Method and device for determining blocked degree of antenna, electronic equipment and storage medium

Abstract

The invention provides an antenna blocking degree determination method and device, electronic equipment and a medium, and the method comprises the steps: determining a change percentage corresponding to a target base station according to a real-time performance data set of the target base station and a reference performance data set corresponding to the target base station; according to the change percentage, determining a target interval where the change percentage is located from the plurality of candidate intervals; and determining a target blocked degree corresponding to the target base station according to a target mapping relationship between the plurality of candidate intervals and the plurality of candidate blocked degrees. The blocking degree of the target base station can be determined when the target base station is blocked, so that corresponding processing can be executed according to the blocking degree of the target base station, the blocking degree does not need to be manually determined on site, and the labor cost can be reduced.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and in particular to a method, apparatus, electronic device, and storage medium for determining the degree of antenna obstruction. Background Technology

[0002] With the development of wireless communication technology, base station antennas in mobile communication networks are facing increasing physical obstacles, such as buildings and trees. These obstacles can obstruct wireless signals, leading to signal attenuation, increased interference, and other problems, thus affecting communication quality. Therefore, timely and accurate identification of antenna obstructions is crucial for optimizing network coverage and improving user experience. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for determining the degree of antenna obstruction.

[0004] The first aspect of this disclosure provides a method for determining the degree of antenna obstruction. The method includes: determining the percentage change corresponding to the target base station based on a real-time performance dataset of the target base station and a baseline performance dataset corresponding to the target base station; determining the target interval in which the percentage change is located from multiple candidate intervals based on the percentage change; and determining the degree of target obstruction corresponding to the target base station based on the target mapping relationship between the multiple candidate intervals and the multiple candidate degrees of obstruction.

[0005] In some embodiments of this disclosure, the method further includes: collecting multiple reference performance datasets of the target base station within a first time period, wherein the starting time point of the first time period is the time point at which the target base station performs a single test, and the target base station is not blocked within the first time period; and determining a baseline performance dataset based on the multiple reference performance datasets.

[0006] In some embodiments of this disclosure, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station includes: determining multiple differences between multiple first data included in the real-time performance dataset and multiple second data included in the benchmark performance dataset; when the multiple differences meet a first preset condition, determining whether the target base station has a base station fault or cell outage problem based on the real-time performance dataset; when the target base station does not have a base station fault or cell outage problem, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station; or, when the multiple differences meet a second preset condition, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station.

[0007] In some embodiments of this disclosure, the first preset condition is that multiple differences are all greater than or equal to a first preset threshold, and the second preset condition is that among the multiple differences, at least one difference is greater than or equal to the first preset threshold.

[0008] In some embodiments of this disclosure, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station includes: determining multiple first weights corresponding to multiple first data; and determining the percentage change corresponding to the target base station based on the multiple first weights, the multiple first data, and the multiple second data.

[0009] In some embodiments of this disclosure, determining multiple first weights corresponding to multiple first data includes: acquiring multiple sets of score data, wherein each set of score data includes weight scores of multiple first data; determining multiple sets of ranking data based on the multiple sets of score data, wherein each set of ranking data includes a ranking result of the weight scores of multiple first data; determining a consistency coefficient based on the multiple sets of score data and the multiple sets of ranking data; determining multiple first weights based on the multiple sets of score data when the value of the consistency coefficient is greater than or equal to a second preset threshold; and reacquiring multiple sets of score data when the value of the consistency coefficient is less than the second preset threshold, and determining the consistency coefficient based on the reacquiring multiple sets of score data, until the consistency coefficient is greater than or equal to the second preset threshold.

[0010] In some embodiments of this disclosure, the method further includes: determining the percentage change corresponding to each of the plurality of reference base stations; determining the predicted degree of obstruction corresponding to each of the plurality of reference base stations based on an initial mapping relationship between the plurality of preset reference intervals and the plurality of obstruction degrees; determining at least one correction value based on the predicted degree of obstruction and the actual degree of obstruction corresponding to each of the plurality of reference base stations; correcting the interval range of the plurality of preset reference intervals based on the at least one correction value to obtain a plurality of candidate intervals; and determining the target mapping relationship between the plurality of candidate intervals and the plurality of candidate obstruction degrees.

[0011] In some embodiments of this disclosure, at least one of a plurality of first data and a plurality of second data includes: traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data.

[0012] A second aspect of this disclosure provides an antenna obstruction degree determination device, comprising a first processing unit, a second processing unit for determining a change percentage corresponding to a target base station based on a real-time performance dataset of a target base station and a baseline performance dataset corresponding to the target base station; a third processing unit for determining a target interval containing the change percentage from multiple candidate intervals based on the change percentage; and a fourth processing unit for determining the target obstruction degree corresponding to the target base station based on a target mapping relationship between multiple candidate intervals and multiple candidate obstruction degrees.

[0013] A third aspect of this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods described in the first aspect of this disclosure.

[0014] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first aspect of this disclosure.

[0015] A fifth aspect of this disclosure provides a computer program product including a computer program that is executed by a processor using the methods described in the first aspect of this disclosure.

[0016] In summary, the antenna obstruction determination method, apparatus, electronic device, and storage medium proposed in this disclosure can determine the percentage change corresponding to the target base station based on real-time performance datasets and benchmark performance datasets. Subsequently, the target obstruction degree corresponding to the target base station can be determined based on the percentage change. This enables the determination of the obstruction degree based on benchmark values ​​and real-time performance data, improving the accuracy, real-time performance, and intelligence of antenna obstruction identification. This facilitates the execution of corresponding processing based on the obstruction degree of the target base station, eliminating the need for manual on-site determination of the obstruction degree and reducing labor costs.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0019] Figure 1 A flowchart illustrating a method for determining the degree of antenna obstruction provided in this embodiment of the disclosure;

[0020] Figure 2 A flowchart illustrating a method for determining the degree of antenna obstruction provided in this embodiment of the disclosure;

[0021] Figure 3 A flowchart illustrating a method for determining the degree of antenna obstruction provided in this embodiment of the disclosure;

[0022] Figure 4 A flowchart illustrating an antenna obstruction identification method based on multidimensional data fusion and machine learning, provided for embodiments of this disclosure;

[0023] Figure 5 This is a schematic diagram of a device for determining the degree of antenna obstruction provided in an embodiment of the present disclosure;

[0024] Figure 6 This is a schematic diagram of the electronic device structure provided in the embodiments of this disclosure;

[0025] Figure 7 This is a schematic diagram of the chip structure provided in an embodiment of this disclosure. Detailed Implementation

[0026] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0027] With the development of wireless communication technology, base station antennas in mobile communication networks are facing increasing physical obstacles, such as buildings and trees. These obstacles can obstruct wireless signals, leading to signal attenuation, increased interference, and other problems, thus affecting communication quality. Therefore, timely and accurate identification of antenna obstructions is crucial for optimizing network coverage and improving user experience.

[0028] Traditionally, there are six main methods to determine whether a base station antenna is blocked:

[0029] ① Manual on-site inspection: Staff will go to the actual location of the base station antenna and visually inspect whether there are buildings, trees or other large objects around the antenna that may obstruct it.

[0030] ② Driving Test (DT) Analysis: This involves using specialized testing equipment to measure signal strength on roads. By analyzing signal variations at different locations, a sudden weakening or abnormal fluctuation in signal strength in a particular area may indicate that the base station antenna in that area is obstructed.

[0031] ③ Indoor Coverage Quality Test (CQT) Analysis: Signal testing is conducted indoors. By measuring and analyzing the signal strength at different locations within the room, the indoor signal coverage is assessed. If the indoor signal is poor, it may be due to obstruction of the base station antenna, preventing the signal from being transmitted effectively indoors.

