A method and device for diagnosing poor cell communication quality

Abstract

The present invention discloses a method and device for diagnosing poor cell communication quality, which is used to solve the problem of low efficiency in diagnosing poor cell communication quality. This solution includes: obtaining negative communication evaluation data and multiple communication performance data of a cell with poor communication quality during a historical period of poor communication quality; determining the correlation coefficient threshold and peak matching threshold corresponding to each communication performance data based on the negative communication evaluation data and the multiple communication performance data; respectively determining the correlation coefficient and peak matching degree between the negative communication evaluation data and each communication performance data; and determining the communication performance represented by the communication performance data with a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold as the cause of the poor cell communication quality. This solution can diagnose the cause of poor cell communication quality from two dimensions: correlation coefficient and peak matching degree, and can accurately identify communication performance data that is closely related to changes in negative communication evaluation data, effectively improving diagnostic efficiency.

Description

Technical Field

[0001] The present invention relates to the field of communications, and in particular to a method and device for diagnosing poor cell communication quality. Background Art

[0002] In the communications sector, users can express their satisfaction with cell communication quality in a variety of ways, such as through the Net Promoter Score (NPS). The NPS measures the likelihood that a customer will recommend a business or service to others. A poor NPS indicates an increase in negative communication reviews, indicating a poor user experience.

[0003] In reality, cell communication quality is dependent on a variety of performance parameters. Manually checking these parameters to diagnose the actual cause of poor cell communication quality often results in low diagnostic efficiency. Furthermore, this manual inspection method relies heavily on the technical expertise of the technician, leading to inaccurate diagnostics in practice.

[0004] How to improve the efficiency of diagnosing poor cell communication quality is the technical problem to be solved by this application. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method and apparatus for diagnosing poor cell communication quality, so as to solve the problem of low efficiency in diagnosing poor cell communication quality.

[0006] In a first aspect, a method for diagnosing poor cell communication quality is provided, comprising:

[0007] Obtaining negative communication evaluation data and multiple communication performance data of cells with poor communication quality during historical periods of poor communication quality;

[0008] Determining, based on the negative communication evaluation data and the plurality of communication performance data, a correlation coefficient threshold and a peak matching degree threshold corresponding to each of the communication performance data;

[0009] Determining the correlation coefficient and peak matching degree between the negative communication evaluation data and each of the communication performance data, respectively, wherein the peak matching degree represents the matching degree between the time when the peak in the negative communication evaluation data is located and the time when the peak of the communication performance data is located;

[0010] The communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold is determined as the reason why the poor communication quality of the cell in poor communication quality is poor during the historical poor communication quality period.

[0011] In a second aspect, a device for diagnosing poor cell communication quality is provided, comprising:

[0012] An acquisition module, which acquires communication negative evaluation data and multiple communication performance data of cells with poor communication quality during a historical period of poor communication quality;

[0013] A first determining module determines, based on the negative communication evaluation data and a plurality of communication performance data, a correlation coefficient threshold and a peak matching degree threshold corresponding to each of the communication performance data;

[0014] A second determination module is configured to determine a correlation coefficient and a peak matching degree between the negative communication evaluation data and each of the communication performance data, wherein the peak matching degree represents a matching degree between a time point at which a peak in the negative communication evaluation data is located and a time point at which a peak in the communication performance data is located;

[0015] The diagnosis module determines the communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold as the cause of the poor communication quality of the cell during the historical poor communication quality period.

[0016] In a third aspect, an electronic device is provided, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method of the first aspect when executed by the processor.

[0017] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of the first aspect are implemented.

[0018] The embodiment of the present application obtains the communication negative evaluation data and multiple communication performance data of the cell with poor communication quality during the historical communication quality period; determines the correlation coefficient threshold and peak matching threshold corresponding to each of the communication performance data according to the communication negative evaluation data and the multiple communication performance data; determines the correlation coefficient and peak matching between the communication negative evaluation data and each of the communication performance data, respectively, and the peak matching represents the matching degree between the peak moment in the communication negative evaluation data and the peak moment of the communication performance data; determines the communication performance represented by the communication performance data with a correlation coefficient greater than the correlation coefficient threshold and a peak matching greater than the peak matching threshold as the cause of the poor communication quality of the cell with poor communication quality during the historical communication quality period. This solution can diagnose the cause of poor cell communication quality from two dimensions: correlation coefficient and peak matching, and can accurately identify communication performance data that is closely related to changes in the communication negative evaluation data, effectively improving diagnostic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 This is one of the flow charts of a method for diagnosing poor cell communication quality according to an embodiment of the present invention.

[0021] Figure 2 This is a second flow chart of a method for diagnosing poor cell communication quality according to an embodiment of the present invention.

[0022] Figure 3 This is a third flow chart of a method for diagnosing poor cell communication quality according to an embodiment of the present invention.

[0023] Figure 4 This is a fourth flow chart of a method for diagnosing poor cell communication quality according to an embodiment of the present invention.

[0024] Figure 5 This is the fifth flow chart of a method for diagnosing poor cell communication quality according to an embodiment of the present invention.

[0025] Figure 6 This is the sixth flow chart of a method for diagnosing poor cell communication quality according to an embodiment of the present invention.

[0026] Figure 7 The present invention is a schematic structural diagram of a device for diagnosing poor cell communication quality according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The figure numbers in this application are only used to distinguish the various steps in the scheme, and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0028] In order to solve the problems existing in the prior art, the embodiment of the present application provides a method for diagnosing poor cell communication quality, such as Figure 1 As shown, the following steps are included:

[0029] S11: Obtaining communication negative evaluation data and multiple communication performance data of the cell with poor communication quality during a historical period of poor communication quality.

[0030] The cell described in this embodiment, also called a cellular cell, refers to an area covered by a base station or a part of a base station in a cellular mobile communication system. In this area, a mobile station can reliably communicate with the base station through a wireless channel.

