Methods, devices, equipment and media for anomaly detection in indoor distribution systems

Abstract

This application provides an anomaly detection method, apparatus, device, and medium for an indoor distribution system, belonging to the field of communication technology. The method includes: performing moving average processing on target data of the indoor distribution system collected at different times to obtain a first moving average value of the target data within different set time periods with the current time as the cutoff time, wherein the target data is used to measure the physical link signal transmission quality of the signal source in the indoor distribution system; determining whether the deviation between the first moving average values ​​of the target data within different set time periods is greater than a first preset threshold; and determining that an anomaly exists in the indoor distribution system if the deviation between the first moving average values ​​of the target data within different set time periods is greater than the first preset threshold.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and in particular to an abnormality detection method, device and equipment of an indoor distribution system and a medium. BACKGROUND

[0002] The indoor distribution system is often used to solve the problem of insufficient indoor coverage. When the indoor distribution system is constructed, a signal source is usually connected with an indoor feeder distribution system (including a large number of couplers, ceiling antennas and multiple sections of feeder lines, etc.) to expand the coverage area of the signal source and adapt to the complex bridge structure in the indoor environment.

[0003] In the related art, the abnormality of the indoor distribution system is mainly detected based on the performance indicators of resident users. However, when the indoor distribution system is partially damaged, it usually does not affect the normal use of most users (for example, only the mobile network quality in a local area is affected), so it is difficult to detect the related abnormality in time based on the performance indicators of resident users, and the problem is often found after the user complains, so the operation and maintenance is relatively lagging, which seriously affects the user experience. SUMMARY

[0004] In view of the above problems, the embodiments of the present application provide an abnormality detection method, device, equipment and medium of an indoor distribution system in order to overcome the above problems or at least partially solve the above problems.

[0005] In a first aspect, the embodiments of the present application provide an abnormality detection method of an indoor distribution system, which comprises:

[0006] Performing a moving average processing on target data of the indoor distribution system collected at different time instants to obtain a first moving average value of the target data in different set time lengths with a current time instant as a cutoff time instant, the target data being used to measure the physical link signal transmission quality of a signal source in the indoor distribution system;

[0007] Judging whether a deviation between the first moving average values of the target data in the different set time lengths is greater than a first preset threshold value;

[0008] In a case where the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold value, it is determined that the indoor distribution system has an abnormality.

[0009] As a possible implementation manner, the first moving average value of the target data in a single set time length with the current time instant as the cutoff time instant is determined by the following steps:

[0010] For each target data in a single set time length, a weight value is set for each target data in a descending order according to the time dimension distance between the collection time instant of each target data and the current time instant;

[0011] The target data in each of the set time lengths is weighted and moving average processed based on a weight value set for each of the target data, to obtain a first moving average value of the target data in each of the set time lengths.

[0012] As a possible implementation, when the target data is a standing wave ratio, the first moving average value of the target data in each of the set time lengths is determined by a first formula, which is expressed as follows:

[0013]

[0014] wherein, represents the first moving average value of the standing wave ratio in each of the set time lengths, N represents the number of collection time points in each of the set time lengths, represents the standing wave ratio collected at the current time point, represents a moving average value obtained by weighted and moving average processing on the standing wave ratios corresponding to N-1 time points in each of the set time lengths, the standing wave ratios corresponding to the N-1 time points including the remaining standing wave ratios in each of the set time lengths except the standing wave ratio collected at the current time point.

[0015] As a possible implementation, the different set time lengths include a first set time length and a second set time length, and the time length of the first set time length is less than that of the second set time length.

[0016] The method further includes:

[0017] obtaining a second moving average value of the target data in the first set time length, the second moving average value being different from the moving average processing mode corresponding to the first moving average value;

[0018] determining an abnormality degree of the target data in the first set time length according to the deviation between the second moving average value of the target data in the first set time length and the target data collected at the current time point;

[0019] The determination that the indoor distribution system is abnormal in the case where the deviation between the first moving average values of the target data in the different set time lengths is greater than a first preset threshold value includes:

[0020] The determination that the indoor distribution system is abnormal in the case where the deviation between the first moving average values of the target data in the different set time lengths is greater than a first preset threshold value, and the abnormality degree of the target data in the first set time length is greater than a second preset threshold value.

[0021] As one possible implementation, when the target data is the standing wave ratio (SWR), the anomaly degree of the target data within the first set time period is determined by a second formula, which is expressed as follows:

[0022]

[0023] in, This indicates the degree of anomaly in the VSWR within the first set time period. This indicates the standing wave ratio (SWR) collected at the current moment. This represents the second moving average of the VSWR within the first set time period.

[0024] As one possible implementation, the target data is the standing wave ratio (SWR); before determining whether the deviation between the first moving averages of the target data within different set time periods is greater than a first preset threshold, the method further includes:

[0025] Determine whether the standing wave ratio (SWR) collected at the current moment is greater than the preset SWR alarm threshold;

[0026] If the standing wave ratio (SWR) collected at the current time is greater than the preset SWR alarm threshold, the anomaly detection will be stopped and a SWR alarm will be issued.

