High-latency cell identification methods, devices, electronic equipment and storage media

Abstract

This application relates to the field of network operation technology and discloses a method, apparatus, electronic device, and storage medium for identifying high-latency cells. The method includes: acquiring multiple evaluations of a cell to be identified within a preset time period; determining the cell to be identified as a high-latency cell when the number of negative evaluations among the multiple evaluations meets a judgment condition; the generation process of any evaluation includes: in response to a target terminal residing in the cell to be identified and corresponding to any evaluation meeting a preset trigger condition, acquiring the target terminal's target `dur_tcp2nd` data; calculating the expected latency corresponding to any evaluation based on the target `dur_tcp2nd` data and the expected latency corresponding to the previous evaluation, where the previous evaluation corresponds to the target terminal; generating any evaluation where the target `dur_tcp2nd` data is less than or equal to the expected latency corresponding to any evaluation, and vice versa. This method improves the accuracy of high-latency cell identification.

Description

Technical Field

[0001] This application relates to the field of network operation technology, and in particular to a high-latency cell identification method, apparatus, electronic device, and storage medium. Background Technology

[0002] The rapid development of mobile communication technology has led to continuously increasing user demands for network service quality. Network latency, as a core indicator of mobile communication network performance, directly determines the user's service experience, such as webpage loading, video playback, and game interaction. The presence of high-latency cells significantly reduces user satisfaction; therefore, accurately identifying high-latency cells and optimizing the network is a critical requirement for mobile communication network operation.

[0003] In related technologies, the mainstream method for identifying high-latency cells is the Top N method based on latency-related key performance indicators (KPIs). This method collects macro-level latency KPIs (such as mean, maximum, etc.) for the entire network or individual cells, sorts all cell latency KPIs in descending order, and selects the top N cells as high-latency cells, using this as the basis for network optimization.

[0004] However, KPI indicators are a macroscopic reflection of the overall performance of a cell, which can lead to misjudgment or underjudgment of high-latency cells. Summary of the Invention

[0005] The purpose of this application is to provide at least one method, apparatus, electronic device and storage medium for identifying high-latency cells, which can at least eliminate interference caused by terminal differences when identifying high-latency cells, and at least improve the accuracy of high-latency cell identification and reduce false positives and false negatives.

[0006] To address the aforementioned technical problems, at least one embodiment of this application provides a high-latency cell identification method, comprising: acquiring evaluations of a cell to be identified within a preset time period, obtaining multiple evaluations, each evaluation being either positive or negative; determining the cell to be identified as a high-latency cell when the number of negative evaluations among the multiple evaluations meets a determination condition; wherein each evaluation corresponds to a terminal, and any two evaluations among the multiple evaluations correspond to the same or different terminals, and the generation process of any evaluation includes: in response to a target terminal residing in the cell to be identified and corresponding to any evaluation meeting a preset trigger condition, acquiring the target dur_tcp2nd data of the target terminal in the cell to be identified; calculating the expected latency corresponding to any evaluation based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of any evaluation, wherein the previous evaluation corresponds to the target terminal; generating the any evaluation, wherein the any evaluation is positive when the target dur_tcp2nd data is less than or equal to the expected latency corresponding to the any evaluation, and the any evaluation is negative when the target dur_tcp2nd data is greater than the expected latency corresponding to the any evaluation.

[0007] By introducing an evaluation method based on terminal-level `dur_tcp2nd` data to determine whether a cell to be identified is a high-latency cell, the cell latency determination is transformed from a macro-statistic to terminal-level fine-grained data, improving the accuracy of high-latency cell identification. Using the terminal's own expected latency as a comparison benchmark can eliminate interference from differences in hardware performance and processing capabilities among different terminals, ensuring that the evaluation results truly reflect the cell's actual transmission latency level, further improving the accuracy of high-latency cell identification and reducing false positives and false negatives.

[0008] In some optional embodiments, calculating the expected latency corresponding to any evaluation based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of any evaluation includes: calculating the expected latency corresponding to any evaluation according to the following formula:

[0009] in, The expected delay corresponding to any of the above evaluations. For preset weighting coefficients, The expected delay corresponding to the previous evaluation. The target data is dur_tcp2nd.

[0010] Using the formula in this embodiment to calculate the expected latency can smooth the fluctuations of historical latency (the expected latency corresponding to the previous evaluation), while assigning a certain weight to the current sampled data (target dur_tcp2nd data), so that the expected latency can reflect the long-term average latency level of the terminal and make timely adjustments to latency changes.

