Abnormality identification method, device and equipment of indoor distribution system, storage medium and program product

Abstract

The invention discloses an abnormal identification method and device for an indoor distribution system, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a three-dimensional model of a target building and measurement report data of a target cell associated with the target building; wherein the target cell comprises a macro station cell and an indoor distribution cell; determining an anomaly diagnosis result of the target building based on the measurement report data; when the abnormality diagnosis result indicates that the target building is abnormal, performing point cloud processing on the measurement report data of the macro station cell to obtain point cloud data; performing visual superposition on the point cloud data and the three-dimensional model to obtain visual data of signal coverage in the target building; and determining an abnormal identification result of the indoor distribution system based on the visual data. According to the embodiment of the invention, when the abnormity of the indoor distribution system is identified, manual field testing is not needed, and the abnormity checking efficiency of the indoor distribution system is improved.

Description

Technical Field

[0001] This invention relates to the field of communications, and more particularly to an anomaly identification method, apparatus, device, storage medium, and program product for an indoor distribution system. Background Technology

[0002] An Indoor Distribution System (IDS) is a dedicated communication system consisting of a signal source, transmission equipment, and terminal antennas. It is used to solve signal coverage problems in indoor environments such as office buildings and shopping malls, ensuring user communication quality and is a crucial component of mobile communication networks. With the widespread adoption of 5G technology and the surge in indoor data demand, accurately identifying hidden problems in IDS (such as weak coverage and macro base station intrusion) has become key for operators to enhance their competitiveness. The current mainstream troubleshooting method is manual on-site inspection. Technicians carry CQT (Call Quality Test) equipment to conduct on-site tests in each area, recording signal quality indicators and manually observing fluctuations in test data to determine if coverage problems exist in the area. However, manual troubleshooting, from planning the test scheme and coordinating on-site deployment to conducting on-site testing and data processing and analysis, typically takes several days or even weeks. This makes it difficult to quickly respond to user complaints or network optimization requests, leading to persistent anomalies and impacting user experience. Summary of the Invention

[0003] The purpose of this invention is to provide a method, apparatus, device, storage medium, and program product for anomaly identification of indoor distribution systems, which eliminates the need for manual on-site testing and improves the efficiency of anomaly detection in indoor distribution systems.

[0004] To achieve the above objectives, embodiments of the present invention provide an anomaly identification method for an indoor distribution system, comprising: Acquire a 3D model of the target building and measurement report data of the target cell associated with the target building; wherein, the target cell includes macro cell and indoor distributed cell; The anomaly diagnosis results of the target building are determined based on the measurement report data; When the anomaly diagnosis result indicates that there is an anomaly in the target building, the measurement report data of the macro base station cell is processed into point cloud data. The point cloud data is overlaid with the 3D model to obtain visualized data on signal coverage within the target building; The anomaly identification results of the indoor distribution system are determined based on the visualized data.

[0005] As an improvement to the above solution, the step of determining the anomaly diagnosis result of the target building based on the measurement report data includes: Based on the spatial positioning parameters in the measurement report data and the engineering parameter positioning parameters of the target cell, the two-dimensional coordinates of the sampling points are obtained; wherein, the sampling points are the signal sampling points corresponding to the measurement report data generated during the communication between the target cell and the user terminal; Cluster matching is performed between the two-dimensional coordinates and the vector map of the target building to filter out valid sampling points that fall within the range of the target building; The anomaly diagnosis result of the target building is determined based on the effective sampling points.

[0006] As an improvement to the above scheme, the step of determining the anomaly diagnosis result of the target building based on the effective sampling points includes: For all valid sampling points, obtain the number of macro base station sampling points corresponding to the macro base station cell; Calculate the proportion of macro-station sampling points to the total number of valid sampling points; When the ratio is greater than a preset threshold, an anomaly diagnosis result indicating that the target building has an anomaly is generated; when the ratio is less than or equal to the preset threshold, an anomaly diagnosis result indicating that the target building has no anomaly is generated.

[0007] As an improvement to the above scheme, the point cloud processing of the measurement report data of the macro base station cell to obtain point cloud data includes: The three-dimensional coordinates of the macro base station sampling points are determined based on the measurement report data of the macro base station cell; Perform coordinate transformation on the three-dimensional coordinates; Clustering algorithms are used to cluster the transformed 3D coordinates in order to filter out noisy data that meet the preset filtering conditions; The filtered set of 3D coordinates is used as point cloud data.

[0008] As an improvement to the above solution, the step of visually overlaying the point cloud data with the 3D model to obtain visualized data on signal coverage within the target building includes: The coordinates of the three-dimensional model of the target building are calibrated. The point cloud data is intersected with the calibrated 3D model to filter out the target point cloud data located inside the target building; The target point cloud data is colored and marked to generate a distribution heat map of the macro station signal; The distributed thermal layer is overlaid with the three-dimensional model to obtain visualized data on signal coverage within the target building.

[0009] As an improvement to the above solution, determining the anomaly identification result of the indoor distribution system based on the visualized data includes: Extract the distribution locations of strong and weak coverage areas of macro station signals within the target building from the visualized data; The abnormal areas of the target building are located based on the distribution location, and the abnormal areas are used as the anomaly identification results of the indoor distribution system.