[0031] The above-mentioned cell with poor communication quality can be a cell with abnormal communication performance, or a cell that has received complaints from communication users. In actual applications, the above-mentioned criteria for determining a cell with poor communication quality can be pre-set, such as large fluctuations in communication performance parameters, a sudden drop in the number of communication users, and a surge in the number of communication performance complaints.

[0032] The aforementioned historical period of poor communication quality refers to a period of time when a cell's communication quality was relatively poor. This period can be determined based on attributes that characterize the cell's poor communication quality. For example, if a cell with poor communication quality experiences a surge in communication performance complaints, then the historical period of poor communication quality can be a period of time when a large number of user complaints were received. For another example, if a cell with poor communication quality experiences significant fluctuations in communication performance parameters, then the historical period of poor communication quality can be a period of time when such fluctuations were significant.

[0033] Optionally, in order to fully and comprehensively diagnose the cause of poor cell communication quality, in actual applications, the time period when cell communication abnormalities occur and a certain length of time before and after it can be jointly determined as a historical period of poor communication quality, so that the communication performance parameters before and after the abnormal communication performance can be obtained. For example, assuming that the time period with large fluctuations in communication performance parameters is 18:00-19:00, then the corresponding historical period of poor communication quality includes the above-mentioned 18:00-19:00 time period. In order to fully and comprehensively diagnose the cause of poor cell communication quality, a certain length of time before and after this time period can be jointly determined as a historical period of poor communication quality, such as determining 17:45-19:15 as a historical period of poor communication quality. By extending the historical period of poor communication quality, relevant parameters before and after the abnormal cell communication performance can be obtained, providing data support for diagnosing cell communication abnormalities in subsequent steps.

[0034] In this step, negative communication evaluation data and multiple communication performance data from the above-mentioned historical period of poor communication quality are obtained. The negative communication evaluation data is used to represent the communication user's satisfaction with the communication performance of their cell. In this example, the negative communication evaluation data can be specifically determined based on the Net Promoter Score (NPS) quality indicator. The more satisfied the communication user is with the communication quality, the larger the Net Promoter Score and the smaller the value of the negative communication evaluation data.

[0035] The plurality of communication performance data may be data representing communication performance. For example, the plurality of communication performance data acquired in this step may include multiple items of the following:

[0036] Uplink physical resource block (PRB) utilization, downlink physical resource block (PRB) utilization, proportion of tracking areas (TA) greater than or equal to the preset tracking area value, uplink interference level, proportion of channel quality indicators (CQI) less than the preset channel quality indicator value, handover failure rate, etc.

[0037] In addition, various indicator parameters related to communication performance, such as cell load, connection rate, drop rate, interference, etc., can also be obtained.

[0038] S12: Determine, based on the negative communication evaluation data and the plurality of communication performance data, a correlation coefficient threshold and a peak matching degree threshold corresponding to each of the communication performance data.

[0039] In this step, the correlation coefficient threshold and the peak matching degree threshold can be determined by preprocessing the communication negative evaluation data and multiple communication performance data. For example, the communication negative evaluation data and multiple communication performance data for each time period under normal communication conditions can be pre-acquired, and the correlation coefficient threshold and peak matching degree threshold corresponding to each time period can be determined based on a big data preprocessing algorithm.

[0040] For example, for a communication cell, the correlation coefficient between negative communication evaluation data and multiple communication performance data items during a normal communication period is determined. For each communication performance data item, the average value of the correlation coefficient during the normal communication period is used as the correlation coefficient threshold. This correlation coefficient threshold can express the correlation between the corresponding communication performance data item and the negative communication evaluation data item under normal communication conditions.

[0041] In this example, a corresponding correlation coefficient threshold is determined for each communication performance data. If the correlation coefficient of the communication performance data exceeds the corresponding correlation coefficient threshold, it indicates that the communication performance data is closely related to the communication negative evaluation data.

[0042] Based on the aforementioned method for determining the correlation coefficient threshold, a similar method can be used to determine the peak matching threshold. For example, the peak values ​​of negative communication evaluation data and multiple communication performance data points can be pre-obtained for each time period under normal communication conditions. The peak matching threshold corresponding to each time period can then be determined using a big data preprocessing algorithm.

[0043] In addition to the above-mentioned method of determining the threshold based on the big data preprocessing algorithm, the above-mentioned correlation coefficient threshold and peak matching degree threshold may also be set manually.

[0044] S13: respectively determining the correlation coefficient and peak matching degree between the negative communication evaluation data and each of the communication performance data, wherein the peak matching degree represents the matching degree between the peak moment of the negative communication evaluation data and the peak moment of the communication performance data.

[0045] The correlation coefficient is used to characterize the correlation between the negative communication evaluation data and the communication performance data. In this step, the correlation coefficient between the negative communication evaluation data and each communication performance data can be determined based on a preset correlation algorithm to obtain a correlation coefficient corresponding to each of the multiple communication performance data.

[0046] The peak matching degree is used to characterize the matching degree between the peak value in the negative communication evaluation data and the peak value in the communication performance data. In this step, the peak value therein can be determined based on the changing trend of the negative communication evaluation data. For example, the change point between the increase in data and the decrease in data is the peak value of the data. Accordingly, the peak value in the communication performance data can also be determined based on the increase or decrease in the above-mentioned data. The peak matching degree in this step can refer to the matching degree between the data containing the peak value in the above-mentioned negative communication evaluation data and the data containing the peak value in the communication performance data. Specifically, the matching degree between the negative communication evaluation data and each communication performance data can be determined based on a preset matching degree algorithm to obtain the peak matching degree corresponding to multiple communication performance data.

[0047] S14: Determine the communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold as the cause of the poor communication quality of the cell during the historical poor communication quality period.

