Anomaly detection method, apparatus, device, and storage medium

Abstract

The application provides an anomaly detection method and device, equipment and a storage medium, relates to the technical field of communication, and is used for realizing anomaly detection on a cell under an indoor distribution system, guaranteeing the network use experience of a user, and the method comprises the following steps: an anomaly detection device determines an anomaly value of a target index based on historical index data of a to-be-detected cell; the historical index data is index data of the target index of the to-be-detected cell in a first historical time period. Further, the anomaly detection device acquires target index data of the to-be-detected cell, and the target index data is index data of the target index of the to-be-detected cell every day in a second historical time period. Finally, the anomaly detection device determines the to-be-detected cell as an anomaly cell in the case that the target index data and the anomaly value satisfy a preset condition. The preset condition is that the target index data is greater than an anomaly upper limit value or the target index data is less than an anomaly lower limit value.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to an anomaly detection method, apparatus, device, and storage medium. Background Technology

[0002] As buildings become increasingly dense and taller in cities, coupled with fully enclosed exterior finishes, the shielding, attenuation, and interference of radio signals increase, resulting in poor signal quality indoors. A common solution to this problem is to install indoor distribution systems within buildings.

[0003] Indoor distribution systems utilize indoor antenna distribution systems to evenly distribute base station signals throughout a building, ensuring ideal signal coverage in every area and improving the mobile communication environment within the building. However, due to the large number of network elements connected to the indoor distribution system, such as indoor antennas and passive devices, and the lack of effective monitoring methods for these elements, when a fault occurs in a local area, the network management platform and performance platform cannot detect it in a timely manner, thus failing to quickly eliminate potential network risks. Summary of the Invention

[0004] This application provides an anomaly detection method, apparatus, device, and storage medium for detecting anomalies in cells under an indoor distribution system, thereby ensuring the user's network experience.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, an anomaly detection method is provided. This method includes: an anomaly detection device determining outliers of a target indicator based on historical indicator data of a cell under test; the outliers include an upper limit and a lower limit, and the historical indicator data are the target indicator data of the cell under test within a first historical time period. Further, the anomaly detection device acquires the target indicator data of the cell under test, which are the daily indicator data of the target indicator within a second historical time period, where the second historical time period is shorter than the first historical time period. Finally, if the target indicator data and the outliers meet preset conditions, the anomaly detection device identifies the cell under test as an anomaly cell. The preset conditions are that the target indicator data is greater than the upper limit or less than the lower limit.

[0007] The anomaly detection method provided in this application determines anomalies based on data from the cell under test in the first historical time period, and then compares the data from the recent second historical time period with the upper or lower limit of the anomaly to determine whether the cell under test is an anomaly. This achieves anomaly detection for indoor distribution systems and notifies maintenance personnel to troubleshoot the indoor distribution system when the detected cell is an anomaly.

[0008] In one possible design, the anomaly detection device determines outliers of a target indicator based on historical indicator data of the cell under test. This includes: the anomaly detection device acquiring daily indicator data for the target indicator within a first historical time period. Further, the anomaly detection device determines the lower quartile and upper quartile of the daily indicator data for the target indicator; and based on the lower quartile and upper quartile, determines the upper and lower limits of the target indicator's outlier. This design implements a method for the anomaly detection device to determine more reliable outliers to ensure the accuracy of detecting abnormal cells.

[0009] In one possible design, when the cell to be detected is a non-abnormal cell, the above-mentioned anomaly detection method further includes: the anomaly detection device determining multiple weak coverage ratios of the cell to be detected within a second historical time period, where each of the multiple weak coverage ratios is the weak coverage ratio for each day within the second historical time period. Further, if each of the multiple weak coverage ratios is greater than a preset weak coverage ratio, the anomaly detection device determines the cell to be detected as a weak coverage cell. This design enables the anomaly detection device to detect the weak coverage ratio of a cell and determine whether the cell is a weak coverage cell, even when no anomalies are found in the detected cell, in order to ensure the user's network experience.

[0010] In one possible design, the aforementioned target metrics include at least one of the following: number of sampling points, traffic volume, and weak coverage ratio.

[0011] Secondly, an anomaly detection device is provided, including a determining unit and an acquiring unit. The determining unit is used to determine outliers of a target indicator based on historical indicator data of the cell to be detected; the outliers include an upper limit and a lower limit, and the historical indicator data are the indicator data of the target indicator of the cell to be detected within a first historical time period. The acquiring unit is used to acquire the target indicator data of the cell to be detected, which are the daily indicator data of the target indicator of the cell to be detected within a second historical time period, where the second historical time period is shorter than the first historical time period. The determining unit is also used to determine the cell to be detected as an anomalous cell if the target indicator data and the outlier meet preset conditions; the preset conditions are that the target indicator data is greater than the upper limit or less than the lower limit.

