Base station antenna fault monitoring method, device and non-volatile storage medium

Abstract

The present application discloses a method, device and non-volatile storage medium for monitoring base station antenna faults. The method includes: obtaining the communication status data of the communication base station within the monitoring period; using a first model to extract the data features corresponding to the communication status data, and determining the fault status label corresponding to the communication base station based on the data features; when the fault status label is the first label, obtaining the alarm information corresponding to the communication base station, wherein the first label is used to characterize the existence of a base station antenna fault in the communication base station; using a second model to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna fault. The present application solves the technical problem of long fault response time and low maintenance efficiency caused by the fact that traditional fault troubleshooting methods can only be performed after an alarm occurs.

Description

Technical Field

[0001] The present application relates to the field of wireless communications and terminal technologies, and in particular to a base station antenna fault monitoring method, device and non-volatile storage medium. Background Art

[0002] There are two main methods for early warning of base station failures in the industry: 1) Early warning is only performed for overall base station failures, and the key indicator is "the preset fault parameters for the current early warning". It only performs multiple fault diagnoses in a general manner, does not specify the fault parameters of base station antenna failures, and does not clearly point out the precise indicators that can distinguish different faults. For example, it is not clearly specified which key indicators should be used to distinguish loose network cables, loose E1 connection cables, loose antennas, etc. 2) A diagnostic method dedicated to a certain base station failure, which is only used for network traffic, temperature, electricity, energy consumption, base station load, etc. There is no method dedicated to early warning of base station antenna failures, nor is there a machine learning method dedicated to early warning of base station antenna failures.

[0003] Therefore, there is no early warning method specifically for base station antenna failures in the prior art, such as water ingress, rust, poor contact, short circuit, damage, angle tilt or signal source interference, etc.; it also fails to clearly distinguish different types of antenna failures, and does not specify specific indicators for identifying specific failures such as loose antennas, loose network cables, loose E1 connection cables, etc.; and the current troubleshooting method relies on historical alarm files, work orders, and logs, which means that only after the alarm file is generated can fault diagnosis be performed through a model (such as a machine learning model), which limits the real-time and efficiency of fault warning and troubleshooting.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a base station antenna fault monitoring method, device and non-volatile storage medium to at least solve the technical problems of long fault response time and low maintenance efficiency caused by the fact that traditional fault troubleshooting methods can only be performed after an alarm occurs.

[0006] According to one aspect of an embodiment of the present application, a base station antenna fault monitoring method is provided, including: obtaining communication status data of a communication base station within a monitoring period, wherein the communication status data is used to characterize the signal strength, traffic status and user-end connection status of each base station sector corresponding to the communication base station; using a first model to extract data features corresponding to the communication status data, and determining a fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether a communication base station has a fault; when the fault status label is the first label, obtaining alarm information corresponding to the communication base station, wherein the first label is used to characterize the presence of a base station antenna fault in the communication base station; using a second model to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna fault.

[0007] Optionally, the fault status label includes: a first label, a second label and a third label, wherein the second label is used to indicate that a fault exists in the communication base station, and the fault is a base station antenna fault or other fault, and the third label is used to indicate that the communication base station has no fault;

[0008] Optionally, the method also includes: when the fault status label is the second label, obtaining alarm information corresponding to the communication base station; using a third model to determine the fault type corresponding to the communication base station based on the communication status data and the alarm information, wherein the third model is used to determine the fault type of the communication base station, and the fault type includes at least one of the following: base station antenna failure, other failures; when the fault status label is the third label, waiting for the next monitoring cycle, and after obtaining the communication status data of the communication base station in the next monitoring cycle, re-determining the fault status label corresponding to the communication base station based on the data characteristics.

[0009] Optionally, the method also includes: when the third model determines that the fault type corresponding to the communication base station is a base station antenna failure, using the second model to determine the cause of the antenna failure corresponding to the communication base station based on the communication status data and the alarm information; when the third model determines that the fault type corresponding to the communication base station is other faults, sending a prompt message to the network management system, wherein the prompt message is used to characterize that the communication base station has other faults other than the base station antenna failure, and the other faults include at least one of the following: network terminal, global positioning system locator failure.

[0010] Optionally, the training step of the first model includes: obtaining a first training data set, wherein the first training data set includes: multiple first training data, and a fault status label corresponding to each first training data, the first training data includes: historical communication status data and other fault indication information, other fault feature indication information is used to indicate whether the communication base station has other fault features, the historical communication status data includes: the average signal strength of each base station sector corresponding to the communication base station, the lowest signal strength value within the coverage area of ​​the communication base station, the average traffic of each base station sector corresponding to the communication base station, and the call quality information corresponding to the communication base station, the call quality information is used to characterize whether the voice service provided by the communication base station has noise or too low volume, and the number of user connections of each base station sector corresponding to the communication base station; obtaining an initial model, and using the first training data set to train the initial model to obtain a first model, wherein the type of the initial model includes one of the following: a neural network model, a decision tree model, and a probability statistics model.

[0011] Optionally, the training step of the second model includes: obtaining a second training data set, wherein the second training data set includes: multiple second training data, and the cause of antenna failure corresponding to each second training data, the second training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the cause of antenna failure includes at least one of the following: antenna interference or obstruction, antenna short circuit or disconnection, antenna component damage, and other reasons; obtaining an initial model, and using the second training data set to train the initial model to obtain a second model.

[0012] Optionally, the training step of the third model includes: obtaining a third training data set, wherein the third training data set includes: multiple third training data, and a fault type corresponding to each third training data, the third training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the historical communication status data includes: the average signal strength of each base station sector corresponding to the communication base station, the lowest signal strength within the coverage area of ​​the communication base station, the average traffic of each base station sector corresponding to the communication base station, and call quality information corresponding to the communication base station, the call quality information is used to characterize whether there is any audio abnormality in the voice service provided by the communication base station, the number of user connections of each base station sector corresponding to the communication base station, and the fault types include: base station antenna failure and other failures; obtaining an initial model, and using the third training data set to train the initial model to obtain a third model, wherein the types of initial models include: neural network model, decision tree model, and probability statistical model.

