A method and system for analyzing data in wireless communication operation and maintenance

Abstract

The present invention relates to the field of wireless communication technologies, and discloses a method and system for analyzing wireless communication operation and maintenance data, including the following steps: in all sub-regions of a wireless communication operation and maintenance area, perform high-frequency similarity analysis on the service traffic value data of each historical time period, and construct a first set from the data analyzed for each time period; perform distance analysis on the first set of each time period, and construct a second set based on the distance analysis results; perform influence analysis on the sub-regions in the second set, and construct a third set based on the influence analysis results. The present invention can accurately identify the mutually influential and key analysis sub-regions in a wireless communication network, so that operation and maintenance personnel can focus on key areas, conduct key monitoring on these key analysis sub-regions, allocate network resources more reasonably, increase bandwidth, optimize base station configuration, etc. in key areas, and improve resource utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and particularly relates to a method and system for analyzing wireless communication operation and maintenance data. Background Art

[0002] With the rapid development of wireless communication technologies, wireless communication networks are increasingly widely used in people's daily lives, work, and various industries. From the popularization of smart phones to the large-scale access of Internet of Things devices, the amount of data carried by wireless communication networks has grown explosively, which poses extremely high requirements on the performance and stability of the networks.

[0003] However, in long-term wireless communication operation and maintenance practices, operation and maintenance personnel first noticed the instability of network performance. When allocating network resources, it was found that allocating resources based on experience could not well identify the mutually influential and key analysis sub-regions in the wireless communication network, enabling operation and maintenance personnel to focus on key regions, rationally allocate network resources, and improve resource utilization efficiency. For example, due to the failure to identify key regions in advance and predict peaks, serious network congestion may occur, and users cannot normally use network services. Summary of the Invention

[0004] An object of the present invention is to provide a method and system for analyzing wireless communication operation and maintenance data to solve at least one of the above-mentioned prior art problems.

[0005] In a first aspect, the present invention provides a method for analyzing wireless communication operation and maintenance data, including the following steps:

[0006] In all sub-regions of the wireless communication operation and maintenance area, perform high-frequency similarity analysis on the service traffic value data of each historical time period, and construct a first set from the data analyzed for each time period.

[0007] Perform distance analysis on the first set of each time period, and construct a second set through the distance analysis results.

[0008] Perform influence analysis on the sub-regions in the second set, construct a third set through the influence analysis results, and perform influence range analysis on the sub-regions in the third set to obtain key sub-regions.

[0009] As a further solution of the present invention: The process of obtaining the first set is as follows:

[0010] Obtain the historical service traffic value data of each analysis region, and set the analysis period and analysis time period.

[0011] For any one analysis time period in the same analysis period of all analysis sub-regions, use the Chebyshev distance method to judge and obtain a fourth set.

[0012] Obtain the occurrence times of the analysis sub-regions included in all similar analysis sub-region sets respectively, and calculate the ratio with the total number of analysis periods respectively to obtain the proportion of occurrence times.

[0013] Mark the analysis sub-regions with an occurrence proportion greater than or equal to the occurrence proportion threshold as high-frequency similar sub-regions, and construct the first set of this analysis period.

[0014] As a further solution of the present invention: the process of obtaining the second set is as follows:

[0015] Calculate the distance between any two analysis regions in any high-frequency similar analysis sub-region set through the distance formula, and construct an Euclidean distance matrix.

[0016] Calculate the average value jz and the standard deviation bz of the non-zero elements in the Euclidean distance matrix. If , then mark the second set, where α is a proportionality coefficient.

[0017] As a further solution of the present invention: the process of obtaining the third set is as follows:

[0018] Perform data analysis on the analysis sub-region combinations in the second set to obtain the relevant influence degree values, and mark the analysis sub-region combinations in the second set with a relevant influence degree greater than the relevant influence degree threshold as the third set.

[0019] As a further solution of the present invention: the process of obtaining the relevant influence degree value is as follows:

[0020] Count the number of analysis periods in which two adjacent analysis sub-regions in the adjacent analysis sub-region combinations appear in the high-frequency similar analysis sub-region set respectively, and calculate the ratio with the total number of analysis periods to obtain the regional similarity proportion.