[0012] In one possible design, the acquisition unit is further used to acquire the daily indicator data of the target indicator for the cell under test within a first historical time period. The determination unit is further used to determine the lower quartile and upper quartile of the daily indicator data of the target indicator. The determination unit is further used to determine the upper limit and lower limit of the abnormality of the target indicator based on the lower quartile and upper quartile.

[0013] In one possible design, the determining unit is further configured to determine multiple weak coverage proportions of the cell to be detected within a second historical time period, wherein each weak coverage proportion is the weak coverage proportion for each day within the second historical time period. The determining unit is also configured to determine the cell to be detected as a weak coverage cell if each of the multiple weak coverage proportions is greater than a preset weak coverage proportion.

[0014] In one possible design, the target metrics include at least one of the following: number of sampling points, traffic volume, and weak coverage ratio.

[0015] Thirdly, an anomaly detection device is provided, the anomaly detection device including a memory and a processor; the memory and the processor are coupled, the memory being used to store computer program code including computer instructions, and when the processor executes the computer instructions, the anomaly detection device performs an anomaly detection method as provided in the first aspect or any possible design thereof.

[0016] Fourthly, a computer-readable storage medium is provided, which stores instructions that, when executed on an anomaly detection device, cause the anomaly detection device to perform an anomaly detection method as provided in the first aspect or any possible implementation thereof. Attached Figure Description

[0017] Figure 1 A schematic diagram of a communication system structure provided for an embodiment of this application;

[0018] Figure 2 A flowchart illustrating an anomaly detection method provided for embodiments of this application. Figure 1 ;

[0019] Figure 3 A flowchart illustrating an anomaly detection method provided for embodiments of this application. Figure 2 ;

[0020] Figure 4 A flowchart illustrating an anomaly detection method provided for embodiments of this application. Figure 3 ;

[0021] Figure 5 A schematic diagram illustrating the determination of outliers provided for an embodiment of this application;

[0022] Figure 6 A flowchart illustrating an anomaly detection method provided for embodiments of this application. Figure 4 ;

[0023] Figure 7 A schematic diagram of an anomaly detection device provided for an embodiment of this application;

[0024] Figure 8 A schematic diagram of an anomaly detection device structure provided for embodiments of this application. Figure 1 ;

[0025] Figure 9 A schematic diagram of an anomaly detection device structure provided for embodiments of this application. Figure 2 . Detailed Implementation

[0026] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0027] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0028] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" and "multiple" refer to two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0029] As buildings become increasingly dense and taller in cities, coupled with fully enclosed exterior finishes, the shielding, attenuation, and interference of radio signals increase, resulting in poor signal quality indoors. A common solution is to install indoor distribution systems within buildings. However, these systems consist of numerous network elements, including indoor antennas and passive components, and suffer from a lack of effective monitoring mechanisms. This means that when a fault occurs in a localized area, the network management and performance platforms cannot detect it promptly, hindering the rapid elimination of potential network risks.

[0030] To address the aforementioned issues, this application provides an anomaly detection method, apparatus, device, and storage medium. The anomaly detection apparatus determines outlier values ​​for target indicators based on historical indicator data of the cell under test. Outlier values ​​include an upper and lower limit for outliers, and the historical indicator data refers to the target indicator data of the cell under test within a first historical time period. Further, the anomaly detection apparatus acquires the target indicator data of the cell under test, which is the daily indicator data of the target indicator within a second historical time period, which is shorter than the first historical time period. Finally, if the target indicator data and outlier values ​​meet preset conditions, the anomaly detection apparatus identifies the cell under test as an anomaly cell. These preset conditions are that the target indicator data is greater than the upper limit for outliers, or that the target indicator data is less than the lower limit for outliers. In this way, the anomaly detection method provided by this application determines outlier values ​​based on data from the cell under test within a first historical time period, and then compares these outlier values ​​with recent data from a second historical time period to determine whether the cell under test is an anomaly cell. This achieves anomaly detection for indoor distributed systems, and when a cell is identified as an anomaly, it notifies maintenance personnel to troubleshoot the indoor distributed system.

[0031] Figure 1 A communication system is illustrated, and the anomaly detection method provided in this application embodiment can be applied to, for example, Figure 1 The communication system 10 shown is used to detect whether there are any anomalies in the cells under the indoor distribution system. For example... Figure 1 As shown, the communication system 10 includes an anomaly detection device 11 and a network management platform 12.

[0032] The anomaly detection device 11 is connected to the network management platform 12, which can be wired or wireless, and this embodiment does not limit the connection.

[0033] The anomaly detection device 11 can be used to obtain historical indicator data of the cell to be detected from the network management platform 12, and determine the abnormal value of the target indicator based on the historical indicator data.

