Voice paging latency cell detection method, apparatus, device, medium and product
Patent Information
- Application Number
- CN202510529467.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-25
- Publication Date
- 2026-10-27
AI Technical Summary
[0004]本申请提供一种语音寻呼时延小区检测方法、装置、设备、介质及产品，解决现有方案精准度不足，容易出现小区误判的情况，不仅加大了运营商网络优化人员工作量，还降低了实际发生问题小区优化效率的问题
[0015]本申请提供的语音寻呼时延小区检测方法、装置、设备、介质及产品，通过小区业务量序列对小区高寻呼时延次数序列进行修正，消除小区业务量波动对小区高寻呼时延次数的影响，将修正后的小区高寻呼时延次数序列输入至不同类型小区对应的寻呼时延异常检测模型，预测得到该类型小区的高寻呼时延阈值预测值以便进行异常小区识别，与寻呼时延前N名或统一阈值的识别方案相比，考虑到不同类型小区对阈值的影响，提高了识别精准度，大大降低了小区误判的概率，有助于提升实际发生问题小区优化效率。
Smart Images
Figure CN122994716A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of wireless communication technology, and in particular to a method, apparatus, device, medium and product for detecting voice paging delay cells. Background Technology
[0002] Voice paging latency is the time interval between the called network sending a paging message to the called terminal and the called network receiving a response from the called terminal during a voice call. Higher paging latency not only affects user experience but also increases the risk of call connection failure. The length of voice paging latency depends on the quality of the radio cell accessed by the called user. Identifying and detecting cells with high paging latency is key to optimizing voice service experience.
[0003] Existing high paging latency and poor cell quality identification schemes collect paging latency data for each call detail record (CDR) session, including the called access cell and its paging latency. They then calculate the daily paging latency values for all called access cells, determine the average paging latency, and set the top N cells with the lowest paging latency or those with an average paging latency exceeding a certain threshold as optimization targets. However, these existing schemes lack accuracy and are prone to misidentification, increasing the workload for network optimization personnel and reducing the efficiency of optimizing problematic cells. Summary of the Invention
[0004] This application provides a method, apparatus, equipment, medium, and product for detecting cell delays during voice paging, which solves the problems of insufficient accuracy and easy misjudgment of cells in existing solutions. This not only increases the workload of network optimization personnel of operators, but also reduces the efficiency of optimizing cells that actually have problems.
[0005] This application provides a method for detecting cell delays during voice paging, including: Based on the collected voice paging delay data, a high paging delay frequency sequence and a cell traffic volume sequence are determined. The high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds a preset high paging delay threshold. The high paging delay frequency sequence of the cell is corrected based on the cell traffic volume sequence; The corrected sequence of high paging delay times in the cell is input into the paging delay anomaly detection model corresponding to different types of cells to obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. Based on the predicted high paging delay threshold, cells with abnormal paging delays are identified.
[0006] As one embodiment, the step of correcting the cell high paging delay frequency sequence based on the cell traffic volume sequence includes: Based on the traffic volume sequence of the cell, determine the average traffic volume at each time point within the detection window period; Determine the business volume fluctuation coefficient based on the average business volume; The sequence of high paging delays in the cell is corrected based on the traffic fluctuation coefficient.
[0007] As one embodiment, determining the business volume fluctuation coefficient based on the average business volume includes: The ratio of the cell traffic volume sequence to the average traffic volume is used as the traffic volume fluctuation coefficient. Correspondingly, the step of correcting the high paging delay frequency sequence of the cell based on the traffic fluctuation coefficient includes: The ratio of the high paging delay frequency sequence of the cell to the traffic fluctuation coefficient is calculated to correct the high paging delay frequency sequence of the cell.
[0008] As one embodiment, determining the cell high paging delay frequency sequence and cell traffic volume sequence based on the collected voice paging delay data includes: Based on the called access cell ID in the voice paging delay data, cell aggregation is performed on the voice paging delay data to determine the sequence of high paging delay times in the cell; Based on the called access cell ID, the total number of initial and final voice service calls occurring to the access user in the voice paging delay data is aggregated by cell to determine the cell service volume sequence.
[0009] As an example, the determination step of the paging delay anomaly detection model includes: Based on community attribute factors and date factors, a clustering algorithm is selected to cluster the communities, resulting in different types of communities; The time series prediction model is trained based on historical voice paging delay data of different types of cells to obtain paging delay anomaly detection models corresponding to different types of cells.