[0021] Calculate the ratio of the distance value between these two adjacent analysis sub-regions and the judgment distance threshold to obtain the regional distance ratio.

[0022] Calculate the relevant characterization value using the mutual information correlation coefficient.

[0023] Perform data processing on the regional similarity proportion, the regional distance ratio, and the relevant characterization value to obtain the relevant influence degree value.

[0024] As a further solution of the present invention: the process of obtaining the relevant characterization value is as follows:

[0025] For each analysis period, calculate the relevant degree value of the data change of the business flow value between two analysis sub-regions using the mutual information correlation coefficient.

[0026] The correlation degree values corresponding to all analysis cycles in the same analysis period are averaged to obtain the average correlation degree of an analysis period, and then the average correlation degrees of all analysis periods are averaged to obtain the correlation characterization value.

[0027] As a further solution of the present invention: the process of obtaining the key analysis sub-region is as follows:

[0028] Count the non-repeated analysis sub-regions in the combination of analysis sub-regions in the third set, and mark them as the analysis sub-regions to be marked;

[0029] Traverse all the combinations of analysis sub-regions in the third set and mark each analysis sub-region, respectively count the number of times each analysis region is marked, and calculate the ratio with the analysis sub-regions to be marked respectively to obtain the marking times ratio. The analysis sub-regions with a marking times ratio greater than or equal to the threshold are...

[0030] As a further solution of the present invention: it further includes:

[0031] Construct a service traffic prediction model through the historical service traffic value data of the key analysis sub-region, predict the service traffic value data, and identify the peak analysis cycle.

[0032] As a further solution of the present invention: obtain the key analysis sub-region and obtain the corresponding historical service traffic value data;

[0033] Construct a service traffic prediction model for each key analysis sub-region and obtain a sequence of service traffic prediction value data;

[0034] Extract the number of service traffic prediction values greater than the service traffic limit value, and calculate the ratio with the total number of service traffic prediction values to obtain the proportion of the number of high service traffic values;

[0035] Calculate the difference between the service traffic prediction values greater than the service traffic limit value and the service traffic limit value respectively, and perform averaging processing, and then calculate the ratio with the service traffic limit value to obtain the high service traffic degree value;

[0036] Calculate the high service traffic value proportion and the high service traffic degree value to obtain the peak characterization value, and mark the analysis cycle corresponding to the key analysis sub-region with a peak characterization value greater than the peak characterization threshold as the peak analysis cycle.

[0037] In the second aspect, the present invention provides a wireless communication operation and maintenance data analysis system, which includes:

[0038] Similarity recognition module: In all sub-regions of the wireless communication operation and maintenance area, perform high-frequency similarity analysis on the service traffic value data of each historical period, and construct the data analyzed in each period into a first set;

[0039] Distance recognition module: perform distance analysis on the first set for each time period, and construct the second set based on the distance analysis results;

[0040] Influence and key recognition module: perform influence analysis on the sub-regions in the second set, construct the third set based on the influence analysis results, and perform influence range analysis on the sub-regions in the third set to obtain the key sub-regions.

[0041] Advantages of the present invention:

[0042] 1. The present invention can help operation and maintenance personnel clearly master the distribution of similar regions of service traffic in different time periods, provide a basis for accurately planning network resources, improve resource utilization efficiency, ensure network stability, and can also discover the changing rules and patterns of service traffic, providing a reference for long-term network optimization and development planning. At the same time, by discovering the similar regions of service traffic with spatial aggregation characteristics, it solves the problems of unclear service traffic distribution, lack of pertinence in network resource planning, and low fault troubleshooting efficiency in wireless communication networks to a certain extent, and helps the operation and maintenance work of wireless communication to be carried out more efficiently;

[0043] 2. The present invention can accurately identify the mutually influential and key analysis sub-regions in the wireless communication network, enabling operation and maintenance personnel to focus on key regions, conduct key monitoring on these key analysis sub-regions, allocate network resources more reasonably, increase bandwidth and optimize base station configuration in key regions, etc., and improve resource utilization efficiency. Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 is a flowchart of a method for analyzing wireless communication operation and maintenance data of the present invention;

[0046] Figure 2 is a structural schematic diagram of a wireless communication operation and maintenance data analysis system of the present invention. Detailed Embodiments

[0047] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solution in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work shall fall within the scope of protection of the present invention.

