Base station operation and maintenance method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to the technical field of communication, and particularly relates to a base station operation and maintenance method and device, electronic equipment and storage medium. According to an aspect of the present disclosure, a base station operation and maintenance method based on a knowledge graph is provided, including: collecting health degree data of a base station; determining a health state of the base station based on the health degree data and a knowledge graph of base station operation and maintenance rules; determining a target fault problem of the base station based on the health degree data, the health state and the knowledge graph; determining an operation and maintenance method corresponding to the target fault problem based on the target fault problem and the knowledge graph; guiding operation and maintenance of the target fault problem based on the operation and maintenance method; wherein the knowledge graph is used to represent the correlation between the health state, the target fault problem and the operation and maintenance method. The present disclosure can clearly point out the cause, influence and recommended operation and maintenance method of the fault, thereby improving the explainability of the decision.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a base station operation and maintenance method, apparatus, electronic device and storage medium. Background Technology

[0002] With the continuous development of mobile communication technology, the development trend of mobile communication has brought enormous challenges to network operation and maintenance. As a key infrastructure of mobile communication networks, the stable operation of base stations ensures network quality and user experience. Therefore, achieving highly reliable and efficient proactive operation and maintenance of base stations is of paramount importance.

[0003] However, existing base station operation and maintenance mainly relies on artificial intelligence technologies such as machine learning (ML) models to select appropriate operation and maintenance strategies. These models have "black box characteristics," resulting in poor interpretability during the operation and maintenance process and relatively low credibility of operation and maintenance decisions. Summary of the Invention

[0004] To address the aforementioned technical issues, a base station operation and maintenance method, apparatus, electronic device, and storage medium are provided.

[0005] According to one aspect of this disclosure, a knowledge graph-based base station operation and maintenance method is provided, comprising: collecting base station health data; determining the health status of the base station based on the health data and a knowledge graph of base station operation and maintenance rules; determining a target fault problem of the base station based on the health data, health status, and knowledge graph; determining the operation and maintenance strategy corresponding to the target fault problem based on the target fault problem and the knowledge graph; and providing guidance for the operation and maintenance of the target fault problem based on the operation and maintenance strategy; wherein the knowledge graph is used to represent the relationship between the health status, the target fault problem, and the operation and maintenance strategy.

[0006] Furthermore, according to one aspect of the knowledge graph-based base station operation and maintenance method disclosed herein, the health status of a base station is determined based on a knowledge graph of health data and base station operation and maintenance rules, including:

[0007] Based on health data and knowledge graphs, determine the health assessment conditions for base stations;

[0008] The health status of the base station is determined based on the assessment conditions and health data;

[0009] The health status of the base station is determined based on health scores and knowledge graphs;

[0010] The knowledge graph includes the relationships between assessment conditions, health level, and health status.

[0011] Furthermore, according to one aspect of the knowledge graph-based base station operation and maintenance method disclosed herein, based on health data, health status, and a knowledge graph, the target fault problem of the base station is determined, including:

[0012] Based on health status and knowledge graph, determine the fault judgment conditions corresponding to the health status;

[0013] Based on the fault judgment conditions and health data, determine the probability of the fault judgment conditions;

[0014] Based on probability, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem of the base station.

[0015] The knowledge graph includes the relationships between health status, fault judgment conditions, and target fault problems.

[0016] Furthermore, according to one aspect of the knowledge graph-based base station operation and maintenance method disclosed herein, based on a target fault problem and a knowledge graph, an operation and maintenance strategy corresponding to the target fault problem is determined, including:

[0017] Based on the target fault problem and the knowledge graph, determine the optimization algorithm for the target fault problem;

[0018] Based on optimization algorithms, determine the corresponding operation and maintenance strategies for the target fault problem;

[0019] The knowledge graph includes the relationships between target fault problems, optimization algorithms, and operation and maintenance strategies.

[0020] According to another aspect of this disclosure, a knowledge graph-based base station operation and maintenance device includes:

[0021] The data acquisition module is used to collect health data of the base station;

[0022] The status determination module is used to determine the health status of a base station based on a knowledge graph of health data and base station operation and maintenance rules.

[0023] The problem identification module is used to identify the target fault problem of the base station based on health data, health status, and knowledge graph;

[0024] The operation and maintenance method determination module is used to determine the operation and maintenance strategy corresponding to the target fault problem based on the target fault problem and knowledge graph;

[0025] The operations and maintenance module is used to guide the operations and maintenance of target faults based on operations and maintenance strategies.

[0026] Among them, the knowledge graph is used to represent the relationship between health status, target failure issues, and operation and maintenance strategies.

[0027] Furthermore, according to another aspect of the knowledge graph-based base station operation and maintenance device disclosed herein, the status determination module is also used for:

[0028] Based on health data and knowledge graphs, determine the health assessment conditions for base stations;

[0029] The health status of the base station is determined based on the assessment conditions and health data;

[0030] The health status of the base station is determined based on health scores and knowledge graphs;

[0031] The knowledge graph includes the relationships between assessment conditions, health level, and health status.

[0032] Furthermore, according to another aspect of the knowledge graph-based base station operation and maintenance device disclosed herein, the problem determination module is also used for:

[0033] Based on health status and knowledge graph, determine the fault judgment conditions corresponding to the health status;

[0034] Based on the fault judgment conditions and health data, determine the probability of the fault judgment conditions;

[0035] Based on probability, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem of the base station.

[0036] The knowledge graph includes the relationships between health status, fault judgment conditions, and target fault problems.