[0010] As one embodiment, determining the abnormal paging delay cell based on the predicted high paging delay threshold includes: The predicted high paging latency threshold is compared with the actual number of high paging latency events in the corresponding cell. If the actual number of high paging latency events is not lower than the predicted high paging latency threshold, the actual traffic volume of the cell is calculated, and the cell whose actual traffic volume is higher than the traffic volume threshold is identified as an abnormal paging latency cell.
[0011] This application also provides a voice paging delay cell detection device, including: The first determining module is used to determine the cell high paging delay frequency sequence and the cell traffic volume sequence based on the collected voice paging delay data. The cell high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds the preset high paging delay threshold. The correction module is used to correct the high paging delay frequency sequence of the cell based on the cell traffic volume sequence; The prediction module is used to input the corrected sequence of high paging delay times in the cell into the paging delay anomaly detection model corresponding to different types of cells, and obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. The second determining module is used to determine the abnormal paging delay cell based on the predicted value of the high paging delay threshold.
[0012] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described voice paging delay cell detection methods.
[0013] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the voice paging delay cell detection method as described above.
[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the voice paging delay cell detection method as described above.
[0015] The voice paging delay cell detection method, apparatus, equipment, medium, and product provided in this application corrects the cell high paging delay frequency sequence by using the cell traffic volume sequence, eliminating the impact of cell traffic volume fluctuations on the cell high paging delay frequency. The corrected cell high paging delay frequency sequence is input into the paging delay anomaly detection model corresponding to different cell types to predict the high paging delay threshold value of that cell type for anomaly cell identification. Compared with the identification scheme of the top N paging delays or a uniform threshold, this method considers the impact of different cell types on the threshold, improves the identification accuracy, greatly reduces the probability of cell misjudgment, and helps to improve the optimization efficiency of actual problematic cells. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is one of the flowcharts of the voice paging delay cell detection method provided in this application.
[0018] Figure 2 This is a schematic diagram of the correction process for the high paging delay sequence of the cell provided in this application.
[0019] Figure 3 This is the second flowchart of the voice paging delay cell detection method provided in this application.
[0020] Figure 4 This is a schematic diagram of the structure of the voice paging delay cell detection device provided in this application.
[0021] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0023] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and regulations of the locality and with authorization from the owner of the relevant device.
[0024] Existing solutions for identifying high paging latency and poor cell quality rely heavily on pre-set thresholds or top-N segmentation, depending on human experience and requiring continuous threshold correction, resulting in low identification efficiency. Furthermore, these solutions fail to consider the actual wireless environment, traffic volume, and fluctuations in traffic within each cell, leading to insufficient accuracy and an inability to precisely pinpoint the cells with the real problems.
[0025] Therefore, this application provides a method, apparatus, device, medium, and product for detecting cell delay in voice paging, which will be described in detail below with reference to the accompanying drawings.
[0026] Figure 1 This is one of the flowcharts illustrating the voice paging delay cell detection method provided in this application, such as... Figure 1 As shown, this application provides a method for detecting cell delay in voice paging, including steps S100-S400.
[0027] Step S100: Based on the collected voice paging delay data, determine the cell high paging delay frequency sequence and the cell traffic volume sequence. The cell high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds the preset high paging delay threshold.
[0028] Specifically, a Deep Packet Inspection (DPI) system can be used to collect signaling data measurements of cells or all cells within a preset range during the voice call phase and generate a document. By calculating the time interval between the issuance of paging signaling on the N1N2 or S1-MME interface and the arrival of service request signaling in the document, the paging delay of a single voice call service can be obtained. Voice paging delay data of cells or all cells within the preset range can be obtained. Based on the high paging delay threshold set in the current network specifications, the sequence of high paging delay times for each cell can be determined. The cell traffic volume sequence is used to characterize the number of voice paging times for each cell within the corresponding time period of the voice paging delay data.
[0029] Step S200: Correct the cell high paging delay frequency sequence based on the cell traffic volume sequence. Specifically, based on the cell traffic volume sequence, determine the traffic volume fluctuation coefficient for each cell to correct the cell high paging delay frequency sequence and remove the influence of traffic volume fluctuation factors.
[0030] Step S300: The corrected sequence of high paging delay occurrences in the cell is input into the paging delay anomaly detection model corresponding to different cell types to obtain the predicted high paging delay threshold output by the paging delay anomaly detection model. This application constructs paging delay anomaly detection models for cells with different attributes and different time dimensions, enabling the acquisition of predicted high paging delay thresholds for various cell types, thus improving the accuracy of the predicted high paging delay thresholds.