[0048] Embodiment 1

[0049] Figure 1 It is a flowchart of a method for analyzing wireless communication operation and maintenance data provided in Embodiment 1 of the present invention. The embodiments of the present invention are applicable to the situation of analyzing service traffic distribution in a wireless communication network. This method for analyzing wireless communication operation and maintenance data can be executed by a system for analyzing wireless communication operation and maintenance data, which can be implemented by software and / or hardware, and can be configured in a device for analyzing wireless communication operation and maintenance data. Optionally, a device for analyzing wireless communication operation and maintenance data can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0050] A method for analyzing wireless communication operation and maintenance data provided in the embodiments of the present invention specifically includes the following steps:

[0051] Step 1: In all sub-regions of the wireless communication operation and maintenance area, perform high-frequency similarity analysis on the service traffic value data of each historical period, and construct a high-frequency similarity analysis sub-region set (the first set) from the data analyzed in each period.

[0052] In some embodiments, divide the wireless communication operation and maintenance analysis area into several analysis sub-regions, and obtain the historical service traffic value data of each analysis area.

[0053] Among them, the service traffic value is a quantitative index for measuring the service transmission volume in a wireless communication network, reflecting the amount of various service data passing through the network within a specific time period. The acquisition methods include but are not limited to: network device statistics, service platform data interfaces.

[0054] Set an analysis period, and divide the analysis period into several analysis periods. Among them, the analysis period and the analysis periods are set by those skilled in the art. Generally, the analysis period is set to 24h (that is, every day), and the analysis periods are set to 2h, 4h.

[0055] Based on all analysis sub-regions, in any one analysis period of the same analysis period, use the Chebyshev distance method to judge similar analysis sub-regions. The specific process is as follows:

[0056] Assume there are N analysis sub - regions in total. For the i - th analysis sub - region, the sequence of service traffic values during the analysis period is: , where m is the number of historical service traffic values during the analysis period;

[0057] Exemplarily, assume that for the wireless communication operation and maintenance data analysis of the central business district of a city, this area is divided into 8 analysis sub - regions, namely sub - region 1 (the first office building), sub - region 2 (the first office building), sub - region 3 (shopping mall), sub - region 4 (restaurant concentration area), sub - region 5 (hotel), sub - region 6 (bank branch area), sub - region 7 (cafe block), sub - region 8 (park green space), then N = 8;

[0058] Set the analysis period as one day (24 hours), and the analysis time period is set to 2 hours, then there are 12 analysis time periods (0 - 2 hours, 2 - 4 hours, ……, 22 - 24 hours). The service traffic value data of each analysis sub - region in each analysis time period for the past 15 days (15 analysis periods) are collected. Assume that the number of historical service traffic values m in each analysis time period is 2 (that is, the service traffic value is recorded once per hour);

[0059] For any two analysis sub - regions i and j, calculate the Chebyshev distance , where the Chebyshev distance calculation formula is: , by looping through all combinations of analysis sub - regions, construct a Chebyshev distance matrix D of N, where represents the Chebyshev distance between analysis sub - regions i and j during the analysis time period, 、 respectively represent the service traffic value of the k - th sampling point in the analysis time period of the i - th analysis sub - region and the service traffic value of the k - th sampling point in the analysis time period of the j - th analysis sub - region;

[0060] The Chebyshev distance focuses on the maximum difference between the service traffic value sequences of two analysis sub - regions at corresponding positions. This enables, when judging similar analysis sub - regions, not to be masked by the overall average difference for local significant differences, and can accurately reflect the difference degree of the service traffic change patterns between sub - regions in extreme cases, thereby accurately screening out sub - regions with similar service traffic change characteristics;