[0048] The correlation coefficient can express the correlation between data changes in the communication performance data and the negative communication evaluation data, and the peak matching degree can express the correlation between the peak values ​​of the communication performance data and the peak values ​​of the negative communication evaluation data. If the correlation coefficient of the communication performance data is greater than the corresponding correlation coefficient threshold, and the peak matching degree is also greater than the peak matching degree threshold, then it indicates that the communication performance data is closely correlated with the negative communication evaluation data. This can then be determined to be the primary cause of the change in the negative communication evaluation data, i.e., the cause of the poor communication quality of the cell during the historical period of poor communication quality.

[0049] The embodiment of the present application obtains the communication negative evaluation data and multiple communication performance data of the cell with poor communication quality during the historical communication quality period; determines the correlation coefficient threshold and peak matching threshold corresponding to each of the communication performance data according to the communication negative evaluation data and the multiple communication performance data; determines the correlation coefficient and peak matching between the communication negative evaluation data and each of the communication performance data, respectively, and the peak matching represents the matching degree between the peak moment in the communication negative evaluation data and the peak moment of the communication performance data; determines the communication performance represented by the communication performance data with a correlation coefficient greater than the correlation coefficient threshold and a peak matching greater than the peak matching threshold as the cause of the poor communication quality of the cell with poor communication quality during the historical communication quality period. This solution can diagnose the cause of poor cell communication quality from two dimensions: correlation coefficient and peak matching, and can accurately identify communication performance data that is closely related to changes in the communication negative evaluation data, effectively improving diagnostic efficiency.

[0050] Optionally, an embodiment of the present application further provides a network performance adjustment method, characterized by comprising:

[0051] Obtaining negative communication evaluation data and multiple communication performance data of cells with poor communication quality during historical periods of poor communication quality;

[0052] Determining, based on the negative communication evaluation data and the plurality of communication performance data, a correlation coefficient threshold and a peak matching degree threshold corresponding to each of the communication performance data;

[0053] Determining the correlation coefficient and peak matching degree between the negative communication evaluation data and each of the communication performance data, respectively, wherein the peak matching degree represents the matching degree between the time when the peak in the negative communication evaluation data is located and the time when the peak of the communication performance data is located;

[0054] Determine a target communication performance parameter having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold;

[0055] Communication adjustments are performed on the target cell based on a direction of optimizing the target communication performance parameter.

[0056] Through the solution provided by the embodiment of the present application, after determining the target communication performance that causes the poor communication quality of the cell with poor communication quality during the historical period of poor communication quality, communication adjustments are made for the target communication performance. Specifically, the specific steps for making communication adjustments can be determined based on the target communication performance. For example, if the target communication performance characterizes that the cell capacity is too small and it is difficult to meet the communication service needs, the capacity of the cell with poor communication quality can be expanded and adjusted. If the target communication performance characterizes that the signal of the above-mentioned cell with poor communication quality is unstable, the communication power of the cell with poor communication quality can be increased or a new base station can be added to ensure the signal coverage area and improve communication stability. If the target communication performance characterizes that the signal interference of the above-mentioned cell with poor communication quality is serious, an interference check can be performed in the vicinity of the cell to eliminate interference and improve communication stability. In addition, if the target communication performance characterizes that the cell switching during user communication is abnormal, the switching parameters of the cell can be adjusted, etc.

[0057] Optionally, in order to improve the diagnostic efficiency, the acquired data may be pre-processed in step S11. For example, the data of cells with poor communication quality may be pre-processed into a data set with one row per hour and one column per communication performance. At the same time, in order to facilitate later comparison and output trend charts, each indicator may be normalized. nom-cell :A nom-cell ={X,Y1,Y2,Y3,Y4,Y5,Y6}

[0058] Among them, X is the normalized NPS index of this cell in multiple time periods. That is: X=[x t1 , x t2 ,……,x tn ] T Y1, Y2, Y3, Y4, Y5, and Y6 are the normalized indicators of "uplink PRB utilization", "downlink PRB utilization", "TA greater than 4 ratio", "uplink interference level", "CQI cell 7 ratio", and "handover failure rate" in each period of this cell, namely: Y i =[y it1 ,y it2 ,……,y itn ] T .

[0059] Through the solution provided in the embodiments of the present application, communication adjustments are made to cells with poor communication quality based on target communication performance, and the fundamental parameters that lead to poor communication quality can be adjusted, effectively solving the problem of poor cell communication quality, improving network performance, and enhancing quality indicators and user satisfaction with network performance.

[0060] Based on the solution provided in the above embodiment, optionally, before the above step S11, as Figure 2 As shown, it also includes:

[0061] S21: Obtaining communication negative evaluation data of multiple cells to be diagnosed within a historical period.

[0062] In this step, the negative communication evaluation data of multiple cells to be diagnosed within a historical period is obtained. Optionally, the multiple cells to be diagnosed can be multiple cells to be diagnosed based on geographically adjacent locations. When a communication user moves within the communication range covered by multiple cells to be diagnosed, handover may be performed between different cells. The negative communication evaluation data of the above-mentioned multiple cells to be diagnosed also have a certain correlation. This step obtains the negative communication evaluation data of multiple cells to be diagnosed within a historical period to provide a data basis for subsequently determining cells with poor communication quality.

[0063] S22: Determine an average value of the negative communication evaluation data of the plurality of cells to be diagnosed within the historical period as a negative communication evaluation threshold within the historical period.

[0064] In this step, a negative communication rating threshold is determined based on the negative communication rating data of multiple cells to be diagnosed over a historical period. The average of these negative communication rating data represents the overall negative communication rating value of the multiple cells to be diagnosed. Using this average as the negative communication rating threshold effectively distinguishes cells with high and low negative communication ratings from the multiple cells to be diagnosed.

[0065] S23: Determine a cell with poor communication quality from the multiple cells to be diagnosed according to the negative communication evaluation threshold, wherein the negative communication evaluation of the cell with poor communication quality in the historical period exceeds the negative communication evaluation threshold.