[0027] As one possible implementation, the method further includes:

[0028] If the standing wave ratio at the current moment is not greater than the preset standing wave alarm threshold, and if an anomaly is determined in the indoor distribution system based on the standing wave ratio within the different set time periods, a work order will be issued to remind relevant personnel to locate the anomaly in the indoor distribution system.

[0029] A second aspect of this application provides an anomaly detection device for an indoor distribution system, the device comprising:

[0030] The first processing module is used to perform moving average processing on the target data of the indoor distribution system collected at different times to obtain the first moving average value of the target data within different set time periods with the current time as the cutoff time. The target data is used to measure the physical link signal transmission quality of the information source in the indoor distribution system.

[0031] The first judgment module is used to determine whether the deviation between the first moving average values ​​of the target data within different set time periods is greater than a first preset threshold.

[0032] The first detection module is used to determine that there is an anomaly in the indoor distribution system when the deviation between the first moving average of the target data within different set time periods is greater than a first preset threshold.

[0033] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the anomaly detection method for the indoor distribution system described in the first aspect.

[0034] A fourth aspect of this application provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the steps of the anomaly detection method for an indoor distribution system as described in the first aspect.

[0035] The embodiments of this application include the following advantages: Considering that partial damage to the indoor distribution system directly affects the physical link signal transmission quality of the signal source, this application measures the physical link signal transmission quality based on target data to effectively detect anomalies related to partial damage to the indoor distribution system; furthermore, considering the inherent volatility of the target data, this application uses the deviation between the moving averages of the target data over different set time periods—that is, whether there are significant differences in the long-term and short-term trends of the physical link signal transmission quality—as the basis for anomaly detection. This eliminates the interference of the inherent volatility of the target data and improves the accuracy of anomaly detection. Thus, this application can achieve timely and accurate detection of anomalies related to partial damage to the indoor distribution system, helping to improve the timeliness of operation and maintenance, thereby reducing user complaints and improving user experience. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating the implementation of an anomaly detection method for an indoor distribution system according to an embodiment of this application.

[0038] Figure 2 This is a schematic diagram illustrating a trend of VSWR variation in an embodiment of this application;

[0039] Figure 3 This is a schematic diagram of the VSWR variation trend and anomaly degree in an embodiment of this application;

[0040] Figure 4 This is a schematic diagram of another VSWR variation trend and anomaly in the embodiments of this application;

[0041] Figure 5This is a schematic diagram of the structure of an anomaly detection device for an indoor distribution system according to an embodiment of this application;

[0042] Figure 6 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0043] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] With the development of wireless communication technology, after a large number of macro base stations have formed effective area coverage, the issue of deep coverage quality in indoor scenarios such as commercial buildings, hospitals, and university buildings has begun to receive widespread attention.

[0045] Currently, indoor distribution systems are mainly used to address the problem of insufficient indoor deep coverage (i.e., poor deep coverage quality). In an indoor distribution system, a single signal source is often planned for signal coverage of a large area (e.g., around 10,000 square meters). Due to the complex structure of indoor cable trays, the signal source is usually connected to a large number of couplers, ceiling antennas, and multiple feeder lines to achieve indoor signal coverage during the construction of an indoor distribution system.

[0046] This complex connection structure, along with the irregular renovations of indoor environments, makes indoor distribution systems more susceptible to partial damage. For example, the connection between the coupler and the ceiling antenna (or between feeders) of the indoor distribution system may be damaged, leading to a significant decrease in coverage (i.e., the quality of mobile networks in local areas), which in turn causes severe degradation in the perception of nearby users.

[0047] In related technologies, anomaly detection of indoor distribution systems is mainly based on the performance indicators of resident users. However, considering that the antenna output power is relatively small after a large number of couplers and feeder losses, and that the system is often partially damaged (e.g., the backbone is damaged) but most users can still use it normally, the performance degradation of some users caused by the partial damage to the indoor distribution system has little impact on the performance indicators of resident users of the signal source. As a result, it is difficult to directly detect related anomalies from changes in resident user performance indicators such as the reference signal received power (RSRP) quality rate, number of users, and physical resource block (PRB) utilization rate. Often, the problem can only be discovered after users complain, resulting in a relatively slow operation and maintenance, which seriously affects the user experience.

[0048] Furthermore, indoor scenarios such as hospitals, office buildings, university teaching buildings, and dormitories experience significant user tidal effects, leading to large fluctuations in the number of system sampling points and traffic. This makes it difficult to determine whether an indoor distributed system is experiencing anomalies using resident user performance indicators. Moreover, anomaly detection based on resident user performance indicators is easily affected by performance degradation caused by coverage blind spots in the indoor distributed system. For example, if an indoor distributed system has been installed in a building but has blind spots (such as a meeting room), the performance indicators will deteriorate when a large number of resident users enter the meeting room for meetings. Even with extended monitoring periods, the performance indicators of resident users remain poor due to the large number of users and the long overall occupancy time in the meeting room. This can lead to a false positive for a properly functioning indoor distributed system.