[0037] Furthermore, according to another aspect of this disclosure, the knowledge graph-based base station operation and maintenance device further includes:

[0038] The knowledge graph management module is used to store and optimize knowledge graphs.

[0039] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the knowledge graph-based base station operation and maintenance methods described above.

[0040] This disclosure also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the knowledge graph-based base station operation and maintenance methods described above.

[0041] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements any of the knowledge graph-based base station operation and maintenance methods described above.

[0042] The base station operation and maintenance method, apparatus, electronic equipment, and storage medium disclosed herein can quickly and accurately determine the health status of a base station by collecting base station health data and based on a pre-constructed knowledge graph of base station operation and maintenance rules. Based on the determined health status, further utilizing the health data, health status, and related information in the knowledge graph, specific target faults can be precisely located. This allows for guidance on target faults based on operation and maintenance methods stored in the knowledge graph. When a base station malfunctions, the knowledge graph-based method can clearly indicate the cause, impact, and recommended operation and maintenance methods, thereby improving the interpretability of decisions. Furthermore, due to the transparency of the knowledge graph, operation and maintenance personnel can more easily verify the correctness of decisions, thus enhancing the credibility of operation and maintenance decisions. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram illustrating the intelligent proactive operation and maintenance process of a B5G base station in the prior art according to embodiments of this disclosure.

[0045] Figure 2 This is a schematic flowchart illustrating a knowledge graph-based base station operation and maintenance method provided according to an embodiment of this disclosure.

[0046] Figure 3 This diagram illustrates the process of constructing a knowledge graph according to an embodiment of this disclosure.

[0047] Figure 4 This is a further schematic diagram illustrating the process of a knowledge graph-based base station operation and maintenance method provided according to an embodiment of the present disclosure.

[0048] Figure 5 This is a further schematic diagram illustrating the process of a knowledge graph-based base station operation and maintenance method provided according to an embodiment of the present disclosure.

[0049] Figure 6 This is a functional block diagram of a knowledge graph-based base station operation and maintenance device provided according to an embodiment of the present disclosure.

[0050] Figure 7 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present disclosure. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this disclosure clearer, the technical solutions of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0052] With the continuous development of technologies such as the Internet of Things, artificial intelligence, and cloud computing, 5G technology is also constantly advancing. 5G has enabled applications such as telemedicine, autonomous driving, smart cities, and smart homes in three major application scenarios: enhanced mobile broadband, ultra-reliable low-latency communication, and massive machine-type communication, profoundly impacting society. To meet the communication needs of increasingly complex future scenarios and further support the key transformation of the economy and industries towards digitalization, networking, and intelligence, a more efficient, reliable, flexible, and intelligent communication network is still needed. In response, research on B5G in academia and industry has become increasingly active.

[0053] However, the development trend of mobile communications has brought enormous challenges to network operation and maintenance. As a critical infrastructure of mobile communication networks, the stable operation of base stations ensures network quality and user experience; therefore, achieving highly reliable and efficient proactive base station operation and maintenance is crucial. Intelligent proactive base station operation and maintenance utilizes artificial intelligence technologies such as machine learning (ML) to select appropriate operation and maintenance strategies, maximizing system performance and achieving automated and intelligent base station operation and maintenance and network optimization. This addresses the high cost and low efficiency issues of traditional optimization models that rely solely on expert experience when facing massive data, complex online network environments, and highly agile service demands.

[0054] Figure 1 This is a schematic diagram of the intelligent proactive operation and maintenance process for B5G base stations in existing technologies.

[0055] like Figure 1 The intelligent proactive operation and maintenance process of B5G base stations shown is mainly divided into two key stages: the model training stage and the model application stage.

[0056] Model training phase: This phase involves collecting historical base station data from various sources, including measurement reports, statistical information, and alarm records. The collected data forms a training dataset used to train machine learning (ML) models such as Convolutional Neural Networks (CNN), Graph Neural Networks (GNN), Generative Adversarial Networks (GAN), and Long Short-Term Memory (LSTM). The trained models are stored in a model library for future applications.

[0057] Model Application Phase: This phase uses the collected current base station health data as input, applies the trained model to the following three steps, and ultimately outputs an optimization strategy. The next steps are base station health detection, base station fault location, and base station operation and maintenance decision-making.

[0058] First, the system performs a base station health check, assessing the current health status of the base station based on collected health data to determine if further maintenance is needed. During the base station fault location phase, the system uses the current health status combined with base station data to accurately locate the fault. Figure 1 In the example shown, a base station's health status is detected as degraded. The model indicates that it is carrying too many services, causing excessive load. The final step is base station operation and maintenance decision-making. Based on the detected fault, the most appropriate operation and maintenance decision, such as task migration, is selected to improve base station availability and optimize network performance.

[0059] The aforementioned intelligent proactive operation and maintenance process for B5G base stations mainly uses machine learning (ML) models to select appropriate operation and maintenance strategies. However, these models have "black box characteristics," resulting in poor interpretability and relatively low credibility of operation and maintenance decisions.

[0060] With the continuous development of 5G and future B5G technologies, the complexity and challenges of base station operation and maintenance are increasing. Traditional operation and maintenance methods based on machine learning models suffer from poor interpretability and low decision credibility. Therefore, this disclosure proposes a knowledge graph-based base station operation and maintenance method to improve the interpretability and credibility of operation and maintenance decisions.

[0061] Figure 2 This is a schematic flowchart illustrating a knowledge graph-based base station operation and maintenance method according to an embodiment of the present disclosure.

[0062] like Figure 2 As shown, the knowledge graph-based base station operation and maintenance method according to the embodiments of this disclosure specifically includes the following steps.

[0063] Step 201: Collect the health data of the base station.