[0010] To achieve the above objectives, embodiments of the present invention also provide an anomaly identification device for an indoor distribution system, comprising: The data acquisition module is used to acquire a 3D model of the target building and measurement report data of the target community associated with the target building; wherein, the target community includes macro cell communities and indoor distributed cell communities; An anomaly diagnosis module is used to determine the anomaly diagnosis result of the target building based on the measurement report data; The point cloud data acquisition module is used to perform point cloud processing on the measurement report data of the macro base station cell to obtain point cloud data when the anomaly diagnosis result indicates that there is an anomaly in the target building; The visualization data acquisition module is used to visually overlay the point cloud data with the three-dimensional model to obtain visualized data of signal coverage within the target building; An anomaly identification module is used to determine the anomaly identification result of the indoor distribution system based on the visualized data.

[0011] To achieve the above objectives, embodiments of the present invention also provide an anomaly identification device for an indoor distribution system, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the anomaly identification method for an indoor distribution system as described in any of the above embodiments.

[0012] To achieve the above objectives, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the anomaly identification method of the indoor distribution system as described in any of the above embodiments.

[0013] To achieve the above objectives, embodiments of the present invention also provide a computer program product, including computer instructions, which, when executed by a processor, implement the anomaly identification method for an indoor distribution system as described in any of the above embodiments.

[0014] Compared to existing technologies, the anomaly identification method, device, equipment, storage medium, and program product of the indoor distribution system disclosed in this invention acquires a 3D model of the target building and measurement report data from associated macro stations and indoor distribution cells. It first performs a rough judgment of anomalies in the target building based on the measurement report data. Only when anomalies are determined to exist is point cloud processing of the macro station measurement report data performed specifically. Then, the point cloud data is overlaid with the 3D model to generate visual signal coverage data. Finally, based on the visual data, the anomaly identification result of the indoor distribution system is accurately determined. Overall, this achieves accurate, efficient, and visual identification of anomalies in the indoor distribution system. When identifying anomalies in the indoor distribution system, no manual on-site testing is required, improving the efficiency of anomaly investigation. Furthermore, by employing a layered processing logic of initial coarse judgment followed by detailed investigation, indiscriminate full-data processing is avoided, reducing data processing costs and improving the efficiency of indoor distribution system anomaly identification. Combining 3D model and point cloud visualization overlay technology, abstract signal data is transformed into intuitive visualization results of signal distribution and abnormal areas within the building. This overcomes the limitations of traditional indoor distribution system anomaly identification, which relies on manual investigation and has vague positioning. It enables precise positioning of abnormal areas in the indoor distribution system, effectively improving the accuracy and convenience of indoor distribution system anomaly identification. This provides a clear and reliable technical basis for subsequent optimization and rectification of the indoor distribution system, ensuring the signal coverage quality and operational stability of the indoor distribution system. Attached Figure Description

[0015] Figure 1 This is a flowchart of an anomaly identification method for an indoor distribution system provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the three-dimensional model provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the target cell selection provided in an embodiment of the present invention; Figure 4 This is a flowchart of the measurement report data processing provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the vAOA parameter definition provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the visualization data provided in the embodiments of the present invention; Figure 7 This is a flowchart of the anomaly investigation process provided in the embodiments of the present invention; Figure 8 This is a structural block diagram of an anomaly identification device for an indoor distribution system provided in an embodiment of the present invention; Figure 9 This is a structural block diagram of an anomaly identification device for an indoor distribution system provided in an embodiment of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] See Figure 1 , Figure 1 This is a flowchart of an anomaly identification method for an indoor distribution system provided by an embodiment of the present invention, the anomaly identification method for an indoor distribution system includes steps S1 to S5.

[0018] S1. Obtain a 3D model of the target building and measurement report data of the target cell associated with the target building; wherein, the target cell includes macro cell and indoor distributed cell.

[0019] For example, a target building refers to a high-rise building whose height is not less than the site height, selected from 3D building model data conforming to the WebGL (Web Graphics Library) protocol obtained from a third-party platform (such as map software). This means the building's heights are greater than or equal to the site height. The site height refers to the antenna installation height of the macro base stations surrounding the target building, used to distinguish high-rise buildings requiring focused analysis and avoid the need for indoor distribution anomaly checks on low-rise buildings due to sufficient natural macro base station signal coverage. The geospatial data table for the target building mainly involves the fields shown in Table 1. Table 1 lists the record items for the geospatial information of the target building, including field names (parameterType names), corresponding storage lengths, data types, and field descriptions. For example, the Id field records the building's unique ID, the name field records the building name, the heights field records the building's height, the city, district, and province fields record the city, district, and province where the building is located, respectively, and the geometry field records the corresponding geospatial information of the building. These fields work together to achieve complete and standardized storage of the target building's geospatial data, providing structured data for subsequent operations such as target building selection and association with target cells. The data types include bigint (large integer type), varchar (variable length string type), float (floating-point type), and geometry (space data type).

[0020] Table 1 Geospatial Data of the Target Building

[0021] For example, a 3D model refers to a 3D digital map model constructed based on geospatial data conforming to the WebGL protocol provided by a third-party platform. Compared to traditional 2D vector maps, it has higher accuracy and includes geospatial information of buildings (such as geometric shape and height), providing a data foundation for subsequent 3D point cloud processing. See [link to relevant documentation]. Figure 2 , Figure 2 This is a schematic diagram of a three-dimensional model provided in an embodiment of the present invention. The model is constructed by extracting geospatial data corresponding to the target building from a third-party platform and combining it with information such as building height and geometric shape.