[0034] The target indicators include at least one of the following: number of sampling points, traffic volume, and weak coverage ratio. Outliers include upper and lower limits for outliers. Historical indicator data refers to the indicator data of the target cells to be tested within the first historical time period stored on the network management platform 12.

[0035] The anomaly detection device 11 can also be used to acquire target indicator data for the cell under test. The target indicator data consists of the daily target indicator data for the cell under test within a second historical time period.

[0036] It should be noted that the second historical period is shorter than the first historical period.

[0037] The anomaly detection device 11 can also be used to identify the cell to be detected as an abnormal cell when the target indicator data and the abnormal value meet the preset conditions.

[0038] It should be noted that the preset condition is that the target indicator data is greater than the upper limit of the abnormality, or the target indicator data is less than the lower limit of the abnormality.

[0039] Figure 2 This is a flowchart illustrating an anomaly detection method according to some exemplary embodiments. In some embodiments, the above-described anomaly detection method can be applied to, for example... Figure 1 The communication system 10 shown includes an anomaly detection device 11. Hereinafter, this application will describe the anomaly detection method by taking the application of the anomaly detection method to the anomaly detection device 11 as an example.

[0040] like Figure 2 As shown, the anomaly detection method provided in this application includes the following steps S201-S205.

[0041] S201. The anomaly detection device acquires historical indicator data of the cell to be detected.

[0042] Among them, the historical indicator data refers to the indicator data of the target indicator of the community to be tested within the first historical time period.

[0043] It should be noted that the target indicators include at least one of the following: number of sampling points, traffic volume, and weak coverage ratio, wherein the number of sampling points refers to the number of sampling points for reference signal receiving power (RSRP).

[0044] As one possible implementation, the anomaly detection device retrieves the target indicator data of the cell to be detected from the network management platform based on the identifier of the cell to be detected and the dates included in the first historical time period.

[0045] For example, the target metrics data stored in the network management platform are shown in Table 1 below.

[0046] Table 1: Indicator Data for Target Indicators

[0047]

[0048]

[0049] If the first historical time period is from June 25, 2022 to September 27, 2022, the cell to be detected is cell A, and the target indicator is traffic volume, then the anomaly detection device queries the network management platform for the daily traffic volume indicator data of cell A during the period from June 25, 2022 to September 27, 2022, thereby obtaining the historical indicator data of the cell to be detected.

[0050] It should be noted that the first historical time period can be preset in the anomaly detection device by the communication system's maintenance personnel. A longer first historical time period results in more accurate anomaly values ​​determined based on the indicator data within that period, but also increases the computational load. Conversely, a shorter first historical time period reduces the accuracy of anomaly values ​​but decreases the computational load. Generally, the first historical time period can be set to 30-90 days; this embodiment does not impose a specific limitation on this.

[0051] As another possible implementation, the network management platform periodically sends the previous day's indicator data to the anomaly detection device. Correspondingly, the anomaly detection device stores the received indicator data, and when historical indicator data is needed, it queries the relevant historical indicator data from its own storage space.

[0052] S202. The anomaly detection device determines the abnormal values ​​of the target indicator based on the historical indicator data of the cell to be detected.

[0053] Outliers include upper and lower limits.

[0054] In some embodiments, after acquiring historical indicator data of the cell to be detected, the anomaly detection device determines the maximum and minimum values ​​in the historical indicator data, and determines the maximum value as the upper limit of anomalies and the minimum value as the lower limit of anomalies, thereby obtaining the anomaly value corresponding to the target indicator.

[0055] For example, if the sampling point quantity index of the cell to be tested includes 150, 120, 115, 128, 80, and 178, the anomaly detection device determines the upper limit of the anomaly for the sampling point quantity index to be 178 and the lower limit to be 80. If the traffic volume index of the cell to be tested includes 300, 250, 50, 225, 170, and 90, the anomaly detection device determines the upper limit of the anomaly for the traffic volume index to be 300 and the lower limit to be 50. If the weak coverage ratio index of the cell to be tested includes 8%, 7%, 9%, 3%, 15%, and 11%, the anomaly detection device determines the upper limit of the anomaly for the weak coverage ratio index to be 15% and the lower limit to be 3%.

[0056] In some embodiments, to avoid the anomaly detection device being affected by the abnormal data in the historical indicator data when determining the anomaly value, the method for the anomaly detection device to determine the anomaly value may also be: the anomaly detection device determines the maximum value and minimum value in the historical indicator data of the target indicator, and determines the value obtained by subtracting a first preset value from the maximum value as the upper limit of the anomaly, and determines the value obtained by adding a second preset value to the minimum value as the lower limit of the anomaly, thereby obtaining the anomaly value corresponding to the target indicator.