[0031] Step S400: Based on the predicted high paging delay threshold, determine the cells with abnormal paging delay. Perform paging delay anomaly detection on the cells based on the predicted high paging delay threshold corresponding to each cell type to determine the cells with abnormal paging delay.
[0032] Understandably, this application corrects the high paging delay frequency sequence of a cell by using the cell traffic volume sequence, eliminating the impact of cell traffic volume fluctuations on the high paging delay frequency. The corrected high paging delay frequency sequence is then input into the paging delay anomaly detection model corresponding to different cell types to predict the high paging delay threshold for that cell type for anomaly cell identification. Compared with the identification scheme of the top N paging delays or a uniform threshold, this approach considers the impact of different cell types on the threshold, improves the identification accuracy, greatly reduces the probability of cell misjudgment, and helps improve the optimization efficiency of cells with actual problems.
[0033] Based on the above embodiments, as an optional embodiment, the step of determining the cell high paging delay frequency sequence and cell traffic volume sequence according to the collected voice paging delay data includes steps S110-S120.
[0034] Step S110: Based on the called access cell ID in the voice paging delay data, perform cell aggregation on the voice paging delay data to determine the sequence of high paging delay times in the cell.
[0035] The operator's DPI system collects, records, and generates relevant documents by using interface probes such as N1N2 and S1-MME to measure signaling data during voice calls. The paging latency of a single voice call can be obtained by calculating the time interval between the issuance of paging signaling and the arrival of service request signaling on the N1N2 or S1-MME interface in the document. According to the current network specifications, paging latency exceeding a fixed threshold is defined as high paging latency. Further aggregation and statistics are performed based on the called access cell ID in the document to obtain the number of high paging latency events per hour for different cells in the current network. Finally, the sequence Y(t) of the number of high paging latency events per day for each cell over 24 hours is obtained.
[0036] Step S120: Based on the called access cell ID, perform cell aggregation on the total number of initial and final voice services generated by the access user in the voice paging delay data to determine the cell service volume sequence.
[0037] The volume of voice traffic in a cell is defined as the total number of initial and final voice calls made by users accessing the cell within a certain time period. Combining the information recorded in the DPI system document as either an initial or final call, the same cell aggregation method described above is used to obtain the daily 24-hour traffic volume sequence T(t) for each cell.
[0038] Understandably, this application uses cell aggregation to determine the cell high paging delay frequency sequence and cell traffic volume sequence, providing a basis for subsequent correction of the cell high paging delay frequency sequence.
[0039] like Figure 2 As shown, based on the above embodiments, as an optional embodiment, the step of correcting the cell high paging delay number sequence according to the cell traffic volume sequence includes steps S210-S230.
[0040] Step S210: Determine the average traffic volume at each time point within the detection window period based on the cell traffic volume sequence.
[0041] The formula for calculating the average business volume is as follows: in, The detection window represents the average traffic volume at each time point within the detection window period, where n is the length of the detection window. This length can be adjusted according to the needs of the anomaly detection algorithm. Time points with zero traffic volume need to be removed from the window. In this embodiment, the detection window (test) is set to 24 hours, corresponding to n being 24.
[0042] Step S220: Determine the business volume fluctuation coefficient based on the average business volume.
[0043] Optionally, determining the business volume fluctuation coefficient based on the average business volume includes: The ratio of the cell traffic volume sequence to the average traffic volume is used as the traffic volume fluctuation coefficient.
[0044] The mean traffic volume represents the average level of traffic volume in the cell within the detection window, while the fluctuation coefficient represents the fluctuation range of traffic volume from the mean at each time point within the window. After obtaining the mean, the fluctuation coefficient V(t) within the window is further calculated using the following formula: , t∈[1,n] in, This is the business volume fluctuation coefficient.
[0045] Step S230: Correct the sequence of high paging delay times in the cell according to the traffic fluctuation coefficient.
[0046] Optionally, the step of correcting the high paging delay frequency sequence of the cell based on the traffic fluctuation coefficient includes: The ratio of the high paging delay frequency sequence of the cell to the traffic fluctuation coefficient is calculated to correct the high paging delay frequency sequence of the cell.
[0047] To enable the anomaly detection model to better analyze and understand the basic trends and cyclical fluctuations of data, and to ensure detection accuracy, a fluctuation coefficient is used to adjust the high paging delay sequence within the detection window. This removes the influence of traffic volume fluctuations, allowing the model to make more accurate decisions. In this embodiment, the fluctuation coefficient V(t) at each time point within the detection window is used to adjust the high paging delay frequency sequence Y(t) at the same time, finally generating the corrected sequence Y'(t). The adjustment formula is as follows: =Y(t) / V(t), t∈[1,n] in, This is a corrected sequence of high paging delay times in the cell.