[0011] In some optional embodiments, the preset triggering condition is either condition 1 or condition 2; condition 1 includes: the target terminal switches from the cell to be identified to another cell; condition 2 includes: the target terminal continuously camps in the cell to be identified, and the target terminal is determined to meet the preset triggering condition once every preset time interval; or, condition 2 includes: the target terminal continuously performs network service interaction in the cell to be identified, and the target terminal is determined to meet the preset triggering condition once every preset number of network service interactions are completed.

[0012] By setting two complementary triggering conditions, comprehensive and continuous monitoring of cell latency is achieved. Handover triggering ensures that sampling is completed before the terminal leaves the cell, avoiding data loss. Periodic triggering ensures that terminals that stay in the cell for a long time can also be continuously sampled, without data loss due to the lack of handover. The sampling timing is related to the actual behavior of the terminal (movement, stay, service interaction), making the sampled data more representative.

[0013] In some optional embodiments, obtaining the target dur_tcp2nd data of the target terminal in the cell to be identified includes: collecting dur_tcp2nd data of the target terminal in the cell to be identified within a target time period to obtain multiple dur_tcp2nd data, wherein the target time period is the time period between a first time point and a second time point, the first time point being the time point at which the dur_tcp2nd data of the target terminal in the cell to be identified was last collected, and the second time point being the time point at which the dur_tcp2nd data of the target terminal in the cell to be identified is collected this time; and based on the multiple dur_tcp2nd data, obtaining dur_tcp2nd data representing the latency of the target terminal within the target time period to obtain the target dur_tcp2nd data.

[0014] By collecting multiple dur_tcp2nd data points within a time period and further obtaining the target dur_tcp2nd data, misjudgments caused by occasional anomalies in a single TCP connection establishment (such as instantaneous network jitter or instantaneous high terminal load) can be avoided, making the target dur_tcp2nd data more representative of the target terminal's true latency level within that time period.

[0015] In some optional embodiments, obtaining the target dur_tcp2nd data based on the plurality of dur_tcp2nd data to represent the latency of the target terminal within the target time period, and obtaining the target dur_tcp2nd data, includes: sorting the plurality of dur_tcp2nd data to obtain a sorting result; and selecting the median from the sorting result to obtain the target dur_tcp2nd data.

[0016] Using the median as a representative value provides strong resistance to outlier interference. Compared to the mean, the median is not affected by extreme large or small values ​​and can more robustly reflect the latency level of the terminal within the sampling period.

[0017] In some optional embodiments, the determination criteria include: the proportion of negative reviews in the plurality of evaluations is greater than a preset proportion threshold; or, the proportion of negative reviews in the plurality of evaluations is greater than a preset proportion threshold, and the number of negative reviews in the plurality of evaluations is greater than a preset value.

[0018] The first scenario (proportion threshold only) can quickly identify relatively abnormal cells and is sensitive to minor latency increases. The second scenario (proportion threshold combined with quantity threshold) adds additional filtering conditions, preventing low-traffic cells from being mistakenly identified as high-latency cells due to a small number of negative reports but an inflated proportion, further improving the accuracy and reliability of the judgment. Both judgment conditions can be flexibly selected or combined according to network operation needs, enhancing the adaptability of the solution.

[0019] At least one embodiment of this application also provides a high-latency cell identification device, comprising: an acquisition module, configured to acquire evaluations of a cell to be identified within a preset time period, obtaining multiple evaluations, each evaluation being either positive or negative, wherein each evaluation corresponds to a terminal, and any two evaluations correspond to the same or different terminals; a determination module, configured to determine that the cell to be identified is a high-latency cell when the number of negative evaluations in the multiple evaluations meets a determination condition; and a generation module, configured to perform a generation process for any evaluation, the generation process for any evaluation including: responding to a target terminal residing in the cell to be identified, the terminal corresponding to the any evaluation. If the target terminal meets the preset triggering conditions, the target terminal's target dur_tcp2nd data in the cell to be identified is acquired; based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of any evaluation, the expected latency corresponding to the previous evaluation is calculated, where the previous evaluation corresponds to the target terminal; any evaluation is generated, where the target dur_tcp2nd data is less than or equal to the expected latency corresponding to the evaluation, and the evaluation is a positive evaluation when the target dur_tcp2nd data is greater than the expected latency corresponding to the evaluation, and the evaluation is a negative evaluation when the target dur_tcp2nd data is greater than the expected latency corresponding to the evaluation.