[0013] Optionally, after determining the cause of the antenna failure corresponding to the communication base station, the method also includes: sending the cause of the antenna failure to the terminal equipment of the maintenance personnel corresponding to the communication base station; obtaining troubleshooting feedback information, and updating the cause of the antenna failure corresponding to the second training data in the second training data set corresponding to the second model based on the troubleshooting feedback information, wherein the troubleshooting feedback information is used to characterize the cause of the antenna failure determined by the maintenance personnel after troubleshooting the base station antenna.

[0014] According to another aspect of an embodiment of the present application, a base station antenna fault monitoring device is also provided, including: a first acquisition module, used to acquire communication status data of a communication base station within a monitoring period, wherein the communication status data is used to characterize the signal strength, traffic conditions and user-end connection status of each base station sector corresponding to the communication base station; a fault judgment module, used to adopt a first model to extract data features corresponding to the communication status data, and determine a fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether a communication base station has a fault; a second acquisition module, used to acquire alarm information corresponding to the communication base station when the fault status label is a first label, wherein the first label is used to characterize the existence of a base station antenna fault in the communication base station; a cause analysis module, used to adopt a second model to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether a communication base station has a fault.

[0015] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the above base station antenna fault monitoring method is executed when the program is run.

[0016] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above base station antenna fault monitoring method by running the computer program.

[0017] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the above base station antenna fault monitoring method are implemented.

[0018] In an embodiment of the present application, the communication status data of the communication base station within the monitoring period is obtained, wherein the communication status data is used to characterize the signal strength, traffic situation and user-end connection status of each base station sector corresponding to the communication base station; a first model is used to extract data features corresponding to the communication status data, and a fault status label corresponding to the communication base station is determined based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether there is a fault in the communication base station; when the fault status label is the first label, the alarm information corresponding to the communication base station is obtained, wherein the first label is used to characterize the existence of a base station antenna fault in the communication base station; a second model is used to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna fault, thereby achieving the purpose of early warning and accurate diagnosis of faults, thereby solving the technical problem of long fault response time and low maintenance efficiency caused by the fact that traditional fault troubleshooting methods can only be performed after an alarm occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 It is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for monitoring base station antenna faults according to an embodiment of the present application;

[0021] Figure 2 is a schematic diagram of a method flow for monitoring a base station antenna fault provided in accordance with an embodiment of the present application;

[0022] Figure 3 It is a timing diagram of a prediction process of a base station antenna failure provided according to an embodiment of the present application;

[0023] Figure 4 It is a structural schematic diagram of a base station antenna fault monitoring device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] In the related art, the traditional fault troubleshooting method can only analyze and process after the alarm occurs, so there is a problem that the real-time and efficiency of fault warning and troubleshooting are limited. In order to solve this problem, the embodiment of the present application provides a relevant solution, which is described in detail below.

[0027] According to an embodiment of the present application, a method embodiment of base station antenna fault monitoring is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or electronic device) for implementing a base station antenna fault monitoring method is shown. Figure 1 As shown, the computer terminal 10 (or electronic device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or electronic device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the base station antenna fault monitoring method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned base station antenna fault monitoring method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0033] In the above operating environment, the embodiment of the present application provides a base station antenna fault monitoring method. Figure 2 is a schematic diagram of a method flow for monitoring a base station antenna fault according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0034] Step S202, obtaining the communication status data of the communication base station within the monitoring period, wherein the communication status data is used to characterize the signal strength, traffic situation and user terminal connection status of each base station sector corresponding to the communication base station.

[0035] In step S202, it is first necessary to determine the length of the monitoring period, which can be fixed, such as hourly, daily or weekly, or dynamic, and adjusted according to network conditions, user activity patterns or seasonal changes. The acquisition of communication status data is carried out through the base station monitoring system or network management system, and the signal strength, traffic conditions and user terminal connection status information of each base station sector are collected from the base station in real time. Among them, the signal strength is obtained by measuring the average signal strength, signal quality (such as SINR) and the minimum value of the signal coverage range in the base station sector; the traffic conditions include uplink and downlink traffic, user data transmission rate, peak traffic and average traffic of the base station sector; the user terminal connection status is obtained by counting the number of user connections in the base station sector, connection success rate, drop rate, call quality (such as whether there is noise or the volume is too low) and other data. Ensure the integrity and real-time nature of the data during data collection to avoid affecting the accuracy and response speed of the subsequent model due to data loss or delay.

[0036] Step S204, using the first model to extract data features corresponding to the communication status data, and determine the fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether the communication base station has a fault.

[0037] In step S204, two key parts are involved: feature extraction and fault status prediction. Specifically, feature extraction uses preprocessing and feature engineering techniques to extract features from communication status data that are helpful for predicting base station antenna faults, including but not limited to volatility of signal strength, abnormal surges or decreases in traffic, abnormal changes in the number of user connections, etc. The extracted features are input into the first model for prediction. The first model can be a deep neural network or a decision tree model, which is trained based on the extracted features and outputs a fault status label, such as "antenna fault exists", "antenna fault or other fault exists" or "no fault". The purpose of this step is to identify antenna faults before the alarm information is generated, so as to achieve active early warning of faults.

[0038] Step S206: When the fault status tag is a first tag, obtain alarm information corresponding to the communication base station, wherein the first tag is used to indicate that the communication base station has a base station antenna fault.

[0039] Specifically, when the fault status label predicted by the first model is "antenna fault exists" (i.e., the first label), relevant alarm information will be collected from the base station or network management system, including but not limited to: abnormal alarm of antenna equipment maintenance link, abnormal standing wave ratio (VSWR) alarm, abnormal signal strength drop alarm, user connection failure alarm, etc. The acquisition of alarm information helps the training of the second-stage model, so that it can combine real-time communication status data and historical alarm information to more accurately diagnose the specific cause of the antenna fault.

[0040] Step S208, using the second model, based on the communication status data and the alarm information, determine the cause of the antenna failure corresponding to the communication base station, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna failure.

[0041] In step S208, based on the communication status data and warning letters obtained in the above steps, a second model (such as another deep neural network or a more complex classification model) is used to conduct a more in-depth analysis of the base station antenna failure. The training data of the second model includes specific instances of base station antenna failures, and each instance is marked with a fault cause label. By learning these instances, the second model can identify the communication status characteristics and alarm patterns related to specific fault causes, thereby determining the specific fault type of the base station antenna in practical applications. Specifically, the causes of the fault include but are not limited to: communication status data and warning letters of water ingress or rust of the antenna, poor antenna contact or short circuit, damage to antenna components, tilted antenna angle, signal source interference near the antenna, etc.