[0048] Understandably, this application corrects the cell high paging delay frequency sequence by using the cell traffic volume sequence. During sequence detection, it eliminates the impact of cell traffic volume fluctuations on the cell high paging delay frequency, thereby improving the recognition accuracy.
[0049] Based on the above embodiments, as an optional embodiment, the step of determining the paging delay anomaly detection model includes: Based on community attribute factors and date factors, a clustering algorithm is selected to cluster the communities, resulting in different types of communities; The time series prediction model is trained based on historical voice paging delay data of different types of cells to obtain paging delay anomaly detection models corresponding to different types of cells.
[0050] The community attribute factor is used to characterize whether the community's location is residential, commercial, or office, while the date factor is used to characterize whether the current time is a weekday. In other embodiments, the date factor can also be used to characterize whether the current time is busy or off-peak. Clustering algorithms can include K-Means clustering, hierarchical clustering, or density-based clustering algorithms. In this embodiment, combining expert experience and prior data analysis, the K-means algorithm is selected to cluster the communities based on two dimensions: the community's location (residential, commercial, office) and whether it is a weekday.
[0051] Time series prediction models include three types: Long Short Term Memory (LSTM), Facebook Prophet, and Autoregressive Integrated Moving Average (ARIMA). This application selected these three algorithms for selection experiments, using model accuracy and computational efficiency as evaluation metrics. The ARIMA-based model achieved an accuracy of over 80% and consumed less computation time, ultimately leading to its selection. Paging delay anomaly detection models were constructed for different cell types. The constructed models used the historical high paging delay counts within a window to predict the high paging delay threshold for the cell at the detection time point.
[0052] Understandably, this application fully considers the impact of cell location and other attributes on detection results and optimization needs, eliminating the influence of cell location attributes and time factors, and constructing targeted detection models for different types of cells. This allows for more refined detection models and improves the accuracy of detection results. Currently, determining abnormal paging latency cells in the network requires extensive expert experience and relies on fixed thresholds to decide whether to optimize, resulting in high manual dependence and the inability to update thresholds in real time, leading to poor accuracy and ineffective optimization. This application introduces a time-series prediction model to dynamically predict high paging latency thresholds for cells in future time periods, significantly improving detection accuracy and automation.
[0053] Based on the above embodiments, as an optional embodiment, determining the abnormal paging delay cell according to the predicted high paging delay threshold includes: The predicted high paging latency threshold is compared with the actual number of high paging latency events in the corresponding cell. If the actual number of high paging latency events is not lower than the predicted high paging latency threshold, the actual traffic volume of the cell is calculated, and the cell whose actual traffic volume is higher than the traffic volume threshold is identified as an abnormal paging latency cell.
[0054] Optionally, the corrected high paging delay count sequence for each type of cell is input into the cell high paging delay anomaly detection model to obtain the paging delay threshold for the cell in the future time period. When a service occurs, the actual number of high paging delays in the cell is calculated in real time and compared with the predicted value. If it is greater than the predicted value, it is added to the optimization candidate sequence. The service volume of each cell in the optimization candidate sequence is further calculated (here, the service volume is defined as the sum of the number of initial and final voice services of the cell access users within the current processing time period). If the service volume is greater than the service volume threshold (the service volume threshold is derived by combining a large amount of real network data and expert experience analysis; in this application embodiment, 5 is used as an example), then the cell is finally determined as the optimization target and is finally judged as a cell with abnormal paging delay.
[0055] Figure 3 This is the second flowchart of the voice paging delay cell detection method provided in this application, as shown below. Figure 3As shown, the high paging latency cell anomaly detection scheme proposed in this application comprises four core modules: cell aggregation, sequence correction, cell clustering and detection model construction, and sequence detection and anomaly cell determination. Cell aggregation involves aggregating hourly high paging latency frequency sequences and traffic volume sequences for different cells based on user access cell and paging latency data from the DPI system voice session latency records. Furthermore, a high paging latency sequence correction scheme is proposed to eliminate the impact of cell traffic volume fluctuations on the number of high paging latency events. Next, cells are clustered in multiple dimensions based on whether it is a weekday and the cell's inherent attributes (residential, commercial, office), classifying cells into different types. Targeted detection models are then constructed for different cell types based on the ARIMA algorithm. Finally, based on the constructed ARIMA model, the high paging delay sequence after cell correction is detected to obtain the threshold of the number of high paging delays in the future period. Compared with the actual number of high paging delays, if the actual number of occurrences is greater than the threshold and the optimization start condition is met (cell traffic volume is greater than 5 times), the cell is determined to be a cell with abnormal paging delay, i.e., a cell with poor latency quality.