[0020] In some optional embodiments, the generation module is configured to calculate the expected latency corresponding to any one of the evaluations according to the following formula:

[0021] in, The expected delay corresponding to any of the above evaluations. For preset weighting coefficients, The expected delay corresponding to the previous evaluation. The target data is dur_tcp2nd.

[0022] In some optional embodiments, the acquisition module is used to collect the dur_tcp2nd data of the target terminal in the cell to be identified within a target time period, obtaining multiple dur_tcp2nd data. The target time period is the time period between a first time point and a second time point. The first time point is the time point at which the dur_tcp2nd data of the target terminal in the cell to be identified was last collected, and the second time point is the time point at which the dur_tcp2nd data of the target terminal in the cell to be identified is collected this time. Based on the multiple dur_tcp2nd data, dur_tcp2nd data representing the latency of the target terminal within the target time period is obtained, thus obtaining the target dur_tcp2nd data.

[0023] In some optional embodiments, the acquisition module is used to sort the plurality of dur_tcp2nd data to obtain a sorting result; and select the median from the sorting result to obtain the target dur_tcp2nd data.

[0024] At least one embodiment of this application also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the high-latency cell identification method described above.

[0025] At least one embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the high-latency cell identification method described above.

[0026] At least one embodiment of this application also provides a computer program product, including a computer program that, when executed by a processor, implements the high-latency cell identification method described above. Attached Figure Description

[0027] One or more embodiments are illustrated by way of example with reference to the accompanying drawings, and these illustrative descriptions do not constitute a limitation on the embodiments.

[0028] Figure 1 This is a flowchart of a high-latency cell identification method provided in one embodiment of this application; Figure 2 This is a flowchart of the evaluation generation process provided in one embodiment of this application; Figure 3 This is a schematic diagram of a high-latency cell identification device provided in another embodiment of this application; Figure 4 This is a schematic diagram of a high-latency cell identification device provided in another embodiment of this application; Figure 5 This is a schematic diagram of the initial delay distribution of a simulated network environment in another embodiment of this application; Figure 6 This is a schematic diagram of the average cell delay distribution in another embodiment of this application; Figure 7 This is a schematic diagram of the distribution of negative review ratios in another embodiment of this application. Detailed Implementation

[0029] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0030] Furthermore, the accompanying drawings are merely illustrative of this application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0031] The rapid development of mobile communication technology has led to continuously increasing user demands for network service quality. Network latency, as a core indicator of mobile communication network performance, directly determines the user's service experience, such as webpage loading, video playback, and game interaction. The presence of high-latency cells significantly reduces user satisfaction; therefore, accurately identifying high-latency cells and optimizing the network is a critical requirement for mobile communication network operation.

[0032] Currently, the mainstream method for identifying high-latency cells in mobile communication networks is to sort them by latency-related KPIs and select the Top N cells. However, this method has at least the following drawbacks: 1. KPI data is easily affected by various factors, leading to misjudgment or omission of high-latency cells. In the actual network environment, the network structure changes dynamically, user service types are diverse, and terminal equipment performance varies greatly. Macro KPI indicators will be affected by these factors and cannot truly reflect the latency level of the cell itself. High latency caused by reasons other than cell may be judged as cell problems, or cells with actual latency anomalies may be missed.

[0033] 2. Macro-level KPI indicators cannot accurately pinpoint cell latency issues; KPI indicators are a macro-level reflection of the overall performance of a cell, but they do not distinguish between network transmission latency and terminal processing latency, making it difficult to isolate interference caused by differences in terminals and failing to meet the needs of refined network optimization.

[0034] 3. Insensitive to minor latency anomalies; when a cell experiences a small increase in latency, the changes in macro KPI indicators are not obvious. The TopN ranking method cannot identify such high-latency cells with minor anomalies, resulting in latency problems not being detected and dealt with in a timely manner.

[0035] To address the aforementioned technical problems, this application proposes a high-latency cell identification method. The implementation details of the high-latency cell identification method in this embodiment are described below. The following implementation details are provided for ease of understanding and are not essential for implementing this solution.

[0036] Example 1: The high-latency cell identification method of this embodiment can be applied to electronic devices with communication, computing, and data storage capabilities. Its specific process can be as follows: Figure 1 As shown, it includes: S101-S102.

