Monitoring method and device for room division system and electronic equipment

Abstract

The application discloses a kind of monitoring method, device and electronic equipment of room distribution system.The method comprises: obtaining the standing wave ratio data of room distribution system;According to the standing wave ratio data, determine the first room distribution system, wherein the first room distribution system is part of the room distribution system in abnormal state;Determine the user characteristic data of first room distribution system and second room distribution system, and according to the user characteristic data, the residual network is trained, to obtain the room distribution monitoring model, wherein the second room distribution system is the room distribution system in normal state;The room distribution monitoring model is used to monitor the room distribution system, and the monitoring result of room distribution system is obtained.The application solves the technical problem that the room distribution monitoring technology in the related art is difficult to effectively identify the signal quality decline caused by the small change of passive device or loose connection, especially in the environment where user tidal effect is significant and index fluctuation is large, false alarm or false negative is easy to occur, which affects network maintenance efficiency and user experience.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a monitoring method, device, and electronic equipment for an indoor distribution system. Background Technology

[0002] In modern wireless communication networks, indoor distributed antenna systems (DAS) play a crucial role, especially in high-traffic and complex building structures such as hospitals, large shopping malls, and office buildings. DAS are the primary means for operators to address insufficient indoor coverage. However, the numerous passive components in DAS, such as couplers, power dividers, and feeders, are susceptible to significant signal quality degradation if connections become loose, devices suffer physical damage, or their performance declines. This, in turn, affects the quality of indoor mobile communication services. Such problems are often only discovered after users complain about network quality degradation, delaying fault location and repair, and directly impacting user experience and the operator's network service reputation.

[0003] In related technologies, indoor distributed antenna system (DAS) monitoring typically relies on monitoring changes in user traffic, number of users, and user performance indicators to identify potential system anomalies. However, these methods have significant limitations in practical applications. First, the large fluctuations in indicators caused by user tidal effects make it difficult to accurately determine whether an indoor DAS system is truly malfunctioning based solely on changes in user performance indicators. Second, the existence of coverage blind spots in indoor DAS systems can lead to misjudgments by the telecommunications network; even if the system is functioning normally, false reports of network quality degradation may occur due to ineffective coverage in certain areas. Furthermore, failures in passive components typically do not trigger any direct alarm signals, further increasing the difficulty of monitoring indoor DAS systems.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a monitoring method, device, and electronic device for an indoor distributed antenna system (DAS) system, which at least solves the technical problem that indoor DAS monitoring technology in related technologies is difficult to effectively identify signal quality degradation caused by minor changes in passive components or loose connections, especially in environments with significant user tidal effects and large fluctuations in indicators, which can easily lead to false alarms or missed alarms, affecting network maintenance efficiency and user experience.

[0006] According to one aspect of the embodiments of this application, a monitoring method for an indoor distributed antenna system (DAS) is provided, comprising: acquiring standing wave ratio (SWR) data of the DAS; determining a first DAS based on the SWR data, wherein the first DAS is a DAS in which a portion of the DAS is in an abnormal state; determining user characteristic data of the first DAS and a second DAS, and training a residual network based on the user characteristic data to obtain an indoor DAS monitoring model, wherein the second DAS is an DAS in a normal state; and monitoring the DAS using the indoor DAS monitoring model to obtain monitoring results of the DAS, wherein the monitoring results are used to reflect the abnormal state of the DAS.

[0007] Optionally, determining the first indoor distribution system based on VSWR data includes: determining the actual VSWR fluctuation amplitude, trend value, trend index, and trend strength of the indoor distribution system based on VSWR data; determining the average trend index of the indoor distribution system based on the actual VSWR fluctuation amplitude, trend value, trend index, and trend strength; and determining the first indoor distribution system based on the average trend index and a first preset threshold.

[0008] Optionally, determining user characteristic data for the first and second indoor distributed antenna systems includes: identifying target users in the first and second indoor distributed antenna systems, wherein the target users represent users who can reflect the overall performance of the distributed antenna systems within a preset time period; acquiring behavioral characteristic data of the target users, wherein the behavioral characteristic data includes at least one of the following: the target user's reference signal received power, signal-to-noise ratio, and power margin report; and converting the behavioral characteristic data into a feature matrix form to obtain user characteristic data.

[0009] Optionally, determining target users in the first and second indoor distributed antenna systems includes: identifying abnormal data in the first and second indoor distributed antenna systems; removing abnormal data and determining the daily call detail record (CDR) duration for all users in the first and second indoor distributed antenna systems, wherein the daily CDR duration represents the length of time a user effectively communicates with the network within a day; and identifying users whose daily CDR duration is lower than a second preset threshold as target users.

[0010] Optionally, the residual network is trained based on user feature data, including: performing preliminary processing on the user feature data through convolutional layers in the residual network to obtain a first feature map; performing deep feature learning on the first feature map through multiple residual blocks in the residual network to obtain a second feature map; and performing fusion processing on the second feature map through fully connected layers in the residual network to obtain a prediction result corresponding to the user feature data, wherein the prediction result includes a first classification label used to determine the abnormal state of the indoor distribution system.

[0011] Optionally, the method further includes: determining the difference between the first classification label and the second classification label through an objective loss function, wherein the second classification label is a manually labeled true label used to represent the status of the indoor distribution system; adjusting the model parameters of the residual network according to the difference value to obtain the indoor distribution monitoring model.