[0057] For example, based on the historical data of each target indicator in the above examples, if the first preset value for the number of sampling points indicator is 20 and the second preset value is 15, then the anomaly detection device determines that the upper limit of the anomaly for the number of sampling points indicator is 158 and the lower limit of the anomaly is 95. If the first preset value for the traffic volume indicator is 40 and the second preset value is 25, then the anomaly detection device determines that the upper limit of the anomaly for the traffic volume indicator is 260 and the lower limit of the anomaly is 75. If the first preset value for the weak coverage ratio indicator is 3% and the second preset value is 2%, then the anomaly detection device determines that the upper limit of the anomaly for the weak coverage ratio indicator is 12% and the lower limit of the anomaly is 5%.

[0058] It should be noted that the first preset value and the second preset value can be set in advance in the anomaly detection device by the operation and maintenance personnel of the communication system, and this application embodiment does not specifically limit them.

[0059] This application also provides a more accurate method for determining outliers of target indicators, which can be found in the following description of the embodiments of this application.

[0060] S203, The anomaly detection device acquires the target indicator data of the cell to be detected.

[0061] The target indicator data refers to the daily target indicator data of the cell to be tested within the second historical time period, which is shorter than the first historical time period.

[0062] As one possible implementation, the anomaly detection device retrieves the target indicator data of the cell to be detected within the second historical time period from the network management platform, based on the identifier of the cell to be detected and the dates included in the second historical time period.

[0063] As another possible implementation, the network management platform periodically sends the previous day's indicator data to the anomaly detection device. Correspondingly, the anomaly detection device stores the received indicator data, and when it needs to obtain target indicator data, it queries its own storage space for the target indicator data of the cell to be detected within a second historical time period and retrieves it.

[0064] It should be noted that the specific implementation method of the anomaly detection device acquiring the target indicator data of the cell to be detected is the same as that of the anomaly detection device acquiring the historical indicator data of the cell to be detected, the difference being the first historical time period and the second historical time period.

[0065] The second historical time period can be preset in the anomaly detection device by the operation and maintenance personnel of the communication system. Generally, the first historical time period can be set to 3-7 days. This application embodiment does not make a specific limitation on this.

[0066] In some embodiments, if the second historical time period falls during a holiday, the anomaly detection device adds one day to the preset number of days in the second historical time period to avoid the impact of holiday fluctuations when determining anomaly indicators, thus ensuring the reliability of the anomaly cell determination in this application embodiment.

[0067] For example, if the second historical time period is 3 days and covers the May Day holiday, then the second historical time period is further updated to 4 days the day before the May Day holiday.

[0068] S204. The anomaly detection device determines whether the target indicator data and the abnormal value meet the preset conditions.

[0069] The preset conditions are that the target indicator data is greater than the upper limit of the abnormality, or the target indicator data is less than the lower limit of the abnormality.

[0070] As one possible implementation, the anomaly detection device compares the target indicator data of each target indicator with the corresponding outlier value to determine whether the target indicator data of each target indicator is greater than the upper limit of the outlier or less than the lower limit of the outlier.

[0071] Specifically, the anomaly detection device compares the target indicator data based on the number of sampling points with the corresponding upper and lower limits of the abnormality. If the indicator data for the number of sampling points is greater than the upper limit or less than the lower limit for each day in the second historical time period, the indicator of the number of sampling points is determined to be an abnormal indicator.

[0072] The anomaly detection device compares the target indicator data of business volume with the corresponding abnormal upper limit and abnormal lower limit values ​​of business volume. If the indicator data of each day in the second historical time period of business volume is greater than the abnormal upper limit value or less than the abnormal lower limit value, the business volume indicator is determined to be an abnormal indicator.

[0073] The anomaly detection device compares the target indicator data of the weak coverage ratio with the corresponding upper and lower limits of the weak coverage ratio. If the indicator data for each day in the second historical time period of the weak coverage ratio is greater than the upper limit of the abnormality or less than the lower limit of the abnormality, the weak coverage ratio indicator is determined to be an abnormal indicator.

[0074] Furthermore, if the anomaly detection device determines whether there are any abnormal indicators among the sampling point quantity indicator, traffic volume indicator, and weak coverage ratio indicator, the anomaly detection device determines that the target indicator data and the abnormal value meet the preset conditions.

[0075] In some embodiments, if the anomaly detection device determines that a target indicator data point contains a value greater than the upper limit of anomalies or a value less than an anomaly value, it identifies the corresponding target indicator as an anomaly indicator. Further, the anomaly detection device determines that the target indicator data and the anomaly value meet preset conditions.