[0037] S101: Obtain evaluations of the cell to be identified within a preset time period, and obtain multiple evaluations, each of which is either a positive or negative evaluation.

[0038] In some cases, the electronic device executing this method stores evaluations of the cell to be identified within a preset time period. When applying these evaluations, they can be directly obtained from the stored evaluations to obtain the multiple evaluations.

[0039] Obtaining the evaluation of the cell to be identified within a preset time period refers to the evaluation of the cell to be identified within the preset time period prior to the start of the acquisition action.

[0040] The embodiments of this application do not limit the specific duration of the preset time period. For example, the preset time period may be 1 hour, 5 hours, or 24 hours, etc.

[0041] Each evaluation corresponds to one terminal, and any two evaluations may correspond to the same or different terminals.

[0042] In some examples, such as Figure 2 As shown, the process of generating any evaluation (any evaluation) may include S201-S203.

[0043] S201, in response to the target terminal residing in the cell to be identified and corresponding to any evaluation meeting the preset triggering condition, the target dur_tcp2nd data of the target terminal in the cell to be identified is obtained.

[0044] Among them, the cell to be identified is the cell whose high latency needs to be determined.

[0045] Regarding the dur_tcp2nd data, the maturity of Deep Packet Inspection (DPI) technology provides refined data support for network performance analysis. The DPI system can parse complete information from network packets, recording key data such as timestamps during the TCP (Transmission Control Protocol) connection establishment process, forming XDR (External Data Representation) data. This XDR data includes the TCP connection establishment phase two delay (dur_tcp2nd) field, which reflects the transmission latency between the terminal and the network, as well as the terminal's own processing latency.

[0046] The embodiments of this application do not impose any restrictions on the specific number of terminals residing in the cell to be identified.

[0047] For any terminal residing in the cell to be identified, after the preset triggering condition is met, the electronic device executing this method will acquire the target dur_tcp2nd data of the terminal in the cell to be identified, wherein the target dur_tcp2nd data is used to reflect the network latency of the terminal in the cell to be identified.

[0048] The embodiments of this application do not limit the specific conditions that the preset trigger conditions should be.

[0049] In some examples, the preset trigger condition is that condition 1 or condition 2 is met.

[0050] Condition 1 includes: the target terminal switching from the cell to be identified to another cell.

[0051] Condition 2 includes: the target terminal continuously camps in the cell to be identified, and the target terminal is determined to meet the preset trigger condition once every preset time interval; or, condition 2 includes: the target terminal continuously performs network service interaction in the cell to be identified, and the target terminal is determined to meet the preset trigger condition once every preset number of network service interactions are completed.

[0052] The embodiments of this application do not limit the specific duration or quantity of the preset time. For example, the preset duration is 5 minutes and the preset quantity is 10.

[0053] By setting two complementary triggering conditions, comprehensive and continuous monitoring of cell latency is achieved. Handover triggering ensures that sampling is completed before the terminal leaves the cell, avoiding data loss. Periodic triggering ensures that terminals that stay in the cell for a long time can also be continuously sampled, without data loss due to the lack of handover. The sampling timing is related to the actual behavior of the terminal (movement, stay, service interaction), making the sampled data more representative.

[0054] In some examples, obtaining the target dur_tcp2nd data of the target terminal in the cell to be identified includes: collecting the dur_tcp2nd data of the target terminal in the cell to be identified within a target time period, obtaining multiple dur_tcp2nd data, where the target time period is the time period between a first time point and a second time point, the first time point being the time point at which the target terminal's dur_tcp2nd data in the cell to be identified was last collected, and the second time point being the time point at which the target terminal's dur_tcp2nd data in the cell to be identified is collected this time; and based on the multiple dur_tcp2nd data, obtaining dur_tcp2nd data representing the latency of the target terminal within the target time period, thus obtaining the target dur_tcp2nd data.

[0055] In some cases, if the target terminal's dur_tcp2nd data in the cell to be identified has not been collected before, then "the time point when the target terminal's dur_tcp2nd data was last collected in the cell to be identified" is the time point when the target terminal began to camp in the cell to be identified.

[0056] By collecting multiple dur_tcp2nd data points within a time period and further obtaining the target dur_tcp2nd data, misjudgments caused by occasional anomalies in a single TCP connection establishment (such as instantaneous network jitter or instantaneous high terminal load) can be avoided, making the target dur_tcp2nd data more representative of the terminal's true latency level within that time period.