[0012] Optionally, the method further includes: determining true positives, false positives, true negatives, and false negatives of the indoor distribution system, wherein true positives represent the number of indoor distribution systems correctly identified as abnormal by the indoor distribution monitoring model; false positives represent the number of indoor distribution systems incorrectly identified as abnormal by the indoor distribution monitoring model; true negatives represent the number of indoor distribution systems correctly identified as normal by the indoor distribution monitoring model; and false negatives represent the number of indoor distribution systems incorrectly identified as normal by the indoor distribution monitoring model. Based on the true positives, false positives, true negatives, and false negatives, the block accuracy of the user feature data is determined, wherein the block accuracy represents the classification accuracy of each feature matrix in the user feature data.

[0013] Optionally, the method further includes: determining the station accuracy of the indoor distribution system based on the block accuracy, wherein the station accuracy is used to represent the overall classification accuracy of the indoor distribution system.

[0014] According to another aspect of the embodiments of this application, a monitoring device for an indoor distribution system is also provided, comprising: an acquisition module for acquiring standing wave ratio (SWR) data of the indoor distribution system; a determination module for determining a first indoor distribution system based on the SWR data, wherein the first indoor distribution system is an indoor distribution system in which a portion is in an abnormal state; a training module for determining user characteristic data of the first indoor distribution system and a second indoor distribution system, and training a residual network based on the user characteristic data to obtain an indoor distribution monitoring model, wherein the second indoor distribution system is an indoor distribution system in which a portion is in a normal state; and a monitoring module for monitoring the indoor distribution system through the indoor distribution monitoring model to obtain monitoring results of the indoor distribution system, wherein the monitoring results are used to reflect the abnormal state of the indoor distribution system.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory and a processor, wherein the memory is used to store program instructions; and the processor is connected to the memory and used to execute the monitoring method for implementing the above-described indoor distribution system.

[0016] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored computer program, wherein the device containing the non-volatile storage medium executes the above-described monitoring method of the indoor distribution system by running the computer program.

[0017] According to another aspect of the embodiments of this application, a computer program product is also provided, including computer instructions, which, when executed by a processor, implement the monitoring method of the above-described indoor distribution system.

[0018] In this embodiment, the VSWR data of the indoor distributed antenna system (DAS) is obtained; a first indoor DAS is determined based on the VSWR data, wherein the first indoor DAS is a partially abnormal indoor DAS; user characteristic data of the first and second indoor DAS are determined, and the residual network is trained based on the user characteristic data to obtain an indoor DAS monitoring model, wherein the second indoor DAS is an indoor DAS in a normal state; the indoor DAS is monitored through the indoor DAS monitoring model to obtain the monitoring results of the indoor DAS, wherein the monitoring results are used to reflect the abnormal state of the indoor DAS, achieving the purpose of accurately identifying and locating explicit and implicit obstacles in the indoor DAS, thereby realizing early warning and rapid response, and effectively improving the technical effect of indoor mobile network service quality. This solves the technical problem that indoor DAS monitoring technology in related technologies is difficult to effectively identify signal quality degradation caused by minor changes or loose connections of passive components, especially in environments with significant user tidal effects and large index fluctuations, which easily leads to false alarms or missed alarms, affecting network maintenance efficiency and user experience. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a hardware structure diagram of a computer terminal for implementing a monitoring method for an indoor distribution system according to an embodiment of this application;

[0021] Figure 2 This is a flowchart of a monitoring method for an indoor distribution system according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of the structure of a residual block according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of a loss value change curve according to an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of a block accuracy variation curve according to an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of station accuracy according to an embodiment of this application;

[0026] Figure 7This is a schematic diagram of a confusion matrix for station accuracy according to an embodiment of this application;

[0027] Figure 8 This is a structural diagram of a monitoring device for an indoor distribution system according to an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] First, some nouns or terms that appear in the explanation of the embodiments of this application shall be interpreted as follows:

[0031] Indoor Distributed System (IDS): A system used to improve wireless signal coverage and quality inside buildings. It distributes signals from a signal source to various corners of the room through a distributed antenna network, especially for solving signal coverage problems in large buildings or underground spaces.

[0032] Passive components: In indoor distribution systems, passive components refer to those components that can operate without an external power supply, such as couplers, power dividers, combiners, feeders, connectors, etc. They are used for signal distribution and transmission.

[0033] Residual Network (ResNet): A deep learning neural network architecture that addresses the vanishing and exploding gradient problems in deep networks by introducing residual blocks. This allows the network to be trained at deeper layers without significantly degrading performance. Residual blocks allow the network to learn residual functions—the difference between the input and output—rather than directly learning the input-to-output mapping, making the training of deep residual networks more efficient.

[0034] VSWR (Voltage Standing Wave Ratio) is a key parameter that measures the impedance matching between the antenna and the transmission line (feeder) in a wireless communication system. In the field of wireless communication, especially in mobile communication networks, VSWR is often used to evaluate the health status and signal transmission efficiency of indoor distributed antenna systems (DAS).

[0035] RSRP (Reference Signal Received Power) is a key technical indicator in LTE (Long Term Evolution) and NR (New Radio, 5G) networks, used to measure the power level of the reference signal received by user equipment. In indoor distributed antenna system (DAS) monitoring, a continuous decrease in RSRP value may indicate a problem with the connection between the signal source and the receiver, or changes in the indoor environment affecting signal propagation. Therefore, it is an important parameter for detecting the health status of indoor DAS systems.

[0036] SINR (Signal-to-Interference plus Noise Ratio) is a commonly used metric for measuring signal quality in wireless communication. It represents the ratio of signal power to the sum of interference and noise power. A higher SINR indicates better signal quality and higher communication stability and reliability. In monitoring indoor distributed antenna systems (DAS), changes in SINR can reveal the presence of external interference or antenna performance degradation, helping to diagnose potential system faults.