[0076] In some embodiments, such as Figure 3 As shown, the anomaly detection device first acquires the target index data for the number of sampling points and determines whether the target index data and the corresponding outliers for the number of sampling points meet preset conditions. If the preset conditions are met, the number of sampling points is determined to be an anomaly; otherwise, it is determined to be a normal index. Further, the anomaly detection device acquires the target index data for the traffic volume index and determines whether the target index data and the corresponding outliers for the traffic volume index meet preset conditions. If the preset conditions are met, the traffic volume index is determined to be an anomaly; otherwise, it is determined to be a normal index. Finally, the anomaly detection device acquires the target index data for the weak coverage ratio and determines whether the target index data and the corresponding outliers for the weak coverage ratio meet preset conditions. If the preset conditions are met, the weak coverage ratio is determined to be an anomaly; otherwise, it is determined to be a normal index.

[0077] Understandably, through the above implementation method, the anomaly detection device sequentially checks whether the number of sampling points, traffic volume, and weak coverage ratio are anomaly indicators. Once an anomaly indicator is determined, the process ends, thus saving the computing resources of the anomaly detection device and improving the efficiency of anomaly indicator determination while determining the anomaly indicator.

[0078] S205. When the target indicator data and the abnormal value meet the preset conditions, the anomaly detection device will identify the cell to be detected as an abnormal cell.

[0079] As one possible implementation, the anomaly detection device determines whether each target indicator meets preset conditions based on step S204 above. If there are target indicator data and outliers that meet the preset conditions, the anomaly detection device determines the cell to be detected as an abnormal cell. Furthermore, if the anomaly detection device determines that the cell to be detected is an abnormal cell, it issues an alarm to remind maintenance personnel that the current cell to be detected is an abnormal cell, and to troubleshoot the abnormal cell.

[0080] It is understood that in the anomaly detection method provided in this application embodiment, by determining whether there are any anomalies in the target indicators of the cell to be detected, it is possible to determine in a timely manner whether there are any abnormal cells in the indoor distribution system, so as to monitor the operation status of the indoor distribution system and ensure the network usage experience of users.

[0081] In one design, to ensure the reliability of outliers corresponding to the determined target indicators, the anomaly detection method provided in this application embodiment includes, for example... Figure 4 As shown, it also includes S301-S303.

[0082] S301, The anomaly detection device acquires the daily indicator data of the target indicator of the cell to be detected within the first historical time period.

[0083] It should be noted that the specific implementation method of the anomaly detection device acquiring the daily indicator data of the target indicator of the cell under test within the first historical time period can be referred to the description of step S201 in the above embodiment of this application, and will not be repeated here.

[0084] S302, The anomaly detection device determines the lower quartile and upper quartile of the daily indicator data of the target indicator.

[0085] As one possible implementation, the anomaly detection device sorts the daily indicator data of the target indicator obtained in step S301 to obtain indicator data sorted from smallest to largest. Further, the anomaly detection device calculates the lower quartile and upper quartile from the sorted indicator data.

[0086] For example, let the lower quartile be Q1 and the upper quartile be Q3. If the index data sorted from smallest to largest are x1, x2, ..., x... n The anomaly detection device then determines the position of Q1 as follows: The position of Q3 is Furthermore, the anomaly detection device detects x1, x2, ..., x n In the middle, determine For Q1, determine For Q3.

[0087] S303. The anomaly detection device determines the upper and lower limits of anomalies for the target indicator based on the lower and upper quartiles.

[0088] As one possible implementation, the anomaly detection device determines the interquartile range of historical indicator data based on the lower quartile and upper quartile determined in step S302. Further, the anomaly detection device determines the lower limit of anomalies based on the lower quartile and the interquartile range, and determines the upper limit of anomalies based on the upper quartile and the interquartile range.

[0089] Specifically, the anomaly detection device can determine the lower limit and upper limit of anomalies according to the following formula.

[0090] IQR = Q3 - Q1

[0091] G1=Q1-k*IQR

[0092] G2=Q3+k*IQR

[0093] Where IQR is the interquartile range, Q3 is the upper quartile, Q1 is the lower quartile, G1 is the lower limit of anomalies, k is the interquartile range coefficient (exemplarily 1.5), and G2 is the upper limit of anomalies. For example, the upper and lower limits of anomalies determined by the anomaly detection device are as follows: Figure 5 As shown, when the indicator data exceeds the upper or lower limit of the abnormal value, the indicator data is identified as an abnormal value.

[0094] In some embodiments, if it is determined that the lower limit of outliers is negative, and the indicator data based on each target indicator cannot be negative, then the lower limit of outliers is determined to be 0.

[0095] Understandably, in the anomaly detection method provided in this application embodiment, the anomaly detection device uses a box plot algorithm to determine the upper and lower limits of the target indicator based on historical indicator data, so as to detect the target indicator data of the cell to be detected and determine whether the cell to be detected is an abnormal cell.

[0096] In one design, when the cell to be detected is a non-abnormal cell, in order to ensure the network usage experience of users in the indoor distribution system, the anomaly detection method provided in this application embodiment, such as... Figure 6 As shown, it also includes S401-S403.

[0097] S401, The anomaly detection device determines the proportion of multiple weak coverage areas of the cell to be detected within the second historical time period.