[0057] The embodiments of this application do not limit how to obtain the target dur_tcp2nd data representing the latency of the target terminal within the target time period based on the multiple dur_tcp2nd data, and thus obtain the target dur_tcp2nd data.

[0058] In some examples, based on the multiple dur_tcp2nd data, obtaining dur_tcp2nd data representing the latency of the target terminal within the target time period, and obtaining the target dur_tcp2nd data, may include: sorting the multiple dur_tcp2nd data to obtain the sorting result; selecting the median from the sorting result to obtain the target dur_tcp2nd data.

[0059] Using the median as a representative value provides strong resistance to outlier interference. Compared to the mean, the median is not affected by extreme large or small values ​​and can more robustly reflect the latency level of the terminal within the sampling period.

[0060] In other examples, based on these multiple `dur_tcp2nd` data, obtaining `dur_tcp2nd` data representing the latency of the target terminal within the target time period, and thus obtaining the target `dur_tcp2nd` data, may include: removing data from the multiple `dur_tcp2nd` data that exceeds ±3... The outliers in the range are then calculated, and the arithmetic mean of the remaining dur_tcp2nd data is obtained to get the target dur_tcp2nd data.

[0061] S202, based on the target dur_tcp2nd data and the expected delay corresponding to the previous evaluation for any evaluation, calculate the expected delay corresponding to any evaluation.

[0062] In this context, the previous evaluation corresponds to the target terminal, and any evaluation also corresponds to the target terminal.

[0063] In some examples, the expected latency for any evaluation is calculated based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation for that evaluation, including: Calculate the expected delay corresponding to any evaluation using the following formula 1: (1) in, The expected delay corresponding to any one of these evaluations. For preset weighting coefficients, This is the expected delay corresponding to the previous evaluation. This refers to the target dur_tcp2nd data (i.e., the sampling delay).

[0064] If the target terminal does not have the expected latency corresponding to the previous evaluation, the expected latency corresponding to the previous evaluation can be a preset default value or the sampling latency of the current round.

[0065] It should be noted that if the expected latency corresponding to the previous evaluation of the target terminal is calculated based on the target dur_tcp2nd data within the cell to be identified, then the expected latency corresponding to that previous evaluation is the expected latency of the target terminal within that cell. If the expected latency corresponding to the previous evaluation of the target terminal is calculated based on the target dur_tcp2nd data within other cells, then the expected latency corresponding to that previous evaluation is the expected latency of the target terminal within those other cells.

[0066] In electronic devices, the expected latency can be stored according to the terminal's identifier, which makes it easier to obtain the expected latency corresponding to the terminal's previous evaluation.

[0067] Regarding preset weighting coefficients The specific value is not limited in the embodiments of this application. For example, It equals 0.125.

[0068] In some cases, the network latency variation characteristics of the cell to be identified can be used to... Set as a dynamically adjustable factor. Increase it when network latency fluctuates significantly. A value (e.g., 0.25) makes Formula 1 effective for the data collected in this round. More sensitive; when network latency is stable, reduce A value (such as 0.0625) makes the desired delay more stable.

[0069] Using Formula 1 in this embodiment to calculate the expected latency can smooth out fluctuations in historical latency data, while assigning a certain weight to the current sampled data (target dur_tcp2nd data), so that the expected latency can reflect the long-term average latency level of the terminal and make timely adjustments to latency changes.

[0070] S203, generate any evaluation. If the target dur_tcp2nd data is less than or equal to the expected latency corresponding to any evaluation, the evaluation is a positive one. If the target dur_tcp2nd data is greater than the expected latency corresponding to any evaluation, the evaluation is a negative one.

[0071] Using the terminal's own expected latency as a benchmark can eliminate interference caused by differences in hardware performance and processing capabilities of different terminals, so that the evaluation results can truly reflect the transmission latency level of the cell itself.

[0072] The above S201-S203 describes the process by which the target terminal generates any of the evaluations. Terminals residing in the cell to be identified can generate evaluations.

[0073] S102, when the number of negative reviews in the multiple evaluations meets the judgment condition, the cell to be identified is determined to be a high-latency cell.

[0074] The embodiments of this application do not limit the specific conditions for this determination.