[0037] PHR (Power Headroom Report): Part of the uplink in LTE and NR networks, it primarily reports the power headroom of user equipment (UE) during uplink transmission. PHR provides the difference between the maximum power a UE can use under current conditions and the actual power used. In indoor distributed antenna systems (DAS), monitoring PHR helps assess whether the UE's power is limited and whether the DAS can effectively support the UE's uplink transmission, indirectly reflecting the DAS's performance and stability.

[0038] To address the issue of poor indoor monitoring efficiency in related technologies, this application provides a monitoring method for an indoor distribution system. This method can operate in... Figure 1 The computer terminal shown is described below.

[0039] The monitoring method for indoor distribution systems provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a monitoring method for an indoor distribution system is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions connected via wired and / or wireless networks. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0040] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be implemented wholly or partially as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0041] The memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the indoor distribution system monitoring method in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned indoor distribution system monitoring method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0042] The transmission module 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission module 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0043] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0044] It should be noted here that, in some optional embodiments, the above... Figure 1 The computer terminal shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 1 This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned computer terminal.

[0045] In the above operating environment, this application provides an embodiment of a monitoring method for an indoor distribution system. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0046] Figure 2 This is a flowchart of a monitoring method for an indoor distribution system according to an embodiment of this application, such as... Figure 2As shown, the method includes the following steps:

[0047] Step S202: Obtain the VSWR data of the indoor distribution system.

[0048] In step S202 above, regular data collection of the indoor distribution system is required, for example, measuring the standing wave ratio (VSWR) twice daily. VSWR is a crucial indicator of antenna system matching. Ideally, the antenna and feed line should be perfectly matched, resulting in a VSWR of 1, indicating that all transmitted energy is absorbed by the antenna with no reflection. However, in real-world environments, the VSWR value is typically greater than 1, indicating that some energy is reflected back to the feed line, reflecting the efficiency of energy transmission. By obtaining VSWR data, we can further analyze the physical link signal transmission quality of the indoor distribution system.

[0049] Step S204: Determine the first indoor distribution system based on the VSWR data, wherein the first indoor distribution system is an indoor distribution system in an abnormal state.

[0050] In step S204 above, improved quantitative financial data statistical characteristics can be used to evaluate indicators such as the true fluctuation amplitude, trend value, trend index, and trend strength of the VSWR, ultimately obtaining the average trend index (an exponentially weighted moving average) of the indoor distributed antenna system (DAS). Subsequently, by analyzing the average trend index of the indoor DAS, the first DAS system with a relatively significant change in wireless link transmission quality is identified, i.e., the system with latent or overt faults. Through in-depth analysis of VSWR data, potential problems in the indoor DAS can be detected at an early stage, without waiting for user complaints or obvious network performance degradation.

[0051] Step S206: Determine the user characteristic data of the first indoor distribution system and the second indoor distribution system, and train the residual network based on the user characteristic data to obtain the indoor distribution monitoring model, wherein the second indoor distribution system is the indoor distribution system in a normal state.

[0052] In step S206 above, the core task is to construct and optimize a deep learning model for monitoring the status of the indoor distribution system. Specifically, firstly, target users (high-quality users) are selected from the identified first indoor distribution system (abnormal system) and second indoor distribution system (normal system), and user feature data, including but not limited to indicators such as RSRP, SINR, and PHR, are processed to form a high-quality feature dataset. Subsequently, a residual network (ResNet) is used to train on these datasets, and deep learning is used to extract and learn user behavior features under normal and abnormal states.

[0053] Unlike traditional monitoring approaches, this application abandons the consideration of single-user temporal continuity and instead focuses on pattern recognition of different user characteristics, processing the data into a feature matrix, which effectively improves the training efficiency and judgment accuracy of the model. Ultimately, after multiple rounds of training and optimization, an indoor distribution monitoring model is obtained, which can accurately determine whether the indoor distribution system is in an abnormal state based on user characteristic data, providing a solid foundation for subsequent intelligent monitoring and fault location.

[0054] Step S208: Monitor the indoor distribution system using the indoor distribution monitoring model to obtain the monitoring results of the indoor distribution system, wherein the monitoring results are used to reflect the abnormal state of the indoor distribution system.

[0055] In step S208 above, after model training is completed, the indoor distribution monitoring model is applied to the entire indoor distribution system to perform intelligent monitoring of the system in real time or at regular intervals. The indoor distribution monitoring model can determine the current state of the indoor distribution system based on the patterns learned from user characteristic data and output monitoring results. These results reflect whether the system is in an abnormal state.

[0056] Through steps S202 to S208, the goal of accurately identifying and locating explicit and implicit faults in the indoor distribution system is achieved, thereby realizing early warning and rapid response, and effectively improving the quality of indoor mobile network services. This solves the technical problem that indoor distribution monitoring technology in related technologies struggles to effectively identify signal quality degradation caused by minor changes in passive components or loose connections, especially in environments with significant user tidal effects and large fluctuations in indicators, easily leading to false alarms or missed alarms, thus affecting network maintenance efficiency and user experience. A detailed explanation follows.

[0057] In step S204 above, determining the first indoor distribution system based on the VSWR data includes: determining the actual VSWR fluctuation amplitude, trend value, trend index, and trend strength of the indoor distribution system based on the VSWR data; determining the average trend index of the indoor distribution system based on the actual VSWR fluctuation amplitude, trend value, trend index, and trend strength; and determining the first indoor distribution system based on the average trend index and a first preset threshold.