[0042] Through the above steps, the communication status data of the communication base station within the monitoring period is obtained, wherein the communication status data is used to characterize the signal strength, traffic situation and user-end connection status of each base station sector corresponding to the communication base station; the first model is used to extract the data features corresponding to the communication status data, and the fault status label corresponding to the communication base station is determined based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether there is a fault in the communication base station; when the fault status label is the first label, the alarm information corresponding to the communication base station is obtained, wherein the first label is used to characterize that there is a base station antenna fault in the communication base station; the second model is used to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna fault, thereby achieving the purpose of early warning and accurate diagnosis of faults, thereby solving the technical problems of long fault response time and low maintenance efficiency caused by the fact that traditional fault troubleshooting methods can only be performed after an alarm occurs.

[0043] The base station antenna fault monitoring method in steps S202 to S208 of the embodiment of the present application is further introduced below.

[0044] In some embodiments of the present application, the fault status label includes: a first label, a second label and a third label, wherein the second label is used to indicate that there is a fault in the communication base station, and the fault is a base station antenna fault or other fault, and the third label is used to indicate that there is no fault in the communication base station.

[0045] In the above embodiment, the first model is used to extract the data features corresponding to the communication status data, and determine the fault status label corresponding to the communication base station based on the data features. The model identifies whether the base station may have a fault and the preliminary type of fault by analyzing the fluctuation of signal strength, changes in traffic, abnormalities in the number of user connections, and the appearance of alarm information. The output results of the first model include the following three labels: The first label: specific to the base station antenna failure, which means that the antenna is flooded, rusted, has poor contact, short-circuited, damaged, or tilted at an angle. The second label: characterizes that the base station has a fault, but does not specifically refer to an antenna fault, including antenna faults or other types of faults (such as power problems, software faults, etc.). The third label: indicates that the base station is currently operating normally and there is no abnormal state. The setting of the three labels helps operation and maintenance personnel to accurately locate antenna faults and improve the speed and efficiency of fault handling.

[0046] According to some optional embodiments of the present application, it is also used to perform the following steps: when the fault status label is the second label, obtaining the alarm information corresponding to the communication base station; using the third model to determine the fault type corresponding to the communication base station based on the communication status data and the alarm information, wherein the third model is used to determine the fault type of the communication base station, and the fault type includes at least one of the following: base station antenna failure, other failures; when the fault status label is the third label, waiting for the next monitoring cycle, and after obtaining the communication status data of the communication base station in the next monitoring cycle, re-determining the fault status label corresponding to the communication base station based on the data characteristics.

[0047] In the above embodiment, when the prediction result of the first model is the second label, it indicates that there is a fault in the communication base station, but the fault can be an antenna fault or other types of faults. At this time, it is necessary to obtain the latest alarm information from the base station or network management system for further analysis. The alarm information usually includes but is not limited to: abnormal alarm of antenna equipment maintenance link, abnormal decrease of antenna signal strength, abnormal alarm of base station power supply, and abnormal software or hardware failure of base station. These alarm information will be used together with real-time communication status data to accurately determine the subsequent fault type.

[0048] The alarm information will then be input into the third model together with the real-time communication status data to determine the fault type corresponding to the communication base station. It should be noted that the third model is a classification model, which is used to further determine the type of base station fault in the presence of a fault (second label), including but not limited to antenna fault, power fault, software fault, etc. This model is also trained based on historical data and fault type labels, and can identify the association between different fault types and communication status data and alarm information. During implementation, the real-time communication status data is combined with the acquired alarm information and input into the third model for classification prediction. The output result is the type label of the base station fault, such as "antenna fault" or "power fault".

[0049] If the prediction result of the first model is the third label, that is, it is determined that the base station is currently operating normally and there is no fault state, no troubleshooting or early warning measures will be taken at this time, but the system will enter a waiting state until the next monitoring cycle begins. After entering the next monitoring cycle, the first model is re-run to predict the fault state based on the newly collected communication status data. This process is periodic and continuous, ensuring real-time monitoring of the base station operation status and timely detection of any potential or new faults.

[0050] Through the above-mentioned specific implementation methods, the present application can effectively predict and diagnose base station failures, especially in the early warning and accurate classification of antenna failures, providing strong technical support for the maintenance and optimization of communication networks.

[0051] According to other optional embodiments of the present application, it is also used to perform the following steps: when the third model determines that the fault type corresponding to the communication base station is a base station antenna failure, the second model is used to determine the cause of the antenna failure corresponding to the communication base station based on the communication status data and the alarm information; when the third model determines that the fault type corresponding to the communication base station is other faults, a prompt message is sent to the network management system, wherein the prompt message is used to characterize that the communication base station has other faults other than the base station antenna failure, and the other faults include at least one of the following: network terminal, global positioning system locator failure.

[0052] In the above embodiment, after the preliminary fault prediction and classification in the first and second stages, if the output result of the third model is "base station antenna failure", it means that based on the analysis of the communication status data and other fault indication information, it is judged that the current problem faced by the base station is mainly caused by the antenna failure. At this time, it is necessary to further determine the specific cause of the antenna failure.

[0053] Specifically, when the third model determines that the base station failure is an antenna failure, the second model will be started to further explore and determine the specific cause of the antenna failure. First, the communication status data at the current moment is integrated with the latest alarm information obtained from the base station or network management system to form the input data of the second model. The integrated data is input into the second model, wherein the second model is a deep neural network or other classification model, which has been trained with historical data and can identify the association between different antenna failure causes and communication status characteristics and alarm information. The second model analyzes the input data and outputs a specific antenna failure cause label, such as "water ingress into the antenna", "antenna rust", "poor antenna contact", "antenna short circuit", "antenna damage", "antenna angle tilt" or "signal source interference near the antenna". Based on the antenna failure cause output by the second model, the operation and maintenance personnel can take more targeted maintenance actions, such as checking the water source near the antenna, checking the physical state of the antenna connection, adjusting the antenna angle, etc., thereby improving the efficiency and effectiveness of fault handling.