[0049] Therefore, how to detect anomalies in indoor distribution systems in a timely and accurate manner before user complaints are received, so as to improve the timeliness of operation and maintenance and enable operation and maintenance personnel to repair anomalies in a timely manner to restore or improve network quality, is an urgent problem that needs to be solved.

[0050] To address the problems existing in the aforementioned related technologies, this application proposes an anomaly detection scheme for indoor distribution systems. This scheme can be applied to full-band indoor distribution systems using 4G and 5G technologies. This application achieves anomaly detection for partially damaged indoor distribution systems by analyzing the physical link signal transmission quality of the signal source within the system. This solves the problems of poor detection timeliness and low accuracy in traditional indoor distribution system anomaly detection schemes, helping to improve the timeliness of operation and maintenance, thereby reducing user complaints and enhancing user experience.

[0051] The following description, in conjunction with the accompanying drawings, details an anomaly detection method, apparatus, device, and medium for an indoor distribution system provided in this application, through some embodiments and application scenarios.

[0052] Firstly, referring to Figure 1 The diagram shown is an implementation flowchart of an anomaly detection method for an indoor distribution system provided in this application embodiment. The method may include the following steps:

[0053] Step S11: Perform moving average processing on the target data of the indoor distribution system collected at different times to obtain the first moving average value of the target data within different set time periods with the current time as the cutoff time. The target data is used to measure the physical link signal transmission quality of the signal source in the indoor distribution system.

[0054] In practice, target data of the indoor distribution system is collected periodically, such as by the hour or by the day. The collected target data is then processed by moving average to monitor the changing trend of physical link signal transmission quality within a set period.

[0055] For example, with a single set duration of the most recent 3 days, a moving average is applied to the target data collected on days 1 to 4. Specifically, on day 3, based on the target data collected from days 1 to 3, the first moving average of the most recent 3 days is calculated with day 3 as the cutoff time (i.e., the current time). On day 4, based on the target data collected from days 2 to 4, the first moving average of the most recent 3 days is calculated with day 4 as the cutoff time (i.e., the current time). Thus, by applying moving averages to the periodically collected target data, the first moving average of the target data within different set durations with different cutoff times can be continuously obtained (reflecting the changes in the target data within the set duration, i.e., reflecting the changes in the physical link signal transmission quality). This allows for dynamic monitoring of the changing trends in the physical link signal transmission quality.

[0056] Optionally, the different set durations can be set with significantly different time lengths, such as setting the different set durations to the most recent 2 days and the most recent 7 days, so that the moving average of the target data corresponding to the different set durations can more accurately reflect the long-term and short-term changes in the physical link signal transmission quality.

[0057] The target data can be data such as VSWR that can measure (i.e. quantify) the signal transmission quality of the physical link.

[0058] It should be noted that the standing wave ratio (SWR) refers to the ratio of the voltage amplitude at the antinodes to the voltage amplitude at the troughs of a transmission line. When the SWR is equal to 1, it means that the impedance of the feeder and the antenna are perfectly matched, and all high-frequency energy is radiated by the antenna without any energy reflection loss. When the SWR is greater than 1, it means that some radio waves are reflected back, eventually turning into heat, causing the feeder to heat up. The reflected radio waves will generate a fairly high voltage at the signal source output port, which may damage the signal source.

[0059] In other words, a higher VSWR indicates more signal reflection and poorer impedance matching. It reflects a decline in the physical link signal transmission quality of the signal source (such as signal strength loss and communication quality of ceiling antennas) and a significant degradation in user perception. When the indoor distribution system is partially damaged, such as when the backbone (i.e., the physical link where the signal source is located, and the branches can be regarded as branches of this physical link) or a few branches are damaged (such as abnormalities in the coupler, feeder, or antenna connection), the VSWR will increase to varying degrees. Therefore, the VSWR can be used as target data to detect anomalies related to partial damage to the indoor distribution system.

[0060] Step S12: Determine whether the deviation between the first moving averages of the target data within different set time periods is greater than a first preset threshold.

[0061] In practice, the first preset threshold can be determined based on experience or experimentation, and it is used to measure whether the long-term and short-term trends of physical link signal transmission quality have deviated too much.

[0062] It is understandable that if the indoor distribution system is currently experiencing an anomaly (such as damage to the main trunk or branch trunks), the target data currently collected will differ significantly from the previously collected target data (compared to its own volatility). This will lead to varying degrees of change in the long-term and short-term trends of the target data (i.e., the corresponding moving averages) (the longer the set time period, the smaller the change), resulting in a significant difference between the two. Therefore, a first preset threshold can be set for the deviation between the first moving averages to detect whether there is a significant difference in the long-term and short-term trends of the current target data, thereby effectively detecting anomalies related to partial damage to the indoor distribution system.