[0032] ④ Standing Wave Ratio (SWR) Measurement: The SWR can reflect the matching status of the antenna system. If the SWR is high, it may be due to the antenna being blocked, resulting in increased signal reflection.

[0033] ⑤ User Feedback Collection: Collect user complaints and feedback to understand the signal problems users encounter during use. If multiple users report poor signal in the same area, it may be that the base station antenna in that area is blocked.

[0034] ⑥ Radiation Pattern Test: Use professional testing equipment to measure the antenna's radiation pattern, i.e., the antenna's radiation performance in different directions. By comparing the actual measured radiation pattern with the theoretical radiation pattern, it can be determined whether the antenna is obstructed, and the degree and direction of the obstruction.

[0035] Among these methods, manual on-site inspection requires a significant investment of manpower and time, especially when there are numerous base stations or complex terrain, resulting in low efficiency. Road test analysis can only roughly determine the areas where antennas may be obstructed, but cannot accurately pinpoint the specific cause and extent of obstruction. Indoor coverage test analysis can only provide some clues and cannot definitively determine whether the signal problem is caused by antenna obstruction or other reasons. Standing wave ratio (SWR) measurement shows that a high SWR is not necessarily caused entirely by obstruction; it could also be due to antenna installation problems, connection issues, or other factors. User feedback collection is heavily influenced by subjective factors and makes it difficult to accurately pinpoint the specific cause of the problem. Radiation pattern testing requires specialized equipment and technicians.

[0036] In summary, traditional methods often rely on manual inspections or simple signal strength monitoring, which are inefficient and unable to reflect complex obstruction situations in real time. They also suffer from high manpower consumption, long processing times, low accuracy, and high levels of expertise required. Therefore, operators need to research a better antenna obstruction identification method to achieve improved antenna obstruction detection and provide a theoretical basis for further remediation of obstructing antennas.

[0037] Therefore, to address the aforementioned issues, this disclosure proposes a method for determining the degree of antenna obstruction. This method involves collecting base station cell traffic, call volume, number of users, coverage rate, utilization rate, number of sampling points, angle of arrival, number of handovers, and tracking area distribution data. Preprocessing and index weight extraction are performed using expert scoring and Kendall consistency tests. Then, machine learning is combined for model training and real-time identification to accurately determine whether an antenna is obstructed. The specific details of this method are as follows.

[0038] Figure 1 This is a flowchart illustrating a method for determining the degree of antenna obstruction provided in an embodiment of this disclosure. Figure 1 As shown, the method may include the following steps.

[0039] Step 101: Determine the percentage change of the target base station based on the real-time performance dataset of the target base station and the baseline performance dataset of the target base station.

[0040] In some embodiments, real-time performance data of the target base station can be collected to form a real-time performance dataset. In other words, real-time performance data of the target base station can be collected in real time, but not limited to this. Performance data of the target base station can be collected periodically to form real-time performance data. For example, multiple performance data of the target base station can be collected from a first time point to the current time point. Multiple data can be processed, such as determining the statistical value (e.g., average value) of multiple performance data to obtain the real-time performance data of the target base station and form a real-time performance dataset. Optionally, the performance data can be collected using the Operation and Maintenance Center (OMC) network management system. The performance dataset may include traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data.

[0041] Optionally, periodic data collection can be performed on a monthly or weekly basis. Then, a single performance data point can be identified for each period. For example, when collecting data monthly, the real-time performance dataset for each month can be represented as follows:

[0042]

[0043] Traffic data refers to the sum of data bytes that the network management system needs to process, including both sent and received data. For example, it refers to the amount of data a target base station needs to send and receive per unit of time. Traffic is a crucial indicator of network load and performance. By analyzing traffic, we can understand the network's busyness, identify potential network bottlenecks, and take corresponding measures for adjustment and optimization to ensure network stability and efficiency.

[0044] Traffic volume data refers to the amount of voice communication processed by a telephone exchange or network per unit of time, usually measured in "voices per hour" (commonly measured in Erl) or "voices per second". For example, it could be the amount of voice communication that a target base station can process per unit of time. Traffic volume is a key indicator for measuring the load on a communication network. By monitoring traffic volume, the network's carrying capacity can be assessed, future communication demands can be predicted, and network planning and optimization can be carried out accordingly to meet users' voice communication needs.

[0045] The number of users refers to the number of users of a network service, which can include registered users, active users, and new users. For example, it could be the number of users of a target base station service. The number of users is an important indicator for measuring the popularity and market share of a network service. By analyzing the number of users, we can understand user habits, changes in demand, and market trends, thereby developing more effective marketing and user retention strategies.

[0046] Coverage data refers to the extent to which a network or service is covered in a specific area or among a target group, including geographical coverage, network coverage, and service coverage. For example, it could be the coverage of a target base station. Coverage is an important indicator for measuring the popularity and quality of a network or service. By improving coverage, network service providers can expand their market reach, increase user satisfaction and loyalty, and thus enhance their market competitiveness.

[0047] Utilization rate refers to the frequency or proportion of network resources (such as links, nodes, node processors, etc.) used per unit of time. For example, the frequency or proportion of resources used by a target base station per unit of time. Utilization rate is an important indicator for measuring the efficiency and performance of network resource utilization. By monitoring the utilization rate, idle or overloaded resources can be detected in a timely manner, and corresponding measures can be taken for adjustment and optimization to improve resource utilization efficiency and network performance.

[0048] The number of sampling points (Measurement Report, MR) refers to the number of specific data points collected through a Measurement Report in a mobile communication network. It includes the number of data points collected regarding the wireless environment, signal strength, and other information.

[0049] Angle of Arrival (AOA) refers to the angle between the electromagnetic wave and the receiver's direction when the electromagnetic wave arrives at the receiver. For example, the angle between the electromagnetic wave from a target base station and the receiver's direction when the electromagnetic wave arrives at the receiver. This concept has important applications in radar, communication, and radio positioning systems to determine the target's position, orientation, and motion status.

[0050] The number of handovers refers to the process by which a mobile station must switch from the original voice channel to a new, idle voice channel to continue the call when it moves from one base station coverage area to another during a call, or when the call quality deteriorates due to external interference. For example, the number of handovers can be the number of handovers to the target base station.

[0051] Tracking Area (TA) distribution data refers to how multiple base station cells are divided into different tracking areas in a network for user equipment (UE) location management and paging. The tracking area is a new concept established by the system for UE location management. It is defined as the free movement area where the UE does not need to update location services. For example, it can be the distribution data of the tracking area to which the target base station belongs, and may include data such as timing advance and sampling point ratio.

[0052] In some embodiments, after collecting the above performance data, the performance data can be processed to construct data-granular correlation relationships. Optionally, when collecting multiple performance data within a time period, such as collecting multiple traffic data, multiple call volume data, multiple user counts, multiple coverage data, multiple utilization data, multiple sampling point counts, multiple angle of arrival data, multiple handover counts, and multiple tracking area distribution data at multiple time points, the above multiple performance data can be divided according to the multiple time points collected, that is, the correlation between multiple performance data collected at the same time point can be realized. For example, a data point after the correlation is completed can be represented as:

[0053]

[0054] Optionally, when collecting multiple performance data at multiple time points, multiple performance data points can be obtained, each corresponding to a time point. A real-time performance dataset can be generated based on the multiple performance data points. Optionally, statistical values ​​of the multiple performance data points can be determined, and the real-time performance dataset can include the statistical values ​​of the multiple performance data points. When collecting one performance data point, the real-time performance dataset can include the collected data point, that is, the real-time performance dataset can include one data point. One data point includes traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data.

[0055] In some embodiments, the method further includes: collecting multiple reference performance datasets of the target base station within a first time period, wherein the starting time point of the first time period is the time point at which the target base station performs a single test, and the target base station is not blocked within the first time period; and determining a baseline performance dataset based on the multiple reference performance datasets.