[0066] Because the negative communication evaluation data can represent the communication performance of a cell, in this step, based on the negative communication evaluation threshold determined in the above step, cells with poor communication quality whose negative communication evaluation exceeds the negative communication evaluation threshold are identified from the multiple cells to be diagnosed. Furthermore, after identifying the cells with poor communication quality, a historical period of poor communication quality can be determined based on the specific values ​​of the negative communication evaluation data for the cells with poor communication quality during the historical period. This historical period of poor communication quality falls within the above historical period.

[0067] Optionally, if there are multiple cells to be diagnosed whose negative communication evaluation exceeds the above-mentioned negative communication evaluation threshold, multiple cells to be diagnosed can be determined as cells with poor communication quality, and diagnosis can be performed one by one on these cells with poor communication quality to determine the cause of the poor communication quality in each cell with poor communication quality.

[0068] In actual applications, to reduce the amount of calculation, if there are multiple cells to be diagnosed whose negative communication evaluation exceeds the above-mentioned negative communication evaluation threshold, the cell to be diagnosed with the most negative communication evaluation can also be determined as a cell with poor communication quality, and diagnosis and optimization adjustments can be performed on this cell with poor communication quality. Since the communication quality of multiple cells to be diagnosed often has a certain correlation. After accurately diagnosing and optimizing the cell with the worst communication quality, the communication quality of multiple related cells may be improved. After optimizing the cell with the worst communication quality, negative communication evaluation data can be obtained again. If there are still cells with poor communication quality, the cells with poor communication quality can be diagnosed and optimized again until the negative communication evaluation data of multiple cells to be diagnosed do not exceed the negative communication evaluation threshold.

[0069] Through the solution provided in the embodiment of the present application, the communication negative evaluation threshold is determined based on multiple cells to be diagnosed, and the cells with high communication negative evaluation data can be determined as cells with poor communication quality, and then diagnosis is performed on the cells with poor communication quality, which is conducive to efficiently reducing the overall communication negative evaluation of multiple cells to be diagnosed.

[0070] Based on the solution provided in the above embodiment, optionally, before the above step S12, as Figure 3 As shown, it also includes:

[0071] S31: Acquire multiple pieces of communication performance data of the multiple cells to be diagnosed within the historical period.

[0072] In actual applications, the same type of communication performance data of multiple cells to be diagnosed is obtained. For example, six communication performance data items, including "uplink PRB utilization", "downlink PRB utilization", "TA greater than 4 proportion", "uplink interference level", "CQI cell 7 proportion", and "switching failure rate" are obtained for each cell to be diagnosed.

[0073] Optionally, the acquired communication performance data may be preprocessed, such as filtering out null values, abnormal data outside a preset range, and performing data normalization. The purpose of preprocessing is to optimize the quality of the communication performance data and improve the accuracy of diagnosis.

[0074] S32: generating a communication data set of cells to be diagnosed based on the communication negative evaluation data and the plurality of communication performance data of the plurality of cells to be diagnosed, wherein the communication data set includes the communication negative evaluation data and the plurality of communication performance data associated with the cells to be diagnosed;

[0075] In practical applications, the above-mentioned communication dataset of the cell to be diagnosed can be generated through plug-ins. For example, the Pandas plug-in can be used to combine the above-mentioned negative communication evaluation data and multiple communication performance data with time and cell number as the correlation mark to obtain the communication dataset A of the cell to be diagnosed. all={X a ,Y a1 ,Y a2 ,Y a3 ,Y a4 ,Y a5 ,Y a6}. Among them, A all represents the communication data set of the cell to be diagnosed, X a Indicates the negative communication evaluation data of the cell to be diagnosed, Y a1 ~Y a6 Respectively represent the above six communication performance data. a and Y a1 ~Y a6 Specifically, each includes multiple data values ​​corresponding to multiple moments.

[0076] The above step S12 includes:

[0077] S33: performing correlation analysis on the communication negative evaluation data associated with the same cell to be diagnosed and various communication performance data in the communication data set of the cell to be diagnosed according to a correlation coefficient algorithm to obtain a correlation coefficient matrix of the communication data set of the cell to be diagnosed.

[0078] In this step, calculate A all Medium X a With Y ai The correlation coefficient algorithm in this embodiment can be the Pearson correlation coefficient algorithm, which is as follows:

[0079]

[0080] By using the above Pearson correlation coefficient algorithm, X a With Y a1 Substitute into the formula to calculate Y a1 The correlation coefficient of X. a With Y a1 Contains multiple data values ​​corresponding to multiple moments, so the Y obtained by the above algorithm a1 The correlation coefficient of also includes multiple correlation coefficient values ​​at the corresponding time. In this step, Y a1 ~Y a6 Calculate the correlation coefficient and summarize it to get the correlation coefficient matrix ρ corresponding to the communication data set of the cell to be diagnosed a :

[0081]

[0082] S34: Determine the correlation coefficient threshold corresponding to each of the communication performance data according to the correlation coefficient matrix of the communication data set of the cell to be diagnosed.

[0083] The above correlation coefficient matrix ρ a Indicates the full correlation coefficient value between the communication negative evaluation data and other communication performance data. This value can be used as the correlation coefficient threshold of the corresponding communication performance parameter, that is:

[0084]

[0085] Through the solution provided in the embodiment of the present application, the data of multiple cells to be diagnosed can be integrated to determine a reasonable correlation coefficient threshold for each communication performance parameter to improve the diagnosis accuracy.

[0086] Based on the solution provided in the above embodiment, optionally, the above step S12, such as Figure 4 Shown, including:

[0087] S41: Determine a first total number of peaks in the communication negative evaluation data of the communication data set of the cell to be diagnosed, wherein the data value at the moment of the peak is greater than the data value at the previous moment and the data value at the next moment based on adjacent time.