[0061] Set a distance threshold, loop through the Chebyshev distance matrix D. If , then mark analysis sub - regions i and j as having similar changes during this analysis time period, and the analysis sub - regions with similar changes can be grouped and stored in a set;

[0062] Exemplarily, for the analysis time period t, the set storing the combination of similar analysis sub - regions is ;

[0063] After processing all analysis time periods according to the above steps, a set of similar analysis sub-regions (the fourth set) corresponding to each analysis time period is obtained;

[0064] Based on any one analysis time period, obtain the sets of similar analysis sub-regions for all analysis cycles. For any one set of similar analysis sub-regions, obtain the number of occurrences of the analysis sub-regions included in the set of similar analysis sub-regions, and calculate the ratio with the total number of analysis cycles to obtain the proportion of occurrences;

[0065] Set a threshold for the proportion of occurrences. Mark the analysis sub-regions with a proportion of occurrences greater than or equal to the threshold as high-frequency similar sub-regions, otherwise, mark them as non-high-frequency similar sub-regions;

[0066] Obtain the set of high-frequency similar analysis sub-regions and mark it as the set of high-frequency similar analysis sub-regions for this analysis time period;

[0067] Obtain the sets of all high-frequency similar analysis sub-regions for each analysis time period;

[0068] Exemplarily, taking the analysis time period "10 - 12 o'clock" as an example, after calculation, the combination of similar analysis sub-regions is: , and store it in the corresponding set ;

[0069] For the analysis time period "10 - 12 o'clock", count the sets of similar analysis sub-regions for the past 15 analysis cycles;

[0070] Suppose that in these 15 cycles, the set of similar analysis sub-regions containing sub-region 1 appears 12 times, the set of similar analysis sub-regions containing sub-region 2 appears 10 times, the set of similar analysis sub-regions containing sub-region 3 appears 8 times, and the set of similar analysis sub-regions containing sub-region 5 appears 6 times;

[0071] Then the proportion of occurrences of sub-region 1 is 80%; the proportion of occurrences of sub-region 2 is 67%; the proportion of occurrences of sub-region 3 is 53%; the proportion of occurrences of sub-region 5 is 40%;

[0072] Based on the threshold of the proportion of occurrences again, sub-region 1 and sub-region 2 are marked as high-frequency similar sub-regions, and sub-region 3 and sub-region 5 are marked as non-high-frequency similar sub-regions;

[0073] After the above steps, the set of high-frequency similar analysis sub-regions for the analysis time period "10 - 12 o'clock" is {1, 2};

[0074] For the remaining 11 analysis time periods, the above process is carried out for each to obtain all high-frequency similar analysis sub-region sets for each analysis time period. For example, the high-frequency similar analysis sub-region set for the analysis time period "18:00 - 20:00" may be {3, 4, 7}, and the high-frequency similar analysis sub-region set for the analysis time period "2:00 - 4:00" may be an empty set;

[0075] Based on these sets, operation and maintenance personnel can understand which areas have similar changes in wireless communication service traffic at different time periods, so as to better plan network resources and perform operation and maintenance operations;

[0076] By calculating the Chebyshev distance, screening out the high-frequency similar analysis sub-region sets, and then determining the peak time periods, operation and maintenance personnel can clearly understand the regional distribution of similar changes in service traffic at different time periods, so as to target network resource planning during the time periods when similar regions are concentrated. For example, allocate more bandwidth in advance for relevant regions and increase the base station capacity during peak time periods to improve resource utilization efficiency and ensure the stable operation of the network;

[0077] Analyzing a large amount of historical data based on the Chebyshev distance can uncover potential laws and patterns of service traffic changes in different analysis sub-regions at different time periods. These laws help operation and maintenance personnel deeply understand the usage characteristics of wireless communication networks, such as the traffic change laws of different functional areas (office buildings, shopping malls, etc.) at different times, providing a reference for long-term network optimization and development planning;

[0078] Step 2: Perform distance analysis on the high-frequency similar analysis sub-region sets for each time period, and construct adjacent analysis sub-region combinations (the second set) based on the distance analysis results;

[0079] Among them, adjacent means close or near, highlighting that although there is a relatively close distance relationship between regions in space, they are not necessarily directly adjacent;