[0058] In this embodiment, the nonlinear fitting capability of deep learning technology is fully utilized, and data analysis methods from the financial field are introduced into indoor distributed antenna system (DAS) monitoring. This solves problems that traditional monitoring methods struggle to address, such as variations in the wireless environment, user tidal effects, and the lack of alarms from passive devices. The specific process is as follows:

[0059] First, by analyzing VSWR data, the true fluctuation range (reflecting the degree of change in VSWR), trend value (indicating the upward or downward trend of VSWR), trend index (quantifying the strength of the trend), and trend strength (a measure of the overall trend) of the indoor distributed antenna system (DAS) are calculated. These indicators are calculated based on improved quantitative financial data statistical methods, identifying short-term and long-term fluctuation patterns by comparing VSWR values ​​at different time points. The following sections explain the data for each of these indicators:

[0060] (1) True fluctuation range of VSWR TR:

[0061] The True Range (TR) of the Standing Wave Ratio (SWR) is an indicator used to calculate the degree of change in the SWR. It measures the amplitude of the SWR fluctuation by comparing the maximum and minimum values ​​of the SWR on a given day with the average value of the previous day. A higher TR value indicates more drastic fluctuations in the SWR, which may indicate system instability or a fault.

[0062] The specific expression is as follows:

[0063] TR = max(V) H -V L V H -V PF V PF -V L )

[0064] In the formula, V H V is the maximum value of the standing wave ratio on that day. L V is the minimum value of the standing wave ratio on that day. PF This represents the average standing wave ratio of the previous day.

[0065] (2) Positive and negative trend values ​​(+DM and -DM):

[0066] The trend value describes the upward (+DM) or downward (-DM) trend of the VSWR over a period of time. By comparing the maximum and minimum values ​​of the previous day, it is possible to calculate whether the VSWR has increased or decreased compared to the previous day, and the magnitude of the change. A positive trend value indicates an upward trend, while a negative trend value indicates a downward trend.

[0067] The specific expression is as follows:

[0068]

[0069] In the formula, V PH V represents the maximum value of the standing wave ratio from the previous day. PL This is the minimum value of the standing wave ratio from the previous day.

[0070] To reduce the impact of fluctuations, an M-day exponentially weighted moving average can be applied, as shown in the following expression:

[0071] EX M =[X×2+EX M-1 [×(M-1)] / (M+1)

[0072] In the formula, EX M EX is the exponential average of day M. M-1 X is the index average for day M-1, and X is the indicator to be processed, such as TR or ±DM.

[0073] (3) Positive and negative trend indices (+DI and -DI):

[0074] The Directional Movement Index (DPI) reduces the impact of short-term fluctuations on trend judgment by weighting trend values. It uses an exponentially decreasing weighted moving average to calculate the average of trend values ​​over multiple consecutive days (e.g., M days), thus more accurately reflecting the long-term trend of the standing wave ratio (SWR). +DI and -DI represent the strength of positive and negative trends, respectively.

[0075] The specific expression is as follows:

[0076] +DI=EX +DM / EX TR ×100

[0077] -DI=EX -DM / EX TR ×100

[0078] In the formula, EX +DM EX represents the exponential average of +DM. -DM EX represents the exponential average of -DM. TR This represents the exponential average of TR.

[0079] (4) Trend strength (DX):

[0080] Trend strength is measured by the absolute value of the difference between the positive and negative DX indices, representing the relative strength between upward and downward trends in the VSWR. A larger DX value indicates a more pronounced trend in the VSWR, potentially caused by system anomalies.

[0081] The specific expression is as follows:

[0082] DX=|+DI-(-DI)| / |+DI+(-DI)|×100

[0083] Secondly, after obtaining the aforementioned statistical indicators of VSWR, the Average Trend Index (ADX) of the indoor distribution system is further calculated. This is a comprehensive indicator optimized for differences in the wireless environment. ADX is processed by an exponentially weighted moving average, which can more accurately reflect the overall state of the indoor distribution system over a period of time, including whether it tends towards anomalies.

[0084] The specific expression is as follows:

[0085] ADX = Exponential Moving Average (DX, M)

[0086] Finally, by comparing ADX with a first preset threshold, those first indoor distribution systems exhibiting abnormalities can be identified. For example, regarding ADX... N :

[0087] When ADX 1,…,N-1 When the mean is ≤0.5, if ADX N If the value is ≥10, the indoor distribution system is abnormal;

[0088] When ADX 1,…,N-1 When the mean is greater than 0.5, if ADX N If the value is ≥25, then there is a problem with the indoor distribution system.

[0089] At this point, some indoor distribution systems with hidden faults have been detected. Field verification showed that the accuracy of the VSWR monitoring scheme using the above method was 99.85%.

[0090] Meanwhile, after a period of monitoring and verification, data accumulation, combined with daily inspections and tests of indoor distribution scenarios, can yield a list of indoor distribution sectors with a sufficient number of positive and negative samples.

[0091] In step S206 above, determining the user characteristic data of the first indoor distribution system and the second indoor distribution system includes: determining the target users in the first indoor distribution system and the second indoor distribution system, wherein the target users are used to represent users who can reflect the overall performance of the indoor distribution system within a preset time period; obtaining the behavioral characteristic data of the target users, wherein the behavioral characteristic data includes at least one of the following: the target user's reference signal received power, signal-to-noise ratio, and power margin report; and converting the behavioral characteristic data into a feature matrix form to obtain the user characteristic data.

[0092] The process of identifying target users in the first and second indoor distributed antenna systems includes: identifying abnormal data in the first and second indoor distributed antenna systems; removing abnormal data and determining the daily call detail record (CDR) duration for all users in the first and second indoor distributed antenna systems, wherein the daily CDR duration represents the length of time a user has effectively communicated with the network within a day; and identifying users whose daily CDR duration is lower than a second preset threshold as target users.