[0054] On the other hand, if the judgment result of the third model is "other faults", this indicates that the current base station problem is not related to the antenna fault, but is caused by network interruption, global positioning system (GPS) locator failure or other types of faults. In this case, a prompt message will be sent to the network management system to remind the operation and maintenance personnel that the base station has other problems other than antenna failure, which requires further analysis and processing. Specifically, a prompt message is sent to the network management system to clearly point out that the base station has other problems other than antenna failure. The types of faults involved in "other faults" include but are not limited to: network terminal failure (such as disconnection between the base station and the core network, network congestion, etc.), global positioning system locator failure (such as loss of GPS signal, damage to the locator, etc.), software failure (such as base station performance degradation or service interruption, etc.). This information contains an overview of the communication status of the base station during the current monitoring cycle, as well as a detailed description of any related alarms, so that the operation and maintenance team can quickly understand the nature and scope of the problem and take corresponding troubleshooting and repair measures. After receiving these fault prompts, the operation and maintenance personnel will formulate a reasonable troubleshooting and repair plan based on the fault type, combined with the operating status and network environment of the base station, so as to ensure the stable operation of the base station and the continuity of network services.

[0055] Through the above steps, the third model preliminarily classifies the base station fault types, distinguishes antenna faults from other faults, and ensures the accuracy and directionality of fault warnings. For cases determined to be antenna faults, the second model further accurately locates the cause of the fault and provides specific guidance for antenna maintenance and repair; for other faults, it sends prompt information to the network management system to remind operation and maintenance personnel to pay attention to non-antenna fault problems of the base station, thereby comprehensively improving the efficiency of base station fault handling and network service quality. This process design fully considers the diversity and complexity of faults, and realizes refined management and maintenance of the base station operation status through phased and type-based fault diagnosis strategies.

[0056] In some optional embodiments of the present application, the training of the first model is used to perform the following steps: obtaining a first training data set, wherein the first training data set includes: multiple first training data, and a fault status label corresponding to each first training data, the first training data includes: historical communication status data and other fault indication information, other fault feature indication information is used to indicate whether the communication base station has other fault features, the historical communication status data includes: the average signal strength of each base station sector corresponding to the communication base station, the lowest signal strength value within the coverage area of ​​the communication base station, the average traffic of each base station sector corresponding to the communication base station, and the call quality information corresponding to the communication base station, the call quality information is used to characterize whether the voice service provided by the communication base station has noise or too low volume, and the number of user connections of each base station sector corresponding to the communication base station; obtaining an initial model, and using the first training data set to train the initial model to obtain a first model, wherein the type of the initial model includes one of the following: a neural network model, a decision tree model, and a probability statistics model.

[0057] In the above embodiment, in order to build a model that can effectively predict base station failures, it is necessary to first prepare a first training data set. First, information containing clear fault records and normal operating status is filtered out from the historical database, wherein the historical data covers multiple base stations, and the data of each base station includes data of at least one monitoring cycle. Then the collected historical communication status data is matched with the base station status record, and a fault status label is assigned to each data. It should be noted that if the historical data clearly indicates that there is an antenna failure (such as water ingress, rust, poor contact, etc.), it is marked as "antenna failure" (first label). If there is a communication anomaly in the historical data, but there is no clear antenna failure record, or some key features are missing (such as call quality information), it is marked as "there may be an antenna failure or other failures" (second label). If the historical data shows that the base station is operating normally and there is no sign of failure, it is marked as "no fault" (third label). Finally, the historical communication status data is cleaned and preprocessed, including removing invalid data, filling missing values, and standardizing or normalizing feature values ​​such as signal strength, traffic, and number of user connections to ensure data quality and model training effect. The obtained first training data set contains multiple pieces of data after the above classification and corresponding fault status labels, and the data types include but are not limited to: the average signal strength of base station sectors 1, 2 and 3, the minimum signal strength value of the communication base station coverage area, the average flow call quality information of base station sectors 1, 2 and 3 (such as noise report, low volume report), the number of user connections of base station sectors 1, 2 and 3, and other fault feature indication information (such as power supply abnormality, software failure report).

[0058] Then, the initial model is trained based on the first training data set to obtain the first model. First, according to the requirements and data characteristics of fault prediction, a suitable initial model type is selected, including but not limited to a neural network model, a decision tree model or a probabilistic statistical model. Then, the hyperparameters of the model are set, such as the number of layers, the number of nodes, the learning rate, etc. of the neural network. Then, the first training data set is input into the initial model for training. During the training process, the model will learn how to identify the fault status label from the input features, that is, how to predict the status of the base station based on features such as signal strength, traffic, call quality information, and the number of user connections. Finally, through mechanisms such as back propagation and weight adjustment, the model parameters are continuously optimized to improve the model's prediction accuracy for fault status. After the training is completed, the model is verified using a portion of the data that was not involved in the training to evaluate its prediction performance and ensure the reliability of the model in practical applications.

[0059] Through the above steps, a first model that can predict the fault status from the real-time communication status data of the base station can be constructed and trained. The accuracy and reliability of the model are directly related to the effectiveness of the early warning system. Therefore, in the process of model selection and training, it is necessary to fully consider the characteristics of the data and the applicability of the model to ensure that the final model can effectively respond to the early warning needs of base station antenna failures.

[0060] As some optional embodiments of the present application, the training of the second model is used to perform the following steps: obtaining a second training data set, wherein the second training data set includes: multiple second training data, and the cause of antenna failure corresponding to each second training data, the second training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the cause of antenna failure includes at least one of the following: antenna interference or obstruction, antenna short circuit or disconnection, antenna component damage, and other reasons; obtaining an initial model, and using the second training data set to train the initial model to obtain a second model.

[0061] In the above embodiment, in order to build a second model that can accurately determine the specific cause of the antenna failure, it is first necessary to prepare a targeted second training data set. Specifically, first, data containing clear antenna failure records are screened out from the historical database, including but not limited to antenna interference or obstruction, antenna short circuit or disconnection, antenna component damage, etc. For each piece of historical communication status data, its corresponding historical alarm information is associated, such as the antenna equipment maintenance link abnormality alarm, the antenna signal strength abnormal drop alarm, etc., which will serve as the key input for the training of the second model. Then, an antenna failure cause label is assigned to each piece of historical communication status data. For example, the historical data and alarm information indicate that the antenna signal is interfered with, and the label of the data strip is marked as "antenna interference or obstruction."