[0080] In some embodiments, obtain the high-frequency similar analysis sub-region sets for each time period;

[0081] It should be noted that there are sets with two or more analysis sub-regions in the high-frequency similar analysis sub-region sets;

[0082] Obtain the longitude and latitude coordinates of the center points of each analysis sub-region. Among them, the acquisition methods of longitude and latitude coordinates include, but are not limited to: extracting from map data, base station positioning data, or regional planning materials through a geographic information system (GIS);

[0083] Exemplarily, for sub-regions such as office buildings and shopping malls, the longitude and latitude of the center point can be calculated according to their boundary ranges on the map;

[0084] Based on any set of high-frequency similar analysis sub-regions, calculate the distance between any two analysis regions through a distance formula;

[0085] Among them, the distance value between any two analysis regions can be calculated through the Euclidean distance. The specific formula is: , where is the central coordinate of analysis sub-region m, is the central coordinate of analysis sub-region n;

[0086] Exemplarily, if the central point coordinates of analysis sub-region m are (116.40, 39.90) and the central point coordinates of analysis sub-region n are (116.42, 39.91), substituting the coordinates into the formula can calculate the Euclidean distance between them;

[0087] For r regions in the high-frequency similar analysis sub-region set, traverse each pair of analysis sub-regions through nested loops, and store the calculated distances in an r×r Euclidean distance matrix JL, where represents the distance between region m and region n. When m = n, ;

[0088] Calculate the average value jz and standard deviation bz of the non-zero elements in the Euclidean distance matrix, and set the judgment distance threshold , where α is a proportionality coefficient, which is set by those skilled in the art according to the data characteristics and experience;

[0089] If , then mark the corresponding two analysis sub-regions as adjacent analysis sub-regions;

[0090] If , then mark the corresponding two analysis sub-regions as non-adjacent analysis sub-regions;

[0091] Respectively obtain all marked combinations of adjacent analysis sub-regions in each high-frequency similar analysis sub-region set;

[0092] The effect of judging adjacent sub-regions is that distance analysis of high-frequency similar analysis sub-regions to obtain adjacent analysis sub-regions helps to discover business traffic similar regions with spatial aggregation characteristics;

[0093] When conducting wireless communication fault troubleshooting, since adjacent analysis sub-regions may be affected by the same factors, if a region has a fault, key attention can be paid to the adjacent regions to pre-check and prevent the spread of the fault in advance, improving the reliability and stability of the network;

[0094] The technical solution of this embodiment is as follows: divide the wireless communication operation and maintenance analysis area into several sub-areas, set the analysis period and time period, collect the historical service traffic value data of each sub-area, construct a distance matrix using the Chebyshev distance method, set a distance threshold to screen out similar analysis sub-area combinations, and then determine the high-frequency similar analysis sub-area set by calculating the proportion of occurrence times, so as to clarify the areas with similar changes in service traffic at different time periods. Then, based on the high-frequency similar analysis sub-area set in Step 1, extract the set containing two or more sub-areas, obtain the longitude and latitude coordinates of the center points of each sub-area, calculate the distance using the Euclidean distance formula, and mark the adjacent analysis sub-area combinations by setting a judgment distance threshold.

[0095] Based on the above process, it can help operation and maintenance personnel clearly master the distribution of areas with similar service traffic at different time periods, provide a basis for accurately planning network resources, improve resource utilization efficiency, ensure network stability, and can also discover the rules and patterns of service traffic changes, providing a reference for the long-term optimization and development planning of the network.

[0096] At the same time, by discovering the areas with similar service traffic with spatial aggregation characteristics, it solves the problems such as unclear service traffic distribution, lack of pertinence in network resource planning, and low fault troubleshooting efficiency in the wireless communication network to a certain extent, and helps the wireless communication operation and maintenance work to be carried out more efficiently.