[0093] In this embodiment, the process of determining the target users and their behavioral characteristic data in the first and second indoor distribution systems is a crucial step in the refined management of indoor distribution system monitoring data. The specific steps are as follows:

[0094] S1: Identify the target users.

[0095] Target users refer to users who can reflect the overall performance of the indoor distribution system within a preset time period. Their behavioral characteristics data are more representative and therefore suitable for training and validating deep learning models.

[0096] Specifically, firstly, to avoid interference from IoT lag and abnormal users, it is necessary to detect and remove abnormal data from both the first and second indoor distributed antenna system (DAS) to ensure the quality and integrity of the dataset. Abnormal data includes, but is not limited to, erroneous measurements, extreme values, or invalid values ​​generated by network failures. Next, the daily call detail record (CDR) duration for all users is calculated, i.e., the length of time a user effectively interacts with the network within a day. Finally, a second preset threshold (e.g., P hours) is set to filter target users. Users with CDR durations below this threshold are identified as target users. The purpose of this step is to exclude user data with extremely short call times or very little usage, as this data may not adequately reflect the overall performance of the DAS.

[0097] S2: Obtain behavioral feature data.

[0098] Behavioral characteristic data mainly includes the target user's reference signal received power (RSRP), signal-to-noise ratio (SINR), and power headroom report (PHR). These indicators are directly related to the user's perceived network quality and the operating status of the indoor distribution system.

[0099] S3: Data Conversion and Processing.

[0100] Behavioral feature data is cleaned and converted into a feature matrix format to provide structured data input for deep learning models. The feature matrix effectively organizes behavioral feature data from multiple users, facilitating batch processing and feature learning by neural networks. The hourly feature matrix data format for a sector of an indoor distribution system can be shown below:

[0101]

[0102] Among them, DataHour KY This represents the performance data for the Kth target user in the Yth hour.

[0103] This process not only yields high-quality user behavior data but also ensures that every data point in the dataset originates from target users who accurately reflect the status of the indoor distribution system. Thus, data collected from both the first (abnormal) and second (normal) indoor distribution systems provides valuable input for training the neural network model, thereby improving the model's accuracy and robustness in monitoring the status of the indoor distribution system.

[0104] Furthermore, the residual network is trained based on user feature data, including: performing preliminary processing on the user feature data through convolutional layers in the residual network to obtain a first feature map; performing deep feature learning on the first feature map through multiple residual blocks in the residual network to obtain a second feature map; and performing fusion processing on the second feature map through fully connected layers in the residual network to obtain a prediction result corresponding to the user feature data, wherein the prediction result includes a first classification label used to determine the abnormal state of the indoor distribution system.

[0105] In this embodiment of the application, ResNet introduces, for example... Figure 3 The residual blocks shown are short-circuited, avoiding direct learning of complex mapping relationships. Instead, they learn the residuals between the input and output, making gradient propagation more efficient during backpropagation and mitigating the vanishing gradient problem. Specifically, the input x of the residual block passes through weight layers (a series of convolutional operations), activation functions, etc., to obtain the residual function F(x). The residual block output H(x) is obtained by element-wise addition of F(x) and x. Subsequently, for the residual network, F(x) = H(x) - x is directly learned. By learning the residuals, the network can also distinguish between effective and redundant features in different layers, avoiding network degradation.

[0106] ResNet offers five different network structures with 18, 34, 50, 101, and 152 layers. This application uses ResNet-18, which consists of convolutional layers, residual blocks, and fully connected layers. Specifically, firstly, user feature data undergoes preliminary feature extraction through ResNet's convolutional layers (7×7 dimensions, stride 2, padding 3), generating a first feature map that captures spatial correlations in the data. Subsequently, multiple residual blocks are used to perform deep learning on the first feature map to enhance the network's learning ability and feature representation. Each residual block contains two 3×3 convolutional layers with stride 1 and padding 1, and a residual connection. Each convolutional layer is followed by batch normalization and a ReLU function. Between multiple residual blocks, the feature map size of the convolutional data map is halved, while the number of channels is doubled. Finally, fully connected layers fuse the second feature map obtained through deep learning, outputting the first classification label, i.e., the prediction result of whether the indoor distribution system has an abnormal state.

[0107] This series of operations fully leverages the advantages of ResNet, effectively handling the complexity of the wireless environment and the diversity of datasets, achieving accurate detection of hidden obstacles in indoor distribution systems, greatly improving the accuracy and efficiency of monitoring, and providing strong support for the maintenance and optimization of indoor distribution systems.

[0108] Optionally, the above-mentioned indoor distribution monitoring model is determined by: determining the difference between the first classification label and the second classification label through the objective loss function, wherein the second classification label is a manually labeled true label used to represent the status of the indoor distribution system; adjusting the model parameters of the residual network according to the difference value to obtain the indoor distribution monitoring model.

[0109] In this embodiment, the objective loss function is used to quantify the difference between the first classification label generated by the residual network and the manually labeled second classification label, i.e., the gap between the model's prediction result and the actual state of the indoor distribution system. By calculating this difference value, the prediction accuracy of the model during training can be clearly evaluated, and the network's model parameters can be adjusted accordingly to optimize the network's learning process.

[0110] The specific expression is as follows:

[0111]

[0112] In the formula, J is the difference value, P is the number of sample points (user feature data), K is the number of label categories, and y ic To digitally encode the target value of the sample, h θ (x i ) c For the observed sample x i The predicted probability value for belonging to category c.