[0062] Based on the above classified multiple historical communication status data, corresponding historical alarm information and antenna fault cause labels, a second training data set is obtained. The second training data set is used to train the initial model to obtain a second model. Specifically, based on the identification requirements of the antenna fault causes, the complexity of the fault causes and the characteristics of the data, a suitable initial model type is selected, such as a deep neural network model or a decision tree model. Then the model is initialized, and the architecture parameters of the initial model are set, such as the number of layers and nodes of the neural network, or the depth of the decision tree, and the model weights are initialized at the same time. The historical communication status data and historical alarm information in the second training data set are then input into the initial model, and the model parameters are adjusted through optimization mechanisms such as the back propagation algorithm so that the model can learn the recognition patterns of different antenna fault causes from the data. After the training process is completed, the model is tested using a validation data set that did not participate in the training to evaluate the accuracy and generalization ability of the model to ensure that it can be effectively applied to the fault cause identification of new data.

[0063] Through the above steps, a second model can be trained, which can identify the specific causes of antenna failures based on communication status data and alarm information, including antenna interference or shielding, antenna short circuit or disconnection, antenna component damage, etc. The accuracy and reliability of this model are crucial for the rapid location and handling of antenna failures, and can help operation and maintenance personnel quickly take targeted maintenance measures to reduce the impact of failures on network services.

[0064] In some optional embodiments of the present application, the training of the third model is used to perform the following steps: obtaining a third training data set, wherein the third training data set includes: multiple third training data, and a fault type corresponding to each third training data, the third training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the historical communication status data includes: the average signal strength of each base station sector corresponding to the communication base station, the lowest signal strength within the coverage area of ​​the communication base station, the average traffic of each base station sector corresponding to the communication base station, and call quality information corresponding to the communication base station, the call quality information is used to characterize whether there is any audio abnormality in the voice service provided by the communication base station, the number of user connections of each base station sector corresponding to the communication base station, and the fault types include: base station antenna failure and other failures; obtaining an initial model, and using the third training data set to train the initial model to obtain a third model, wherein the types of initial models include: neural network model, decision tree model, and probability statistical model.

[0065] In the above embodiment, in order to train a third model that can effectively identify base station fault types (base station antenna faults and other faults), it is first necessary to construct a high-quality third training data set. Specifically, firstly, communication status data related to base station antenna faults and other faults are extracted from the historical database, including but not limited to the average signal strength of each sector, the lowest signal value within the coverage area, the average flow of the sector, call quality information (including audio abnormality reports), and the number of user connections. For each communication status data, accurately associate its corresponding historical alarm information, such as antenna fault alarm, power supply abnormality alarm, software fault alarm, etc., so that the model can learn the indication of the fault type from the alarm. Then assign a fault type label to each historical communication status data. For example, if there is an abnormal decrease in antenna signal strength or other antenna fault-related alarms in the alarm information, the data strip is marked as "base station antenna fault". On the contrary, if the alarm information points to power, software or other non-antenna faults, it is marked as "other faults".

[0066] Based on the historical communication status data, corresponding alarm information and fault type labels contained in the third training data set, the initial model is trained using the third training data set to obtain the third model. Specifically, according to the specific requirements of fault type identification, an appropriate initial model type is selected. It can be a neural network model (such as a deep neural network), a decision tree model or a probabilistic statistical model, depending on the complexity of the data and the prediction accuracy requirements of the model. Then the hyperparameters of the initial model are set to initialize the model, such as the number of layers, the number of nodes, the learning rate, etc. of the neural network. For example, if a decision tree or a probabilistic statistical model is selected, the corresponding model structure parameters are initialized. Then the historical communication status data and historical alarm information in the third training data set are input into the initialized model, and the fault type label of each data is provided. The model learns how to accurately identify the fault type from the input data through multiple rounds of iterative training, such as "base station antenna failure" or "other failures". During and after the training process, the performance of the model is evaluated using a cross-validation or reserved validation data set. By adjusting the model structure, optimizing the hyperparameters, etc., the accuracy and generalization ability of the model are improved to ensure that it can effectively identify new base station fault types in practical applications.

[0067] Through the above specific implementation, a third model can be trained, which can accurately distinguish base station antenna failures from other types of failures based on historical communication status data and alarm information. This will significantly enhance the efficiency and accuracy of base station operation and maintenance, help operation and maintenance personnel locate problems more quickly, take appropriate measures to repair them, thereby reducing network interruption time and improving user communication experience.

[0068] As some other optional embodiments of the present application, after determining the cause of the antenna failure corresponding to the communication base station, it is also used to perform the following steps: sending the cause of the antenna failure to the terminal equipment of the maintenance personnel corresponding to the communication base station; obtaining troubleshooting feedback information, and updating the cause of the antenna failure corresponding to the second training data in the second training data set corresponding to the second model based on the troubleshooting feedback information, wherein the troubleshooting feedback information is used to characterize the cause of the antenna failure determined by the maintenance personnel after troubleshooting the base station antenna.

[0069] In the above embodiment, once the second model determines the cause of the antenna failure of a communication base station, this information will be sent to the terminal device of the maintenance personnel responsible for the maintenance of the base station. Specifically, the antenna failure cause output by the model (such as antenna interference or obstruction, antenna short circuit or disconnection, antenna component damage, etc.) is first converted into a clear and easy-to-understand text description, so that the maintenance personnel can quickly grasp the details of the failure. Then, the fault cause information is sent to the terminal device of the maintenance personnel through a preset communication interface (such as SMS, e-mail, notification function of a dedicated operation and maintenance APP, etc.). And according to the urgency of the fault and the possible scope of impact, an urgency mark is added to the information to guide maintenance personnel to give priority to high-priority faults.