[0088] In this embodiment, based on the communication data set described in the above embodiment, the peak value in the data is determined according to the rising and falling trend of the communication negative evaluation data. Specifically, for the communication negative evaluation data of the communication data set of the cell to be diagnosed, for any non-first and last data value x k , where k can be a time series value used to represent time, x k A data value that is neither the first nor the last data value in the data set. First, calculate the value of each x in the data set. k The difference between its two adjacent elements based on time: dx k =[x k -x k-1 ,x k+1 -x k ]. When the left side is an upward trend or the right side is a downward trend, it means that this point is in the rising or falling stage of a peak, and this point is recorded as a peak point.

[0089] Optionally, the peak value in the communication negative evaluation data of the communication data set of the cell to be diagnosed can be counted based on the peak point counter. k -x k-1 >0 and x k+1 -x k <0, the peak point counter f x Add 1. Through this solution, the sum of peak points in the negative communication evaluation data of multiple cells to be diagnosed can be obtained.

[0090] S42: Determine a second total number of communication performance data of the same cell to be diagnosed that is associated with the peak value in the negative communication evaluation data and is also a peak value at the time when the peak value is located.

[0091] Based on the peak value of the communication negative evaluation data determined above, the time when the communication negative evaluation data of each cell to be diagnosed is at the peak value can be determined. In this step, the number of communication performance data that is also at the peak value at the above time is determined. Optionally, for a type of communication performance data, based on the above k, calculate y ik The difference between the adjacent elements on both sides of the time: dy ik =[y ik -y i(k-1) ,dy i(k+1) -dy ik ]. When the left side shows an upward trend or the right side shows a downward trend, it means that this point is in the rising or falling stage of a peak, and this point is recorded as a peak point. Based on the peak moment in the above-mentioned communication negative evaluation data, if the communication performance data is also at a peak at the same time, it can be recorded through the peak point counter. The peak point counter f Yi Add 1.

[0092] S43: Determine the ratio of the second total number to the first total number as the peak matching threshold.

[0093] In this step, the f of the cell to be diagnosed x Sum and f Yi After summing, the ratio of the two is used as the peak matching threshold: Peak_rate i_th =∑(f Yi ) / ∑(f x ).

[0094] It should be noted that Yi in this embodiment can specifically be any one of the six communication performance data in the above embodiment. In actual applications, the peak matching threshold corresponding to each communication performance data can be determined for each communication performance data using the solution provided in the embodiment of this application, where each communication performance data can correspond to each peak matching threshold.

[0095] Through the solution provided in the embodiment of the present application, the data of multiple cells to be diagnosed can be integrated to determine a reasonable peak matching threshold to improve the diagnosis accuracy.

[0096] Based on the solution provided in the above embodiment, optionally, Figure 5 As shown, the above step S13 includes:

[0097] S51: respectively determining correlation coefficients between the negative communication evaluation data of the cell with poor communication quality and each item of the communication performance data of the cell with poor communication quality.

[0098] In this step, based on the negative communication evaluation data for cells with poor communication quality, correlation coefficients are determined for each item of communication performance data. Specifically, the correlation coefficients can be determined using the Pearson correlation coefficient algorithm described in the above embodiment. The correlation coefficients for each item of communication performance data determined in this step correspond one-to-one with each item of communication performance data.

[0099] S52: If there is a first target communication performance data whose correlation coefficient is greater than the correlation coefficient threshold of the first target communication performance data, determine the peak matching degree between the negative communication evaluation data and the first target communication performance data.

[0100] In this step, based on the correlation coefficient threshold of the communication performance data determined in the above embodiment, it is determined whether there is first target communication performance data whose correlation coefficient of the communication performance data is greater than the corresponding threshold. Specifically, for an item of communication performance data, its corresponding correlation coefficient threshold is obtained, and the obtained threshold is compared with the correlation coefficient of the communication performance data. If the correlation coefficient is greater than the corresponding correlation coefficient threshold, it indicates that the correlation between the communication performance data and the negative communication evaluation data is high, and the peak matching degree of the communication performance data is further determined. Specifically, the step of determining the peak matching degree can refer to the relevant steps of determining the peak point in S41 and S42 above. In this step, the peak matching degree is the matching degree of the peak value in the negative communication evaluation data with the peak value in the first target communication performance data. The peak matching degree can be the ratio of the number of first target communication performance data that are at a peak value while the negative communication evaluation data is at a peak value to the number of peak values ​​in the negative communication evaluation data.

[0101] Through the above steps of the embodiment of the present application, various communication performance data can be screened based on the correlation coefficient, and the first target communication performance data with a high correlation with the communication negative evaluation data can be selected, and further peak matching degree comparison can be performed.

[0102] The above step S14 includes:

[0103] S53: If the peak matching degree of the first target communication performance data is greater than the peak matching degree threshold of the first target communication performance data, the communication performance represented by the first target communication performance data is determined as the reason for the poor communication quality of the cell with poor communication quality during the historical poor communication quality period.

[0104] In the above steps, the first target communication performance data is obtained by screening based on the correlation coefficient threshold and is closely related to the negative communication evaluation data. In this step, a judgment is made based on the corresponding peak matching threshold for the first target communication performance data that is closely related to the negative communication evaluation data. If the peak matching degree of the first target communication performance data is greater than the peak matching threshold of the first target communication performance data, it indicates that the peak value of the first target communication performance data is closely related to the peak value of the negative communication evaluation data, and the first target communication performance data is the key reason for the peak value of the negative communication evaluation data, that is, the reason for the poor communication quality of the cell with poor communication quality during the historical poor communication quality period.