[0064] In one embodiment of this disclosure, health data refers to the base station's performance indicators (such as transmit power, receive sensitivity, and transmission speed), hardware indicators (such as device temperature, voltage, and current), and alarm information (such as device fault alarms and performance alarms). During base station operation and maintenance, health data can be collected through sensors, network management systems, and other channels.

[0065] Step 202: Determine the health status of the base station based on the knowledge graph of health data and base station operation and maintenance rules.

[0066] In one embodiment of this disclosure, combining collected health data with a knowledge graph can determine the health status of a base station. Specifically, the collected health data is compared and analyzed with the knowledge graph to determine the health status of the base station. This process can use machine learning algorithms and expert experience to judge the health status of the base station equipment. Here, the health status can be divided into different levels, such as healthy, sub-healthy, pathological, and deteriorated, to reflect the operating status and maintenance needs of the base station. Exemplarily, the collected health data is compared and analyzed with preset rules in the knowledge graph, and the health status of the base station equipment is judged through machine learning algorithms and expert experience.

[0067] Among them, expert experience refers to the knowledge and experience accumulated in the field of base station operation and maintenance, which comes from...

[0068] The data sources include structured data such as base station alarm information and measurement reports, semi-structured data such as encyclopedic knowledge, and unstructured data such as 3GPP protocol documents and professional literature related to base station operation and maintenance. The knowledge graph of base station operation and maintenance rules integrates the above-mentioned structured data, forming a structured knowledge base. It represents and stores knowledge in the field of base station operation and maintenance by integrating data from different sources and types into a relational network. The base station operation and maintenance rules in the knowledge graph enable operation and maintenance personnel to more effectively understand and handle complex operation and maintenance problems, improving operation and maintenance efficiency and service quality.

[0069] Step 203: Based on health data, health status, and knowledge graph, determine the target fault problem of the base station.

[0070] In one embodiment of this disclosure, the target fault problem refers to the most likely cause of a fault affecting the performance and stability of the base station, derived through knowledge graph analysis based on the current health status and health data. This fault problem may be the main reason for the current poor health status. Specifically, the collected health data, combined with the health status determined in step 102, is analyzed and compared with the knowledge graph to identify the fault problem that best matches the current health status, thus determining that the best-matching fault problem is the target fault problem of the base station. For example, in the knowledge graph, the health status of the device, fault problems, etc., are represented as entities. By analyzing and reasoning the relationships between these entities, the fault problem that best matches the current health status, i.e., the target fault problem, can be determined.

[0071] Step 204: Based on the target fault problem and the knowledge graph, determine the corresponding operation and maintenance strategy for the target fault problem.

[0072] In one embodiment of this disclosure, an operation and maintenance strategy refers to a set of action plans and measures formulated to resolve or prevent specific fault problems. Information from a knowledge graph is used to query operation and maintenance strategies related to the target fault problem. Thus, the most suitable strategy or solution for different fault problems is selected as the corresponding operation and maintenance strategy using the information stored in the knowledge graph. For example, through the relationship network in the knowledge graph, operation and maintenance strategies related to the target fault problem are found, and the most suitable operation and maintenance strategy is selected based on factors such as the effectiveness and feasibility of the strategy.

[0073] Step 205: Based on the operation and maintenance strategy, provide guidance on the operation and maintenance of the target fault problem.

[0074] Among them, the knowledge graph is used to represent the relationship between health status, target failure issues, and operation and maintenance strategies.

[0075] It's important to understand that knowledge graphs can store and represent the health status of base stations. Within a knowledge graph, the health status of a device can be represented as an attribute of an entity. For example, for a specific base station, its health status can be an attribute of that base station entity. By monitoring and collecting device health data in real time, this attribute can be dynamically updated, reflecting the device's current health status. Based on the health status, the most likely target fault can be identified through the relationship network in the knowledge graph. Once the target fault is identified, corresponding operation and maintenance strategies or solutions can be found through the knowledge graph. These strategies or solutions can be based on summaries of historical experience, or recommendations based on expert experience and machine learning models. For instance, operation and maintenance personnel can correctly execute operation and maintenance strategies and perform fault diagnosis and repair work according to the specific steps and instructions provided in the knowledge graph.

[0076] In one embodiment of this disclosure, after determining the operation and maintenance strategy by matching and selecting the most suitable strategy or solution based on the target fault problem, information from a knowledge graph is used to guide operation and maintenance personnel in performing operations, helping them to correctly execute the operation and maintenance strategy. In the knowledge graph, these operation and maintenance strategies or solutions can be represented as entities or relationships related to the target fault problem. By matching and selecting the most suitable strategy or solution, operation and maintenance personnel can be guided in troubleshooting and repairing faults.

[0077] In summary, according to the technical solution provided in this disclosure, by collecting base station health data and based on the knowledge graph of pre-constructed base station operation and maintenance rules, the health status of the base station can be quickly and accurately determined. Based on the determined health status, further utilizing the health data, health status, and related information in the knowledge graph, specific target faults can be precisely located. This allows for guidance on target faults based on the operation and maintenance strategies stored in the knowledge graph. When a base station malfunctions, the knowledge graph-based method can clearly indicate the cause, impact, and recommended operation and maintenance strategies, thereby improving the interpretability of decisions. Furthermore, due to the transparency of the knowledge graph, operation and maintenance personnel can more easily verify the correctness of decisions, thus enhancing the credibility of operation and maintenance decisions.