[0075] In some examples, the criteria include: the proportion of negative reviews in the multiple reviews is greater than a preset proportion threshold; or, the proportion of negative reviews in the multiple reviews is greater than a preset proportion threshold, and the number of negative reviews in the multiple reviews is greater than a preset value.

[0076] The embodiments of this application do not limit the specific value of the preset ratio threshold or the preset value. For example, the preset ratio threshold is 30%, and the preset value is 50.

[0077] The first scenario of the judgment condition (proportion threshold only) can quickly identify relatively abnormal cells and is sensitive to slight latency increases. The second scenario (proportion threshold combined with quantity threshold) adds additional filtering conditions, which can prevent low-traffic cells from being mistakenly judged as high-latency cells due to a small number of negative reports but an inflated proportion, further improving the accuracy and reliability of the judgment. The two judgment conditions can be flexibly selected or combined according to network operation needs, enhancing the adaptability of the solution.

[0078] By introducing an evaluation method based on terminal-level `dur_tcp2nd` data to determine whether a cell to be identified is a high-latency cell, the cell latency determination is transformed from a macro-statistic to terminal-level fine-grained data, improving the accuracy of high-latency cell identification. Using the terminal's own expected latency as a comparison benchmark can eliminate interference from differences in hardware performance and processing capabilities among different terminals, ensuring that the evaluation results truly reflect the cell's actual transmission latency level, further improving the accuracy of high-latency cell identification and reducing false positives and false negatives.

[0079] Example 2: Another embodiment of this application relates to a high-latency cell identification device. The implementation details of this high-latency cell identification device are described below. The following details are for ease of understanding and are not essential for implementing this solution. A schematic diagram of the high-latency cell identification device in this embodiment can be seen as follows: Figure 3 As shown, it includes: DPI data acquisition module 31, delay sampling module 32, expected delay calculation module 33, cell evaluation module 34, and high-latency cell determination module 35.

[0080] The DPI data acquisition module 31 is deployed in the communication link between the user terminal and the service server. It monitors the TCP three-way handshake messages in real time, records the timestamps of SYN (the first packet of the TCP connection), SYN+ACK (the acknowledgment flag in the TCP packet header, which acknowledges the received TCP packets), and ACK messages, calculates and generates XDR data, extracts the dur_tcp2nd field, and sends the dur_tcp2nd data along with the corresponding terminal ID, cell ID, and timestamp information to the delay sampling module 32.

[0081] The delay sampling module 32 is used to receive input data from the DPI data acquisition module 31, process the dur_tcp2nd data when the sampling condition is triggered, generate the sampling delay (SampleRTT), and send the SampleRTT and the corresponding terminal ID and cell ID to the expected delay calculation module 33.

[0082] The expected delay calculation module 33 is used to update the expected delay (EstimatedRTT) of each terminal based on the SampleRTT according to the above formula 1, and send the EstimatedRTT, SampleRTT and corresponding terminal ID and cell ID to the cell evaluation module 34.

[0083] The cell evaluation module 34 is used to compare SampleRTT and EstimatedRTT, output positive / negative ratings for cells, calculate the negative rating ratio of each cell, and send the negative rating ratio data and cell ID of each cell to the high latency cell determination module 35.

[0084] The high-latency cell determination module 35 is used to set a negative evaluation ratio threshold, determine cells with a negative evaluation ratio exceeding the threshold as high-latency cells, and output a list of high-latency cells and their corresponding negative evaluation ratios to provide a basis for network optimization.

[0085] A simulation experiment was designed based on the high-latency cell identification device in Embodiment 2 of this application.

[0086] 1. Experimental environment setup: such as Figure 5 As shown, a mobile communication network simulation scenario with 20×20 cells and a total of 400 cells is constructed and divided into three types of areas: urban (basic latency 15ms), county (basic latency 20ms), and rural (basic latency 25ms). 2% (8 cells) of cells are randomly selected as abnormal cells and an abnormal latency increment of 5ms is set. 10 terminals are configured for each cell and the terminal processing latency is a random value of 1-10ms.

[0087] 2. Deployment: Deploy the various modules of Example 2 in the simulated scenario, setting a sampling delay threshold of 5 minutes, as shown in Formula 1. =0.125, negative review ratio threshold 30%, evaluation statistics period (preset period in S101) 1 hour.