[0097] Embodiment Two

[0098] Based on the above embodiment, as Figure 1 shown, a wireless communication operation and maintenance data analysis method provided by an embodiment of the present invention specifically includes the following steps:

[0099] Step Three: Based on the adjacent analysis sub-area combinations, conduct an impact analysis on the analysis sub-areas in the adjacent analysis sub-area combinations, and construct an interactive impact analysis sub-area combination (the third set) through the impact analysis results.

[0100] In some embodiments, obtain all the marked adjacent analysis sub-area combinations in each set of analysis sub-areas to be judged.

[0101] Based on any one of the adjacent analysis sub-area combinations, count the number of analysis time periods in which these two adjacent analysis sub-areas appear in the high-frequency similar analysis sub-area set, and calculate the ratio with the total number of analysis time periods to obtain the regional similarity ratio.

[0102] Calculating the regional similarity ratio is to measure the similarity degree of adjacent analysis sub-areas in the service traffic change pattern, so as to provide a basis for evaluating the degree of mutual influence between them. In the wireless communication operation and maintenance scenario, areas with similar service traffic change patterns are more likely to influence each other in terms of network performance, service usage, etc.

[0103] Calculate the distance value between these two adjacent analysis sub-regions and calculate the ratio with the judgment distance threshold to obtain the regional distance ratio;

[0104] Calculating the regional distance ratio is to introduce the spatial distance factor for quantitative consideration when evaluating the mutual influence degree of adjacent analysis sub-regions. In wireless communication operation and maintenance, the spatial distance is one of the important factors affecting the mutual influence between regions. The smaller the regional distance ratio, the closer the two adjacent analysis sub-regions are in space. Under the same other conditions, the possibility and degree of their mutual influence are usually greater;

[0105] When calculating the relevant influence degree value, the regional distance ratio, as one of the key parameters, is operated with other data values to help comprehensively evaluate the mutual influence degree of adjacent analysis sub-regions, and then more accurately determine the combination of mutual influence analysis sub-regions, providing an important quantitative basis for subsequent operation and maintenance work such as network optimization;

[0106] Count the analysis time periods when these two adjacent analysis sub-regions appear in the high-frequency similar analysis sub-region set and obtain the corresponding service traffic value data;

[0107] For each analysis time period, use the mutual information correlation coefficient to calculate the correlation degree value of the change in service traffic value data between the two analysis sub-regions. The calculation process is as follows:

[0108] The service traffic values of two analysis sub-regions A and B. The service traffic value of analysis sub-region A is and the service traffic value of analysis sub-region B is , where k represents the number of service traffic values;

[0109] The calculation formula of the mutual information correlation coefficient:

[0110] ;

[0111] The calculated mutual information correlation coefficient is the correlation degree value. Perform mean processing on the correlation degree values corresponding to all analysis cycles in the same analysis time period to obtain the correlation degree mean value of one analysis time period;

[0112] Perform mean processing on the correlation degree mean values of all analysis time periods to obtain the correlation characterization value;

[0113] Perform data processing on the regional similarity ratio xs, the regional distance ratio jz, and the correlation characterization value xg to obtain the relevant influence degree value YX;

[0114] The specific data processing formula is: , where 、 、 is a preset proportionality coefficient, which is set by implementers in this field according to experience;

[0115] The function of calculating the relevant influence degree value is as follows: it enables the operation and maintenance personnel to quickly and accurately identify the sub-region combinations with a relatively high degree of mutual influence between regions, and exclude the combinations with less influence; for the region combinations with a high degree of mutual influence, they can be regarded as a whole for resource allocation during network planning; it can effectively formulate fault troubleshooting and prevention strategies. When troubleshooting a fault in a certain region, synchronously check and prevent the regions that interact with it, discover potential fault hazards in advance, prevent the spread of faults, and improve the reliability and stability of the network;

[0116] Set the relevant influence degree threshold, and mark the adjacent analysis sub-region combinations that are greater than the relevant influence degree threshold as the mutual influence analysis sub-region combinations, otherwise, mark them as non-relevant influence analysis sub-region combinations;

[0117] Obtain all the relevant influence analysis sub-region combinations;

[0118] Step Four: Based on the mutual influence analysis sub-region combinations, conduct an influence range analysis to obtain the key analysis sub-regions;