[0113] Specifically, after each training iteration, the loss function calculates the difference between the model's predicted classification label and the actual label. This difference guides the direction of model parameter updates, ensuring that the model's learning direction aligns with the target. Subsequently, an adaptive moment estimation algorithm (such as Adam) is used to optimize the learning rate, dynamically adjusting the step size of parameter updates and helping the model converge to its optimal state more quickly. Furthermore, techniques such as Dropout are added to prevent overfitting, further improving the model's generalization ability and enabling it to accurately determine the state of the indoor distribution system even on unseen data.

[0114] Figure 4 This shows the loss value changes during ResNet-18 training, with green and red representing the loss value curves during training and testing, respectively. Figure 4 It can be seen that as the number of iterations increases, the loss value gradually stabilizes, and the difference between the model prediction and the actual result gradually decreases.

[0115] Optionally, the above method further includes: determining true positives, false positives, true negatives, and false negatives of the indoor distribution system, wherein true positives represent the number of indoor distribution systems correctly identified as abnormal by the indoor distribution monitoring model; false positives represent the number of indoor distribution systems incorrectly identified as abnormal by the indoor distribution monitoring model; true negatives represent the number of indoor distribution systems correctly identified as normal by the indoor distribution monitoring model; and false negatives represent the number of indoor distribution systems incorrectly identified as normal by the indoor distribution monitoring model. Based on the true positives, false positives, true negatives, and false negatives, the block accuracy of the user feature data is determined, wherein the block accuracy represents the classification accuracy of each feature matrix in the user feature data.

[0116] Furthermore, the station accuracy of the indoor distribution system can be determined based on the block accuracy, where the station accuracy is used to represent the overall classification accuracy of the indoor distribution system.

[0117] In this embodiment, the hourly data within a single sector over Y days is divided into multiple feature matrices (a total of N). Subsequently, the indoor distribution monitoring model independently predicts each feature matrix and outputs the judgment result for the entire indoor distribution system, i.e.:

[0118] S = [s1, s2, ..., s N ]

[0119] Where N is the number of user feature matrices; s i Block accuracy, i.e., the accuracy of each feature matrix, takes the value of 0 or 1, representing normal or abnormal state respectively, i = 1, ..., N; S is station accuracy, i.e. the accuracy of the entire indoor distribution system.

[0120] It should be noted that accuracy is a comprehensive metric used to measure the proportion of correctly classified samples on test data. In other words, it is the proportion of all classification decisions in which the model correctly predicts the total number of samples of all categories (including normal and abnormal states).

[0121] Specifically, block accuracy is calculated for each feature matrix s. i The accuracy calculation is suitable for evaluating the model's ability to classify a single user feature matrix and can directly reflect the model's accuracy when processing individual data blocks.

[0122] The specific calculation formula is as follows:

[0123] Acc = (TP + TN) / (TP + TN + FP + FN)

[0124] In the formula, TP, FP, TN, and FN represent the true positive, false positive, true negative, and false negative examples of the indoor distribution system, respectively. A detailed analysis follows:

[0125] True Case (TP): The number of times the model correctly identifies an actual abnormal indoor distribution system as an abnormal state, reflecting the model's effectiveness in detecting abnormal situations.

[0126] False positives (FP): The number of times the model incorrectly identifies a normal indoor distribution system as an abnormal state, which usually reflects the false alarm rate of the model under specific conditions.

[0127] True Negative Examples (TN): The number of times the model correctly identifies an indoor distribution system that is actually in a normal state as being in a normal state, demonstrating the model's accuracy in excluding anomalies.

[0128] False negatives (FN): The number of times the model incorrectly identifies an abnormal indoor distribution system as a normal one, meaning that the model may miss the real problem in some cases.

[0129] Station accuracy is the accuracy of judging the status of the entire indoor distribution system. Considering that the prediction of a single data block may be affected by local interference or data noise, station accuracy employs a decision mechanism: if the majority of data blocks s... i If the prediction results tend to be abnormal (≥3 / 5N), the entire indoor distribution system is judged to be abnormal; otherwise, it is normal.

[0130] The specific calculation formula is as follows:

[0131]

[0132] Figure 5 This shows the block accuracy variation curves during ResNet-18 training, where green and red represent the accuracy curves during training and testing, respectively. Figure 5 As can be seen, with the increase of the number of iterations, the block accuracy gradually rises to 85.3%, and the model prediction results become more and more accurate.

[0133] Figure 6 This represents the station accuracy after ResNet-18 training, with different points representing different indoor distribution sectors. Figure 6 It can be seen that there were 120 stations in the test, and 115 of them met the 3 / 5N condition, with a station accuracy rate of 95.83%.

[0134] Figure 7 This is the confusion matrix representing the station accuracy after ResNet-18 training, showing the specific sample distribution in the test set. Figure 7 It can be seen that there are a total of 120 samples, of which 61 are positive and 59 are negative; 56 samples were correctly predicted for label 0 and 59 samples were correctly predicted for label 1.

[0135] In this application embodiment, a trend-based AI indoor distribution system monitoring method is proposed by combining the statistical characteristics of data in the financial field with wireless communication technology and deep learning. This method effectively filters out systems with hidden obstacles by calculating the true fluctuation amplitude, trend value, and trend index of the indoor distribution system's standing wave ratio (VSWR), solving the problem of data acquisition difficulties caused by differences in the wireless environment. Simultaneously, by using an improved residual network (ResNet) to train on the behavioral feature data of selected users, it not only overcomes the misjudgment problem of traditional monitoring methods under user tidal effects but also significantly improves the model's accuracy by introducing a target loss function and parameter adjustment mechanism. This enables the detection of anomalies in the indoor distribution system before user complaints, allowing for timely repairs and significantly improving network quality and user experience. Particularly in indoor scenarios such as hospitals, large shopping malls, and office buildings, it has extremely high monitoring and early warning capabilities for network quality degradation caused by passive component problems, thereby optimizing operators' maintenance strategies, reducing operation and maintenance costs, and enhancing the stability and reliability of the indoor distribution system.