[0088] 3. Implementation process: The simulated terminal moves randomly 10 times in the network, triggering the sampling conditions for cell handover / long-term attachment. The DPI data acquisition module generates dur_tcp2nd data. Each module completes sampling, expected latency calculation, cell evaluation and negative evaluation ratio statistics according to the above steps.

[0089] 4. Implementation Results: The average latency distribution of the cell is as follows: Figure 6 As shown, the distribution of negative review rates for the community is as follows: Figure 7 As shown, the negative feedback rate of the 8 abnormal cells all exceeded 40%, and they were accurately identified as high-latency cells; the negative feedback rate of normal cells was all below 20%, with no misjudgments; compared with the traditional method of selecting the Top N cells based on latency-related KPI statistics and sorting, this solution can still identify high-latency cells with 100% accuracy even with a small abnormal latency increment of 5ms, verifying the effectiveness and feasibility of the solution.

[0090] Example 3: Another embodiment of this application relates to a high-latency cell identification device. The implementation details of this high-latency cell identification device are described below. The following details are for ease of understanding and are not essential for implementing this solution. A schematic diagram of the high-latency cell identification device in this embodiment can be seen as follows: Figure 4 As shown, the system includes: an acquisition module 41, used to acquire evaluations of the cell to be identified within a preset time period, obtaining multiple evaluations, each of which is either a positive or negative evaluation, wherein each evaluation corresponds to a terminal, and any two evaluations correspond to the same or different terminals; a judgment module 42, used to determine that the cell to be identified is a high-latency cell when the number of negative evaluations in the multiple evaluations meets a judgment condition; and a generation module 43, used to perform a generation process for any evaluation, the generation process of any evaluation including: in response to the target terminal residing in the cell to be identified and corresponding to the any evaluation meeting a preset trigger condition, acquiring the target dur_tcp2nd data of the target terminal in the cell to be identified; calculating the expected latency corresponding to the any evaluation based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of the any evaluation, wherein the previous evaluation corresponds to the target terminal; generating the any evaluation, wherein the any evaluation is a positive evaluation when the target dur_tcp2nd data is less than or equal to the expected latency corresponding to the any evaluation, and the any evaluation is a negative evaluation when the target dur_tcp2nd data is greater than the expected latency corresponding to the any evaluation.

[0091] In some optional embodiments, the generation module 43 is used to calculate the expected delay corresponding to any evaluation according to Formula 1.

[0092] In some optional embodiments, the acquisition module 41 is used to collect the dur_tcp2nd data of the target terminal in the cell to be identified within a target time period, and obtain multiple dur_tcp2nd data. The target time period is the time period between a first time point and a second time point. The first time point is the time point at which the dur_tcp2nd data of the target terminal in the cell to be identified was last collected, and the second time point is the time point at which the dur_tcp2nd data of the target terminal in the cell to be identified is collected this time. Based on the multiple dur_tcp2nd data, dur_tcp2nd data representing the latency of the target terminal in the target time period is obtained, and the target dur_tcp2nd data is obtained.

[0093] In some optional embodiments, the acquisition module 41 is used to sort the plurality of dur_tcp2nd data to obtain a sorting result; and select the median from the sorting result to obtain the target dur_tcp2nd data.

[0094] By introducing an evaluation method based on terminal-level `dur_tcp2nd` data to determine whether a cell to be identified is a high-latency cell, the cell latency determination is transformed from a macro-statistic to terminal-level fine-grained data, improving the accuracy of high-latency cell identification. Using the terminal's own expected latency as a comparison benchmark can eliminate interference from differences in hardware performance and processing capabilities among different terminals, ensuring that the evaluation results truly reflect the cell's actual transmission latency level, further improving the accuracy of high-latency cell identification and reducing false positives and false negatives.

[0095] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed in this application; however, this does not mean that other units are absent in this embodiment.

[0096] Example 4: Another embodiment of this application relates to an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the high-latency cell identification methods described in the above embodiments.

[0097] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0098] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0099] Example 5: Another embodiment of this application relates to a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the method embodiments described above.

[0100] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor 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.

[0101] Example 6: Another embodiment of this application relates to a computer program product, including a computer program. When executed by a processor, the computer program implements the method embodiments described above.

[0102] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0103] Furthermore, although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0104] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware.

[0105] Those skilled in the art will understand that the above embodiments are specific embodiments for implementing this application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of this application.