[0078] Furthermore, according to one aspect of the knowledge graph-based base station operation and maintenance method of this disclosure, the health status of the base station is determined based on a knowledge graph of health data and base station operation and maintenance rules, including:

[0079] Based on health data and knowledge graphs, determine the health assessment conditions for base stations;

[0080] The health status of the base station is determined based on the assessment conditions and health data;

[0081] The health status of the base station is determined based on health scores and knowledge graphs;

[0082] The knowledge graph includes the relationships between assessment conditions, health level, and health status.

[0083] In one embodiment of this disclosure, the knowledge graph includes the relationships between evaluation conditions, health level, and health status. By comparing and analyzing the collected health level data and the knowledge graph, the health level evaluation conditions of the base station can be determined. The evaluation conditions are the basis for evaluating the health status of the base station and can refer to defining what "health level data" is used to evaluate the base station's health. These evaluation conditions can also refer to the weighting of the collected health level data. The health level of the base station is calculated using the weighted health level data. The calculated health level is then compared with the knowledge graph to determine the current health status of the base station.

[0084] For example, the knowledge graph defines the relationship between triplet data of base station health assessment conditions, base station health score ranges, and base station health status. The assessment conditions can refer to the weighting of collected health data. By inputting the weighted health data into a trained health prediction model, a health value is output. This health value is then used to find the corresponding health score range in the knowledge graph based on the assessment conditions, thereby determining the base station's health status according to the corresponding health score range. The health prediction model is an ML model trained using health data collected from historical base station data. For example, the health data collected from historical base station data is input into an LSTM model for training, thus constructing the health prediction model.

[0085] In summary, according to the technical solution provided in this disclosure, by integrating base station health data and operation and maintenance rules using a knowledge graph, and through comparison and analysis, accurate assessment of the base station's health status is achieved. The knowledge graph contains the correlation between assessment conditions, health level, and health status, making the assessment process more intelligent and automated. Simultaneously, by training a health prediction model (such as an LSTM model), the health status of the base station can be predicted, helping to identify potential problems in advance and take preventative measures. This method fully leverages the advantages of data-driven decision-making, improving operation and maintenance efficiency and accuracy, and providing strong support for the stable operation of base stations.

[0086] Furthermore, based on health data, health status, and knowledge graphs, the target faults of the base station are identified, including:

[0087] Based on health status and knowledge graph, determine the fault judgment conditions corresponding to the health status;

[0088] Based on the fault judgment conditions and health data, determine the probability of the fault judgment conditions;

[0089] Based on probability, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem of the base station.

[0090] The knowledge graph includes the relationships between health status, fault judgment conditions, and target fault problems.

[0091] It's important to understand that in a knowledge graph, health status is typically represented as an entity of a base station or other device. This entity describes the device's current health condition. The determination of health status is based on collected health data and base station health assessment conditions. Fault judgment conditions are rules and conditions used to assess whether a device has a fault and the type of fault. In a knowledge graph, these conditions are represented as entities or relationships associated with health status. For example, a certain health status may correspond to a specific set of fault judgment conditions; when these conditions are met, it can be inferred that the device may have experienced a certain fault. Alternatively, a certain health status may correspond to multiple specific sets of fault judgment conditions; when one set of specific fault judgment conditions has a higher probability of occurrence, the target fault problem corresponding to that fault judgment condition can be inferred. The target fault problem refers to the most likely cause of failure affecting device performance and stability, derived through knowledge graph analysis based on the current health status and health data. In a knowledge graph, the target fault problem is represented as an entity or relationship associated with health status and fault judgment conditions. For example, when a device experiences a certain health status, the knowledge graph can determine the possible target fault problem by analyzing the associated fault judgment conditions. This process may involve reasoning and computation involving multiple entities and relationships, but it can ultimately identify one or more of the most likely causes of failure.

[0092] In a knowledge graph, the relationships between health status, fault diagnosis conditions, and target fault problems are represented by entities and relations. These entities and relations together form a complex information network that enables real-time monitoring and evaluation of equipment health. Specifically, health status reflects the current health condition of the equipment, fault diagnosis conditions are rules and conditions for evaluating the equipment's health based on health data, and the target fault problem is the most likely cause of the fault inferred based on these rules and conditions. Based on the relationships between these three elements, potential fault problems can be predicted and diagnosed according to the equipment's real-time health status.

[0093] In one embodiment of this disclosure, fault judgment conditions associated with the base station's health status are searched in a knowledge graph. These conditions can be derived from historical data, expert knowledge, or statistical analysis, and are used to identify characteristics of specific faults. After determining the applicable fault judgment conditions, the next step is to use health data to calculate the probability of these conditions being met, thus determining the likelihood of each fault judgment condition occurring in the current health state. Finally, based on the calculated probability values, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem for the base station. This step is based on the principle of probability theory, that is, the higher the probability value, the greater the likelihood of the fault problem occurring in the current health state. Therefore, selecting the fault problem with the highest probability as the target fault problem can provide more accurate fault location and analysis results. Calculating the probability of each fault judgment condition being met using health data and the determined fault judgment conditions can be obtained using a machine learning model. For example, historical health data, including various performance indicators and alarm information, is collected from the base station. Simultaneously, corresponding fault records are collected to establish a correlation between fault issues and health data. Selectable models include decision trees, random forests, support vector machines (SVMs), and neural networks. The dataset is divided into training, validation, and test sets. The training set is used to train the model, the validation set is used to tune model parameters, and the test set is used to evaluate model performance. The training set is used to train the model, thereby developing a model capable of predicting different fault probabilities in base stations based on health data.