[0098] Each of the multiple weak coverage ratios is the weak coverage ratio for each day within the second historical time period.

[0099] It should be noted that the specific implementation method of the anomaly detection device determining the proportion of multiple weak coverages of the cell to be detected in the second historical time period can refer to the specific implementation method in step S203 above in the embodiment of this application, and will not be repeated here.

[0100] S402, The anomaly detection device determines whether each of the multiple weak coverage ratios is greater than the preset weak coverage ratio.

[0101] As one possible implementation, the anomaly detection device compares the multiple weak coverage ratios determined in step S401 with a preset weak coverage ratio to determine whether each of the multiple weak coverage ratios is greater than the preset weak coverage ratio.

[0102] It should be noted that the preset weak coverage ratio can be set in advance in the anomaly detection device by the operation and maintenance personnel of the communication system. For example, the preset weak coverage ratio can be set to 10%, but this application embodiment does not specifically limit it.

[0103] S403. If the anomaly detection device determines the cell to be detected as a weak coverage cell when each of the multiple weak coverage ratios is greater than the preset weak coverage ratio.

[0104] As one possible implementation, if the anomaly detection device identifies the cell to be detected as a weak coverage cell when each of the multiple weak coverage ratios is greater than the preset weak coverage ratio, it will issue an alarm to remind the operation and maintenance personnel that the cell to be detected is a weak coverage cell and to conduct network coverage investigation on the weak coverage cell.

[0105] It is understood that the anomaly detection method provided in this application determines whether the cell to be detected is a weak coverage cell in order to monitor the network coverage of the indoor distribution system and ensure the user's network experience.

[0106] In some embodiments, the anomaly detection method provided in this application was used in a practical application. The anomaly detection device performed anomaly detection on a cell under an indoor distribution system for 3 months and obtained the data shown in Table 2 below.

[0107] Table 2: Community Anomaly Detection Table

[0108] month Number of abnormal cells Verify and confirm the number of faulty cells accuracy June 35 25 71.4％ July 26 20 76.9％ August 32 24 75.0％

[0109] As can be seen from the table above, the anomaly detection method provided in this application embodiment can achieve an accuracy of over 70% in detecting abnormal cells, demonstrating high reliability.

[0110] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0111] This application embodiment can divide the user equipment into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0112] Figure 7 This is a schematic diagram of an anomaly detection device provided in an embodiment of this application. This anomaly detection device is used to perform the above-described anomaly detection method. Figure 7 As shown, the anomaly detection device 50 includes a determination unit 501 and an acquisition unit 502.

[0113] The determining unit 501 is used to determine outliers of the target indicator based on historical indicator data of the cell to be detected. Outliers include upper and lower limits, and the historical indicator data are the indicator data of the target indicator for the cell to be detected within a first historical time period. For example, ... Figure 2 As shown, the determining unit 501 can be used to execute S201.

[0114] The acquisition unit 502 is used to acquire the target indicator data of the cell to be detected. The target indicator data is the daily indicator data of the target indicator of the cell to be detected within a second historical time period, where the second historical time period is shorter than the first historical time period. For example, ... Figure 2 As shown, the acquisition unit 502 can be used to execute S203.

[0115] The determining unit 501 is also used to determine the cell to be detected as an abnormal cell when the target indicator data and the outlier meet preset conditions; the preset conditions are that the target indicator data is greater than the upper limit of the abnormality value, or the target indicator data is less than the lower limit of the abnormality value. For example, such as Figure 2 As shown, the determining unit 501 can be used to execute S205.

[0116] Optional, such as Figure 7 As shown, in the anomaly detection device 50 provided in this application embodiment, the acquisition unit 502 is further used to acquire the daily indicator data of the target indicator of the cell to be detected within a first historical time period. For example, as Figure 4 As shown, the acquisition unit 502 can be used to execute S301.

[0117] Unit 501 is also used to determine the lower quartile and upper quartile of the daily data for the target indicator. For example, such as... Figure 4 As shown, the determining unit 501 can be used to execute S302.

[0118] Unit 501 is also used to determine the upper and lower limits of abnormality for the target indicator based on the lower and upper quartiles. For example, as... Figure 4 As shown, the determining unit 501 can be used to execute S303.

[0119] Optional, such as Figure 7 As shown, in the anomaly detection device 50 provided in this application embodiment, the determining unit 501 is further configured to determine multiple weak coverage ratios of the cell to be detected within a second historical time period, wherein each weak coverage ratio is the weak coverage ratio for each day within the second historical time period. For example, as... Figure 6 As shown, the determining unit 501 can be used to execute S401.

[0120] The determining unit 501 is also used to determine the cell to be detected as a weak coverage cell when each of the multiple weak coverage ratios is greater than a preset weak coverage ratio. For example, such as Figure 6 As shown, the determining unit 501 can be used to execute S403.