[0063] Step S13: If the deviation between the first moving average of the target data within different set time periods is greater than the first preset threshold, it is determined that there is an anomaly in the indoor distribution system.

[0064] In practice, after determining that there is an anomaly in the indoor distribution system, the maintenance personnel can be proactively reminded to locate and handle the anomaly in the indoor distribution system in a timely manner before users complain, by means of issuing work orders, etc. This can improve the timeliness of maintenance, thereby reducing user complaints and improving user experience.

[0065] Understandably, considering that even if the indoor distribution system is normal, the inherent volatility of the target data, such as the slight increase or decrease in VSWR over time (i.e., inherent volatility), might lead to misjudgments of anomalies if a threshold is directly set for the target data. Therefore, this application measures the difference in the long-term and short-term trends of physical link signal transmission quality based on the deviation between the moving averages of the target data over different set time periods.

[0066] When there are significant differences, that is, when the deviation between the first moving averages of the target data within the different set time periods is greater than the first preset threshold, it is determined that there is an anomaly in the indoor distribution system. This can eliminate the interference of the inherent fluctuations of the target data and improve the accuracy of anomaly detection.

[0067] The technical solution adopted in this application addresses the direct impact of partial damage to the physical link signal transmission quality of the signal source on the indoor distribution system. This application measures the physical link signal transmission quality based on target data to effectively detect anomalies related to partial damage to the indoor distribution system. Furthermore, considering the inherent volatility of the target data, this application uses the deviation between the moving averages of the target data over different set time periods—that is, whether there are significant differences in the long-term and short-term trends of the physical link signal transmission quality—to perform anomaly detection. This eliminates interference from the inherent volatility of the target data and improves the accuracy of anomaly detection. Thus, this application can achieve timely and accurate detection of anomalies related to partial damage to the indoor distribution system, helping to improve the timeliness of operation and maintenance, thereby reducing user complaints and enhancing user experience.

[0068] As one possible implementation, the first moving average of the target data over a single set time period, with the current time as the cutoff time, is determined by the following steps:

[0069] For each target data point within the set time period, a decreasing weight value is assigned to each target data point according to the order of their collection time from the current time in the time dimension, from closest to furthest.

[0070] Based on the weight values ​​set for each of the target data, a weighted moving average is performed on each of the target data to obtain the first moving average of the target data within the set time period.

[0071] In specific implementation, taking the set duration of the most recent 3 days as an example, after setting decreasing weight values ​​for each target data according to the order of the collection time of each target data from the current time in the time dimension from the closest to the farthest, the target data collected on the current day (i.e., the current time) will be assigned the largest weight value so that the target data collected on the current day can have the greatest impact on the first moving average of the target data in the most recent 3 days; the target data collected the day before yesterday will be assigned the smallest weight value so that the target data collected the day before yesterday can have the least impact on the first moving average of the target data in the most recent 3 days; and the target data collected yesterday will be assigned a weight value between the two mentioned above so that the impact of the target data collected yesterday on the first moving average of the target data in the most recent 3 days can be correspondingly between the two mentioned above.

[0072] It is understandable that this application takes into account that the target data collected closer to the current time can better reflect the recent changes in the target data. Therefore, based on the distance from the current time in the time dimension, different weight values ​​are set for the target data collected at different times within a single set time period, so as to adjust the influence of the target data collected at different times on the first moving average. This allows the determined first moving average to more accurately reflect the changing trend of physical link signal transmission quality within a single set time period.

[0073] Optionally, the first moving average of the target data within a single set time period can be obtained based on an exponentially decreasing weighted moving average. For example, when the target data is the standing wave ratio (SWR), the first moving average of the SWR collected at different times can be obtained by performing an exponentially decreasing weighted moving average on the SWR using a first formula, wherein the first formula is expressed as follows:

[0074]

[0075] in, The first moving average of the standing wave ratio within a single set duration is represented by N, where N represents the length of time within the single set duration (i.e., the number of periodic acquisition moments). This represents the standing wave ratio (SWR) collected at the current moment. This represents the moving average value obtained by performing a weighted moving average on the standing wave ratios (SWRs) at N-1 times within a single set time period. The SWRs at the N-1 times include the remaining SWRs within the single set time period excluding the SWR collected at the current time.

[0076] Understandably, if it is necessary to monitor long-term changes in the standing wave ratio, the value of N can be calculated when it is larger. If it is necessary to monitor short-term changes in VSWR, the value of N when it is smaller can be calculated. Thus, the first moving average of the VSWR is obtained over different set time periods (i.e., when N takes larger and smaller values) with the current time as the cutoff time.