[0119] In some embodiments, obtain all the mutual influence analysis sub-region combinations, count all the non-repeated analysis sub-regions among them, and mark them as the analysis sub-regions to be marked;

[0120] Traverse all the mutual influence analysis sub-region combinations and mark each analysis sub-region, count the number of times each analysis region is marked, and calculate the ratio of the number of times each analysis region is marked to the number of analysis sub-regions to be marked respectively to obtain the marking times ratio;

[0121] Exemplarily, if the mutual influence analysis sub-region combinations are {(A,B), (A,C), (B,D)}, then during the traversal process, A appears 2 times, B appears 2 times, C appears 1 time, and D appears 1 time;

[0122] Set the marking times ratio threshold, mark the analysis sub-regions that are greater than or equal to the marking times ratio threshold as the key analysis sub-regions, and mark the analysis sub-regions that are less than the marking times ratio threshold as the non-key analysis sub-regions;

[0123] The technical solution of this embodiment is as follows: First, obtain the adjacent analysis sub-region combinations in each set of analysis sub-regions to be judged and analyzed. For these combinations, calculate the regional similarity ratio and regional distance ratio respectively, obtain the relevant characterization values by combining the mutual information correlation coefficient, calculate the relevant influence degree values through a preset formula, screen out the mutually influential analysis sub-region combinations according to the set threshold, and then based on these combinations, count the non-repeated analysis sub-regions, traverse the combinations to count the marking times of each analysis sub-region and calculate the marking times ratio, and mark the key analysis sub-regions according to the set threshold after sorting;

[0124] It can accurately identify the mutually influential and key analysis sub-regions in the wireless communication network, so that the operation and maintenance personnel can focus on the key areas, conduct key monitoring on these key analysis sub-regions, allocate network resources more reasonably, increase bandwidth and optimize base station configuration in the key areas, etc., improve the resource utilization efficiency, and when troubleshooting, give priority to the key areas, quickly locate and solve problems, prevent the spread of faults, ensure the stable operation of the network, and can also provide a scientific basis for the long-term planning and optimization of the network based on the service traffic characteristics and mutual influence relationships of the key areas, and promote the continuous development of the wireless communication network.

[0125] Embodiment III

[0126] Based on the above embodiments, as Figure 1 shown, a method for analyzing wireless communication operation and maintenance data provided by an embodiment of the present invention specifically includes the following steps:

[0127] Step Five: Construct a service traffic prediction model through the historical service traffic value data of the key analysis sub-regions, predict the service traffic value data, and identify the peak analysis period;

[0128] In some embodiments, obtain the key analysis sub-regions and obtain the corresponding historical service traffic value data;

[0129] Based on any key analysis sub-region, select a suitable prediction model according to the characteristics of the data and the analysis requirements to construct a service traffic prediction model;

[0130] Among them, selecting a suitable prediction model includes but is not limited to: Long Short-Term Memory Network (LSTM), Seasonal Autoregressive Integrated Moving Average model (SARIMA);

[0131] Taking the selection of the LSTM model as an example, the preprocessed data is divided into a training set and a test set according to a certain ratio, such as 70% as the training set and 30% as the test set;

[0132] Determine the structure and parameters of the LSTM model, including but not limited to: the number of hidden layers, the number of neurons, the learning rate, the number of iterations;

[0133] Input the training set data into the LSTM model for training. The model continuously adjusts the weights and biases through the backpropagation algorithm to minimize the error between the predicted value and the actual value;

[0134] During the training process, the early stopping method can be used to prevent overfitting, that is, stop training when the performance of the model on the validation set no longer improves;

[0135] Use the test set data to evaluate the trained model and calculate the evaluation metrics. The evaluation metrics include but are not limited to: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE);

[0136] If the model evaluation result is not ideal, try to adjust the model parameters. The model parameters include but are not limited to: increasing the number of neurons in the hidden layer, adjusting the learning rate;

[0137] Until a business traffic prediction model with satisfactory performance metrics is obtained;

[0138] Based on the business traffic prediction model, predict the business traffic value data for the next analysis period to obtain a sequence of business traffic prediction value data;