[0094] In summary, according to the technical solution provided in this disclosure, by introducing a knowledge graph, the result of fault prediction is no longer a simple number or probability value, but rather explanatory information associated with specific fault judgment conditions. This allows operations and maintenance personnel to understand the prediction results more intuitively, improving the credibility of their decisions. Furthermore, because the knowledge graph integrates information from historical data, expert knowledge, and statistical analysis, and the machine learning model has undergone rigorous training and validation, the accuracy and reliability of the prediction results are improved. This helps operations and maintenance personnel make more informed and effective decisions.

[0095] Furthermore, based on the target fault problem and the knowledge graph, the corresponding operation and maintenance strategy is determined, including:

[0096] Based on the target fault problem and the knowledge graph, determine the optimization algorithm for the target fault problem;

[0097] Based on optimization algorithms, determine the corresponding operation and maintenance strategies for the target fault problem;

[0098] The knowledge graph includes the relationships between target fault problems, optimization algorithms, and operation and maintenance strategies.

[0099] It's important to understand that in a knowledge graph, the target failure problem is typically represented as a node or entity. An optimization algorithm is a mathematical method or computational process used to solve a specific problem. In the operations and maintenance (O&M) domain, optimization algorithms can help find the optimal O&M strategy or solution. In a knowledge graph, optimization algorithms are typically represented as nodes or relationships associated with the target failure problem. These relationships may describe how the algorithm is applied to a specific failure problem, as well as the algorithm's output or result. A knowledge graph can also contain information such as the algorithm's performance metrics and applicable scenarios, enabling O&M personnel to select the appropriate algorithm. O&M strategies refer to the specific operational steps or strategies used to resolve or prevent failures. These methods may include adjusting equipment parameters, replacing faulty components, upgrading software versions, etc. In a knowledge graph, O&M strategies are typically represented as nodes or relationships associated with the target failure problem and the optimization algorithm. These relationships may describe the specific steps, required resources, and expected results of the O&M strategy. In a knowledge graph, a close relationship is formed between the target failure problem, the optimization algorithm, and the O&M strategy. These relationships not only describe their interactions and dependencies but also provide rich information and context.

[0100] In one embodiment of this disclosure, once the target fault problem is identified, optimization algorithms associated with that fault problem can be searched in a knowledge graph. These optimization algorithms may be derived from historical data, expert experience, or advanced algorithms (such as genetic algorithms, particle swarm optimization, etc.), and are designed to solve specific types of fault problems. The most suitable optimization algorithm is selected based on the nature and characteristics of the target fault problem. After determining the optimization algorithm, an operational strategy for the target fault problem is determined based on the algorithm's output or suggestions. The operational strategy may include specific operational steps, required resources, expected results, etc.

[0101] In summary, according to the technical solution provided in this disclosure, by quickly searching for optimization algorithms associated with the target fault in the knowledge graph, operations and maintenance personnel can rapidly locate the most suitable solution for the current fault, thereby significantly reducing fault handling time. Furthermore, since the selection of operations and maintenance strategies is based on the output or suggestions of the optimization algorithms, operations and maintenance decisions are more scientific and reasonable, reducing the subjectivity and uncertainty of human judgment and exhibiting high accuracy and reliability.

[0102] It's important to understand that the knowledge graph for base station operation and maintenance rules is a pre-constructed knowledge graph. A knowledge graph is a relational network that connects all different types of information. Each node represents an "entity" existing in the real world, and each edge represents a "relationship" between entities. The core of a knowledge graph is actually the triple, which consists of an entity, an entity, and a relation. The aforementioned knowledge graph for base station operation and maintenance rules can be constructed using the following methods.

[0103] Obtain data sources for the knowledge graph used to build base station operation and maintenance rules. These data sources include: base station alarm information, measurement reports, encyclopedic knowledge, 3GPP protocol documents, and professional literature related to base station operation and maintenance.

[0104] Entity and relation extraction are performed on the data source to obtain triplet data;

[0105] By fusing triplet data, a knowledge graph is constructed.

[0106] Specifically, see Figure 3 The construction process of a knowledge graph mainly includes three steps: knowledge modeling, knowledge extraction, knowledge fusion, and knowledge graph construction.

[0107] Knowledge modeling includes identifying relevant domain knowledge from data sources used to construct the knowledge graph for base station operation and maintenance rules, and then constructing it into a structured format (i.e., structured data sources such as base station alarm information and measurement reports, semi-structured data sources such as encyclopedic knowledge, and unstructured data sources such as 3GPP protocol documents and professional literature related to base station operation and maintenance). For proactive base station operation and maintenance, this includes defining key entities, such as base station health status, base station fault issues, operation and maintenance decisions, and the relationships between them.

[0108] Knowledge extraction refers to the process of obtaining relevant triples from structured data sources such as base station alarm information and measurement reports, semi-structured data sources such as encyclopedic knowledge, and unstructured data sources such as 3GPP protocol documents and professional literature related to base station operation and maintenance. In proactive base station operation and maintenance, methods such as neural network decision trees (BiLSTM+CRF, LSTM-RNN, NN-DT) are commonly used to extract base station health detection rules and their characteristic indicators, base station fault classification rules and their characteristic indicators, and base station operation and maintenance rules. The specific output triples are as follows:

[0109] (Base station, using base station health assessment conditions);

[0110] (Base station health assessment criteria, base station health score range, base station health status);

[0111] (Base station health status, using base station fault judgment conditions);

[0112] (Base station fault diagnosis criteria, probability of base station fault, specific base station faults);

[0113] (Specific base station faults, optimization algorithms, and base station operation and maintenance decisions).

[0114] Here, "entity" refers to:

[0115] Base station: Represents a specific base station device and is one of the core entities in the knowledge graph.