[0056] In some embodiments, after the target base station is installed, a single verification can be performed on the target base station. Single verification, also known as verification of a single site, is to check whether the site is working properly after the base station is installed. After the single verification of the target base station is completed, the performance data of the target base station can be recorded. Since the target base station is usually installed in an unobstructed location, the performance data collected for a period of time after the target base station is installed is the normal operating data of the target base station in a normal unobstructed environment because the target base station is not obstructed.

[0057] Optionally, the first time period can be preset, for example, it can be preset to 6 months. After 6 months, the performance data of the target base station can continue to be collected, but the data after 6 months is not used to determine the baseline performance dataset. The performance data of the target base station can be continuously observed to see if it is relatively stable compared with the performance data of a period of time after the single test, or to determine whether the target base station is blocked after 6 months. For example, if the performance data of the target base station is relatively stable and not blocked in the 10th month after the single test, the performance data of 10 months collected from the time point of the single test can be used to redetermine the baseline performance dataset to replace the baseline performance dataset determined by the previous 6 months. In other words, the length of the first time period can be increased.

[0058] In some embodiments, optionally, nine performance data points of the target base station can be collected within a first time period, including traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data. Each performance data point includes multiple different values. For example, the traffic data collected at the first time point is 215G, and the value collected at the second time point is 209G. When determining the baseline performance dataset, the statistical values ​​of the nine performance data points can be determined. That is, the baseline performance data can include one data point, which can include traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data. For example, the baseline performance dataset can be represented as follows.

[0059]

[0060] Optionally, a baseline performance dataset can be determined based on the maximum and minimum values ​​of the nine performance data of the target base station within the first time period. In this case, the baseline performance dataset includes the normal value range of the nine performance data. Optionally, the normal value range of the nine performance data is determined based on the maximum and minimum values ​​of the nine performance data. For example, the baseline performance dataset includes the value range of traffic data as 209G-215G. That is, the baseline performance dataset can be used to indicate the normal value range of the performance data of the target base station when it is not blocked.

[0061] In some embodiments, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the corresponding benchmark performance dataset includes: determining multiple differences between multiple first data included in the real-time performance dataset and multiple second data included in the benchmark performance dataset; when the multiple differences satisfy a first preset condition, determining whether the target base station has a base station fault or cell outage problem based on the real-time performance dataset; when the target base station does not have a base station fault or cell outage problem, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the corresponding benchmark performance dataset; or, when the multiple differences satisfy a second preset condition, determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the corresponding benchmark performance dataset. The first preset condition is that all multiple differences are greater than or equal to a first preset threshold, and the second preset condition is that at least one of the multiple differences is greater than or equal to the first preset threshold.

[0062] In some embodiments, at least one of the plurality of first data and plurality of second data includes: traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data.

[0063] In one embodiment, the real-time performance dataset, the baseline performance dataset, and the reference performance dataset include traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data. The following example illustrates the above scheme. In the table below, the first data item (November 2023 - May 2024) is the baseline performance dataset, and the second data item (September 2024) is the real-time performance dataset. The multiple first data items are: traffic data: 150G, call volume data: 104 Erlang, number of users: 85, coverage data: 104 Erlang, and other data. Coverage: 98.90%, Utilization: 22.06%, Number of sampling points: 210345, Angle of arrival: 26.8° (absolute value), Number of handovers: 113765, Tracking area distribution data: TA time advance >= 4 sampling points proportion 41%, Multiple secondary data are traffic data: 215G, Call volume data: 104 Erlang, Number of users: 88, Coverage: 98.78%, Utilization: 24.06%, Number of sampling points: 215123, Angle of arrival: 25° (absolute value), Number of handovers: 126762, Tracking area distribution data: TA time advance >= 4 sampling points proportion 39%.

[0064]

[0065] In some embodiments, the difference between multiple first data and multiple second data is actually the difference between performance data of the same type. The first data is actually the displayed value of the performance data, and the second data is actually the baseline value of the performance data. Optionally, when the performance data is angle of arrival data, the difference between the first data and the second data is the first data minus the second data, that is, the displayed value of the angle of arrival minus the baseline value of the angle of arrival. When the performance data is traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, number of handovers, or tracking area distribution data, the difference between the first data and the second data is the second data minus the first data, that is, the baseline value of the performance data minus the displayed value.

[0066] In some embodiments, when an antenna is blocked, phenomena such as reduced traffic, reduced call volume, reduced number of users, reduced coverage, reduced utilization, reduced number of sampling points, increased angle of arrival, reduced handover frequency, and reduced tracking area distribution typically occur. Therefore, when one or more of these conditions occur, the real-time performance data of the antenna can be analyzed to determine the degree of antenna blockage. Optionally, the first preset condition can be that all of the following nine formulas are satisfied:

[0067]

[0068] Optionally, when the overall performance data (indicator values) of the nine dimensions deteriorate, the network management / OMC / cell outage platform tools can be used to query and investigate whether there are reasons such as base station failure / cell outage that cause the data anomalies of the nine indicators. If there is no base station failure / cell outage problem, it can be determined that the target base station is deteriorating in performance data due to obstruction. At this time, the degree of obstruction of the target base station can be determined.

[0069] In some embodiments, the second preset condition can be that at least one of the above nine formulas is satisfied. For example, if four of the above formulas are satisfied, it can be determined that the target base station's performance data degradation is caused by obstruction, and the degree of obstruction of the target base station can be determined. However, it is not limited to this; it can also be that three formulas are satisfied, and it can be determined that the target base station's performance data degradation is caused by obstruction, etc. Optionally, "0" in the above nine formulas is only one example and can be replaced with other preset thresholds. The specific value can be determined according to actual needs, and this disclosure does not limit it. Furthermore, the thresholds corresponding to each of the above nine formulas can be different, for example:

[0070]

[0071] In some embodiments, the percentage change of the target base station can be determined based on the real-time performance dataset and the baseline performance dataset of the target base station. The percentage change can be used to indicate the extent to which the current performance of the target base station has changed compared to its performance when it was not blocked. Optionally, the percentage change of the target base station can be determined based on the difference between multiple first data and multiple second data, and the weights corresponding to the multiple first data.

[0072] Step 102: Determine the target interval containing the percentage change from multiple candidate intervals based on the percentage change.

[0073] In some embodiments, the range of values ​​for the percentage change can be divided to obtain multiple candidate ranges. For example, the multiple candidate ranges can be [91.88%, 100%], [63.79%, 91.88%], [41.92%, 63.79%], [9.35%, 41.92%], [0%, 9.35%], etc. If the percentage change is 92%, the target range for the percentage change is [91.88%, 100%].

[0074] In some embodiments, the multiple candidate intervals may optionally be reference intervals preset based on historical experience, or may be obtained by modifying preset reference intervals.

[0075] Step 103: Determine the target blocking degree corresponding to the target base station based on the target mapping relationship between multiple candidate intervals and multiple candidate blocking degrees.

[0076] In some embodiments, the degree of blocking of multiple candidates can include "completely blocked", "mostly blocked", "half blocked", "partially blocked", and "no blocking". There can be a mapping relationship between multiple candidate intervals and multiple degrees of blocking of candidates. The target mapping relationship can be represented as follows:

[0077]

[0078] If the target range of the percentage change is [91.88%, 100%], then the degree of obstruction of the target base station can be determined as complete blockage. Optionally, multiple candidate degrees of obstruction can also be represented in other ways, such as percentage, standardized score, ratio, grade, index, etc., which are not limited in this disclosure.