[0022] For example, a macro base station cell refers to the serving cell corresponding to a macro base station covering the area where the target building is located. It is determined by matching the geospatial information of the target building (such as its city and district) with the coverage area of ​​surrounding macro base stations. A macro base station is a high-power base station device deployed in an open outdoor area, with a coverage range typically ranging from hundreds of meters to several kilometers, used to provide mobile communication signal coverage for large areas. An indoor distributed antenna system (DAS) cell refers to the serving cell corresponding to an indoor DAS system deployed inside the target building. It is determined by associating the target building's identification information (such as building number and name) with the corresponding DAS system configuration data. The DAS system is used to compensate for the signal attenuation problem of macro base stations within buildings. See also... Figure 3 , Figure 3 This is a schematic diagram of the target cell selection provided by an embodiment of the present invention. The dark area in the diagram represents the target building, and the base station icon on the outside of the building corresponds to the macro base station. For example, based on the border of the target building, a buffer zone is set up within a 200-meter range corresponding to the average TA value of dense urban areas (i.e., the solid line area around the building in the diagram). The serving cell corresponding to the macro base station covering the target building within the buffer zone is defined as the macro base station cell, and the serving cell corresponding to the indoor distributed antenna system deployed inside the building is defined as the indoor distributed antenna system cell (as shown by the asterisk inside the building). This clarifies the mapping relationship between the macro base station cells and indoor distributed antenna systems associated with the target building.

[0023] For example, Measurement Report (MR) data refers to signal data generated during communication between macrocells, indoor distributed antenna systems (DAS) and user terminals. It includes spatial positioning parameters, such as at least one of CGI (Cell Global Identifier), hAOA (Horizontal Angle of Arrival), vAOA (Vertical Angle of Arrival), TA (Timing Advance), and timestamp. Measurement Report data serves as the data source for subsequent anomaly diagnosis and point cloud processing. See also... Figure 4 , Figure 4This is a flowchart of the measurement report data processing provided in this embodiment of the invention. First, the measurement report data is parsed using XML (Extensible Markup Language) to extract fields such as cgi, hAOA, vAOA, TA, and timestamp. Then, the parsed data is cleaned and format converted. Next, the processed data is aggregated according to preset rules. Then, the aggregated data is checked for parameter matching to ensure that the data is consistent with the parameters of the target cell. After that, the coordinate information of the sampling points is calculated based on the checked parameters. Finally, the data processing flow is completed, and standardized data that can be used for subsequent analysis is output.

[0024] S2. Determine the anomaly diagnosis results of the target building based on the measurement report data.

[0025] For example, an anomaly diagnosis result refers to the conclusion drawn by analyzing measurement report data to determine whether the target building has an indoor distributed antenna system (DAS) coverage anomaly, i.e., whether an anomaly exists or not. This result can be determined based on measurement report data because the data contains signal parameters when the user terminal communicates with macro cells and indoor DAS cells. Under normal circumstances, the target building should primarily be covered by indoor DAS cells, with the corresponding macro cell signal ratio being relatively low. If the sampling ratio of macro cell signals within the building exceeds a preset threshold in the measurement report data, it indicates that the DAS system is not effectively providing coverage, and there is macro cell signal intrusion within the building. This can be used to conversely determine whether the target building has an indoor DAS coverage anomaly.

[0026] Furthermore, step S2 specifically includes steps S21 to S23.

[0027] S21. Based on the spatial positioning parameters in the measurement report data and the engineering parameter positioning parameters of the target cell, obtain the two-dimensional coordinates of the sampling point; wherein, the sampling point is the signal sampling point corresponding to the measurement report data generated during the communication between the target cell and the user terminal.

[0028] For example, spatial positioning parameters refer to parameters in the measurement report data that reflect the relative position of the user terminal and the base station. These parameters include the horizontal angle of arrival (hAOA), vertical angle of arrival (vAOA), and timing advance (TA). Engineering parameter positioning parameters refer to location-related information in the engineering parameters corresponding to the target cell, such as cell longitude, cell latitude, cell azimuth, and cell downtilt angle. Further, this invention provides a calculation process for the latitude and longitude of sampling points that satisfies the following formula: (1); (2); in, The longitude of the sampling point; The dimension of the sampling points; The longitude of the target community; It is a cosine function; This is a function that converts angles to radians, used to convert angle values ​​into the radian values ​​required for trigonometric function calculations. The downslope angle of the target residential area; It is a sine function; The azimuth angle of the target residential area; The latitude of the target cell is given by the formula. These two formulas, combined with the spatial positioning parameters in the measurement report and the engineering positioning parameters of the target cell, use trigonometric functions to convert the relative position information (angle, distance) between the user terminal and the base station into the geographic latitude and longitude coordinates of the sampling point, ultimately obtaining the two-dimensional geographic location of the signal sampling point.

[0029] S22. Cluster the two-dimensional coordinates with the vector map of the target building to filter out valid sampling points that fall within the range of the target building.

[0030] For example, a vector map of a target building refers to 2D graphic data that records the geographic boundary information of the target building in vector form, including the building's latitude and longitude outline. Clustering matching is used to spatially correlate the two-dimensional coordinates of sampling points with the vector boundary of the target building, filtering out sampling points whose coordinates are within the building outline, thus eliminating invalid sampling points outside the building, and ensuring that subsequent analysis only targets signal data within the target building.

[0031] S23. Determine the anomaly diagnosis result of the target building based on the effective sampling points.

[0032] For example, the coverage status of the indoor distributed antenna system (DAS) is determined by statistically analyzing the proportion of sampling points corresponding to macro base stations and indoor distributed antenna system (DAS) cells among the valid sampling points. Under normal circumstances, the signal in the target building should be mainly provided by the indoor DAS cells, so the proportion of macro base station sampling points will be at a low level. If the proportion of macro base station sampling points exceeds a preset threshold, it indicates that the indoor DAS coverage is insufficient and should be judged as abnormal.