[0116] Health assessment criteria: Various conditions and indicators used to assess the health status of base stations.

[0117] Base station health status: Indicates the current health status of the base station, such as "normal", "warning" or "serious warning".

[0118] Base station fault judgment conditions: Conditions and rules used to determine whether a base station has a fault and the type of fault.

[0119] Specific base station faults: These indicate the various types of faults that may occur in a base station, such as "signal coverage problems" or "hardware failures".

[0120] Operation and maintenance decisions: Operation and maintenance strategies and suggestions proposed for specific base station faults.

[0121] Relationship refers to:

[0122] "Adopted" indicates that an entity (such as a base station) has adopted a certain condition or rule (such as a health assessment condition).

[0123] Base station health score range: This indicates the correspondence between the range of health scores obtained from the evaluation conditions and a certain health status.

[0124] The probability of determining a base station fault: This represents the correlation between a certain judgment condition and a certain fault problem. It is used to calculate the probability of a base station experiencing a specific fault based on a certain judgment condition.

[0125] Optimization algorithm: refers to finding the optimal operation and maintenance decision through calculation and analysis for a specific fault.

[0126] Among them, the base station health detection rules and their characteristic indicators refer to:

[0127] Base station, using base station health assessment conditions;

[0128] Base station health assessment criteria, base station health score range, base station health status;

[0129] The classification rules and characteristic indicators for base station faults refer to:

[0130] Base station health status is assessed using base station fault judgment criteria.

[0131] Base station fault diagnosis criteria, probability of base station faults, and specific base station faults;

[0132] Base station operation and maintenance rules refer to:

[0133] Specific base station faults (target fault problems), optimization algorithms, and base station operation and maintenance decisions.

[0134] Knowledge Fusion and Knowledge Graph Construction: After knowledge extraction, the next step is knowledge fusion, which integrates the aforementioned triplet data to create a conflict-free, unified, and complete representation. The final step is to construct a knowledge graph, structuring the modeled knowledge into a graph-based format. Nodes represent entities, and edges represent relationships and dependencies. In this way, the base station operation and maintenance system can simultaneously leverage data-driven and knowledge-driven insights, making the proactive base station operation and maintenance decision-making process more comprehensive and interpretable.

[0135] Figure 4 This is a further schematic diagram illustrating the process of a knowledge graph-based base station operation and maintenance method provided according to an embodiment of the present disclosure.

[0136] like Figure 4 As shown, a knowledge graph-based base station operation and maintenance method is provided according to an embodiment of this disclosure.

[0137] Leveraging expert experience—including structured data sources like base station alarm information / indicators and measurement reports, semi-structured data sources like encyclopedic knowledge / maintenance logs, and unstructured data sources like 3GPP protocol documents and professional literature in the base station maintenance field (such as root causes of faults)—as a knowledge foundation, a base station maintenance rule knowledge graph is constructed. The internal structure of this knowledge graph (such as the definition and association of entities, relationships, and attributes) is transparent to its builders and users, exhibiting white-box characteristics, enabling knowledge-driven operations, and possessing reliability and interpretability. Combining the knowledge graph with ML models helps enhance the intelligent configuration optimization pipeline for base stations. First, base station health detection: Base station health data (such as alarm information) is collected. Using this health data, the selected base station health assessment conditions are determined from the maintenance rule knowledge graph (i.e., the aforementioned base station maintenance rule knowledge graph) to calculate the base station's health. Based on the health score, the current health status of base stations in the network is determined, classifying the base station as healthy, degraded, dangerous, or faulty. The results of the health score calculation can be achieved using an ML model combined with the knowledge graph. The ML model takes base station health assessment indicators (i.e., the aforementioned health data) as input, such as alarm information, transmit power, and transmission rate, and outputs a score for the current base station's health.

[0138] Secondly, if the health status is at risk, base station fault localization is performed: similarly, using a knowledge graph, the fault judgment condition with the highest probability value is selected to locate the specific base station fault (i.e., the aforementioned target fault problem). For example, based on the judgment condition and its probability, the fault can be located from degradation to base station overload. The probability value can be calculated using an ML model combined with a knowledge graph. The input to the ML model is base station-related data, including one or more of the following: health data, health score, base station handover success rate, and base station frequency resource utilization rate; the output is the specific fault category of the base station.

[0139] Finally, after locating the specific fault (i.e., identifying the target fault problem), and combining the knowledge graph, the corresponding path is selected from the fault entity to output the final operation and maintenance solution (i.e., the aforementioned base station operation and maintenance strategy). Base station operation and maintenance strategy (i.e....) Figure 4 The selection of base station operation and maintenance (O&M) decisions is based on the nature and characteristics of the target fault problem, choosing the most suitable optimization algorithm. After determining the optimization algorithm, the O&M method for the target fault problem is determined based on the algorithm's output or suggestions. The optimization algorithm includes reinforcement learning algorithms and specific parameters. The aforementioned optimization algorithm is the ML model. During the optimization process, it also utilizes parameter settings from the O&M rule knowledge graph to adjust the base station, resolve current base station problems, improve base station availability, and enhance network performance. Here, the input of the ML model is selected based on the reinforcement learning algorithm input parameters shown in the graph, such as the number of LRU spare parts, base station health, and maintenance costs. The output O&M strategy can be detected by evaluating the base station's post-O&M status indicators, such as base station health and resource utilization.

[0140] The aforementioned ML can be an ML model formed by collecting historical data from base stations, such as total throughput, number of base station spare parts, and maximum transmission power. The ML model has black-box characteristics, can drive data, and has accuracy and effectiveness.