[0079] In some embodiments, optionally, when the antenna is heavily blocked, such as "completely blocked" or "mostly blocked", a prompt message can be generated. The prompt message can be used to indicate that on-site processing of the target base station is required, such as removing the obstructing object, detecting whether the target base station's hardware is damaged, etc. Optionally, the predicted target blocking degree corresponding to the target base station can be manually verified on-site, that is, the actual degree of antenna blocking can be determined by on-site investigation. Then, the predicted target blocking degree and the actual blocking degree can be compared to determine the prediction accuracy. When the accuracy is low, the range of multiple candidate intervals can be adjusted to optimize the prediction accuracy.

[0080] In summary, the above embodiments of this application can determine the percentage change corresponding to the target base station based on the real-time performance dataset and the benchmark performance dataset. Then, the degree of obstruction of the target base station can be determined based on the percentage change. This can realize the determination of the degree of obstruction based on the benchmark value and real-time performance data, improve the accuracy, real-time performance and intelligence of antenna obstruction identification, so as to perform corresponding processing according to the degree of obstruction of the target base station. It can eliminate the need for manual on-site determination of the degree of obstruction and reduce labor costs.

[0081] Figure 2 This is a flowchart illustrating a method for determining the degree of antenna obstruction provided in an embodiment of this disclosure. Figure 2 As shown, the method may include the following steps.

[0082] Step 201: Determine the multiple first weights corresponding to each of the multiple first data.

[0083] In some embodiments, multiple first weights can be determined for each of the multiple first data. In other words, the weights of multiple types of performance data can be determined, or the weights corresponding to multiple indicators can be determined. For example, when the multiple first data are traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data, the weights corresponding to traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data can be determined.

[0084] In some embodiments, determining multiple first weights corresponding to multiple first data includes: acquiring multiple sets of score data, wherein each set of score data includes weight scores of multiple first data; determining multiple sets of ranking data based on the multiple sets of score data, wherein each set of ranking data includes a ranking result of the weight scores of multiple first data; determining a consistency coefficient based on the multiple sets of score data and the multiple sets of ranking data; determining multiple first weights based on the multiple sets of score data when the value of the consistency coefficient is greater than or equal to a second preset threshold; and reacquiring multiple sets of score data when the value of the consistency coefficient is less than the second preset threshold, and determining the consistency coefficient based on the reacquiring multiple sets of score data, until the consistency coefficient is greater than or equal to the second preset threshold.

[0085] Optionally, when determining the weights of multiple primary data points, an expert scoring method can be used. An expert review panel can be formed, taking into account the experts' backgrounds and qualifications to ensure they possess extensive knowledge and experience in the relevant fields. Attention should be paid to the experts' research directions and achievements, ensuring strong relevance and professionalism to the evaluation indicators. The evaluation indicator system and relevant materials should be provided to the experts in advance to help them better understand the evaluation content and standards. Multiple experts can independently assign weights to multiple primary data points. Optionally, a higher weight indicates greater importance of the indicator in determining the degree of base station obstruction; that is, a higher indicator weight means a greater likelihood of antenna obstruction when the indicator deteriorates. Optionally, each expert can independently determine the weight score for each primary data point. The sum of the weight scores for multiple primary data points is either 1 or 100%. The weight allocation results of each expert for multiple primary data points can form a set of score data, i.e., a set of score data includes the weight scores of multiple primary data points.

[0086] For example, when multiple primary data points are traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data, experts can determine a set of score data including: traffic data with a weight score of 0.165 (16.5%), call volume data with a weight score of 0.145 (14.5%), number of users with a weight score of 0.15 (15%), coverage data with a weight score of 0.068 (6.8%), utilization data with a weight score of 0.12 (12%), number of sampling points with a weight score of 0.16 (16%), angle of arrival data with a weight score of 0.072 (7.2%), number of handovers with a weight score of 0.07 (7%), and tracking area distribution data with a weight score of 0.05 (5%).

[0087] Optionally, multiple first data points can be sorted according to their weight scores in each set of score data to obtain a set of sorted data corresponding to that score data. The sorting of multiple first data points can be done in descending or ascending order of their weight scores. For example, when sorting from largest to smallest, in the example of the score data above, the sorted data corresponding to the score data could be: 1st for traffic data, 4th for call volume data, 3rd for number of users, 8th for coverage data, 5th for utilization data, 2nd for number of sampling points, 6th for angle of arrival data, 7th for number of handovers, and 9th for tracking area distribution data.

[0088] Optionally, multiple first data weight scores determined by each expert can be obtained to obtain multiple sets of score data and ranking data. For example, when the number of experts is 7, the multiple sets of score data and ranking data can be shown in the table below:

[0089]

[0090]

[0091] In some embodiments, consistency checks can be performed based on multiple sets of score data and multiple sets of sorted data. Optionally, a consistency coefficient W can be determined. The range of the consistency coefficient W is [0,1]. When the value of W is close to 0, it indicates that the consistency among multiple experts is very low, indicating that they have a large disagreement on the sorting of multiple first data. When the value of W is close to 1, it indicates that the consistency among multiple experts is very high, indicating that they have very similar or identical sorting of multiple first data.

[0092] Alternatively, the consistency coefficient W can be determined according to any of the following formulas:

[0093]

[0094] in,

[0095]

[0096] R i This represents the sum of K rankings obtained by K experts sorting each type of performance data, or each first data point, or each indicator value; N represents the number of objects being rated, or the number of multiple first data points, or the number of multiple indicator types. Here, N=9, representing 9 indicators; K represents the number of rating evaluators, or the number of multiple experts assigning weights. Here, K=7, representing 7 experts.

[0097] For example, based on the table in step 201, the R values ​​for the nine indicators can be determined respectively. i and The values ​​are as follows.

[0098] ①Flow rate:

[0099] R i (Flow rate) = 1 + 1 + 1 + 1 + 1 + 1 + 1 = 7

[0100] R i (flow) 2 =7 2 =49

[0101] ② Call volume:

[0102] R i (Call volume) = 4 + 4 + 4 + 4 + 4 + 4 + 3 = 27

[0103] R i (Call volume) 2 =27 2 =729

[0104] ③ Number of users:

[0105] R i (Number of users) = 3 + 3 + 3 + 3 + 3 + 4 = 22

[0106] R i (Number of users) 2 =22 2 =484

[0107] ④ Coverage:

[0108] R i (Coverage rate) = 8 + 6 + 6 + 6 + 6 + 6 + 6 = 44

[0109] Ri (Coverage) 2 =44 2 =1936

[0110] ⑤ Utilization rate:

[0111] R i (Utilization rate) = 5 + 5 + 5 + 5 + 5 + 5 = 35

[0112] R i (Utilization rate) 2 =35 2 =1225

[0113] ⑥ Use points:

[0114] R i (Number of sampling points) = 2 + 2 + 2 + 2 + 2 + 2 = 14

[0115] R i (Number of sampling points) 2 =14 2 =196

[0116] ⑦ Angle of arrival:

[0117] R i (Angle of arrival) = 6 + 8 + 8 + 8 + 8 + 8 = 54

[0118] R i (Angle of arrival) 2 =54 2 =2916

[0119] ⑧ Number of switching times:

[0120] R i (Number of switching times) = 7 + 7 + 7 + 7 + 7 + 7 = 49

[0121] R i (Number of switches) 2 =49 2 =2401

[0122] ⑨ Tracking area distribution:

[0123] R i (Tracking area distribution) = 9 + 9 + 9 + 9 + 9 + 9 = 63

[0124] R i (Distribution of tracking areas) 2 =63 2 =3969

[0125] Then, based on the R of the nine indicators... i and The value of S is determined as follows.

[0126]

[0127] Then, based on the values ​​of S, K, and N, the consistency coefficient can be determined as follows:

[0128]

[0129] In some embodiments, a second preset threshold can be set based on historical experience. For example, the second preset threshold can be 0.8. When W is greater than or equal to 0.8, it indicates that the consistency test result is passed. At this time, multiple first weights can be determined based on multiple sets of score data and multiple sets of ranking data. When W is less than 0.8, it indicates that the consistency test result is not passed. At this time, multiple experts can re-allocate the weights of multiple first data and redetermine the weight scores of multiple first data. That is, multiple sets of score data and ranking data can be re-acquired, and the above operation can be repeated until W is greater than or equal to 0.8.