[0033] Further, step S23 specifically includes: for all valid sampling points, obtaining the number of macro base station sampling points corresponding to the macro base station cell; calculating the ratio of the number of macro base station sampling points to the total number of valid sampling points; when the ratio is greater than a preset threshold, generating an anomaly diagnosis result indicating that the target building has an anomaly; when the ratio is less than or equal to the preset threshold, generating an anomaly diagnosis result indicating that the target building has no anomaly.

[0034] For example, the formula for calculating the proportion of macro-station sampling points satisfies: (3); in, The proportion of macro-station sampling points to the total number of valid sampling points; This refers to the number of macro-station sampling points; This represents the total number of valid sampling points. If this percentage is greater than 10% (a preset threshold), it indicates that the macro base station signal ratio within the target building is too high, and the indoor distribution system is not effectively covering the area, thus indicating an anomaly. If the percentage is less than or equal to 10%, it indicates that the indoor distribution system coverage is normal, and no anomaly is detected.

[0035] In this embodiment of the invention, the accuracy of sampling point coordinate calculation is ensured by combining spatial positioning with engineering parameters. Furthermore, irrelevant sampling points outside buildings are eliminated through vector map clustering and matching, avoiding invalid data interference with diagnostic results and improving the accuracy and reliability of anomaly diagnosis. Simultaneously, anomaly determination is based on valid sampling points, laying a solid data foundation for subsequent targeted point cloud processing and visualization analysis. This effectively reduces subsequent data computation, improves the efficiency of the overall identification process, and the determination logic is simple and controllable, adapting to the pre-screening needs of indoor distribution anomalies in various building scenarios.

[0036] S3. When the abnormal diagnosis result indicates that there is an abnormality in the target building, the measurement report data of the macro base station cell is processed into point cloud data.

[0037] For example, the anomaly diagnosis result of the target building is determined by the proportion of macro base station sampling points exceeding a preset threshold. The essence of this anomaly is that the macro base station signal abnormally intrudes into the target building, and the indoor distribution system fails to achieve effective coverage. Therefore, the measurement report data of the macro base station cell can reflect the spatial distribution characteristics of the intruding macro base station signal within the building, and is key data for locating the abnormal area of ​​the indoor distribution system. However, the measurement report data of the indoor distribution system cell cannot effectively reflect the normal signal coverage status within the building due to the failure of the indoor distribution system, so it does not need to be included in this point cloud processing. Focusing only on the macro base station cell data can accurately pinpoint the root cause of the anomaly. At the same time, this measure can also reduce invalid data calculations, thereby improving processing efficiency.

[0038] It's important to note that point cloud data is a dataset of points within a coordinate system, containing rich information such as 3D coordinates, color, classification values, intensity values, and time. Macrocell cell measurement reports consist of discrete signal parameter data, failing to visually represent the spatial distribution of macrocell signals within the target building. Point cloud data, however, constructs a 3D discrete point set within the 3D model space of the target building based on the discrete macrocell sampling points' 2D coordinates and signal intensity information. This transforms abstract macrocell signal data into an intuitive 3D spatial point cloud, clearly reconstructing the coverage and intensity distribution of macrocell signals across different floors and areas of the target building.

[0039] Further, step S3 specifically includes: determining the three-dimensional coordinates of the macro base station sampling points based on the measurement report data of the macro base station cell; performing coordinate transformation on the three-dimensional coordinates; using a clustering algorithm to cluster the transformed three-dimensional coordinates to filter out noisy data that meets preset filtering conditions; using the filtered three-dimensional coordinate set as point cloud data; wherein, the preset filtering conditions are: the distance between the macro base station sampling point and the target building exceeds a preset distance threshold, or the proportion of the number of macro base station sampling points is lower than a preset proportion threshold.

[0040] For example, step S3 transforms the measurement report data of the macro base station cell into point cloud data that can be used for 3D visualization through multi-stage processing.

[0041] First, determine the three-dimensional coordinates of the macrocell sampling point. Then, combine this with the vertical angle of arrival and timing advance from the corresponding cell measurement report data, as well as parameters such as the macrocell's station height and downtilt angle, to calculate the sampling point height using the height calculation formula. The calculation process satisfies the following: (4); in, The height of the sampling point; This refers to the site height of the macro site; For the timing lead time of macro stations; The vertical angle of arrival for the macro station; The downtilt angle of the macro station.

[0042] For example, after obtaining the sampling point height, the three-dimensional coordinates (latitude, longitude + height) of the macro-station sampling point can be obtained by combining it with the latitude and longitude of the sampling point calculated in step S2. See [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram of the vAOA parameter definition provided in this embodiment of the invention. UE represents the user terminal, i.e., a mobile communication device such as a mobile phone, which is the signal transmitter; the antenna panel represents the antenna device of the macro base station, which is the signal receiver; the horizontal direction and the zenith direction are the reference directions of the spatial coordinate system. The horizontal direction is a plane direction parallel to the ground, and the zenith direction is a direction perpendicular to the ground and pointing towards the sky; vAOA, or Vertical Angle of Arrival, refers to the vertical angle relative to the zenith direction when the signal transmitted by the user terminal reaches the base station antenna panel. This diagram intuitively shows the definition of vAOA through the spatial coordinate system and the relative position of the device. After the signal is emitted from the UE, it arrives at the base station antenna panel at a certain vertical angle. This angle is vAOA, which reflects the positional relationship of the UE relative to the base station in the vertical direction and is the core parameter for calculating the sampling point height.

