graphs and diagnostic rules to diagnose suspected root cause alarms, generate repair processes, and record the entire process.

2. According to claim 1, a fault analysis method applied to a 5G base station transmission link is characterized in that: Said S1 comprises: Receive the alarm information of each node on the 5G base station transmission link through the Kafka message queue model; wherein, multiple consumer groups are set in the Kafka message queue model, and each consumer group processes the corresponding type of alarm information respectively; Combined with online learning algorithms, an incremental learning model is constructed to dynamically adjust the internal parameters of the alarm information received based on the Kafka message queue model; Apply timestamps to dynamically adjusted alarm information, record the exact time of occurrence and arrival of each alarm information at the system, and classify and store the alarm information with timestamps by type.

3. According to claim 2, a fault analysis method applied to a 5G base station transmission link is characterized in that: The dynamic adjustment of internal parameters of the alarm information received based on the Kafka message queue model includes: Monitor the alarm information flow of the Kafka message queue in real time, and dynamically adjust the number of consumer groups according to the flow changes; and analyze the type distribution of alarm information, and dynamically adjust the number of consumer instances in each consumer group according to the number of different types of alarm information.

4. According to claim 1, a fault analysis method applied to a 5G base station transmission link is characterized in that: The S2 comprises: Read alarm information with timestamps and perform standardization and normalization; Based on the standardized and normalized alarm information, the pre-trained NLP model is used to parse the text alarm content, extract key information and convert it into structured data; Based on structured data, construct alarm time series and network topology diagrams.

5. According to claim 1, a fault analysis method applied to a 5G base station transmission link is characterized in that: The S3 includes: Convert the timestamp into a relative time value relative to a reference time, and normalize the relative time value to a preset interval to form a time dimension vector; Determine the network node position corresponding to the alarm information by using the network topology relationship diagram, and encode the network node position into a topology dimension vector; Parse the text alarm content, extract key information and convert it into word vectors or sentence vectors to form text dimension vectors; The time dimension vector, topology dimension vector and text dimension vector are combined, and linear dimensionality reduction is performed in conjunction with the PCA algorithm to generate a multi-dimensional vector representation of the alarm information.

6. A fault analysis method for a 5G base station transmission link according to claim 5, characterized in that: The generating of the multi-dimensional vector representation of the warning information further includes: performing vector similarity calculation; the vector similarity calculation includes: Calculate the cosine similarity between the multidimensional vector representation of each warning information and the multidimensional vector representation of all other warning information; Based on a preset similarity threshold, when the cosine similarity calculation result of any two alarm information exceeds the threshold, the two alarm information are determined to be duplicate or highly similar; After repeated or highly similar alarm information is identified, one of the pieces of alarm information is selected as representative alarm information, and the remaining repeated or highly similar alarm information is deduplicated.

7. A fault analysis method for a 5G base station transmission link according to claim 1, characterized in that: The S4 comprises: loading the multidimensional vector representation; Based on the distribution characteristics of the alarm information and the clustering requirements, the neighborhood size in the DBSCAN algorithm and the minimum number of points required to form a dense area are set; Conduct cluster analysis and obtain cluster analysis results; Based on the cluster analysis results, the alarm information belonging to the same group is merged into one alarm group, and a unique identifier is assigned to each alarm group.

8. A fault analysis method for a 5G base station transmission link according to claim 1, characterized in that: The S5 comprises: Load the alarm group and its identifier into the Incident root cause analysis algorithm; Extract key features related to root cause analysis from each alarm and convert them into numerical vectors; the key features include: alarm type, severity, occurrence time, impact scope, and associated network elements; Combine the pre-trained gradient boosting tree model to perform root cause analysis, predict the suspected root cause alarms of each alarm group, and generate a ranked list of suspected root cause alarms; Based on the ranked list of suspected root cause alarms, a final suspected root cause alarm and a corresponding alarm group identifier are determined.

9. A fault analysis method for a 5G base station transmission link according to claim 1, characterized in that: The S6 comprises: Load the knowledge graph and diagnostic rule base; the knowledge graph includes base station equipment, transmission links, alarm types and their correlations in the 5G base station transmission link; the diagnostic rule base includes preset rules and logical reasoning rules for different alarm types, equipment status and historical fault handling experience; Match the suspected root cause alarm information with the nodes and relationships in the loaded knowledge graph, and analyze the associated nodes and relationships to determine the possible fault propagation path and impact range; Combined with the diagnostic rule base, logical reasoning is performed to analyze the relevance, time sequence, and equipment status of alarm information, predict the cause of the fault, and generate a preliminary fault diagnosis report; Generate a repair process for the fault based on the fault diagnosis report and pre-defined repair strategy; Perform the corresponding repair operations, record the operation results, timestamps and possible abnormal conditions of each step in real time, and obtain a complete fault handling log.

10. A fault analysis system applied to a 5G base station transmission link, characterized in that: include: Data acquisition module: used to obtain the alarm information of 5G base station transmission links by integrating real-time data stream processing mechanism and incremental learning model; Preprocessing module: used to preprocess the alarm information to obtain the preprocessed alarm information; Multi-dimensional vector representation generation module: used to convert the pre-processed warning message into a multi-dimensional vector representation based on the time dimension, topology dimension and text dimension; Grouping aggregation module: used for grouping aggregation based on multi-dimensional vector representation combined with DBSCAN algorithm; Root cause analysis module: used to perform in-depth suspected root cause analysis on grouped and aggregated alarm information through the Incident root cause analysis algorithm to determine the suspected root cause alarm; Fault diagnosis and repair module: used to diagnose suspected root cause alarms through knowledge graphs and diagnostic rules, generate repair processes and record the entire process.

Images