[0141] The following is a use case for proactive maintenance to address the issue of excessive base station load. Figure 5 As shown, a knowledge graph-based base station operation and maintenance method is further illustrated according to an embodiment of this disclosure.

[0142] Step 501: Collect network base station data for the user's residential area.

[0143] Specifically, real-time data of the current base station is collected, including transmission power, frequency bandwidth, etc. (i.e., the aforementioned health data).

[0144] Step 502: Construct a base station operation and maintenance rule knowledge graph based on expert experience and domain knowledge (i.e., the aforementioned structured data sources such as base station alarm information and measurement reports, semi-structured data sources such as encyclopedic knowledge, and unstructured data sources such as 3GPP protocol documents and professional literature related to base station operation and maintenance).

[0145] Step 503: Train an ML model based on historical cell network base station data and embed it into a knowledge graph.

[0146] Step 504: Based on the knowledge graph of base station operation and maintenance rules, complete the process of base station health detection, base station fault location, and base station operation and maintenance decision-making in the intelligent proactive operation and maintenance pipeline of base stations.

[0147] Specifically, a pre-trained ML model is used to perform health checks on all base stations in the current network. Based on the operation and maintenance rule knowledge graph and the base station health assessment conditions, the current base station's health status is determined to be degraded. After completing the base station health status assessment, the edge with the highest probability of the corresponding fault judgment condition is found from the knowledge graph to identify the target fault problem. When it is confirmed to be a base station overload problem, the task migration decision output at the end of the graph is executed. Specifically, the reinforcement learning algorithm and its parameters are used for optimization calculation, and the operation and maintenance strategy (i.e., the operation and maintenance decision of base station 5 in the figure) is finally output. This operation and maintenance strategy includes indicators of base station status, including base station health and resource utilization.

[0148] In the aforementioned base station operation and maintenance methods, the application of knowledge graphs enhances base station health detection, identification of base station target faults, and output of base station operation and maintenance strategies.

[0149] 1) Base station health detection: Knowledge graphs can guide feature engineering for base station health detection. By selecting appropriate features, problems caused by insufficient abnormal data or poor data quality can be improved, thereby enhancing detection performance.

[0150] 2) Target Fault Problem: Utilize the white-box characteristics of knowledge graphs to solve the black-box problem of neural networks. At the same time, when facing complex network environments, better capture the relevance of problems to help classify base station faults.

[0151] 3) Base Station Operation and Maintenance Strategy: KG ensures strong interpretability, making the final operation and maintenance decisions trustworthy. Furthermore, it helps to supplement reasoning, making decisions more comprehensive and achieving better base station optimization results.

[0152] Figure 6 This is a functional block diagram of a knowledge graph-based base station operation and maintenance device according to an embodiment of the present disclosure.

[0153] like Figure 6 As shown, the knowledge graph-based base station operation and maintenance device 600 includes: a data acquisition module 601, a status determination module 602, a problem determination module 603, an operation and maintenance method determination module 604, an operation and maintenance module 605, and a knowledge graph management module 606.

[0154] Furthermore, the acquisition module 601 is used to acquire health data of the base station;

[0155] Furthermore, the status determination module 602 is used to determine the health status of the base station based on the health data and the knowledge graph of base station operation and maintenance rules.

[0156] Furthermore, the problem identification module 603 is used to identify the target fault problem of the base station based on health data, health status, and knowledge graph.

[0157] Furthermore, the operation and maintenance method determination module 604 is used to determine the operation and maintenance strategy corresponding to the target fault problem based on the target fault problem and the knowledge graph;

[0158] Furthermore, the operations and maintenance module 605 is used to provide guidance on the operations and maintenance of target faults based on operations and maintenance strategies.

[0159] Among them, the knowledge graph is used to represent the relationship between health status, target failure issues, and operation and maintenance strategies.

[0160] Furthermore, the state determination module 602 is also used for:

[0161] Based on health data and knowledge graphs, determine the health assessment conditions for base stations;

[0162] The health status of the base station is determined based on the assessment conditions and health data;

[0163] The health status of the base station is determined based on health scores and knowledge graphs;

[0164] The knowledge graph includes the relationships between assessment conditions, health level, and health status.

[0165] Furthermore, the problem determination module 603 is also used for:

[0166] Based on the health status and the knowledge graph, determine the fault judgment conditions corresponding to the health status;

[0167] Based on the fault judgment conditions and the health data, determine the probability of the fault judgment conditions;

[0168] Based on the probability, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem of the base station;

[0169] The knowledge graph includes the relationships between the health status, the fault judgment conditions, and the target fault problem.

[0170] Furthermore, the knowledge graph management module 606 is used to store and optimize the knowledge graph.

[0171] Specifically, the knowledge graph management module is responsible for storing the knowledge graph of base station operation and maintenance rules, including all entities (such as base stations, health assessment conditions, health status, fault diagnosis conditions, etc.) and the relationships between them. This ensures the knowledge graph data is structured and organized, facilitating access and use by other modules. Furthermore, as time progresses and operational practices accumulate, the knowledge graph needs continuous updating and optimization to reflect the latest operation and maintenance rules and experiences.

[0172] Furthermore, the knowledge graph management module 606 is also used to maintain the knowledge graph, including adding new entities and relationships, updating existing information, and deleting outdated or no longer applicable rules.

[0173] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740. The processor 710, communications interface 720, and memory 730 communicate with each other via the communication bus 740. The processor 710 can call logical instructions stored in the memory 730 to execute the aforementioned knowledge graph-based base station operation and maintenance method.

[0174] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0175] On the other hand, this disclosure also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the above-described base station operation and maintenance method.