[0077] Taking a single set duration of the most recent 4 days (i.e., N=4) as an example, the process of calculating the first moving average of the VSWR for the most recent 4 days based on the first formula mentioned above is as follows:

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088]

[0089] in, , , , These are the standing wave ratios collected on days 1 to 4, respectively. The standing wave ratio collected on day 4 is the standing wave ratio collected on that day (i.e., at the current moment), which is the first moving average of the standing wave ratios over the most recent 4 days (i.e., a single set duration).

[0090] In the above embodiments, this application considers that the long-term VSWR changes relatively small, and by incorporating it into anomaly detection, it can avoid misjudgments caused by small daily fluctuations in the VSWR; the short-term VSWR changes relatively large, and by incorporating it into anomaly detection, it can be used to determine whether there are any recent abnormal changes in the indoor distribution system; thus, by simultaneously monitoring the changes in long-term and short-term VSWRs (i.e., calculating under different N values), It can effectively detect anomalies related to partial damage to indoor distribution systems.

[0091] For example, refer to Figure 2 The diagram shown illustrates the trend of VSWR variation, when the short-term first moving average... Significantly higher than the long-term first moving average (That is, when there is a significant difference in the trends of VSWR changes between the long and short term) for example When the value exceeds the first preset threshold, it can be determined that there is an anomaly in the indoor distribution system. Then, by issuing work orders or other means, maintenance personnel can be proactively reminded to handle the issue in a timely manner before users complain. This can improve the timeliness of maintenance, thereby reducing user complaints and improving user experience.

[0092] As one possible implementation, the different set durations include a first set duration and a second set duration, wherein the duration of the first set duration is shorter than the duration of the second set duration; the method further includes:

[0093] Step S21: Obtain the second moving average of the target data within the first set time period. The second moving average is processed differently from the moving average of the first moving average.

[0094] In practice, to enhance the richness of the data, moving averages obtained from different moving average processing methods are applied to anomaly detection.

[0095] For example, the first moving average and the second moving average can be obtained by weighted moving average processing under different weight settings.

[0096] For example, to improve data processing efficiency, the second moving average is obtained based on an unweighted moving average processing method, and the first moving average is obtained based on a weighted moving average processing method.

[0097] Step S22: Determine the anomaly degree of the target data within the first set time period based on the deviation between the second moving average value of the target data within the first set time period and the target data collected at the current time.

[0098] In practice, the anomaly of the target data within the first set time period can be the difference or ratio between the second moving average and the target data collected at the current time, so as to reflect the magnitude of the deviation between the two.

[0099] Step S23: If the deviation between the first moving average values ​​of the target data within different set time periods is greater than a first preset threshold, and the abnormality of the target data within the first set time period is greater than a second preset threshold, it is determined that the indoor distribution system is abnormal.

[0100] In this embodiment, the present application uses anomaly degree to assist in anomaly detection. That is, anomalies are determined to exist in the indoor distribution system only when there are significant differences in the short-term and long-term trends of the physical link signal transmission quality and the target data collected at the current moment does not conform to the short-term trend. This can effectively avoid misjudgment of anomalies and further improve the accuracy of anomaly detection.

[0101] Optionally, when the target data is the standing wave ratio, the anomaly degree of the target data within the first set time period is determined by a second formula, which is expressed as follows:

[0102]

[0103] in, This indicates the degree of anomaly in the VSWR within the first set time period. This refers to the standing wave ratio (SWR) collected at the current moment (e.g., the latest SWR collected that day). This represents the second moving average of the VSWR within the first set time period.

[0104] As one possible implementation, the target data is the standing wave ratio (SWR); before determining whether the deviation between the first moving averages of the target data within different set time periods is greater than a first preset threshold, the method further includes:

[0105] Determine whether the standing wave ratio (SWR) collected at the current moment is greater than the preset SWR alarm threshold;

[0106] If the standing wave ratio (SWR) collected at the current time is greater than the preset SWR alarm threshold, the anomaly detection will be stopped and a SWR alarm will be issued.

[0107] In practical implementation, to avoid excessive standing wave ratio (SWR) alarms that overwhelm maintenance personnel and reduce the workload on low-priority alarms like SWR, allowing limited manpower to be allocated to high-priority alarm processing, a relatively lenient SWR alarm threshold (i.e., a larger SWR alarm threshold) can be configured to detect explicit anomalies in indoor distributed systems. For example, when the backbone is damaged, the SWR of the signal source will increase significantly. This explicit anomaly can be detected by setting the SWR alarm threshold, and the SWR alarm can alert relevant personnel to handle it promptly. This eliminates the need for subsequent moving average processing and ensures timely maintenance.

[0108] Optionally, the method further includes:

[0109] If the standing wave ratio at the current moment is not greater than the preset standing wave alarm threshold, and if an anomaly is determined in the indoor distribution system based on the standing wave ratio within the different set time periods, a work order will be issued to remind relevant personnel to locate the anomaly in the indoor distribution system.