Claims

1. A method for identifying high-latency cells, characterized in that, include: Get the evaluations of the cell to be identified within a preset time period, and obtain multiple evaluations, each of which is either a positive or negative evaluation; When the number of negative reviews in the multiple evaluations meets the judgment criteria, the cell to be identified is determined to be a high-latency cell; In this system, each evaluation corresponds to a terminal, and any two evaluations may correspond to the same or different terminals. The generation process of any evaluation includes: in response to the target terminal corresponding to any evaluation residing in the cell to be identified and meeting a preset trigger condition, acquiring the target dur_tcp2nd data of the target terminal in the cell to be identified; calculating the expected latency corresponding to any evaluation based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of any evaluation, wherein the previous evaluation corresponds to the target terminal; generating any evaluation, wherein the evaluation is positive when the target dur_tcp2nd data is less than or equal to the expected latency corresponding to any evaluation, and negative when the target dur_tcp2nd data is greater than the expected latency corresponding to any evaluation.

2. The method according to claim 1, characterized in that, The step of calculating the expected latency corresponding to any evaluation based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of any evaluation includes: Calculate the expected delay corresponding to any of the evaluations using the following formula: in, The expected delay corresponding to any of the above evaluations. For preset weighting coefficients, The expected delay corresponding to the previous evaluation. The target data is dur_tcp2nd.

3. The method according to claim 1, characterized in that, The preset triggering condition is that condition 1 or condition 2 is met; Condition 1 includes: the target terminal switching from the cell to be identified to another cell; Condition 2 includes: the target terminal continuously camps in the cell to be identified, and the target terminal is determined to meet the preset trigger condition once every preset time interval; or, condition 2 includes: the target terminal continuously performs network service interaction in the cell to be identified, and the target terminal is determined to meet the preset trigger condition once every preset number of network service interactions are completed.

4. The method according to claim 1, characterized in that, The step of obtaining the target dur_tcp2nd data of the target terminal in the cell to be identified includes: Collect the target terminal's dur_tcp2nd data in the cell to be identified within the target time period to obtain multiple dur_tcp2nd data points. The target time period is the time period between a first time point and a second time point. The first time point is the time point when the target terminal's dur_tcp2nd data in the cell to be identified was last collected, and the second time point is the time point when the target terminal's dur_tcp2nd data in the cell to be identified is collected this time. Based on the multiple dur_tcp2nd data, dur_tcp2nd data representing the latency of the target terminal within the target time period is obtained, thus obtaining the target dur_tcp2nd data.

5. The method according to claim 4, characterized in that, The step of obtaining target dur_tcp2nd data by acquiring dur_tcp2nd data representing the latency of the target terminal within the target time period based on the plurality of dur_tcp2nd data includes: Sort the multiple dur_tcp2nd data to obtain the sorting result; The median is selected from the sorting results to obtain the target dur_tcp2nd data.

6. The method according to claim 1, characterized in that, The determination criteria include: The proportion of negative reviews in the multiple evaluations is greater than a preset proportion threshold; Alternatively, the proportion of negative reviews in the multiple evaluations is greater than a preset proportion threshold, and the number of negative reviews in the multiple evaluations is greater than a preset value.

7. A high-latency cell identification device, characterized in that, include: The acquisition module is used to acquire evaluations of the cell to be identified within a preset time period, and obtain multiple evaluations, each of which is either a positive or negative evaluation. Each evaluation corresponds to a terminal, and any two evaluations may correspond to the same or different terminals. The determination module is used to determine that the cell to be identified is a high-latency cell when the number of negative reviews in the multiple evaluations meets the determination criteria. A generation module is used to generate any evaluation, the generation process of any evaluation including: in response to a target terminal residing in the cell to be identified and corresponding to the any evaluation meeting a preset trigger condition, acquiring the target dur_tcp2nd data of the target terminal in the cell to be identified; calculating the expected latency corresponding to the any evaluation based on the target dur_tcp2nd data and the expected latency corresponding to the previous evaluation of the any evaluation, wherein the previous evaluation corresponds to the target terminal; generating the any evaluation, wherein the any evaluation is a positive evaluation when the target dur_tcp2nd data is less than or equal to the expected latency corresponding to the any evaluation, and the any evaluation is a negative evaluation when the target dur_tcp2nd data is greater than the expected latency corresponding to the any evaluation.

8. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the high-latency cell identification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the high-latency cell identification method according to 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 high-latency cell identification method according to any one of claims 1 to 6.

Images