[0043] Then, since the latitude and longitude of the sampling points belong to the WGS84 spherical coordinate system, it is not convenient to directly generate 3D point clouds. Therefore, coordinate transformation is required, such as Mercator transformation, which projects the latitude and longitude to a planar coordinate system. That is, the latitude and longitude information needs to be transformed by Mercator. The following is an example of the Mercator transformation formula: (5); (6); in, and These are the x and y coordinates of the plane after Mercator projection, respectively; This is the original longitude value; This is the Earth's equatorial radius; This is the original latitude value; To represent the sine function value corresponding to a latitude value, the latitude must first be... The calculation is performed after converting to radians. The Mercator coordinates are then preserved to integer values ​​to provide a planar coordinate basis for subsequent 3D point cloud construction.

[0044] Finally, K-means and Python were used to implement 3D point cloud clustering. This algorithm mainly clusters based on the spatial density of the data, defining a cluster as the largest set of density-connected points. A cluster is only generated when the number of objects within a certain spatial range around the target point exceeds a set threshold. Using the number of macrocell cells as the cluster number K, the algorithm aggregates sampling points into multiple clusters based on spatial density, retaining only clusters that meet the density requirements. Simultaneously, sampling points that are more than 3 kilometers away from the target building or whose number accounts for less than 1% of the total number of points are filtered out (i.e., preset filtering conditions). The final effective set of three-dimensional coordinates is the point cloud data, which can clearly present the three-dimensional distribution of macrocell signals within the target building. Assume the k-th cluster contains... There are 1 data points, and the three-dimensional coordinates of these points are as follows: ( , , ), ( , , ...( , , If the new cluster center coordinates are: (7); in, Indicates the first Data points, .

[0045] In this embodiment of the invention, the precise construction and transformation of three-dimensional coordinates achieves spatial standardization of macro-station signal sampling data, laying a unified data foundation for subsequent matching and overlay with the target building's three-dimensional model, and avoiding visualization misalignment caused by differences in coordinate systems. Clustering algorithms can accurately remove invalid sampling points far from the target building and interference noise points with extremely low proportions, improving the purity and effectiveness of point cloud data, reducing the interference of redundant data on subsequent analysis. The optimized, high-quality point cloud data can more realistically and accurately reflect the actual distribution of macro-station signals within the target building, providing reliable data support for subsequent signal coverage visualization overlay and abnormal area location, further improving the overall efficiency and accuracy of indoor distribution system anomaly identification.

[0046] S4. Visually overlay the point cloud data with the three-dimensional model to obtain visualized data of signal coverage within the target building.

[0047] For example, visualization overlay is used to spatially align and fuse the 3D point cloud data of abstract macrocell sampling points with the 3D digital model of the target building. By mapping the point cloud data (reflecting the 3D distribution of macrocell signals) onto the 3D model space of the target building, the coverage range and signal strength distribution of macrocell signals in different areas of the target building can be intuitively presented. For example, which floors have dense macrocell signals and which areas have weak signals. This transforms the originally imperceptible signal data into a visualization effect of 3D model and point cloud overlay, making areas with abnormal signal coverage (i.e., areas not effectively covered by the indoor distribution system) clearly visible. This provides an intuitive visual basis for subsequent location of specific faults in the indoor distribution system and the development of optimization plans.

[0048] Further, step S4 specifically includes: performing coordinate calibration on the three-dimensional model of the target building; performing intersection processing on the point cloud data and the calibrated three-dimensional model to filter out the target point cloud data located inside the target building; coloring and marking the target point cloud data to generate a distribution heat map of the macro station signal; and overlaying the distribution heat map with the three-dimensional model to obtain visualized data of signal coverage within the target building.

[0049] For example, by combining a three-dimensional vector building model and a three-dimensional sampling point image, the building signal coverage is obtained through the spatial GIS (Geographic Information System) calculation process. This coverage map can intuitively show the distribution of 5G macro base station signal strength inside the building, and inversely map the coverage problem of 5G indoor distribution within the building, providing a location reference for the next step of systematic optimization and investigation.

[0050] First, examine the 3D GIS data of the target building to determine its position and orientation in the global coordinate system. Then, determine the local coordinate system corresponding to the point cloud data. Typically, the origin is taken as the geometric center of the building, the entrance point, or other feature points. Combined with architectural design documents or field measurement data, establish the correspondence between the origin of the local coordinate system and the global coordinate system, complete the coordinate calibration of the 3D model, and ensure the spatial alignment accuracy between the subsequent point cloud data and the model.

[0051] Next, the 3D point cloud data and the 3D building model are precisely aligned in space to ensure that their coordinate systems are consistent. It is necessary to ensure that the 3D model format used is supported by the selected library or framework. Common formats include obj (Object File Format), gltf (GL Transmission Format), and glb (GLB Binary File Format). Spatial geometry algorithms, such as the Bounding Box Algorithm, are used to perform intersection detection and filter valid point clouds inside the building. First, the axis-aligned bounding box (AABB) of the 3D building model is calculated. For the 3D building model, its minimum and maximum coordinate values ​​on the three coordinate axes (X, Y, Z) are determined. These six coordinate values ​​define a cuboid, i.e., the axis-aligned bounding box. For example, suppose the set of vertex coordinates of the 3D building model (containing a total of...) These n vertices are: ; Calculate the minimum coordinate value: , , ; Calculate the maximum coordinate value: , , ; AABB is determined by these six coordinate values, which satisfy: ; The coordinates of the MR sampling points are: ; If satisfied ， ， If the MR sampling point is inside the AABB, then it is outside the AABB; otherwise, it is outside the AABB.