[0070] After receiving the information about the cause of the antenna failure, the maintenance personnel will go to the base station site to troubleshoot and repair the fault. After the troubleshooting is completed, the maintenance personnel will submit troubleshooting feedback information through their terminal equipment, including the actual cause of the fault and the repair status. After obtaining the troubleshooting feedback information, the actual cause of the fault in the troubleshooting feedback information is matched with the corresponding historical communication status data and historical alarm information in the second training data set. If the cause of the fault predicted by the model is consistent with the actual situation, the fault cause label in the data set remains unchanged; if the prediction is inaccurate, the fault cause label in the data set is updated to reflect the actual troubleshooting results. Based on the updated second training data set, the second model is retrained to correct the prediction deviation and improve the accuracy and reliability of the model. This process can be performed periodically to ensure that the model is always optimized based on the latest fault diagnosis experience.

[0071] Through the above specific steps, not only can the cause of the antenna failure be communicated to the maintenance personnel in a timely manner, but the second model can also be continuously optimized based on the actual troubleshooting feedback to improve the accuracy of fault prediction. This closed-loop mechanism is the key to improving base station maintenance efficiency and network service quality, helping to reduce ineffective troubleshooting and resource waste caused by inaccurate fault prediction, while ensuring that the model's predictive ability continues to increase with the accumulation of fault diagnosis experience, providing strong technical support for the long-term stable operation of base stations.

[0072] The above scheme is further introduced below by giving examples.

[0073] Figure 3 is a timing diagram of a base station antenna failure prediction process provided according to an embodiment of the present application, such as Figure 3 As shown, the system for predicting base station antenna failure includes:

[0074] The data collection module is used to collect the training data required for model 1, model 2, and model 3. Including: the average signal strength of base station sector 1, the average signal strength of base station sector 2, the average signal strength of base station sector 3, the lowest signal value within the coverage area of ​​the base station, the average traffic of base station sector 1, the average traffic of base station sector 2, the average traffic of base station sector 3, the presence of noise in calls (if reported), the call volume is too low (if reported), the number of user connections in base station sector 1, the number of user connections in base station sector 2, the number of user connections in base station sector 3, other fault characteristics, and alarm files.

[0075] Model training module, used to train three different models.

[0076] The model verification and distribution module is used to verify the trained model and distribute and configure the model.

[0077] The fault diagnosis and processing module is used by operation and maintenance personnel to conduct on-site investigation and fault repair based on alarm information and diagnosis and analysis results.

[0078] The specific working steps of the base station antenna fault monitoring system are as follows:

[0079] Step S301, obtain the training data of the first phase. The training data of the first phase includes: the average signal strength of base station sector 1, the average signal strength of base station sector 2, the average signal strength of base station sector 3, the lowest signal value within the coverage area of ​​the base station, the average flow of base station sector 1, the average flow of base station sector 2, the average flow of base station sector 3, the presence of noise in calls (such as reported), the call volume is too low (such as reported), the number of user connections of base station sector 1, the number of user connections of base station sector 2, the number of user connections of base station sector 3, and other fault characteristics.

[0080] Tags include: [base station antenna failure, base station antenna failure or other failure, base station no failure].

[0081] This embodiment uses historical data of one base station for training.

[0082] If a piece of training data comes from a base station antenna failure, it is marked as "base station antenna failure"; if a piece of training data has some missing features of the antenna feature value, such as call noise and call volume features, it is marked as "base station antenna failure or other failure"; if a piece of training data comes from other failures, it is marked as "base station antenna failure or other failure". If a piece of training data is normal, it is marked as "base station no failure".

[0083] Step S302, use a deep neural network to train the first stage base station fault determination model (i.e., the first model). If the model determination result is "base station antenna failure", go to step S304. If the model determination result is "base station antenna failure or other failure", go to step S305. If the model determination result is "base station no fault", the program terminates.

[0084] Step S303, obtaining an alarm file.

[0085] Step S304, training a base station antenna fault classification model (i.e., the second model). The training data are: average signal strength of base station sector 1, average signal strength of base station sector 2, average signal strength of base station sector 3, minimum signal value within the base station coverage area, average flow of base station sector 1, average flow of base station sector 2, average flow of base station sector 3, noise in calls (such as reported), too low call volume (such as reported), number of user connections of base station sector 1, number of user connections of base station sector 2, number of user connections of base station sector 3, and alarm files.

[0086] Tags include: [antenna interference (blocking), antenna short circuit or disconnection, antenna component damage, other faults].

[0087] Step S305, training a base station fault classification model (i.e., the third model), the training data are: the average signal strength of base station sector 1, the average signal strength of base station sector 2, the average signal strength of base station sector 3, the lowest signal value within the coverage area of ​​the base station, the average traffic of base station sector 1, the average traffic of base station sector 2, the average traffic of base station sector 3, the presence of noise in calls (if reported), the call volume is too low (if reported), the number of user connections of base station sector 1, the number of user connections of base station sector 2, the number of user connections of base station sector 3, and the alarm file.

[0088] Tags include: [Base station antenna failure, Base station other failure].

[0089] If the classification result is that the base station antenna is faulty, the process proceeds to step S304. If the classification result is that the base station has other faults, the process proceeds to step S306.

[0090] Step S306, conduct on-site diagnosis and investigation based on the classification information. If the classification result is "antenna interference (blocking)", check whether the antenna is tilted, whether there is interference in the direction of the electromagnetic wave signal, and whether there is an interference source in the surrounding environment. If the classification result is "antenna short circuit or disconnection", check the line. If the classification result is "antenna component damage", check whether the transmitter head, connection board or other components are damaged. If the classification result is "other faults", combine the alarm file to troubleshoot other faults, such as network interruption, GPS locator failure, etc. Perform maintenance based on the troubleshooting results, and feed back the troubleshooting results to the network management background, so that more accurate data can be used in the next round of training.

[0091] Step S307: The above model is packaged, verified and released. The program is run periodically to monitor the operation status of the base station. The operation and maintenance personnel replace, connect or replace the base station antenna according to the classification results.

[0092] Through the above steps, the base station antenna fault monitoring system has designed a closed-loop mechanism. By collecting feedback information from on-site maintenance personnel, the model's training data set is continuously optimized to ensure that the model can learn from actual maintenance experience and continuously improve its prediction and classification capabilities. These models are periodically run to continuously monitor the base station operation status. This method not only enhances the adaptability and flexibility of the system, but also enables the fault warning system to continue to improve with the development of network environment and base station technology, realizes early warning of base station antenna failures, reduces the time for fault diagnosis and repair, ensures the continuity and high quality of communication services, and provides a set of efficient and intelligent solutions for base station maintenance.