[0130] In some embodiments, multiple first weights can be determined based on multiple sets of score data. For a performance data point, or a first data point, or an indicator, multiple experts determine weight scores for the same indicator. Thus, the same indicator can have multiple weight scores determined by multiple experts. For example, according to the table in step 201, traffic data can include 16.50%, 16.30%, 16.60%, 16.40%, 16.20%, 16.10%, 15.90%, and 16.29%, a total of seven weight scores. The weights corresponding to the traffic data can be determined based on these seven weight scores. The statistical values ​​of these seven weight scores can be determined as the weights corresponding to the traffic data. Statistical values ​​include, for example, the average, median, weighted average, mode, etc., which are not limited in this disclosure. Taking the average as an example, the weights of the nine indicators determined according to the table in step 201 can be expressed as follows.

[0131]

[0132] Step 202: Determine the percentage change corresponding to the target base station based on multiple first weights, multiple first data, and multiple second data.

[0133] In some embodiments, the percentage change corresponding to the target base station can be determined based on a plurality of first weights, a plurality of first data and a plurality of second data. Optionally, the percentage change corresponding to the target base station can be determined based on the following formula.

[0134]

[0135]

[0136] In summary, the embodiments of this application can use expert scoring and consistency checks to determine multiple first weights corresponding to multiple first data, which can improve the professionalism and strength of weight setting. Based on multiple first weights, multiple first data, and multiple second data, the percentage change corresponding to the target base station can be determined, so as to determine the degree of target obstruction corresponding to the target base station based on the percentage change. It can realize the determination of the degree of obstruction based on the benchmark value and real-time performance data, improve the accuracy, real-time performance, and intelligence of antenna obstruction identification, so as to perform corresponding processing according to the degree of obstruction of the target base station. It can eliminate the need for manual on-site determination of the degree of obstruction, thereby reducing labor costs.

[0137] Figure 3 This is a flowchart illustrating a method for determining the degree of antenna obstruction provided in an embodiment of this disclosure. Figure 3 As shown, the method may include the following steps.

[0138] Step 301: Determine the percentage change for each of the multiple reference base stations.

[0139] In some embodiments, the percentage change corresponding to each of a plurality of reference base stations can be determined separately, and the plurality of reference base stations may or may not include the target base station.

[0140] Step 302: Determine the predicted blocking degree corresponding to each of the multiple reference base stations based on the initial mapping relationship between multiple preset reference intervals and multiple blocking degrees.

[0141] In some embodiments, the range of values ​​for the percentage change can be divided based on historical experience to obtain multiple preset reference intervals, such as [90%, 100%], [60%, 90%], [40%, 60%], [10%, 40%], and [0%, 10%].

[0142] Optionally, multiple preset reference intervals and multiple degrees of obstruction can be pre-defined as initial mapping relationships. For example, the initial mapping relationships can be pre-defined as follows:

[0143]

[0144]

[0145] Then, the preset reference intervals in which the change percentages of multiple reference base stations are located can be determined. For example, if the change percentage of reference base station A is 83%, then it is in the preset reference interval [60%, 90%), and the predicted blocking degree of reference base station A can be determined to be mostly blocked.

[0146] Step 303: Determine at least one correction value based on the predicted degree of obstruction and the actual degree of obstruction corresponding to each of the multiple reference base stations.

[0147] In some embodiments, optionally, a subset of reference base stations can be selected from multiple reference base stations for on-site verification based on the preset reference intervals where the respective percentage changes of multiple reference base stations fall. On-site verification involves manually determining the actual degree of obstruction of the base stations on-site. For example, 20 cells each with percentage changes of [90%, 100%], [60%, 90%], [40%, 60%], [10%, 40%], and [0%, 10%] can be selected, totaling 100 reference base stations. After on-site verification, the results are shown in the table below:

[0148]

[0149] In other words, the accuracy of the prediction can be determined based on the actual degree of obstruction verified on-site and the predicted degree of obstruction. For example, if the predicted number of all blocked reference base stations is 20, and the actual number of blocked reference base stations verified is 18, then the accuracy rate is 18 / 20 = 90%. Optionally, the correction value corresponding to each preset reference interval can be determined based on the accuracy rate corresponding to all preset reference intervals. Optionally, machine learning parameters can be introduced to optimize and determine the correction value and correct multiple preset reference intervals.

[0150] Step 304: Correct the range of multiple preset reference intervals according to at least one correction value to obtain multiple candidate intervals.

[0151] In some embodiments, at least one correction value can be used to correct the range of multiple preset reference intervals to obtain multiple candidate intervals. For example, the preset reference intervals can be corrected to [91.88%, 100%], [63.79%, 91.88%], [41.92%, 63.79%], [9.35%, 41.92%], [0%, 9.35%].

[0152] Step 305: Determine the target mapping relationship between multiple candidate intervals and the degree to which multiple candidates are blocked.

[0153] In some embodiments, a target mapping relationship can be determined between multiple candidate intervals and multiple candidate blocking degrees. For example, the target mapping relationship can be expressed as:

[0154]

[0155]

[0156] Optionally, during the real-time detection of the degree of base station obstruction, the candidate interval can be adjusted in a timely manner based on the accuracy of the predicted degree of obstruction. For example, when the degree of obstruction in a special zone is lower than a preset threshold, the adjustment of the candidate interval can be triggered.

[0157] In summary, the above embodiments of this application can correct the interval based on the predicted degree of base station obstruction and the actual degree of obstruction, thereby improving the accuracy of prediction, the accuracy, real-time performance, and intelligence of antenna obstruction identification. This allows for the execution of corresponding processing based on the degree of obstruction of the target base station, eliminating the need for manual on-site determination of the obstruction degree and reducing labor costs.

[0158] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should know that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps may be performed in other orders or simultaneously.

[0159] Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by this disclosure.

[0160] The technical solutions of this disclosure will be further described in detail below with reference to specific application embodiments.

[0161] This disclosure provides an antenna obstruction identification method based on multidimensional data fusion and machine learning.

[0162] The specific details of the method in this example are as follows.

[0163] This solution utilizes 4G / 5G network performance data (base station cell traffic, call volume, number of users, coverage, utilization, number of sampling points, angle of arrival, handover, and tracking area distribution) to construct an antenna obstruction identification method and build an identification model. The flowchart of this solution is shown below. Figure 4 As shown, it includes the following steps:

[0164] Step 1: Data Collection

[0165] The OMC network management system collects multidimensional data from base stations and users, including base station cell traffic, call volume, number of users, coverage, utilization, number of sampling points, angle of arrival, handover, and tracking area distribution. This data reflects key information such as the signal transmission quality of base station antennas, user access status, and network performance indicators.

[0166] Traffic refers to the total number of bytes of data that a network management system needs to process, including both sent and received data. Traffic is a crucial indicator of network load and performance. By analyzing traffic, we can understand network congestion levels, identify potential bottlenecks, and take appropriate measures to adjust and optimize the network to ensure its stability and efficiency.

[0167] Traffic volume refers to the amount of voice communication processed by a telephone exchange or network per unit of time, usually measured in "voices per hour" (commonly measured in Erl) or "voices per second". Traffic volume is a key indicator for measuring the load on a communication network. By monitoring traffic volume, the network's capacity can be assessed, future communication demands can be predicted, and network planning and optimization can be carried out accordingly to meet users' voice communication needs.

[0168] User numbers refer to the number of users of an online service, including registered users, active users, and new users. User numbers are an important indicator for measuring the popularity and market share of an online service. By analyzing user numbers, we can understand user habits, changing needs, and market trends, thereby developing more effective marketing and user retention strategies.