[0052] Furthermore, the filtered target point cloud data inside the building is colored and marked. For example, the target point cloud data can be mapped to a color that distinguishes it from the target building, thereby transforming the discrete effective point cloud into a macro station signal distribution thermal layer, which intuitively reflects the spatial differences in signal strength.

[0053] Finally, the colored macro-station signal thermal layer is fused and overlaid with the target building's 3D vector building model to complete the final matching of the 3D point cloud and the building model, thus constructing a 3D signal coverage model of the target building. See also Figure 6 , Figure 6 This is a schematic diagram of the visualization data provided in the embodiment of the present invention. The dots in the diagram represent target point cloud data. This diagram shows the final effect of superimposing the three-dimensional model of the target building with the thermal point cloud of the macro station signal. Core information such as the dense area of ​​macro station signal (weak area of ​​indoor distribution coverage) and the signal blank area in the building can be directly observed, realizing the visualization and location of signal coverage defects.

[0054] In this embodiment of the invention, the coordinate calibration process ensures precise alignment between point cloud data and the 3D model, fundamentally avoiding misjudgments of signal distribution caused by layer overlay misalignment, and laying a solid foundation for the accuracy of subsequent information extraction. By visually presenting the distribution of macro-station signals through thermal layers and constructing a three-dimensional signal coverage scene using a 3D model, the limitations of traditional two-dimensional signal analysis are overcome. This clearly reflects signal differences in different areas and simultaneously correlates and extracts indoor distribution coverage defect information, directly establishing a mapping relationship between macro-station signal distribution and indoor distribution anomalies. Weak areas in indoor distribution coverage can be quickly located without additional complex calculations, providing an intuitive and reliable visual basis for accurately determining the results of indoor distribution system anomaly identification. Simultaneously, it reduces the difficulty for technicians to interpret signal data and improves the efficiency and convenience of anomaly analysis.

[0055] S5. Determine the anomaly identification result of the indoor distribution system based on the visualized data.

[0056] For example, the anomaly identification result is a judgment on the fault status of the indoor distribution system. Based on the thermal distribution characteristics of macro station signals in the visualized data, it reversely locates one or more elements such as weak areas not effectively covered by the indoor distribution system (such as a certain floor or a certain area), the area range of the abnormal area, and the intensity level of macro station signal intrusion (mild / moderate / severe). At the same time, it clarifies the cause of the anomaly, such as the corresponding area lacks indoor distribution signal coverage, insufficient signal power, unreasonable antenna placement, etc. Compared with the macro conclusion of step S2 which only determines whether there is an anomaly, the anomaly identification result of this step achieves precise implementation from whether there is an anomaly to where the anomaly is, the degree of the anomaly, and why the anomaly is. It provides specific and actionable fault location basis for targeted optimization and rectification of the indoor distribution system.

[0057] Further, step S5 specifically includes: extracting the distribution locations of strong and weak coverage areas of macro station signals within the target building from the visualization data; locating abnormal areas of the target building based on the distribution locations; and using the abnormal areas as the anomaly identification results of the indoor distribution system.

[0058] For example, from the visualized data, the specific spatial distribution of strong macro base station signal coverage areas is directly extracted, such as areas where the macro base station signal strength is ≥ a preset strong signal threshold and the point cloud is marked with a high saturation color scheme. Similarly, the specific spatial distribution of weak coverage areas is extracted, such as areas where the macro base station signal strength is < a preset weak signal threshold and the point cloud is marked with a low saturation color scheme. Then, precise geographical information such as the target building floor, building area, and specific location corresponding to each area is determined. In a normal communication scenario inside the target building, the indoor distributed antenna system (DAS) should dominate signal coverage, with the macro base station signal only supplementing it. Therefore, areas with strong macro base station signal coverage are abnormal areas where the DAS coverage fails. These areas are caused by missing DAS signals, insufficient power, or unreasonable antenna placement, leading to abnormal macro base station signal intrusion and becoming the dominant signal; these are the main fault areas of the DAS. Conversely, areas with weak or no macro base station signal coverage are areas where the DAS coverage is normal and there are no signal coverage anomalies. Based on the above judgment logic, the extracted strong coverage area of ​​macro base station signal is directly located as the indoor distribution system abnormal area of ​​the target building. The specific boundaries, coverage floor range, and signal intrusion intensity level of the abnormal area are clearly defined. This accurate abnormal area information (including location, range, and level) is used as the abnormal identification result of the indoor distribution system. This result can directly guide subsequent rectification operations such as indoor distribution system point optimization, power debugging, and fault diagnosis, so as to achieve a precise closed-loop solution to indoor distribution system abnormality problems.

[0059] In this embodiment of the invention, by acquiring the three-dimensional model of the target building and the measurement report data of the associated macro stations and indoor distribution cells, a rough judgment of the target building's anomalies is first made based on the measurement report data. Only when anomalies are determined to exist, point cloud processing of the macro station measurement report data is carried out specifically. Then, the point cloud data is overlaid with the three-dimensional model to generate signal coverage visualization data. Finally, the anomaly identification result of the indoor distribution system is accurately determined based on the visualization data. Overall, the anomaly identification of the indoor distribution system is achieved in a precise, efficient and visualized manner. When identifying anomalies in the indoor distribution system, no manual on-site testing is required, which improves the efficiency of anomaly investigation in the indoor distribution system. Furthermore, by employing a layered processing logic of initial coarse judgment followed by detailed investigation, indiscriminate full-data processing is avoided, reducing data processing costs and improving the efficiency of indoor distribution system anomaly identification. Combining 3D model and point cloud visualization overlay technology, abstract signal data is transformed into intuitive visualization results of signal distribution and abnormal areas within the building. This overcomes the limitations of traditional indoor distribution system anomaly identification, which relies on manual investigation and has vague positioning. It enables precise positioning of abnormal areas in the indoor distribution system, effectively improving the accuracy and convenience of indoor distribution system anomaly identification. This provides a clear and reliable technical basis for subsequent optimization and rectification of the indoor distribution system, ensuring the signal coverage quality and operational stability of the indoor distribution system.