[0121] Optional, such as Figure 7 As shown, in the anomaly detection device 50 provided in this application embodiment, the target indicators include at least one of the following: number of sampling points, traffic volume, and weak coverage ratio.

[0122] In implementing the functions of the integrated modules described above using hardware, this application provides a possible structural diagram of an anomaly detection device. This anomaly detection device is used to execute the anomaly detection method performed by the anomaly detection apparatus in the above embodiments. Figure 8 As shown, the anomaly detection device 60 includes a processor 601, a memory 602, and a bus 603. The processor 601 and the memory 602 can be connected via the bus 603.

[0123] Processor 601 is the control center of the anomaly detection device. It can be a single processor or a collective term for multiple processing elements. For example, processor 601 can be a general-purpose central processing unit (CPU) or other general-purpose processors. The general-purpose processor can be a microprocessor or any conventional processor.

[0124] As one embodiment, processor 601 may include one or more CPUs, for example Figure 8 CPU 0 and CPU 1 are shown in the diagram.

[0125] The memory 602 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0126] In one possible implementation, the memory 602 can exist independently of the processor 601. The memory 602 can be connected to the processor 601 via a bus 603 and is used to store instructions or program code. When the processor 601 calls and executes the instructions or program code stored in the memory 602, it can implement the anomaly detection method provided in the embodiments of this application.

[0127] In another possible implementation, the memory 602 can also be integrated with the processor 601.

[0128] Bus 603 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0129] It should be pointed out that, Figure 8 The structure shown does not constitute a limitation on the anomaly detection device 60. Except... Figure 8 In addition to the components shown, the anomaly detection device 60 may include components that are larger than those shown. Figure 8 It can show more or fewer parts, or combine certain parts, or arrange different parts.

[0130] As an example, combined Figure 7 The functions implemented by the determination unit 501 and the acquisition unit 502 in the anomaly detection device 50 are the same as those implemented by the anomaly detection device 50. Figure 8 The processor 601 in it has the same function.

[0131] Optional, such as Figure 8 As shown, the anomaly detection device provided in this application embodiment may further include a communication interface 604.

[0132] Communication interface 604 is used to connect with other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. Communication interface 604 may include an acquisition unit for receiving data and a transmission unit for sending data.

[0133] In one design, the communication interface of the anomaly detection device provided in this application embodiment can also be integrated into the processor.

[0134] Figure 9 Another hardware structure of the anomaly detection device in this application embodiment is shown. For example... Figure 9 As shown, the anomaly detection device 70 may include a processor 701 and a communication interface 702. The processor 701 is coupled to the communication interface 702.

[0135] The functions of processor 701 can be referred to in the description of processor 601 above. In addition, processor 701 also has storage functions, which can be referred to in the description of memory 602 above.

[0136] The communication interface 702 is used to provide data to the processor 701. The communication interface 702 can be an internal interface of the anomaly detection device, or it can be an external interface of the anomaly detection device (equivalent to communication interface 604).

[0137] It should be pointed out that, Figure 9 The structure shown does not constitute a limitation on anomaly detection equipment, except Figure 9 In addition to the components shown, the anomaly detection device 70 may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0138] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0139] This application also provides a computer-readable storage medium storing instructions. When a computer executes these instructions, the computer performs each step of the method flow shown in the above-described method embodiments.

[0140] Embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform the anomaly detection method described in the above method embodiments.