[0169] Coverage refers to the extent to which a network or service is available in a specific region or among a target group, including geographical coverage, network coverage, and service coverage. Coverage is a crucial indicator for measuring the prevalence and quality of a network or service. By improving coverage, network service providers can expand their market reach, increase user satisfaction and loyalty, and ultimately enhance their market competitiveness.

[0170] Utilization rate refers to the frequency or proportion of network resources (such as links, nodes, and node processors) being used per unit of time. It is an important indicator for measuring the efficiency and performance of network resource utilization. By monitoring utilization rate, situations of resource idleness or overload can be identified in a timely manner, and corresponding measures can be taken for adjustment and optimization to improve resource utilization efficiency and network performance.

[0171] The number of sampling points (Measurement Report, MR) refers to the number of specific data points collected through a Measurement Report in a mobile communication network. It includes the number of data points collected regarding the wireless environment, signal strength, and other information.

[0172] The angle of arrival (AOA) is the angle between the electromagnetic wave and the direction of the receiver when the wave arrives. This concept has important applications in radar, communication, and radio positioning systems to determine the position, orientation, and motion of a target.

[0173] Handover refers to the process where a mobile station moves from one base station coverage area to another during a call, or when call quality deteriorates due to external interference, and must switch from the original voice channel to a new, idle voice channel in order to continue the call.

[0174] Tracking Area (TA) distribution refers to how multiple base station cells are divided into different tracking areas in a network to facilitate user equipment (UE) location management and paging. The tracking area is a new concept established by the system for UE location management; it is defined as a free-moving area where the UE does not need to update location services.

[0175] Step Two: Data Processing

[0176] The collected data are used to construct data granularity relationships, as shown in the table below:

[0177]

[0178] Step 3: Assigning weights to indicators

[0179] An expert scoring method will be employed, with a review panel composed of selected experts. The experts' backgrounds and qualifications will be considered to ensure they possess extensive knowledge and experience in their respective fields. Attention will be paid to the experts' research directions and achievements, ensuring strong relevance and professionalism to the evaluation indicators. The evaluation indicator system will be introduced to the experts in advance, along with relevant materials, to help them better understand the evaluation content and standards. Based on the key indicators corresponding to the cell: traffic volume, call volume, number of users, coverage, utilization, number of sampling points, angle of arrival, handover, and tracking area distribution, a total of 9 indicators, expert group members assigned different weights to each of the 9 indicators in the antenna blocking evaluation model according to the importance of each indicator (the higher the weight of an indicator, the greater the possibility of antenna blocking when that indicator deteriorates; the sum of the weights assigned by each expert to all indicators is 1). The review and scoring output the indicator weights, and the weight values ​​of each expert for the 9 indicators are ranked. (This proposal takes 7 experts, Expert A, Expert B, Expert C, Expert D, Expert E, Expert F, and Expert G, as an example. The weights are ranked from high to low, and the rankings are 1, 2, 3, 4, 5, 6, 7, 8, and 9 respectively. If the weights are the same, the rankings are the same.) As shown in the table below:

[0180]

[0181]

[0182] Step 4: Consistency Check

[0183] In step three, the scoring (weighting) of the expert panel members is tested for consistency. This scheme uses the Kendall consistency test. This method is a non-parametric statistical method. The core idea of ​​the Kendall consistency test is to calculate the degree of consistency among multiple evaluators in their ratings of the same object. The Kendall consistency test usually refers to Kendall's W coefficient, which is used to measure the consistency of ranking a set of objects among multiple evaluators. The formula for calculating Kendall's W coefficient is as follows:

[0184]

[0185] in,

[0186]

[0187] R i This represents the sum of the K ranking levels obtained by the evaluated object;

[0188] N represents the number of objects being rated; here, N = 9, representing 9 indicators.

[0189] K represents the number of rating assessors; here K=7, meaning there are 7 experts.

[0190] Based on the above formula, the detailed calculation process is as follows:

[0191] Based on the table in step three, R is calculated as follows: i and The values ​​can be obtained from the following table:

[0192]

[0193]

[0194] ①Flow rate:

[0195] R i (Flow rate) = 1 + 1 + 1 + 1 + 1 + 1 + 1 = 7

[0196] R i (flow) 2 =7 2 =49

[0197] ② Call volume:

[0198] R i (Call volume) = 4 + 4 + 4 + 4 + 4 + 4 + 3 = 27

[0199] R i (Call volume) 2 =27 2 =729

[0200] ③ Number of users:

[0201] R i (Number of users) = 3 + 3 + 3 + 3 + 3 + 4 = 22

[0202] R i (Number of users) 2 =22 2 =484

[0203] ④ Coverage:

[0204] R i (Coverage rate) = 8 + 6 + 6 + 6 + 6 + 6 + 6 = 44

[0205] R i (Coverage) 2 =44 2 =1936

[0206] ⑤ Utilization rate:

[0207] R i (Utilization rate) = 5 + 5 + 5 + 5 + 5 + 5 = 35

[0208] R i (Utilization rate) 2 =35 2 =1225

[0209] ⑥ Use points:

[0210] R i (Number of sampling points) = 2 + 2 + 2 + 2 + 2 + 2 = 14

[0211] R i (Number of sampling points) 2 =14 2 =196

[0212] ⑦ Angle of arrival:

[0213] R i (Angle of arrival) = 6 + 8 + 8 + 8 + 8 + 8 = 54

[0214] R i (Angle of arrival) 2 =54 2 =2916

[0215] ⑧ Number of switching times:

[0216] R i (Number of switching times) = 7 + 7 + 7 + 7 + 7 + 7 = 49

[0217] R i (Number of switches) 2=49 2 =2401

[0218] ⑨ Tracking area distribution:

[0219] R i (Tracking area distribution) = 9 + 9 + 9 + 9 + 9 + 9 = 63

[0220] R i (Distribution of tracking areas) 2 =63 2 =3969

[0221] From the above calculations, we can obtain:

[0222]

[0223] Furthermore, we can obtain:

[0224]

[0225] Based on the logical analysis that W values ​​range from 0 to 1, values ​​close to 0 indicate low consistency among evaluators, suggesting significant disagreement in their ranking of the items; values ​​close to 1 indicate high consistency among evaluators, suggesting very similar or identical rankings of the items. Historically, W values ​​are typically divided into different intervals to help interpret the level of consistency. In this scheme, the W value interval [0, 1] is divided evenly into 5 segments: [0, 0.2)...

[0226] The intervals are [0.2, 0.4), [0.4, 0.6), [0.6, 0.8), and [0.8, 1]. Each interval has a length of 0.2. When the value of W falls within the corresponding interval, the Kendall consistency test results can be obtained, as shown in the table below:

[0227] W value Kendall consistency test results Kendall's consistency check passed or failed? [0.8,1] Strong consistency pass [0.6,0.8) Strong consistency Not approved [0.4,0.6) Consistency is moderate Not approved [0.2,0.4) Consistency is generally Not approved [0,0.2) Poor consistency Not approved

[0228] In step three, a consistency check is performed on the scores (weighting) given by the expert panel members. When the check result is:

[0229] ①When W takes the value [0.8, 1], the consistency test is passed, proving that the scoring (weighting) of the expert group members is highly consistent;

[0230] ②When W takes the value [0, 0.8), return to step three and organize the expert group members to re-score until the value of the test result W falls in the interval [0.8, 1].