[0105] For example, using NPS quality index and index Y i The match of the temporal trend, i.e., the peak point matching, is used to determine the match. The ratio of the number of times the NPS quality indicator appears in a peak upward or downward trend, and the number of times other indicators also have a peak upward or downward trend at this time, is calculated as the peak point matching, indicating the degree to which the NPS quality indicator and the indicator are trending in the same direction. When the matching degree exceeds the peak matching threshold, the indicator is considered to have the same trend as the NPS quality indicator. The algorithm is as follows:

[0106] First, calculate x for each k (k is not the first or last) k The difference between the adjacent elements on both sides: dx k =[x k -x k-1 ,x k+1 -x k Then, calculate y ik The difference between the adjacent elements on both sides of the time: dy ik =[y ik -y i(k-1) ,dy i(k+1) -dy ik ]. When the left side is an upward trend or the right side is a downward trend, it means that this point is in the rising or falling stage of a peak, and this point is recorded as a peak point. k -x k-1 >0 or x k+1 -x k <0, the peak point counter f x Add 1, and at the same time, if y ik -y i(k-1) >0 or dy i(k+1) -dy ik <0, peak point counter f Yi Add 1. Calculate f Yi / f x . Define when f Yi / f x Peak_rate i_th , you can determine The dimension Y represented by the indicator i This is the reason for the poor quality of NPS.

[0107] Through the solution provided in the embodiment of the present application, it is first determined whether the correlation coefficient exceeds the correlation coefficient threshold, and then it is determined whether the peak matching degree exceeds the peak matching degree threshold, which can reduce the amount of calculation to a certain extent while ensuring diagnostic accuracy.

[0108] Based on the solution provided in the above embodiment, optionally, after the above step S51, as Figure 6 As shown, it also includes:

[0109] S61: If the first target communication performance data greater than the correlation coefficient threshold does not exist, a quadratic function fitting is performed on the negative communication evaluation data of the cell with poor communication quality and each item of the communication performance data of the cell with poor communication quality to obtain a quadratic fitting function corresponding to each item of the communication performance data.

[0110] S62: Determine the negative evaluation average value of the communication negative evaluation data of the cell with poor communication quality;

[0111] S63: performing depreciation correction on data values ​​in the communication negative evaluation data that are greater than the negative evaluation average value according to the quadratic fitting function to generate corrected communication negative evaluation data;

[0112] S64: respectively determining correlation coefficients between the corrected negative communication evaluation data and each item of communication performance data of the cell with poor communication quality.

[0113] The embodiment of the present application is optimized by the correlation enhancement algorithm to achieve poor communication quality diagnosis. In practical applications, since NPS quality is affected by multiple factors at the same time, in order to eliminate the influence of other factors, the enhancement algorithm is used to optimize the correlation algorithm based on X and Y. i If the NPS quality index X is higher in a certain period, but Y in this period is i The indicator is low, while another indicator Y j If (j is not equal to i) is high, it means that the high NPS may be caused by other factors and is unrelated to this indicator. Therefore, this solution performs correlation enhancement based on the above principles, which can achieve correlation optimization and realize poor quality diagnosis.

[0114] Based on the above principle, when Less than or equal to ρ i_th When , the NPS index of this period is reduced accordingly. For example, using the polyfit(x,y,2) function in Numpy,i Perform quadratic function fitting with X to obtain the quadratic fitting function g(X,Y i ). Calculate the relationship between each y value and the function g(X,Y i ) and take the average to get:

[0115] Then, for X greater than Point x k , if the corresponding y ik Less than g(X,Y i )-Avgdelta, indicating that the point falls below the normal error range of the fitting function, corresponding to the lower right area of ​​the scatter plot, y ik Too small, so it is believed that the X value is caused by other factors. ik In Y i The ratio of X k Artificial reduction, generate X′ and then calculate The formula is as follows:

[0116] If and y jk >g(X,j)(j is not equal to i)and y ik <g(X,Y i )-Avgdelta

[0117] but:

[0118]

[0119] Get the new NPS dataset X′:

[0120] X′=[x1,x2,…,x k ′,…,x n ] T

[0121] After correction, X′ and Y i Perform correlation calculations.

[0122]

[0123] If the corrected correlation coefficient Greater than ρ i_th , and then according to the relevant "relationship coefficient When greater than ρ i_th "The method continues to analyze. Through the solution provided in the embodiment of the present application, the correlation can be enhanced, and the corrected NPS is closer to the communication performance data, which is conducive to accurately diagnosing the reasons for the poor quality of NPS.

[0124] The following describes this solution in conjunction with example parameters. The multiple communication performance data in this example include uplink physical resource block PRB utilization, downlink physical resource block PRB utilization, the proportion of tracking areas TA greater than or equal to the preset tracking area value, the uplink interference level, the proportion of channel quality indication CQI less than the preset channel quality indicator value, and the switching failure rate, a total of six communication performance data.

[0125] First, the correlation coefficient of the total data set is calculated using big data to obtain the correlation coefficient threshold:

[0126] ρ_(i_th)=[0.75,0.7,0.7,0.71,0.74,0.76]

[0127] The peak matching rate threshold is obtained through big data calculation:

[0128] Peak_rate i_th =[0.76,0.81,0.80,0.78,0.79,0,81]

[0129] The following table shows the normalized A of various indicators in a certain community. nom-cell matrix:

[0130]

[0131]

[0132]

[0133] Taking the above table as an example, we calculate the correlation coefficient matrix and get: ρ = [0.63, 0.67, 0.90, 0.35, 0.05, 0.12]

[0134] Based on the above parameters, the correlation coefficient (0.9) between NPS_Rate and downlink PRB utilization is greater than ρ i_th (0.7). At this point, further calculate the peak point matching degree between the two: f x =41,f Yi =28. f Yi / fx=0.82>Peak_ratei_th(0.8), therefore, it can be determined that the downlink PRB utilization is the cause of the poor NPS quality.

[0135] Through the above solution, it is determined that downlink PRB utilization is the cause of poor NPS quality, indicating that capacity issues are the root cause of communication users' dissatisfaction with communication performance. The network department can solve the capacity problem in this cell through load balancing or capacity expansion solutions to improve customer satisfaction.