[0110] In practical implementation, after determining that there are no obvious anomalies in the indoor distribution system that would cause significant changes in the standing wave ratio based on the standing wave ratio alarm threshold, the anomaly detection method provided in this application is used to detect whether there are any latent anomalies in the indoor distribution system that would only cause small changes in the standing wave ratio (such as damage to the branch). If the existence of such latent anomalies is confirmed, a work order is issued to remind the operation and maintenance personnel to handle them in a timely manner, thereby ensuring the timeliness of operation and maintenance.

[0111] The following examples, 1 and 2, illustrate the anomaly detection method for an indoor distribution system provided in this application. In Examples 1 and 2, the first preset threshold and the second preset threshold are both 0.03, and the first set duration and the second set duration are the most recent 2 days (corresponding to short-term) and the most recent 7 days (corresponding to long-term), respectively.

[0112] Example 1

[0113] Reference Figure 3 The diagram showing the trend and anomaly of the VSWR can be seen that from day 3 to day 9, even after the exponentially decreasing weighted moving average processing, the short-term first moving average (i.e., the short-term VSWR change) remains the same. There are still slight fluctuations, but the long-term first moving average (i.e., the change in the long-term VSWR) is... The two were relatively stable, with no significant difference, thus avoiding abnormal misjudgments caused by short-term VSWR fluctuations.

[0114] Day 5 to Day 7 The index fluctuated from 1.16 to 1.24, with the highest deterioration of 6.9%. Although it did not reach the first or second set threshold to generate an order, the relevant technical personnel still went to the site to use the standing wave meter to test and confirmed that there was no abnormality in the indoor distribution system and no abnormality was missed.

[0115] On the 10th day, due to the deviation between the first moving averages of the long and short periods... The short-term anomaly score is 0.0601. The value was 0.051, and both monitoring indicators were greater than 0.03, therefore an anomaly was determined in the indoor distribution system and a work order was dispatched. On-site verification revealed that due to a construction process issue, the feeder and coupler at the branch of the indoor distribution system were disconnected, causing the system failure. However, the VSWR was 1.34 at this time, which did not trigger the VSWR alarm on the network management side (the provincial control VSWR alarm threshold is 1.8), making it impossible to detect this anomaly based on the VSWR alarm threshold.

[0116] Example 2

[0117] Reference Figure 4 The diagram showing the trend and anomaly of the VSWR variation illustrates that from day 3 to day 6, the short-term first moving average (i.e., the short-term VSWR variation) is... Small fluctuations and long-term first moving average (i.e., long-term VSWR change) The two were relatively stable, with no significant difference, thus avoiding abnormal misjudgments caused by short-term VSWR fluctuations.

[0118] On the 7th day, due to the deviation between the first moving averages of the long and short periods... The anomaly score is 0.11, indicating a short-term anomaly. The value was 0.0985, and both monitoring indicators were greater than 0.03, therefore an anomaly was determined in the indoor distribution system, and a work order was dispatched. On-site verification revealed that maintenance inside the elevator had damaged the connection between the feeder and coupler at the branch of the indoor distribution system, causing the system failure. However, the VSWR was 1.4 at this time, which did not trigger the VSWR alarm on the network management side (the provincial control VSWR alarm threshold is 1.8), making it impossible to detect this anomaly based on the VSWR alarm threshold.

[0119] Based on the above examples and embodiments, this application considers that partial damage to the indoor distribution system will directly affect the physical link signal transmission quality of the signal source. This application measures the physical link signal transmission quality based on target data to effectively detect anomalies related to partial damage to the indoor distribution system. Furthermore, considering the inherent volatility of the target data, it performs moving average processing (e.g., exponentially decreasing weighted moving average processing) on ​​the target data (e.g., VSWR) collected at different times to monitor the short-term and long-term trends of physical link signal transmission quality. Anomaly detection is based on whether there are significant differences between the short-term and long-term trends of physical link signal transmission quality. This can eliminate the interference of the inherent volatility of the target data and improve the accuracy of anomaly detection.

[0120] Furthermore, this application utilizes a standing wave (SWR) alarm threshold for preliminary anomaly detection (i.e., explicit anomaly detection). Upon successful preliminary anomaly detection, it further combines anomaly degree for dual-judgment, thereby enabling automated and accurate detection of anomalies in indoor distributed systems even when devices have no SWR alarms. Currently, the anomaly detection solution described in this application has been implemented in multiple cities through work order dispatch, achieving a detection accuracy rate of 98.3%. This allows maintenance personnel to promptly restore network quality in indoor distributed systems before user complaints, thereby improving user satisfaction.

[0121] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of this application.

[0122] Secondly, Figure 5 This is a schematic diagram of the structure of an anomaly detection device for an indoor distribution system according to an embodiment of this application. The device includes:

[0123] The first processing module 100 is used to perform moving average processing on the target data of the indoor distribution system collected at different times to obtain the first moving average value of the target data within different set time periods with the current time as the cutoff time. The target data is used to measure the physical link signal transmission quality of the signal source in the indoor distribution system.