[0136] According to embodiments of this application, a monitoring device for an indoor distributed antenna system (DAS) is provided. It should be noted that the monitoring device for the DAS provided in this application can be used to execute the monitoring method for the DAS provided in this application. The monitoring device for the DAS provided in this application is described below.

[0137] Figure 8 This is a structural diagram of a monitoring device for an indoor distribution system provided according to an embodiment of this application. Figure 8 As shown, the device includes:

[0138] Module 80 is used to acquire the VSWR data of the indoor distribution system;

[0139] The determination module 82 is used to determine the first indoor distribution system based on the standing wave ratio data, wherein the first indoor distribution system is an indoor distribution system in which part of the indoor distribution system is in an abnormal state;

[0140] Training module 84 is used to determine the user characteristic data of the first indoor distribution system and the second indoor distribution system, and to train the residual network based on the user characteristic data to obtain the indoor distribution monitoring model. The second indoor distribution system is the indoor distribution system in a normal state.

[0141] The monitoring module 86 is used to monitor the indoor distribution system through the indoor distribution monitoring model and obtain the monitoring results of the indoor distribution system. The monitoring results are used to reflect the abnormal state of the indoor distribution system.

[0142] By utilizing the acquisition, determination, training, and monitoring modules within the aforementioned indoor distributed antenna system (DAS) monitoring device, the system accurately identifies and locates both visible and hidden obstacles. This enables early warning and rapid response, effectively improving the quality of indoor mobile network services. Furthermore, it addresses the technical challenge of indoor DAS monitoring technologies failing to effectively identify signal quality degradation caused by minor changes in passive components or loose connections, particularly in environments with significant user tidal effects and large fluctuations in indicators, which can easily lead to false alarms or missed alarms, impacting network maintenance efficiency and user experience.

[0143] In the monitoring device for an indoor distribution system provided in this application embodiment, the determining module is further configured to determine the true fluctuation amplitude, trend value, trend index, and trend strength of the indoor distribution system based on the standing wave ratio data; determine the average trend index of the indoor distribution system based on the true fluctuation amplitude, trend value, trend index, and trend strength of the standing wave ratio; and determine the first indoor distribution system based on the average trend index and a first preset threshold.

[0144] In the monitoring device for an indoor distribution system provided in this application embodiment, the training module is further used to determine target users in the first indoor distribution system and the second indoor distribution system, wherein the target user is used to represent the user who can reflect the overall performance of the indoor distribution system within a preset time period; to obtain behavioral feature data of the target user, wherein the behavioral feature data includes at least one of the following: the target user's reference signal received power, signal-to-noise ratio, and power margin report; and to convert the behavioral feature data into feature matrix form to obtain user feature data.

[0145] In the monitoring device for an indoor distributed antenna system provided in this application embodiment, the training module is further used to determine abnormal data in the first indoor distributed antenna system and the second indoor distributed antenna system; remove abnormal data, and determine the daily call detail record duration for all users in the first indoor distributed antenna system and the second indoor distributed antenna system, wherein the daily call detail record duration is used to represent the length of time a user has effectively communicated with the network in a day; and identify users whose daily call detail record duration is lower than a second preset threshold as target users.

[0146] In the monitoring device for an indoor distribution system provided in this application embodiment, the training module is further used to perform preliminary processing on user feature data through convolutional layers in the residual network to obtain a first feature map; to perform deep feature learning on the first feature map through multiple residual blocks in the residual network to obtain a second feature map; and to perform fusion processing on the second feature map through fully connected layers in the residual network to obtain a prediction result corresponding to the user feature data, wherein the prediction result includes a first classification label for judging the abnormal state of the indoor distribution system.

[0147] In the monitoring device for an indoor distribution system provided in this application embodiment, the training module is further used to determine the difference value between the first classification label and the second classification label through the target loss function, wherein the second classification label is a manually labeled real label used to represent the state of the indoor distribution system; the model parameters of the residual network are adjusted according to the difference value to obtain the indoor distribution monitoring model.

[0148] In the monitoring device for an indoor distribution system provided in this application embodiment, the training module is further used to determine the true positives, false positives, true negatives, and false negatives of the indoor distribution system. The true positives represent the number of indoor distribution systems correctly identified as abnormal by the indoor distribution monitoring model; the false positives represent the number of indoor distribution systems incorrectly identified as abnormal by the indoor distribution monitoring model; the true negatives represent the number of indoor distribution systems correctly identified as normal by the indoor distribution monitoring model; and the false negatives represent the number of indoor distribution systems incorrectly identified as normal by the indoor distribution monitoring model. Based on the true positives, false positives, true negatives, and false negatives, the block accuracy of the user feature data is determined, where the block accuracy represents the classification accuracy of each feature matrix in the user feature data.

[0149] In the monitoring device for an indoor distribution system provided in this application embodiment, the training module is further used to determine the station accuracy of the indoor distribution system based on the block accuracy, wherein the station accuracy is used to represent the overall classification accuracy of the indoor distribution system.

[0150] This application also provides an electronic device, including: a memory and a processor, wherein the memory is used to store program instructions; and the processor is connected to the memory and used to execute the monitoring method for implementing the above-described indoor distribution system.

[0151] It should be noted that the aforementioned electronic equipment is used to perform Figure 2 The monitoring method for the indoor distribution system shown above also applies to this electronic device, and will not be repeated here.