[0231] When the consistency test result w takes the value [0.8, 1], the arithmetic mean of the scores given by the expert group members is calculated to obtain the indicator weight table, as shown in the table below (where the last row is used as the final indicator weight assignment):

[0232]

[0233] Step 5: Build the model

[0234] To enhance the accuracy of the assessment and ensure that the indicator data represents normal data generated during periods of unobstructed antenna coverage, data from at least 6 months following a single base station cell verification (also known as single-site verification, which involves testing the functionality of a base station after installation) is used as the benchmark (November 2023 - May 2024), as shown in the first row of the table below. To assess the current antenna obstruction situation, average cell data (monthly / weekly granularity) for one period (May, June, July, August, and September 2024) is collected through the network management OMC, and the average values ​​of each indicator are calculated, as shown in the second, third, fourth, fifth, and sixth rows of the table below. The data is averaged daily within the time period, as shown in the table below.

[0235]

[0236]

[0237] Because of fluctuations in the indicators (increases or decreases), it is possible that the indicator value within a current period (monthly or weekly granularity) is better than the single-test baseline value. Therefore, in this scheme, we only consider the situation where the indicators deteriorate after antenna obstruction. Specifically, this manifests as: reduced traffic, reduced call volume, reduced number of users, reduced coverage, reduced utilization, reduced number of sampling points, increased angle of arrival, reduced number of handovers, and reduced tracking area distribution.

[0238] Outlier removal and handling: When data anomalies occur, i.e., the overall values ​​of the nine dimensions deteriorate, use tools such as network management / OMC / cell outage platforms to query and investigate whether base station failures / cell outages are causing the data anomalies in the nine indicators. If no such issues are found, then build the model and calculate the percentage change of multidimensional data fusion. The calculation formula is:

[0239]

[0240]

[0241] The weights are the results calculated in step four, the baseline value is the index value after single-cell verification of the base station, and the displayed value is the data value observed at this stage. Optionally, the antenna obstruction level can be predicted according to the method of this scheme if at least one of the following formulas is satisfied.

[0242]

[0243] After obtaining the percentage change, a mapping relationship between the percentage change and antenna obstruction can be preset based on historical experience, as shown in the table below:

[0244] Percentage of change Proposed classification of antenna obstruction situations [90％，100％] All blocked [60％，90％) Most of the obstacles [40％，60％) Block half [10％，40％) A small portion of the obstruction [0％，10％) No obstruction

[0245] Step Six: Evaluation and Feedback

[0246] Twenty communities each with percentage changes of [90%, 100%], [60%, 90%], [40%, 60%], [10%, 40%], and [0%, 10%] were selected, totaling 100 communities. Verification through on-site inspection yielded the results shown in the table below:

[0247]

[0248] Based on on-site verification and inspection, the model's recognition accuracy rate was 91%.

[0249] Step 7: Machine Learning Parameter Tuning

[0250] Based on the verification results in step six, machine learning parameters were introduced for optimization. Labeled data was added, the model was trained, and the adjusted parameters were used to output antenna obstruction identification results. This was then verified on-site. After multiple iterations, the model parameters tended to stabilize, as shown in the table below:

[0251]

[0252] Step 8: Model Solidification

[0253] Based on steps one through seven above, the antenna obstruction identification method model is derived.

[0254] In summary, the method presented in this example relates to the field of communication technology. Specifically, it is an antenna obstruction identification method that utilizes nine dimensions of data—base station cell traffic, call volume, number of users, coverage, utilization, number of sampling points, angle of arrival, handover, and tracking area distribution—combined with expert scoring, Kendall consistency testing, and machine learning. This method can monitor and analyze antenna obstruction in the wireless communication environment in real time, improving the stability of the communication network and the user experience. The main points are as follows:

[0255] ① Multi-dimensional data fusion: This solution comprehensively considers traffic volume, call volume, number of users, coverage, utilization, number of sampling points, angle of arrival, number of handovers, and tracking area distribution. By fusing these signal values, it can more comprehensively reflect the channel conditions and improve the accuracy of antenna obstruction identification.

[0256] ② Combination of expert scoring method, Kendall consistency test and machine learning: The model is constructed by using expert scoring method and Kendall consistency test to obtain index weights, and then machine learning is combined to train the model and recognize it in real time, so as to realize intelligent judgment of antenna obstruction status.

[0257] ③ Real-time performance and accuracy: This solution can acquire and identify signal values ​​in real time with high accuracy, which can meet the needs of practical applications.

[0258] This solution targets operator big data, using nine dimensions of data, including base station cell traffic, call volume, number of users, coverage, utilization, number of sampling points, angle of arrival, number of handovers, and tracking area distribution. It combines expert scoring, Kendall consistency test, and machine learning to establish an antenna obstruction identification method model.

[0259] Compared with traditional methods, this approach has the following advantages:

[0260] ① High accuracy: Through comprehensive analysis of data from nine dimensions and the application of machine learning, the accuracy of antenna obstruction identification has been improved.

[0261] ② Strong real-time performance: The system can monitor changes in signal parameters in real time, respond quickly and issue early warnings, which helps to detect and deal with antenna obstruction problems in a timely manner.

[0262] ③ High level of intelligence: By utilizing machine learning, it realizes the automatic identification and processing of antenna obstruction in complex environments, reducing the burden of manual inspection.

[0263] ④ Good scalability: The system can be expanded and optimized according to actual needs, and is suitable for communication network environments of different scales and complexities.

[0264] This solution can be extended to model building in fields such as intelligent security monitoring and the Internet of Things (IoT): In the field of intelligent security monitoring, this solution can be used to monitor in real time whether antennas are maliciously blocked or damaged, thereby improving the reliability and security of the security system; in the field of IoT, this solution can be used to realize remote monitoring and management of IoT devices, promptly detect and resolve antenna obstruction issues, and ensure the normal operation of the IoT system.

[0265] Figure 5 This is a block diagram of an antenna obstruction determination device 500 provided in an embodiment of this disclosure. Figure 5As shown, the device 700 includes: a first processing unit 510, configured to determine the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station; a second processing unit 520, configured to determine the target interval in which the percentage change is located from multiple candidate intervals based on the percentage change; and a third processing unit 530, configured to determine the target blocking degree corresponding to the target base station based on the target mapping relationship between multiple candidate intervals and multiple candidate blocking degrees.

[0266] In summary, the device disclosed herein can determine the percentage change corresponding to the target base station based on the real-time performance dataset and the benchmark performance dataset. Then, it can determine the degree of obstruction of the target base station based on the percentage change. This can realize the determination of the degree of obstruction based on the benchmark value and real-time performance data, improve the accuracy, real-time performance and intelligence of antenna obstruction identification, so as to perform corresponding processing according to the degree of obstruction of the target base station. It can eliminate the need for manual on-site determination of the degree of obstruction and reduce labor costs.

[0267] In some embodiments, the antenna obstruction determination device further includes a fourth processing unit, configured to collect multiple reference performance datasets of the target base station within a first time period, wherein the starting time point of the first time period is the time point at which the target base station performs a single test, and the target base station is not obstructed within the first time period; and to determine a baseline performance dataset based on the multiple reference performance datasets.

[0268] In some embodiments, the first processing unit is further configured to determine multiple differences between multiple first data included in the real-time performance dataset and multiple second data included in the benchmark performance dataset; when the multiple differences satisfy a first preset condition, determine whether the target base station has a base station fault or cell outage problem based on the real-time performance dataset; when the target base station does not have a base station fault or cell outage problem, determine the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station; or, when the multiple differences satisfy a second preset condition, determine the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station.

[0269] In some embodiments, the first preset condition is that all of the multiple differences are greater than or equal to the first preset threshold, and the second preset condition is that among the multiple differences, at least one difference is greater than or equal to the first preset threshold.

[0270] In some embodiments, the first processing unit is further configured to determine multiple first weights corresponding to each of the multiple first data; and to determine the percentage change corresponding to the target base station based on the multiple first weights, the multiple first data, and the multiple second data.