[0060] Furthermore, after performing step S5, the method further includes: taking the abnormal area as the analysis object, integrating the network operation data and configuration data of the target cell to perform abnormal cause analysis, and determining the root cause of the abnormality of the indoor distribution system; and generating an optimization strategy for the indoor distribution system based on the root cause of the abnormality.

[0061] For example, see Figure 7 , Figure 7 This is an anomaly investigation flowchart provided by an embodiment of the present invention. The anomaly area determined in step S5 is mapped to a specific floor of the target building (i.e., the problem floor). Analysis is performed using the three-dimensional sampling point image at the height of the anomaly area. If the number of macro base station sampling points at that height accounts for more than 10% of the total sampling points in the building, it is determined to be a floor where macro base station signals have intruded. If the percentage of sampling points at that height is greater than 5%, and the MR_NR5G_SSRP (5G signal received power) field value of the indoor distribution system in the sampling points is 3dB higher than the MR_NR5G_SSRP (5G signal received quality) field value of the total sampling points in the building, it is determined to be a floor with suspected unreasonable interoperability configuration, thus clarifying the specific problem floor corresponding to the anomaly. It should be noted that the above thresholds are only examples and can be set as needed in actual applications.

[0062] For example, the system can be further linked to the indoor distribution design drawings of the target building to confirm the deployment location of hardware devices such as indoor distribution gNodeB and RRU (Remote Radio Unit) on the problematic floor; or it can be linked to the KPI (Key Performance Indicator) data of indoor distribution gNodeB and RRU to obtain key operational information such as service traffic, signal quality, and equipment status of the indoor distribution system in real time to determine whether the working status of the indoor distribution system is abnormal; or parameters such as MR_NR5G_SSRP and MR_NR5G_SSRQP in the MRO file can be extracted to determine whether the interoperability configuration is abnormal. If there are cases such as mismatch in neighbor cell configuration, it is determined to be the cause of interoperability abnormality.

[0063] For example, if the root cause is a hardware failure or signal loss in the indoor distribution system, an optimization strategy to correct the indoor distribution system design is generated, such as adjusting the RRU deployment location or adding antennas. If the root cause is an abnormal operating status of the indoor distribution system, an optimization strategy to troubleshoot based on alarms is generated, such as repairing faulty equipment or restarting abnormal units. If the root cause is an abnormal interoperability configuration, it is further determined whether neighboring cells match; if neighboring cells do not match, a strategy to add neighboring cells is generated; if neighboring cells match, a strategy to optimize the interoperability threshold is generated. If none of the above causes match, an on-site troubleshooting strategy is generated, and the root cause is located through on-site survey. This completes the selection of the optimization strategy for the indoor distribution system.

[0064] In this embodiment of the invention, anomaly areas are used as the analysis object. A deep analysis of the causes of anomalies is conducted by integrating network operation data and configuration data of the target cell. This accurately locates the root causes of anomalies in the indoor distributed antenna system (DAS) and generates targeted optimization strategies. This realizes a process of identifying, analyzing, and implementing solutions for indoor DAS anomalies, overcoming the technical limitations of merely locating anomalies without providing solutions. Through multi-dimensional network data fusion analysis, the limitations of judging based on single signal data are eliminated. This allows for accurate identification of root causes of anomalies such as indoor DAS antenna layout, power configuration, neighbor cell parameters, and signal attenuation, avoiding efficiency losses caused by blind troubleshooting and improving the accuracy and scientific rigor of anomaly root cause determination. Furthermore, based on the actual root causes, adapted optimization strategies are generated, providing clear and implementable technical solutions for indoor DAS system rectification and optimization. No additional analysis by technical personnel is required, effectively shortening the rectification cycle and reducing optimization costs. This solves the problem of disconnect between indoor DAS anomaly identification and rectification, ensuring rapid restoration of signal coverage quality in the indoor DAS system and comprehensively improving the refinement and efficiency of indoor DAS network operation and maintenance.

[0065] See Figure 8 , Figure 8 This is a structural block diagram of an anomaly detection device 100 for an indoor distribution system provided in an embodiment of the present invention. The anomaly detection device 100 for the indoor distribution system includes: The data acquisition module 11 is used to acquire a three-dimensional model of the target building and measurement report data of the target community associated with the target building; wherein, the target community includes macro base station communities and indoor distribution communities; Anomaly diagnosis module 12 is used to determine the anomaly diagnosis result of the target building based on the measurement report data; The point cloud data acquisition module 13 is used to perform point cloud processing on the measurement report data of the macro base station cell to obtain point cloud data when the anomaly diagnosis result indicates that there is an anomaly in the target building; The visualization data acquisition module 14 is used to visualize and overlay the point cloud data with the three-dimensional model to obtain the visualization data of signal coverage within the target building; Anomaly identification module 15 is used to determine the anomaly identification result of the indoor distribution system based on the visualized data.

[0066] Furthermore, the anomaly detection device 100 of the indoor distribution system also includes: The abnormal root cause acquisition module is used to analyze the abnormal area, integrate the network operation data and configuration data of the target cell to perform abnormal cause analysis, and determine the abnormal root cause of the indoor distribution system. An optimization strategy generation module is used to generate an optimization strategy for the indoor distribution system based on the root causes of the anomalies.