[0093] According to an embodiment of the present application, an embodiment of a base station antenna fault monitoring device is also provided. Figure 4 Schematic diagram of a base station antenna fault monitoring device provided according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0094] The first acquisition module 40 is used to acquire the communication status data of the communication base station within the monitoring period, wherein the communication status data is used to characterize the signal strength, flow status and user terminal connection status of each base station sector corresponding to the communication base station.

[0095] The fault judgment module 42 is used to use the first model to extract data features corresponding to the communication status data, and determine the fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether there is a fault in the communication base station.

[0096] The second acquisition module 44 is used to acquire the alarm information corresponding to the communication base station when the fault status tag is the first tag, wherein the first tag is used to indicate that the communication base station has a base station antenna fault.

[0097] The cause analysis module 46 is used to determine the cause of the antenna failure corresponding to the communication base station by using the second model based on the communication status data and the alarm information, wherein the first model is a model obtained by training based on historical data and corresponding labels for predicting whether the communication base station has a failure. It should be noted that each module in the above-mentioned base station antenna failure monitoring device can be a program module (for example, a set of program instructions for implementing a certain specific function) or a hardware module. For the latter, it can be expressed in the following forms, but is not limited thereto: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0098] Optionally, the fault status label includes: a first label, a second label and a third label, wherein the second label is used to indicate that a fault exists in the communication base station, and the fault is a base station antenna fault or other fault, and the third label is used to indicate that the communication base station has no fault;

[0099] Optionally, the base station antenna fault monitoring device is also used to: when the fault status label is the second label, obtain the alarm information corresponding to the communication base station; use the third model to determine the fault type corresponding to the communication base station based on the communication status data and the alarm information, wherein the third model is used to determine the fault type of the communication base station, and the fault type includes at least one of the following: base station antenna failure, other failures; when the fault status label is the third label, wait for the next monitoring cycle, and after obtaining the communication status data of the communication base station in the next monitoring cycle, re-determine the fault status label corresponding to the communication base station based on the data characteristics.

[0100] Optionally, the base station antenna fault monitoring device is also used to: when the third model determines that the fault type corresponding to the communication base station is a base station antenna fault, use the second model to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information; when the third model determines that the fault type corresponding to the communication base station is other faults, send a prompt message to the network management system, wherein the prompt information is used to characterize that the communication base station has other faults other than the base station antenna fault, and the other faults include at least one of the following: network terminal, global positioning system locator fault.

[0101] Optionally, the training step of the first model includes: obtaining a first training data set, wherein the first training data set includes: multiple first training data, and a fault status label corresponding to each first training data, the first training data includes: historical communication status data and other fault indication information, other fault feature indication information is used to indicate whether the communication base station has other fault features, the historical communication status data includes: the average signal strength of each base station sector corresponding to the communication base station, the lowest signal strength value within the coverage area of ​​the communication base station, the average traffic of each base station sector corresponding to the communication base station, and the call quality information corresponding to the communication base station, the call quality information is used to characterize whether the voice service provided by the communication base station has noise or too low volume, and the number of user connections of each base station sector corresponding to the communication base station; obtaining an initial model, and using the first training data set to train the initial model to obtain a first model, wherein the type of the initial model includes one of the following: a neural network model, a decision tree model, and a probability statistics model.

[0102] Optionally, the training step of the second model includes: obtaining a second training data set, wherein the second training data set includes: multiple second training data, and the cause of antenna failure corresponding to each second training data, the second training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the cause of antenna failure includes at least one of the following: antenna interference or obstruction, antenna short circuit or disconnection, antenna component damage, and other reasons; obtaining an initial model, and using the second training data set to train the initial model to obtain a second model.

[0103] Optionally, the training step of the third model includes: obtaining a third training data set, wherein the third training data set includes: multiple third training data, and a fault type corresponding to each third training data, the third training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the historical communication status data includes: the average signal strength of each base station sector corresponding to the communication base station, the lowest signal strength within the coverage area of ​​the communication base station, the average traffic of each base station sector corresponding to the communication base station, and call quality information corresponding to the communication base station, the call quality information is used to characterize whether there is any audio abnormality in the voice service provided by the communication base station, the number of user connections of each base station sector corresponding to the communication base station, and the fault types include: base station antenna failure and other failures; obtaining an initial model, and using the third training data set to train the initial model to obtain a third model, wherein the types of initial models include: neural network model, decision tree model, and probability statistical model.

[0104] Optionally, after determining the cause of the antenna failure corresponding to the communication base station, the base station antenna failure monitoring device is also used to: send the cause of the antenna failure to the terminal equipment of the maintenance personnel corresponding to the communication base station; obtain troubleshooting feedback information, and update the antenna failure cause corresponding to the second training data in the second training data set corresponding to the second model based on the troubleshooting feedback information, wherein the troubleshooting feedback information is used to characterize the cause of the antenna failure determined by the maintenance personnel after troubleshooting the base station antenna.

[0105] It should be noted that the base station antenna fault monitoring device provided in this embodiment can be used to perform Figure 2 The base station antenna fault monitoring method shown, therefore, the relevant explanations and descriptions of the above-mentioned base station antenna fault monitoring method are also applicable to the embodiments of the present application and will not be repeated here.

[0106] An embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following base station antenna fault monitoring method by running the computer program: obtaining communication status data of the communication base station within the monitoring period, wherein the communication status data is used to characterize the signal strength, traffic status and user-end connection status of each base station sector corresponding to the communication base station; using a first model to extract data features corresponding to the communication status data, and determining a fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether a communication base station has a fault; when the fault status label is the first label, obtaining alarm information corresponding to the communication base station, wherein the first label is used to characterize the existence of a base station antenna fault in the communication base station; using a second model to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna fault.

[0107] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the base station antenna fault monitoring method described in each embodiment of the present application: obtaining communication status data of a communication base station within a monitoring period, wherein the communication status data is used to characterize the signal strength, traffic conditions, and user-end connection status of each base station sector corresponding to the communication base station; using a first model to extract data features corresponding to the communication status data, and determining a fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether a communication base station has a fault; when the fault status label is the first label, obtaining alarm information corresponding to the communication base station, wherein the first label is used to characterize the presence of a base station antenna fault in the communication base station; using a second model to determine the cause of the antenna fault corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model trained based on historical data and corresponding labels for determining the specific cause of the base station antenna fault.