[0152] This application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device containing the non-volatile storage medium executes the monitoring method of the above-mentioned indoor distribution system by running the computer program.

[0153] It should be noted that the aforementioned non-volatile storage media is used for execution. Figure 2 The monitoring method for the indoor distribution system shown above is also applicable to this non-volatile storage medium, and will not be repeated here.

[0154] This application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above-described monitoring method for an indoor distribution system.

[0155] It should be noted that the above-mentioned computer program product is used to execute Figure 2 The monitoring method for the indoor distribution system shown above is also applicable to this computer program product, and will not be repeated here.

[0156] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0157] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0159] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0161] If the integrated unit is implemented as 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 this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0162] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A monitoring method for an indoor distribution system, characterized in that, include: Obtain the VSWR data of the indoor distribution system; The first indoor distribution system is determined based on the VSWR data, wherein the first indoor distribution system is a portion of the indoor distribution systems that are in an abnormal state; Determine the user characteristic data of the first indoor distribution system and the second indoor distribution system, and train the residual network based on the user characteristic data to obtain the indoor distribution monitoring model, wherein the second indoor distribution system is the indoor distribution system in a normal state. The indoor distribution system is monitored using the indoor distribution monitoring model to obtain monitoring results, wherein the monitoring results are used to reflect the abnormal state of the indoor distribution system.

2. The method according to claim 1, characterized in that, The first indoor distribution system is determined based on the VSWR data, including: Based on the VSWR data, determine the actual VSWR fluctuation amplitude, trend value, trend index, and trend strength of the indoor distribution system; The average trend index of the indoor distribution system is determined based on the actual fluctuation amplitude of the standing wave ratio, the trend value, the trend index, and the trend strength. The first indoor distribution system is determined based on the average trend index and the first preset threshold.

3. The method according to claim 1, characterized in that, Determining user characteristic data for the first and second indoor distribution systems includes: Identify target users in the first indoor distribution system and the second indoor distribution system, wherein the target users are defined as users who can reflect the overall performance of the indoor distribution system within a preset time period; The behavioral characteristic data of the target user is obtained, wherein the behavioral characteristic data includes at least one of the following: the target user's reference signal received power, signal-to-noise ratio, and power margin report; The behavioral feature data is converted into a feature matrix to obtain the user feature data.

4. The method according to claim 3, characterized in that, Identifying the target users in the first indoor distribution system and the second indoor distribution system includes: Identify abnormal data in the first and second indoor distribution systems; Remove the abnormal data and determine the daily call detail record duration for all users in the first and second indoor distribution systems, wherein the daily call detail record duration is used to represent the length of time a user effectively communicates with the network within a day; Users whose daily call detail record duration is lower than the second preset threshold are identified as the target users.

5. The method according to claim 1, characterized in that, Training the residual network based on the user feature data includes: The user feature data is preliminarily processed by the convolutional layers in the residual network to obtain a first feature map. The second feature map is obtained by performing deep feature learning on the first feature map through multiple residual blocks in the residual network; The second feature map is fused by the fully connected layer in the residual network to obtain a prediction result corresponding to the user feature data. The prediction result includes a first classification label for judging the abnormal state of the indoor distribution system.

6. The method according to claim 5, characterized in that, The method further includes: The difference between the first classification label and the second classification label is determined by a target loss function, wherein the second classification label is a manually labeled true label used to represent the state of the indoor distribution system; The model parameters of the residual network are adjusted based on the difference value to obtain the indoor monitoring model.

7. The method according to claim 1, characterized in that, The method further includes: The true positives, false positives, true negatives, and false negatives of the indoor distribution system are determined, wherein the true positives represent the number of indoor distribution systems correctly identified as abnormal by the indoor distribution monitoring model; the false positives represent the number of indoor distribution systems incorrectly identified as abnormal by the indoor distribution monitoring model; the true negatives represent the number of indoor distribution systems correctly identified as normal by the indoor distribution monitoring model; and the false negatives represent the number of indoor distribution systems incorrectly identified as normal by the indoor distribution monitoring model. Based on the true positives, false positives, true negatives, and false negatives, the block accuracy of the user feature data is determined, wherein the block accuracy is used to represent the classification accuracy of each feature matrix in the user feature data.

8. The method according to claim 7, characterized in that, The method further includes: The station accuracy of the indoor distribution system is determined based on the block accuracy, wherein the station accuracy is used to represent the overall classification accuracy of the indoor distribution system.

9. A monitoring device for an indoor distribution system, characterized in that, include: The acquisition module is used to acquire the VSWR data of the indoor distribution system; The determination module is used to determine the first indoor distribution system based on the standing wave ratio data, wherein the first indoor distribution system is an indoor distribution system in which part of the indoor distribution system is in an abnormal state; The training module is used to determine the user characteristic data of the first indoor distribution system and the second indoor distribution system, and to train the residual network based on the user characteristic data to obtain the indoor distribution monitoring model, wherein the second indoor distribution system is the indoor distribution system in a normal state. The monitoring module is used to monitor the indoor distribution system through the indoor distribution monitoring model and obtain the monitoring results of the indoor distribution system, wherein the monitoring results are used to reflect the abnormal state of the indoor distribution system.

10. An electronic device, characterized in that, include: A memory and a processor, wherein the memory is used to store program instructions; The processor, connected to the memory, is used to execute the monitoring method for the indoor distribution system according to any one of claims 1 to 8.

11. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored computer program, wherein the device containing the non-volatile storage medium executes the monitoring method of the indoor distribution system according to any one of claims 1 to 8 by running the computer program.

12. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the monitoring method of the indoor distribution system according to any one of claims 1 to 8.

Images