[0067] It is worth noting that the working process of each module in the anomaly identification device 100 of the indoor distribution system described in the embodiments of the present invention can refer to the working process of the anomaly identification method of the indoor distribution system described in the above embodiments, and will not be repeated here.

[0068] See Figure 9 , Figure 9 This is a structural block diagram of an anomaly detection device 200 for an indoor distribution system provided in an embodiment of the present invention. The anomaly detection device 200 includes a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the steps in the above-described embodiments of the anomaly detection methods for various indoor distribution systems.

[0069] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the anomaly identification device 200 of the indoor distribution system.

[0070] The anomaly detection device 200 of the indoor distribution system may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the anomaly detection device 200 of the indoor distribution system and does not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the anomaly detection device 200 of the indoor distribution system may also include input / output devices, network access devices, buses, etc.

[0071] The processor 21 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the anomaly detection device 200 of the indoor distribution system, connecting various parts of the anomaly detection device 200 of the entire indoor distribution system via various interfaces and lines.

[0072] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the anomaly identification device 200 of the indoor distribution system by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0073] If the module / unit integrated by the anomaly identification device 200 of the indoor distribution system is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 21, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0074] Furthermore, the present invention also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implements the anomaly identification method for an indoor distribution system as described in any of the above embodiments.

[0075] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for anomaly identification in an indoor distribution system, characterized in that, include: Acquire a 3D model of the target building and measurement report data of the target cell associated with the target building; wherein, the target cell includes macro cell and indoor distributed cell; The anomaly diagnosis results of the target building are determined based on the measurement report data; When the anomaly diagnosis result indicates that there is an anomaly in the target building, the measurement report data of the macro base station cell is processed into point cloud data. The point cloud data is overlaid with the 3D model to obtain visualized data on signal coverage within the target building; The anomaly identification results of the indoor distribution system are determined based on the visualized data.

2. The anomaly identification method for an indoor distribution system as described in claim 1, characterized in that, The determination of the anomaly diagnosis result of the target building based on the measurement report data includes: Based on the spatial positioning parameters in the measurement report data and the engineering parameter positioning parameters of the target cell, the two-dimensional coordinates of the sampling points are obtained; wherein, the sampling points are the signal sampling points corresponding to the measurement report data generated during the communication between the target cell and the user terminal; Cluster matching is performed between the two-dimensional coordinates and the vector map of the target building to filter out valid sampling points that fall within the range of the target building; The anomaly diagnosis result of the target building is determined based on the effective sampling points.

3. The anomaly identification method for an indoor distribution system as described in claim 2, characterized in that, The determination of the anomaly diagnosis result of the target building based on the effective sampling points includes: For all valid sampling points, obtain the number of macro base station sampling points corresponding to the macro base station cell; Calculate the proportion of macro-station sampling points to the total number of valid sampling points; When the ratio is greater than a preset threshold, an anomaly diagnosis result indicating that the target building has an anomaly is generated; when the ratio is less than or equal to the preset threshold, an anomaly diagnosis result indicating that the target building has no anomaly is generated.

4. The anomaly identification method for an indoor distribution system as described in claim 1, characterized in that, The point cloud data obtained by performing point cloud processing on the measurement report data of the macro base station cell includes: The three-dimensional coordinates of the macro base station sampling points are determined based on the measurement report data of the macro base station cell; Perform coordinate transformation on the three-dimensional coordinates; Clustering algorithms are used to cluster the transformed 3D coordinates in order to filter out noisy data that meet the preset filtering conditions; The filtered set of 3D coordinates is used as point cloud data.

5. The anomaly identification method for an indoor distribution system as described in claim 1, characterized in that, The step of visually overlaying the point cloud data with the 3D model to obtain visualized data on signal coverage within the target building includes: The coordinates of the three-dimensional model of the target building are calibrated. The point cloud data is intersected with the calibrated 3D model to filter out the target point cloud data located inside the target building; The target point cloud data is colored and marked to generate a distribution heat map of the macro station signal; The distributed thermal layer is overlaid with the three-dimensional model to obtain visualized data on signal coverage within the target building.

6. The anomaly identification method for an indoor distribution system as described in claim 1, characterized in that, The step of determining the anomaly identification result of the indoor distribution system based on the visualized data includes: Extract the distribution locations of strong and weak coverage areas of macro station signals within the target building from the visualized data; The abnormal areas of the target building are located based on the distribution location, and the abnormal areas are used as the anomaly identification results of the indoor distribution system.

7. An anomaly detection device for an indoor distribution system, characterized in that, include: The data acquisition module is used to acquire a 3D model of the target building and measurement report data of the target community associated with the target building; wherein, the target community includes macro cell communities and indoor distributed cell communities; An anomaly diagnosis module is used to determine the anomaly diagnosis result of the target building based on the measurement report data; The point cloud data acquisition module is used to perform point cloud processing on the measurement report data of the macro base station cell to obtain point cloud data when the anomaly diagnosis result indicates that there is an anomaly in the target building; The visualization data acquisition module is used to visually overlay the point cloud data with the three-dimensional model to obtain visualized data of signal coverage within the target building; An anomaly identification module is used to determine the anomaly identification result of the indoor distribution system based on the visualized data.

8. An anomaly detection device for an indoor distribution system, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the anomaly identification method for an indoor distribution system as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the anomaly identification method for an indoor distribution system as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the anomaly identification method for an indoor distribution system as described in any one of claims 1 to 6.

Images