[0136] In recent years, the mobile internet has developed rapidly, and smart devices have become increasingly popular. This has significantly increased user demand for higher-quality mobile communications. At the same time, the drive for faster speeds and lower prices has intensified competition among telecom operators. For telecom operators, prioritizing customers and continuously improving network quality, thereby increasing customer satisfaction, is crucial to maintaining a more advantageous competitive position.

[0137] Currently, China Mobile has gradually established a closed-loop network improvement system, focusing on planning, construction, maintenance, and optimization, centered around data on negative customer feedback on communication performance. This system links negative communication feedback data with cell-level communication performance data to identify the root causes of customer satisfaction and identify network weaknesses. This allows for targeted network planning, construction, maintenance, and optimization, ultimately improving network quality and ultimately customer satisfaction.

[0138] This proposal addresses the issue of how to correlate negative communication evaluation data with cell performance data to identify the root causes of customer satisfaction. This is a critical step in guiding network planning and optimization. Only by accurately identifying the root causes of network issues can we develop targeted solutions and improve network quality.

[0139] This proposal uses a peak matching-based correlation algorithm and a correlation enhancement algorithm to effectively analyze the causes of poor NPS network performance, providing a clear direction for network planning, construction, and maintenance. This approach improves network analysis efficiency, quickly and effectively addresses issues that lead to user dissatisfaction with communication performance, and ultimately improves network quality and customer satisfaction.

[0140] This embodiment of the application uses a peak matching correlation algorithm to calculate the number of times the NPS quality indicator appears in an upward or downward trend with a peak, and the number of times other indicators also show an upward or downward trend with a peak at that time. The ratio of the two is the peak matching degree. Based on whether the correlation degree is above a threshold and whether the peak matching degree is also above a threshold, the cause of the NPS quality problem can be quickly determined, improving diagnostic accuracy.

[0141] In addition, since poor NPS quality is affected by multiple factors at the same time, when the correlation is not higher than the threshold, a correlation enhancement algorithm is proposed to correct the data and improve the success rate of analyzing the causes of poor NPS quality.

[0142] The solution provided in the embodiments of the present application can deeply analyze the impact of wireless networks on customer satisfaction and more accurately and quickly find the root causes affecting customer satisfaction. This solution improves the accuracy of diagnosing the root causes of poor NPS quality based on peak matching and correlation algorithms.

[0143] Furthermore, this embodiment proposes an enhanced correlation algorithm to address the simultaneous impact of two or more dimensions on poor NPS quality, effectively improving the success rate of analyzing the causes of poor NPS quality. This solution, combined with big data analysis methods, enables centralized processing and analysis of network-wide data, improving work efficiency.

[0144] In order to solve the problems existing in the prior art, the embodiment of the present application provides a device 70 for diagnosing poor cell communication quality, such as Figure 7 Shown, including:

[0145] An acquisition module 71 is configured to acquire negative communication evaluation data and multiple communication performance data of a cell with poor communication quality during a historical period of poor communication quality;

[0146] A first determining module 72 determines, based on the negative communication evaluation data and a plurality of communication performance data, a correlation coefficient threshold and a peak matching degree threshold corresponding to each of the communication performance data;

[0147] A second determining module 73 is configured to determine a correlation coefficient and a peak matching degree between the negative communication evaluation data and each of the communication performance data, wherein the peak matching degree represents a matching degree between a peak moment in the negative communication evaluation data and a peak moment in the communication performance data;

[0148] The diagnosis module 74 determines the communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold as the cause of the poor communication quality of the cell during the historical poor communication quality period.

[0149] Through the device provided in the embodiment of the present application, the communication negative evaluation data and multiple communication performance data of the cell with poor communication quality during the historical communication quality period are obtained; the correlation coefficient threshold and peak matching threshold corresponding to each of the communication performance data are determined based on the communication negative evaluation data and the multiple communication performance data; the correlation coefficient and peak matching degree between the communication negative evaluation data and each of the communication performance data are determined respectively, and the peak matching degree represents the matching degree between the time when the peak in the communication negative evaluation data is located and the time when the peak of the communication performance data is located; the communication performance represented by the communication performance data with a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold is determined as the cause of the poor communication quality of the cell with poor communication quality during the historical communication quality period. This solution can diagnose the cause of poor cell communication quality from two dimensions: correlation coefficient and peak matching degree, and can accurately identify communication performance data that is closely related to changes in negative communication evaluation data, effectively improving diagnostic efficiency.

[0150] The aforementioned modules in the apparatus provided in the embodiments of the present application may also implement the method steps provided in the aforementioned method embodiments. Alternatively, the apparatus provided in the embodiments of the present application may further include other modules in addition to the aforementioned modules to implement the method steps provided in the aforementioned method embodiments. Furthermore, the apparatus provided in the embodiments of the present application can achieve the technical effects achievable by the aforementioned method embodiments.

[0151] Preferably, an embodiment of the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned method embodiment for diagnosing poor cell communication quality are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0152] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements the various processes of the above-mentioned embodiment of the method for diagnosing poor cell communication quality and can achieve the same technical effect. To avoid repetition, the description is omitted here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0153] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0154] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0155] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0157] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0158] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0159] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0160] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0161] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0162] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for diagnosing poor cell communication quality, characterized in that: include: Obtaining negative communication evaluation data and multiple communication performance data for cells with poor communication quality during a historical period of poor communication quality, wherein the negative communication evaluation data is used to represent communication users' satisfaction with the communication performance of the cell, and the negative communication evaluation data is determined based on a net recommendation value poor quality indicator; Determining a preset correlation coefficient threshold and a preset peak matching threshold corresponding to each of the communication performance data, wherein the correlation coefficient threshold is used to evaluate the correlation between the corresponding communication performance data and the communication negative evaluation data, and the peak matching threshold is used to evaluate the matching degree of the data change trend between the corresponding communication performance data and the communication negative evaluation data; Determining the correlation coefficient and peak matching degree between the negative communication evaluation data and each of the communication performance data, respectively, wherein the peak matching degree represents the matching degree between the time when the peak in the negative communication evaluation data is located and the time when the peak of the communication performance data is located; The communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold is determined as the reason why the poor communication quality of the cell in poor communication quality is poor during the historical poor communication quality period.