[0124] The first judgment module 200 is used to determine whether the deviation between the first moving average values ​​of the target data within different set time periods is greater than a first preset threshold.

[0125] The first detection module 300 is used to determine that there is an anomaly in the indoor distribution system when the deviation between the first moving average of the target data within different set time periods is greater than a first preset threshold.

[0126] The technical solution adopted in this application addresses the direct impact of partial damage to the physical link signal transmission quality of the signal source on the indoor distribution system. This application measures the physical link signal transmission quality based on target data to effectively detect anomalies related to partial damage to the indoor distribution system. Furthermore, considering the inherent volatility of the target data, this application uses the deviation between the moving averages of the target data over different set time periods—that is, whether there are significant differences in the long-term and short-term trends of the physical link signal transmission quality—to perform anomaly detection. This eliminates interference from the inherent volatility of the target data and improves the accuracy of anomaly detection. Thus, this application can achieve timely and accurate detection of anomalies related to partial damage to the indoor distribution system, helping to improve the timeliness of operation and maintenance, thereby reducing user complaints and enhancing user experience.

[0127] Optionally, the first processing module 100 includes:

[0128] The first processing submodule is used to set decreasing weight values ​​for each target data within a single set time period, according to the order of the collection time of each target data from the current time in the time dimension from the closest to the farthest.

[0129] The second processing submodule is used to perform a weighted moving average processing on each of the target data based on the weight values ​​set for each of the target data, so as to obtain the first moving average of a single target data within the set time period.

[0130] Optionally, when the target data is the standing wave ratio, the first moving average of the target data within a single set time period is determined by a first formula, which is expressed as follows:

[0131]

[0132] in, This represents the first moving average of the VSWR within a single set duration, where N represents the number of data collection moments within that single set duration. This represents the standing wave ratio (SWR) collected at the current moment. This represents the moving average value obtained by performing a weighted moving average on the standing wave ratios (SWRs) at N-1 times within a single set time period. The SWRs at the N-1 times include the remaining SWRs within the single set time period excluding the SWR collected at the current time.

[0133] Optionally, the different set durations include a first set duration and a second set duration, wherein the duration of the first set duration is shorter than the duration of the second set duration; the device further includes:

[0134] The first acquisition module 400 is used to acquire the second moving average of the target data within the first set time period. The second moving average is processed differently from the moving average of the first moving average.

[0135] The second processing module 110 is used to determine the abnormality of the target data within the first set time period based on the deviation between the second moving average of the target data within the first set time period and the target data collected at the current time.

[0136] The first detection module 300 includes:

[0137] The first detection submodule 301 is used to determine that there is an anomaly in the indoor distribution system when the deviation between the first moving average values ​​of the target data within different set time periods is greater than a first preset threshold and the anomaly degree of the target data within the first set time period is greater than a second preset threshold.

[0138] Optionally, when the target data is the standing wave ratio, the anomaly degree of the target data within the first set time period is determined by a second formula, which is expressed as follows:

[0139]

[0140] in, This indicates the degree of anomaly in the VSWR within the first set time period. This indicates the standing wave ratio (SWR) collected at the current moment. This represents the second moving average of the VSWR within the first set time period.

[0141] Optionally, the target data is the standing wave ratio (SWR); the device further includes:

[0142] The second judgment module 210 is used to determine whether the standing wave ratio collected at the current time is greater than the preset standing wave alarm threshold before determining whether the deviation between the first moving average values ​​of the target data within the different set time periods is greater than the first preset threshold.

[0143] The standing wave alarm module 500 is used to stop anomaly detection and issue a standing wave alarm when the standing wave ratio collected at the current time is greater than a preset standing wave alarm threshold.

[0144] Optionally, the device further includes:

[0145] The work order dispatch module 600 is used to dispatch a work order to remind relevant personnel to locate the abnormality of the indoor distribution system when the standing wave ratio at the current time is not greater than the preset standing wave alarm threshold and the abnormality of the indoor distribution system is determined based on the standing wave ratio within different set time periods.

[0146] It should be noted that the device embodiments are similar to the method embodiments, so the description is relatively simple. For relevant details, please refer to the method embodiments.

[0147] This application also provides an electronic device, see embodiments thereof. Figure 6 , Figure 6 This is a schematic diagram of the electronic device proposed in an embodiment of this application. Figure 6 As shown, the electronic device 700 includes a memory 710 and a processor 720. The memory 710 and the processor 720 are connected via a bus for communication. The memory 710 stores a computer program that can run on the processor 720 to implement the steps in the anomaly detection method of the indoor distribution system disclosed in the embodiments of this application.

[0148] This application also provides a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the anomaly detection method for an indoor distribution system as disclosed in this application.

[0149] This application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the anomaly detection method for an indoor distribution system as disclosed in this application.