[0056] This application uses sequence correction to detect abnormal paging delay cells and clusters the cells, fully considering and eliminating the fluctuations caused by traffic volume in cell attributes and high latency. Compared with traditional fixed threshold-based methods, it greatly improves the recognition accuracy and coverage, and has strong generalization ability, making it applicable to the detection of anomalies in indicators affected by multiple factors in the current network.
[0057] In summary, this application considers the influence of variables such as different cell wireless environments, traffic volume, and cell attributes, thereby improving detection accuracy and expanding the detection range. At the same time, based on the cell traffic volume fluctuation coefficient correction scheme, it eliminates the impact of cell traffic volume fluctuations on model detection accuracy, which helps guide the optimization of precise paging strategies.
[0058] The voice paging delay cell detection device provided in this application is described below. The voice paging delay cell detection device described below can be referred to in correspondence with the voice paging delay cell detection method described above.
[0059] Figure 4 This is a schematic diagram of the structure of the voice paging delay cell detection device provided in this application, as shown below. Figure 4 As shown, this application also provides a voice paging delay cell detection device, comprising: The first determining module 410 is used to determine the cell high paging delay frequency sequence and the cell traffic volume sequence based on the collected voice paging delay data. The cell high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds the preset high paging delay threshold. Correction module 420 is used to correct the cell high paging delay number sequence based on the cell traffic volume sequence; Prediction module 430 is used to input the corrected sequence of high paging delay times in the cell into the paging delay anomaly detection model corresponding to different types of cells, and obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model; The second determining module 440 is used to determine the abnormal paging delay cell based on the predicted value of the high paging delay threshold.
[0060] As one embodiment, the correction module 420 is further configured to: Based on the traffic volume sequence of the cell, determine the average traffic volume at each time point within the detection window period; Determine the business volume fluctuation coefficient based on the average business volume; The sequence of high paging delays in the cell is corrected based on the traffic fluctuation coefficient.
[0061] As one embodiment, the correction module 420 is further configured to: The ratio of the cell traffic volume sequence to the average traffic volume is used as the traffic volume fluctuation coefficient. Correspondingly, the step of correcting the high paging delay frequency sequence of the cell based on the traffic fluctuation coefficient includes: The ratio of the high paging delay frequency sequence of the cell to the traffic fluctuation coefficient is calculated to correct the high paging delay frequency sequence of the cell.
[0062] As an example, the first determining module 410 is further configured to: Based on the called access cell ID in the voice paging delay data, cell aggregation is performed on the voice paging delay data to determine the sequence of high paging delay times in the cell; Based on the called access cell ID, the total number of initial and final voice service calls occurring to the access user in the voice paging delay data is aggregated by cell to determine the cell service volume sequence.
[0063] As an example, the determination step of the paging delay anomaly detection model includes: Based on community attribute factors and date factors, a clustering algorithm is selected to cluster the communities, resulting in different types of communities; The time series prediction model is trained based on historical voice paging delay data of different types of cells to obtain paging delay anomaly detection models corresponding to different types of cells.
[0064] As one embodiment, the second determining module 440 is further configured to: The predicted high paging latency threshold is compared with the actual number of high paging latency events in the corresponding cell. If the actual number of high paging latency events is not lower than the predicted high paging latency threshold, the actual traffic volume of the cell is calculated, and the cell whose actual traffic volume is higher than the traffic volume threshold is identified as an abnormal paging latency cell.
[0065] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute a voice paging delay cell detection method, which includes: Based on the collected voice paging delay data, a high paging delay frequency sequence and a cell traffic volume sequence are determined. The high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds a preset high paging delay threshold. The high paging delay frequency sequence of the cell is corrected based on the cell traffic volume sequence; The corrected sequence of high paging delay times in the cell is input into the paging delay anomaly detection model corresponding to different types of cells to obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. Based on the predicted high paging delay threshold, cells with abnormal paging delays are identified.