2. The method according to claim 1, wherein Before obtaining the communication negative evaluation data and multiple communication performance data of the cell with poor communication quality during the historical period of poor communication quality, the following is also included: Obtaining negative communication evaluation data of multiple cells to be diagnosed within a historical period; Determining an average value of the negative communication evaluation data of the plurality of cells to be diagnosed within the historical period as a negative communication evaluation threshold within the historical period; A cell with poor communication quality is determined from the multiple cells to be diagnosed according to the negative communication evaluation threshold, wherein the negative communication evaluation of the cell with poor communication quality in the historical period exceeds the negative communication evaluation threshold.

3. The method according to claim 2, wherein Before determining the preset correlation coefficient threshold and the preset peak matching degree threshold corresponding to each of the communication performance data, the method further includes: Acquire multiple pieces of communication performance data of the multiple cells to be diagnosed within the historical period; generating a communication data set of cells to be diagnosed based on the communication negative evaluation data and the plurality of communication performance data of the plurality of cells to be diagnosed, wherein the communication data set includes the communication negative evaluation data and the plurality of communication performance data associated with the cells to be diagnosed; Determining the preset correlation coefficient threshold and the preset peak matching degree threshold corresponding to each of the communication performance data includes: performing a correlation analysis on the communication negative evaluation data associated with the same cell to be diagnosed and the various communication performance data in the communication data set of the cell to be diagnosed according to a correlation coefficient algorithm to obtain a correlation coefficient matrix of the communication data set of the cell to be diagnosed; The correlation coefficient thresholds corresponding to each of the communication performance data are determined according to the correlation coefficient matrix of the communication data set of the cell to be diagnosed.

4. The method according to claim 3, wherein Determining a preset correlation coefficient threshold and a preset peak matching degree threshold corresponding to each of the communication performance data, including: Determining a first total number of peaks in the communication negative evaluation data of the communication data set of the cell to be diagnosed, wherein the data value at the moment of the peak is greater than the data value at the previous moment and the data value at the next moment based on adjacent time; Determine a second total number of communication performance data of the same cell to be diagnosed that is associated with the peak value in the negative communication evaluation data and is also a peak value at the time when the peak value is located; A ratio of the second total number to the first total number is determined as the peak matching degree threshold.

5. The method according to claim 1, wherein Obtain negative communication evaluation data and multiple communication performance data for cells with poor communication quality during historical periods of poor communication quality, including: Obtain multiple communication performance data including uplink physical resource block PRB utilization, downlink physical resource block PRB utilization, proportion of tracking areas TA greater than or equal to the preset tracking area value, uplink interference level, proportion of channel quality indication CQI less than the preset channel quality indication value, and switching failure rate of cells with poor communication quality during the historical communication quality period.

6. The method according to any one of claims 1 to 5, wherein Determining the correlation coefficient and peak matching degree between the negative communication evaluation data and each of the communication performance data respectively includes: respectively determining correlation coefficients between the negative communication evaluation data of the cell with poor communication quality and each item of the communication performance data of the cell with poor communication quality; If there is a correlation coefficient of the first target communication performance data that is greater than the correlation coefficient threshold of the first target communication performance data, determining a peak matching degree between the negative communication evaluation data and the first target communication performance data; The communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold is determined as the cause of the poor communication quality of the cell with poor communication quality during the historical poor communication quality period, including: If the peak matching degree of the first target communication performance data is greater than the peak matching degree threshold of the first target communication performance data, the communication performance represented by the first target communication performance data is determined as the reason for the poor communication quality of the cell with poor communication quality during the historical poor communication quality period.

7. The method according to claim 6, wherein After respectively determining the correlation coefficients between the negative communication evaluation data of the cell with poor communication quality and each of the communication performance data of the cell with poor communication quality, the method further includes: If there is no first target communication performance data greater than the correlation coefficient threshold, performing quadratic function fitting on the negative communication evaluation data of the cell with poor communication quality and each item of the communication performance data of the cell with poor communication quality, so as to obtain a quadratic fitting function corresponding to each item of the communication performance data; Determine an average negative evaluation value of the communication negative evaluation data of the cell with poor communication quality; performing depreciation correction on data values ​​in the communication negative evaluation data that are greater than the negative evaluation average value according to the quadratic fitting function to generate corrected communication negative evaluation data; The correlation coefficients between the corrected negative communication evaluation data and each item of the communication performance data of the cell with poor communication quality are determined respectively.

8. A device for diagnosing poor cell communication quality, characterized in that: include: an acquisition module for acquiring negative communication evaluation data and multiple communication performance data of cells with poor communication quality during a historical period of poor communication quality, wherein the negative communication evaluation data is used to represent the satisfaction of communication users with the communication performance of the cell in which they are located, and the negative communication evaluation data is determined based on a net recommendation value poor quality indicator; A first determination module determines a preset correlation coefficient threshold and a preset peak matching threshold corresponding to each of the communication performance data, wherein the correlation coefficient threshold is used to evaluate the correlation between the corresponding communication performance data and the communication negative evaluation data, and the peak matching threshold is used to evaluate the matching degree of the data change trend between the corresponding communication performance data and the communication negative evaluation data; A second determination module is configured to determine a correlation coefficient and a peak matching degree between the negative communication evaluation data and each of the communication performance data, wherein the peak matching degree represents a matching degree between a time point at which a peak in the negative communication evaluation data is located and a time point at which a peak in the communication performance data is located; The diagnosis module determines the communication performance represented by the communication performance data having a correlation coefficient greater than the correlation coefficient threshold and a peak matching degree greater than the peak matching degree threshold as the cause of the poor communication quality of the cell during the historical poor communication quality period.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images