[0176] In another aspect, this disclosure also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the above-described base station operation and maintenance method.

[0177] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0178] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit them. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure.

Claims

1. A base station operation and maintenance method based on knowledge graphs, characterized in that, include: Collect health data from base stations; Based on the health data and the knowledge graph of base station operation and maintenance rules, the health status of the base station is determined; Based on the health data, the health status, and the knowledge graph, the target fault problem of the base station is determined; Based on the target fault problem and the knowledge graph, determine the corresponding operation and maintenance strategy for the target fault problem; Based on the aforementioned operation and maintenance strategy, guidance is provided for the operation and maintenance of the target fault problem; The knowledge graph is used to represent the relationship between health status, target failure issues, and operation and maintenance strategies. The step of determining the target fault problem of the base station based on the health data, the health status, and the knowledge graph includes: Based on the health status and the knowledge graph, determine the fault judgment conditions corresponding to the health status; Based on the fault judgment conditions and the health data, determine the probability of the fault judgment conditions; Based on the probability, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem of the base station; The knowledge graph includes the health status, the fault judgment conditions, and the correlation between the target fault problem; The fault judgment condition is to assign weights to the collected health data; The step of determining the health status of the base station based on the knowledge graph of the health data and base station operation and maintenance rules includes: The health score is obtained by predicting the weighted health score data using a pre-trained health score prediction model. Using the knowledge graph, the range of health scores corresponding to the fault judgment conditions is found based on the health score value; The health status of the base station is determined based on the corresponding health score range; The construction process of the knowledge graph includes: Collect data from network base stations in the user's residential area; A knowledge graph of base station operation and maintenance rules is constructed based on expert experience and domain knowledge; ML models are trained based on user cell network base station data and embedded into knowledge graphs.

2. The knowledge graph-based base station operation and maintenance method according to claim 1, characterized in that, The determination of the health status of the base station based on the knowledge graph of the health data and base station operation and maintenance rules includes: Based on the health data and the knowledge graph, the health assessment conditions of the base station are determined; The health status of the base station is determined based on the evaluation conditions and the health data. The health status of the base station is determined based on the health score and the knowledge graph. The knowledge graph includes the correlation between the evaluation conditions, health level, and health status.

3. The knowledge graph-based base station operation and maintenance method according to claim 1, characterized in that, The method based on the health data, the health status, and the knowledge graph is characterized in that determining the operation and maintenance strategy corresponding to the target fault problem based on the target fault problem and the knowledge graph includes: Based on the target fault problem and the knowledge graph, determine the optimization algorithm for the target fault problem; Based on the optimization algorithm, the operation and maintenance strategy corresponding to the target fault problem is determined; The knowledge graph includes the relationship between the target fault problem, the optimization algorithm, and the operation and maintenance strategy.

4. A base station operation and maintenance device based on a knowledge graph, characterized in that, include: The data acquisition module is used to collect health data of the base station; The status determination module is used to determine the health status of the base station based on the health data and the knowledge graph of base station operation and maintenance rules; The problem determination module is used to determine the target fault problem of the base station based on the health data, the health status, and the knowledge graph. The operation and maintenance method determination module is used to determine the operation and maintenance strategy corresponding to the target fault problem based on the target fault problem and the knowledge graph; The operation and maintenance module is used to provide guidance on the operation and maintenance of the target fault problem based on the operation and maintenance strategy; The knowledge graph is used to represent the relationships between health status, target fault problems, and operation and maintenance methods. The operation and maintenance method determination module is used to determine the fault judgment condition corresponding to the health status based on the health status and the knowledge graph; determine the probability of the fault judgment condition based on the fault judgment condition and the health data; and select the fault problem corresponding to the fault judgment condition with the highest probability as the target fault problem of the base station based on the probability; wherein, the knowledge graph includes the association relationship between the health status, the fault judgment condition and the target fault problem; The fault judgment condition is to assign weights to the collected health data; The status determination module is used to predict the weighted health data using a pre-trained health prediction model to obtain a health value; to search for the health score range corresponding to the fault judgment condition using the knowledge graph; and to determine the health status of the base station based on the corresponding health score range. The construction process of the knowledge graph includes: Collect data from network base stations in the user's residential area; A knowledge graph of base station operation and maintenance rules is constructed based on expert experience and domain knowledge; ML models are trained based on user cell network base station data and embedded into knowledge graphs.

5. The knowledge graph-based base station operation and maintenance device according to claim 4, characterized in that, The state determination module is further configured to: Based on the health data and the knowledge graph, the health assessment conditions of the base station are determined; The health status of the base station is determined based on the evaluation conditions and the health data. The health status of the base station is determined based on the health score and the knowledge graph. The knowledge graph includes the correlation between the evaluation conditions, health level, and health status.

6. The knowledge graph-based base station operation and maintenance device according to claim 4, characterized in that, The problem determination module is also used for: Based on the health status and the knowledge graph, determine the fault judgment conditions corresponding to the health status; Based on the fault judgment conditions and the health data, determine the probability of the fault judgment conditions; Based on the probability, the fault problem corresponding to the fault judgment condition with the highest probability is selected as the target fault problem of the base station; The knowledge graph includes the relationships between the health status, the fault judgment conditions, and the target fault problem.

7. The knowledge graph-based base station operation and maintenance device according to claim 4, characterized in that, The device further includes: The knowledge graph management module is used to store and optimize knowledge graphs.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the knowledge graph-based base station operation and maintenance method as described in any one of claims 1 to 3.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the knowledge graph-based base station operation and maintenance method as described in any one of claims 1 to 3.

Images