[0150] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0151] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0152] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, systems, devices, storage media, and program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0153] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0155] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0156] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0157] The above provides a detailed description of the anomaly detection method, apparatus, equipment, and medium for an indoor distribution system provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of anomaly detection for an indoor distribution system, characterized in that, The method comprises: moving average processing target data of an indoor distribution system collected at different time instants to obtain first moving average values of the target data in different set time lengths with a current time instant as a cutoff time instant, the target data being used to measure physical link signal transmission quality of a signal source in the indoor distribution system; judging whether a deviation between the first moving average values of the target data in the different set time lengths is greater than a first preset threshold value; in a case where the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold value, determining that the indoor distribution system has an anomaly; the different set time lengths comprise a first set time length and a second set time length, and a time length of the first set time length is less than that of the second set time length; obtaining a second moving average value of the target data in the first set time length, the second moving average value being different from the first moving average value in a moving average processing mode; determining an anomaly degree of the target data in the first set time length according to a deviation between the second moving average value of the target data in the first set time length and target data collected at the current time instant; in the case where the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold value, determining that the indoor distribution system has an anomaly, comprising: in a case where the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold value, and the anomaly degree of the target data in the first set time length is greater than a second preset threshold value, determining that the indoor distribution system has an anomaly.

2. The method of claim 1, wherein, The first moving average value of the target data in a single set time length with the current time instant as the cutoff time instant is determined through the following steps: for each target data in a single set time length, setting a decreasing weight value for the target data in an order from near to far in a time dimension according to a collection time instant of the target data; based on the weight value set for each target data, performing weighted moving average processing on the target data to obtain the first moving average value of the target data in the single set time length.

3. The method of claim 2, wherein, In a case where the target data is a standing wave ratio, the first moving average value of the target data in the single set time length is determined through a first formula, and the first formula is as follows: wherein, represents a first moving average value of the standing wave ratio within a single said setting duration, N represents the number of collection time points within a single said setting duration, represents the standing wave ratio collected at the current time point, represents a moving average value obtained by performing a weighted moving average process on the standing wave ratios corresponding to N-1 time points within a single said setting duration, wherein the standing wave ratios corresponding to the N-1 time points include the remaining standing wave ratios except the standing wave ratio collected at the current time point within a single said setting duration.

4. The method of claim 1, wherein, In a case where the target data is a standing wave ratio, the anomaly degree of the target data in the first set time length is determined through a second formula, and the second formula is as follows: wherein, represents the abnormality degree of the standing wave ratio in the first set time length, represents the standing wave ratio collected at the current time point, represents the second moving average value of the standing wave ratio in the first set time length.

5. The method according to any of claims 1 to 4, characterized in that, the target data is a standing wave ratio; before judging whether the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold value, the method further comprises: judging whether the standing wave ratio collected at the current time instant is greater than a preset standing wave alarm threshold value; in a case where the standing wave ratio collected at the current time instant is greater than the preset standing wave alarm threshold value, stopping anomaly detection and performing standing wave alarm.

6. The method of claim 5, wherein, the method further comprises: In a case where the standing wave ratio at the current moment is not greater than a preset standing wave alarm threshold, and it is determined based on the standing wave ratios in the different set time lengths that the indoor distribution system has an abnormality, a work order is dispatched to remind relevant personnel to perform abnormal positioning on the indoor distribution system.

7. An anomaly detection apparatus for an indoor distribution system, characterized by comprising: The apparatus comprises: The first processing module is configured to perform moving average processing on target data of the indoor distribution system collected at different moments to obtain first moving average values of the target data in different set time lengths with a current moment as a cutoff moment, the target data being used to measure physical link signal transmission quality of a signal source in the indoor distribution system. The first determining module is configured to determine whether a deviation between the first moving average values of the target data in the different set time lengths is greater than a first preset threshold. The first detecting module is configured to determine that the indoor distribution system has an abnormality in a case where the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold. The different set time lengths comprise a first set time length and a second set time length, and a time length of the first set time length is less than that of the second set time length; the apparatus further comprises: The first obtaining module is configured to obtain second moving average values of the target data in the first set time length, the second moving average values being different from the first moving average values in a moving average processing manner. The second processing module is configured to determine an abnormality degree of the target data in the first set time length according to a deviation between the second moving average values of the target data in the first set time length and the target data collected at the current moment. The first detecting module comprises: The first detecting submodule is configured to determine that the indoor distribution system has an abnormality in a case where the deviation between the first moving average values of the target data in the different set time lengths is greater than the first preset threshold, and the abnormality degree of the target data in the first set time length is greater than a second preset threshold.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program comprises instructions that, when executed by the processor, cause the electronic device to perform the method of any one of claims 1-7. The processor executes the computer program to implement the indoor distribution system abnormality detection method according to any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the indoor distribution system abnormality detection method according to any one of claims 1 to 6.

Images