[0271] In some embodiments, the first processing unit is further configured to acquire multiple sets of score data, wherein each set of score data includes weighted scores of multiple first data; determine multiple sets of sorted data based on the multiple sets of score data, wherein each set of sorted data includes sorting results of weighted scores of multiple first data; determine a consistency coefficient based on the multiple sets of score data and the multiple sets of sorted data; if the value of the consistency coefficient is greater than or equal to a second preset threshold, determine multiple first weights based on the multiple sets of score data; if the value of the consistency coefficient is less than the second preset threshold, reacquire multiple sets of score data and determine the consistency coefficient based on the reacquired multiple sets of score data, until the consistency coefficient is greater than or equal to the second preset threshold.

[0272] In some embodiments, the fourth processing unit is further configured to: determine the percentage change corresponding to each of the plurality of reference base stations; determine the predicted degree of obstruction corresponding to each of the plurality of reference base stations based on the initial mapping relationship between the plurality of preset reference intervals and the plurality of obstruction degrees; determine at least one correction value based on the predicted degree of obstruction and the actual degree of obstruction corresponding to each of the plurality of reference base stations; correct the interval range of the plurality of preset reference intervals based on the at least one correction value to obtain a plurality of candidate intervals; and determine the target mapping relationship between the plurality of candidate intervals and the plurality of candidate obstruction degrees.

[0273] In some embodiments, at least one of the plurality of first data and plurality of second data includes: traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data.

[0274] Figure 6 This is a block diagram of an electronic device 600 for implementing the above-described method, provided as an embodiment of the present disclosure.

[0275] Based on the hardware implementation of the above program modules, and in order to implement the method of this disclosure embodiment, this disclosure embodiment also provides an electronic device, such as... Figure 6 As shown, the electronic device 600 includes:

[0276] The communication interface 601 enables information exchange with other devices;

[0277] The processor 602 is connected to the communication interface 601 to enable information interaction with other devices and to execute the methods provided by one or more of the above-mentioned technical solutions when running a computer program;

[0278] The computer program is stored in memory 603.

[0279] It should be noted that the specific processing procedure of processor 602 can be understood by referring to the above method.

[0280] Of course, in practical applications, the various components in electronic device 600 are coupled together through bus system 604. It can be understood that bus system 604 is used to realize the connection and communication between these components. In addition to a data bus, bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 6 The general designated all buses as Bus System 604.

[0281] The memory 603 in this embodiment is used to store various types of data to support the operation of the electronic device 600. Examples of such data include any computer program used to operate on the electronic device 600.

[0282] The methods disclosed in the embodiments of this application can be applied to or implemented by processor 602. Processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 602 or by instructions in the form of software. The first processor 602 mentioned above may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 602 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 603. Processor 602 reads the information in memory 603 and combines its hardware to complete the steps of the aforementioned method.

[0283] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0284] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, which can be executed by a processor 620 of an electronic device 600 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0285] Embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the above embodiments of this disclosure.

[0286] Embodiments of this disclosure also propose a chip, such as Figure 7 As shown, the chip includes a processor 710 and an interface 720. The number of processors 710 can be one or more, and the number of interfaces 720 can be multiple. The interface circuitry is used to receive signals from the electronic device's memory and send signals to the processor. The signals include computer instructions stored in the memory. When the processor executes the computer instructions, it causes the electronic device to perform the methods described in the above embodiments of this disclosure.

[0287] It should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0288] It should be understood that the terms "system," "apparatus," "unit," and / or "module" used in this application are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0289] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "a," and / or "the" are not specifically singular and may include the plural. Generally, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements. An element defined by the phrase "comprising an..." does not exclude the presence of other identical elements in the process, method, product, or apparatus that includes the element.

[0290] In the description of the embodiments 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 existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more.

[0291] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0292] Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0293] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0294] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0295] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0296] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0297] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0298] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0299] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for determining the degree of antenna obstruction, characterized in that, include: Based on the real-time performance dataset of the target base station and the baseline performance dataset corresponding to the target base station, determine the percentage change corresponding to the target base station; Based on the percentage change, determine the target interval containing the percentage change from multiple candidate intervals; The target blocking degree corresponding to the target base station is determined based on the target mapping relationship between the multiple candidate intervals and the multiple candidate blocking degrees.

2. The method of claim 1, wherein, The method further includes: Multiple reference performance datasets of the target base station are collected within a first time period. The starting time of the first time period is the time when the target base station performs single-pass verification. During the first time period, the target base station is not blocked. The benchmark performance dataset is determined based on the multiple reference performance datasets.

3. The method of claim 2, wherein, The step of determining the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the baseline performance dataset corresponding to the target base station includes: Determine multiple differences between multiple first data points included in the real-time performance dataset and multiple second data points included in the benchmark performance dataset; When the multiple differences meet the first preset condition, the target base station is determined to have a base station failure or cell outage problem based on the real-time performance dataset. If the target base station does not have the base station fault or the cell outage issue, the percentage change corresponding to the target base station is determined based on the real-time performance dataset of the target base station and the corresponding baseline performance dataset; or, When the multiple differences meet the second preset condition, the percentage change corresponding to the target base station is determined based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station.

4. The method of claim 3, wherein, The first preset condition is that all of the plurality of differences are greater than or equal to a first preset threshold, and the second preset condition is that among the plurality of differences, at least one difference is greater than or equal to the first preset threshold.

5. The method of claim 3, wherein, Based on the real-time performance dataset of the target base station and the corresponding baseline performance dataset of the target base station, the percentage change corresponding to the target base station is determined, including: Determine the multiple first weights corresponding to each of the multiple first data; The percentage change corresponding to the target base station is determined based on the plurality of first weights, the plurality of first data, and the plurality of second data.

6. The method of claim 5, wherein, Determining the multiple first weights corresponding to each of the multiple first data includes: Obtain multiple sets of score data, wherein each set of score data includes the weighted scores of the multiple first data; Multiple sets of sorted data are determined based on the multiple sets of score data, wherein each set of sorted data includes the weighted score sorting results of the multiple first data; Based on the multiple sets of score data and the multiple sets of sorted data, a consistency coefficient is determined; If the value of the consistency coefficient is greater than or equal to the second preset threshold, the plurality of first weights are determined based on the plurality of sets of score data; If the consistency coefficient is less than the second preset threshold, the multiple sets of score data are reacquired, and the consistency coefficient is determined based on the reacquired multiple sets of score data until the consistency coefficient is greater than or equal to the second preset threshold.

7. The method of claim 1, wherein, The method further includes: Determine the percentage change corresponding to each of the multiple reference base stations; Based on the initial mapping relationship between multiple preset reference intervals and the multiple degrees of obstruction, the predicted degree of obstruction corresponding to each of the multiple reference base stations is determined; Based on the predicted degree of obstruction and the actual degree of obstruction corresponding to each of the plurality of reference base stations, at least one correction value is determined; The range of the plurality of preset reference intervals is corrected according to the at least one correction value to obtain the plurality of candidate intervals; Determine the target mapping relationship between the plurality of candidate intervals and the degree to which the plurality of candidates are blocked.

8. The method of claim 3, wherein, At least one of the plurality of first data and the plurality of second data includes: traffic data, call volume data, number of users, coverage data, utilization data, number of sampling points, angle of arrival data, number of handovers, and tracking area distribution data.

9. An antenna blockage level determination apparatus, characterized by, include: The first processing unit is used to determine the percentage change corresponding to the target base station based on the real-time performance dataset of the target base station and the benchmark performance dataset corresponding to the target base station; The second processing unit is used to determine the target interval containing the percentage change from multiple candidate intervals based on the percentage change. The third processing unit is used to determine the target blocking degree corresponding to the target base station based on the target mapping relationship between the multiple candidate intervals and the multiple candidate blocking degrees.

10. An electronic device, characterized in that, include: One or more processors; A storage device communicatively connected to the one or more processors, wherein one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method of any one of claims 1-8.

11. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-8.

Images