[0108] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0109] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0114] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A base station antenna fault monitoring method, characterized in that: include: Acquire communication status data of the communication base station within the monitoring period, wherein the communication status data is used to characterize the signal strength, traffic situation and user terminal connection status of each base station sector corresponding to the communication base station; A first model is used to extract data features corresponding to the communication status data, and a fault status label corresponding to the communication base station is determined based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether the communication base station has a fault; When the fault status tag is a first tag, obtaining alarm information corresponding to the communication base station, wherein the first tag is used to indicate that a base station antenna fault exists in the communication base station; A second model is used to determine the cause of the antenna failure corresponding to the communication base station based on the communication status data and the alarm information, wherein the second model is a model obtained by training based on historical data and corresponding labels to determine the specific cause of the base station antenna failure.

2. The base station antenna fault monitoring method according to claim 1, characterized in that: The fault status label includes: the first label, the second label and the third label, wherein the second label is used to indicate that the communication base station has a fault, and the fault is a base station antenna fault or other fault, and the third label is used to indicate that the communication base station has no fault; the method further includes: When the fault status label is the second label, obtaining the alarm information corresponding to the communication base station; Adopting a third model, according to the communication state data and the alarm information, determining the fault type corresponding to the communication base station, wherein the third model is used to determine the fault type of the communication base station, and the fault type includes at least one of the following: base station antenna fault, other fault; In the case where the fault status label is the third label, wait for the next monitoring cycle, and after obtaining the communication status data of the communication base station in the next monitoring cycle, re-determine the fault status label corresponding to the communication base station based on the data characteristics.

3. The base station antenna fault monitoring method according to claim 2, characterized in that: The method further comprises: In the case where the third model determines that the fault type corresponding to the communication base station is the base station antenna fault, the second model is used to determine the cause of the antenna fault corresponding to the communication base station according to the communication status data and the alarm information; When the third model determines that the fault type corresponding to the communication base station is the other fault, a prompt message is sent to the network management system, wherein the prompt message is used to characterize that the communication base station has other faults other than the base station antenna fault, and the other faults include at least one of the following: network terminal, global positioning system locator fault.

4. The base station antenna fault monitoring method according to claim 1, characterized in that: The training steps of the first model include: Acquire a first training data set, wherein the first training data set includes: a plurality of first training data, and the fault status label corresponding to each of the first training data, the first training data includes: historical communication status data and other fault indication information, the other fault feature indication information is used to indicate whether the communication base station has other fault features, the historical communication status data includes: the average signal strength of each of the base station sectors corresponding to the communication base station, the lowest signal strength value within the coverage area of ​​the communication base station, the average flow of each of the base station sectors corresponding to the communication base station, the call quality information corresponding to the communication base station, the call quality information is used to characterize whether the voice service provided by the communication base station has noise or the volume is too low, and the number of user connections of each of the base station sectors corresponding to the communication base station; An initial model is obtained, and the initial model is trained using the first training data set to obtain the first model, wherein the type of the initial model includes one of the following: a neural network model, a decision tree model, and a probability statistics model.

5. The base station antenna fault monitoring method according to claim 4, characterized in that: The training step of the second model includes: Acquire a second training data set, wherein the second training data set includes: a plurality of second training data, and the antenna failure cause corresponding to each second training data, the second training data includes: the historical communication status data, and historical alarm information corresponding to the historical communication status data, and the antenna failure cause includes at least one of the following: antenna interference or shielding, antenna short circuit or disconnection, antenna component damage, and other reasons; The initial model is obtained, and the second training data set is used to train the initial model to obtain the second model.

6. The base station antenna fault monitoring method according to claim 2, characterized in that: The training steps of the third model include: Obtain a third training data set, wherein the third training data set includes: a plurality of third training data, and the fault type corresponding to each of the third training data, the third training data includes: historical communication status data, historical alarm information corresponding to the historical communication status data, the historical communication status data includes: the average signal strength of each of the base station sectors corresponding to the communication base station, the lowest signal strength value within the coverage area of ​​the communication base station, the average flow of each of the base station sectors corresponding to the communication base station, and call quality information corresponding to the communication base station, the call quality information is used to characterize whether there is an audio abnormality in the voice service provided by the communication base station, and the number of user connections of each of the base station sectors corresponding to the communication base station, and the fault type includes: base station antenna failure and other failures; An initial model is obtained, and the third training data set is used to train the initial model to obtain the third model, wherein the types of the initial model include: a neural network model, a decision tree model, and a probability statistics model.

7. The base station antenna fault monitoring method according to claim 1, characterized in that: After determining the cause of the antenna failure corresponding to the communication base station, the method further includes: Sending the antenna failure cause to the terminal device of the maintenance personnel corresponding to the communication base station; Obtain troubleshooting feedback information, and update the antenna failure cause corresponding to the second training data in the second training data set corresponding to the second model based on the troubleshooting feedback information, wherein the troubleshooting feedback information is used to characterize the antenna failure cause determined by the maintenance personnel after troubleshooting the base station antenna.

8. A base station antenna fault monitoring device, characterized in that: include: A first acquisition module is used to acquire communication status data of a communication base station within a monitoring period, wherein the communication status data is used to characterize the signal strength, traffic situation and user terminal connection status of each base station sector corresponding to the communication base station; A fault judgment module, configured to use a first model to extract data features corresponding to the communication status data, and determine a fault status label corresponding to the communication base station based on the data features, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether the communication base station has a fault; A second acquisition module is used to acquire the alarm information corresponding to the communication base station when the fault status label is a first label, wherein the first label is used to indicate that the communication base station has a base station antenna fault; A cause analysis module is used to use a second model to determine the cause of the antenna failure corresponding to the communication base station based on the communication status data and the alarm information, wherein the first model is a model trained based on historical data and corresponding labels for predicting whether the communication base station has a fault.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the base station antenna fault monitoring method according to any one of claims 1 to 7 is executed when the program is run.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the base station antenna fault monitoring method according to any one of claims 1 to 7 by running the computer program.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the base station antenna fault monitoring method according to any one of claims 1 to 7 are implemented.

Images