[0141] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0142] Since the apparatus, device, computer-readable storage medium, and computer program product in the embodiments of this application can be applied to the above methods, the technical effects that can be obtained can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0143] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An anomaly detection method characterized by, The method comprises: determining an abnormal value of a target index based on historical index data of a to-be-detected cell; the abnormal value comprises an abnormal upper limit value and an abnormal lower limit value, the historical index data is index data of the target index of the to-be-detected cell in a first historical time period; the target index comprises a sampling point number of reference signal received power (RSRP), traffic volume and weak coverage proportion; the abnormal upper limit value comprises a value obtained by subtracting a first preset value from a maximum value in the historical index data; the abnormal lower limit value comprises a value obtained by adding a second preset value to a minimum value in the historical index data; the first historical time period is 30-90 days; obtaining target index data of the to-be-detected cell, the target index data being index data of the target index of the to-be-detected cell every day in a second historical time period, the second historical time period being less than the first historical time period; in the case that the second historical time period falls in a holiday period, one day is added to a preset number of days in the second historical time period; judging, in order of priority of the sampling point number of RSRP, the traffic volume and the weak coverage proportion, whether the index data of the sampling point number of RSRP, the index data of the traffic volume and the index data of the weak coverage proportion are abnormal indexes, and ending the judgment after determining a first abnormal index; in the case that the target index data and the abnormal value satisfy a preset condition, determining the to-be-detected cell as an abnormal cell; the preset condition is that the target index data is greater than the abnormal upper limit value or the target index data is less than the abnormal lower limit value; the method comprises: obtaining index data of the target index of the to-be-detected cell every day in the first historical time period; determining a lower quartile and an upper quartile of the index data of the target index every day; determining the abnormal upper limit value and the abnormal lower limit value of the target index according to the lower quartile and the upper quartile; the abnormal upper limit value and the abnormal lower limit value satisfy the following formula: IQR=Q3-Q1; G1=Q1-k×IQR; G2=Q3+k×IQR; wherein IQR is an interquartile range, Q3 is an upper quartile, Q1 is a lower quartile, G1 is an abnormal lower limit value, k is an interquartile range coefficient, and G2 is an abnormal upper limit value; if the abnormal upper limit value and / or the abnormal lower limit value is determined to be negative, the abnormal upper limit value and / or the abnormal lower limit value is determined to be 0; in the case that the to-be-detected cell is a non-abnormal cell, determining a plurality of weak coverage proportions of the to-be-detected cell in a second historical time period, each weak coverage proportion in the plurality of weak coverage proportions being a weak coverage proportion every day in the second historical time period; in the case that each weak coverage proportion in the plurality of weak coverage proportions is greater than a preset weak coverage proportion, determining the to-be-detected cell as a weak coverage cell.

2. An abnormality detection device characterized by comprising: comprise a determining unit and an obtaining unit; The determining unit is configured to determine an abnormal value of a target index based on historical index data of a to-be-detected cell; the abnormal value includes an abnormal upper limit value and an abnormal lower limit value; the historical index data is index data of the target index of the to-be-detected cell in a first historical time period; the target index includes a sampling point number of a reference signal received power (RSRP), a traffic volume, and a weak coverage ratio; The abnormal upper limit value includes a value obtained by subtracting a first preset value from a maximum value in the historical index data; the abnormal lower limit value includes a value obtained by adding a second preset value to a minimum value in the historical index data; the first historical time period is 30-90 days; The obtaining unit is configured to obtain target index data of the to-be-detected cell, the target index data being index data of the target index of the to-be-detected cell every day in a second historical time period, the second historical time period being less than the first historical time period; In a case where the second historical time period falls in a holiday period, one day is added to a preset number of days in the second historical time period; The determining unit is further configured to determine, in a priority order of the sampling point number of the RSRP, the traffic volume, and the weak coverage ratio, whether index data of the sampling point number of the RSRP, index data of the traffic volume, and index data of the weak coverage ratio are abnormal indexes in sequence, and end the determination after a first abnormal index is determined; The determining unit is further configured to determine the to-be-detected cell as an abnormal cell in a case where the target index data and the abnormal value satisfy a preset condition; the preset condition is that the target index data is greater than the abnormal upper limit value or the target index data is less than the abnormal lower limit value; The obtaining unit is further configured to obtain index data of the target index of the to-be-detected cell every day in the first historical time period; The determining unit is further configured to determine a lower quartile and an upper quartile of the index data of the target index every day; The determining unit is further configured to determine the abnormal upper limit value and the abnormal lower limit value of the target index according to the lower quartile and the upper quartile; the abnormal upper limit value and the abnormal lower limit value satisfy the following formula: IQR=Q3-Q1; G1=Q1-k×IQR; G2=Q3+k×IQR; wherein IQR is an interquartile range, Q3 is the upper quartile, Q1 is the lower quartile, G1 is the abnormal lower limit value, k is an interquartile range coefficient, and G2 is the abnormal upper limit value; if the abnormal upper limit value and / or the abnormal lower limit value is determined to be negative, the abnormal upper limit value and / or the abnormal lower limit value is determined to be 0; if the abnormal upper limit value and / or the abnormal lower limit value is determined to be negative, the abnormal upper limit value and / or the abnormal lower limit value is determined to be 0; The determining unit is further configured to, in a case where the to-be-detected cell is a non-anomalous cell, determine a plurality of weak coverage ratios of the to-be-detected cell in a second historical time period, each of the plurality of weak coverage ratios being a weak coverage ratio of each day in the second historical time period. The determining unit is further configured to, in a case where each of the plurality of weak coverage ratios is greater than a preset weak coverage ratio, determine the to-be-detected cell as a weak coverage cell.

3. An anomaly detection device characterized by comprising: comprising a memory and a processor; the memory and the processor are coupled; the memory is configured to store computer program code, the computer program code comprising computer instructions; when the processor executes the computer instructions, the anomaly detection device executes the anomaly detection method in claim 1.

4. A computer-readable storage medium having stored therein instructions, the computer-readable storage medium comprising: when the instructions run on the anomaly detection device, cause the anomaly detection device to execute the anomaly detection method in claim 1.

Images