[0066] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0067] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the voice paging delay cell detection method provided by the above methods, the method including: Based on the collected voice paging delay data, a high paging delay frequency sequence and a cell traffic volume sequence are determined. The high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds a preset high paging delay threshold. The high paging delay frequency sequence of the cell is corrected based on the cell traffic volume sequence; The corrected sequence of high paging delay times in the cell is input into the paging delay anomaly detection model corresponding to different types of cells to obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. Based on the predicted high paging delay threshold, cells with abnormal paging delays are identified.
[0068] Furthermore, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the voice paging delay cell detection method provided by the methods described above, the method comprising: Based on the collected voice paging delay data, a high paging delay frequency sequence and a cell traffic volume sequence are determined. The high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds a preset high paging delay threshold. The high paging delay frequency sequence of the cell is corrected based on the cell traffic volume sequence; The corrected sequence of high paging delay times in the cell is input into the paging delay anomaly detection model corresponding to different types of cells to obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. Based on the predicted high paging delay threshold, cells with abnormal paging delays are identified.
[0069] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0070] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A method for detecting cell delay during voice paging, characterized in that, include: Based on the collected voice paging latency data, a high paging latency frequency sequence and a cell traffic volume sequence are determined. The high paging latency frequency sequence is used to characterize the number of times the voice paging latency of each cell exceeds a preset high paging latency threshold. The high paging delay frequency sequence of the cell is corrected based on the cell traffic volume sequence; The corrected sequence of high paging delay times in the cell is input into the paging delay anomaly detection model corresponding to different types of cells to obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. Based on the predicted high paging delay threshold, cells with abnormal paging delays are identified.
2. The voice paging delay cell detection method according to claim 1, characterized in that, The step of correcting the cell high paging delay frequency sequence based on the cell traffic volume sequence includes: Based on the traffic volume sequence of the cell, determine the average traffic volume at each time point within the detection window period; Determine the business volume fluctuation coefficient based on the average business volume; The sequence of high paging delays in the cell is corrected based on the traffic fluctuation coefficient.
3. The voice paging delay cell detection method according to claim 2, characterized in that, The step of determining the business volume fluctuation coefficient based on the average business volume includes: The ratio of the cell traffic volume sequence to the average traffic volume is used as the traffic volume fluctuation coefficient. Correspondingly, the step of correcting the high paging delay frequency sequence of the cell based on the traffic fluctuation coefficient includes: The ratio of the high paging delay frequency sequence of the cell to the traffic fluctuation coefficient is calculated to correct the high paging delay frequency sequence of the cell.
4. The voice paging delay cell detection method according to claim 1, characterized in that, The step of determining the high paging latency sequence and the cell traffic volume sequence based on the collected voice paging latency data includes: Based on the called access cell ID in the voice paging delay data, cell aggregation is performed on the voice paging delay data to determine the sequence of high paging delay times in the cell; Based on the called access cell ID, the total number of initial and final voice service calls occurring to the access user in the voice paging delay data is aggregated by cell to determine the cell service volume sequence.
5. The voice paging delay cell detection method according to claim 1, characterized in that, The steps for determining the paging delay anomaly detection model include: Based on community attribute factors and date factors, a clustering algorithm is selected to cluster the communities, resulting in different types of communities; The time series prediction model is trained based on historical voice paging delay data of different types of cells to obtain paging delay anomaly detection models corresponding to different types of cells.
6. The voice paging delay cell detection method according to claim 1, characterized in that, The step of determining abnormal paging delay cells based on the predicted high paging delay threshold includes: The predicted high paging latency threshold is compared with the actual number of high paging latency events in the corresponding cell. If the actual number of high paging latency events is not lower than the predicted high paging latency threshold, the actual traffic volume of the cell is calculated, and the cell whose actual traffic volume is higher than the traffic volume threshold is identified as an abnormal paging latency cell.
7. A voice paging delay cell detection device, characterized in that, include; The first determining module is used to determine the cell high paging delay frequency sequence and the cell traffic volume sequence based on the collected voice paging delay data. The cell high paging delay frequency sequence is used to characterize the number of times the voice paging delay of each cell exceeds the preset high paging delay threshold. The correction module is used to correct the high paging delay frequency sequence of the cell based on the cell traffic volume sequence; The prediction module is used to input the corrected sequence of high paging delay times in the cell into the paging delay anomaly detection model corresponding to different types of cells, and obtain the predicted value of the high paging delay threshold output by the paging delay anomaly detection model. The second determining module is used to determine the abnormal paging delay cell based on the predicted value of the high paging delay threshold.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the voice paging delay cell detection method as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the voice paging delay cell detection method as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the voice paging delay cell detection method as described in any one of claims 1 to 6.