[0139] Extract the number of business traffic prediction values greater than the business traffic limit value, and perform a ratio process with the total number of business traffic prediction values to obtain the proportion of high business traffic value numbers;

[0140] Among them, the business traffic limit value is set by implementers in this field based on historical business traffic values and operation and maintenance work experience;

[0141] Calculate the difference between the business traffic prediction values greater than the business traffic limit value and the business traffic limit value respectively, and perform an average process to obtain a value for ratio calculation with the business traffic limit value to obtain the high business traffic degree value;

[0142] Multiply the proportion of high business traffic value numbers by the high business traffic degree value to obtain the peak characterization value;

[0143] Set a peak characterization threshold, and mark the key analysis sub - regions greater than the peak characterization threshold as peak analysis sub - regions, whose analysis period is the peak analysis period, otherwise, it is a non - peak analysis period;

[0144] Based on the peak analysis sub - regions, obtain other analysis sub - regions in their combination of mutually influencing analysis sub - regions, and perform real - time monitoring on these analysis sub - regions and the peak analysis sub - regions;

[0145] Real-time monitoring of other analysis sub-regions in the mutual influence analysis sub-region combination of the peak analysis sub-region can detect network failures that may be caused by business traffic peaks in advance. Since there are mutual influence relationships between these regions, the high traffic in the peak analysis sub-region may be transmitted to other regions, triggering a chain reaction. Real-time monitoring helps operation and maintenance personnel detect abnormalities in a timely manner, take measures to prevent the spread of faults, improve the reliability and stability of the network, and reduce the impact on users caused by network failures;

[0146] At the same time, implementers in this field can also set the monitoring frequency of the analysis regions that interact with the peak analysis sub-region according to the relevant influence degree values between the peak analysis sub-region and the analysis regions that interact with it. For example, if the relevant influence degree value is small, a larger monitoring frequency is set; if the relevant influence degree value is large, a smaller monitoring frequency is set;

[0147] The technical solution of this embodiment is as follows: Obtain the key analysis sub-region and its historical business traffic value data, select a suitable model according to the data characteristics and analysis requirements, construct a business traffic prediction model, use this model to predict the traffic data in the next analysis period, calculate the proportion of the number of high business traffic values and the high business traffic degree value, and then obtain the peak characterization value. Compare it with the peak characterization threshold to identify the peak analysis sub-region and its cycle. Finally, conduct real-time monitoring on the peak analysis sub-region and other analysis sub-regions in the combination of its mutual influence analysis sub-regions;

[0148] Thus, it is possible to predict and identify the peak analysis sub-region and its cycle, provide a basis for the forward-looking allocation of network resources. At the same time, real-time monitoring of relevant regions can promptly detect and prevent the spread of network failures caused by business traffic peaks, reduce the impact of network failures on users, improve the reliability and stability of the network, and help the operation and maintenance work of wireless communication networks to be carried out more efficiently and intelligently, meeting the growing network service needs of users.

[0149] Embodiment 4

[0150] Based on the above embodiments, as Figure 2 shown, a wireless communication operation and maintenance data analysis system provided by an embodiment of the present invention specifically includes:

[0151] Similarity recognition module: Obtain the business traffic value data of each analysis sub-region in the wireless communication operation and maintenance analysis region from historical data, and conduct time period analysis to obtain the set of high-frequency similar analysis sub-regions for each time period;

[0152] Proximity recognition module: Based on the set of high-frequency similar analysis sub-regions for each time period, conduct distance analysis on the high-frequency similar analysis sub-regions to obtain the combination of adjacent analysis sub-regions;

[0153] Influence recognition module: Based on the combination of adjacent analysis sub-regions, analyze the mutual influence relationship, evaluate the degree of mutual influence of adjacent analysis sub-regions, and obtain the combination of mutual influence analysis sub-regions;

[0154] Key recognition module: Based on the combination of mutual influence analysis sub-regions, conduct analysis, and obtain key analysis sub-regions;

[0155] Prediction recognition module: Based on the historical business traffic value data of key analysis sub-regions, construct a business traffic prediction model, predict the business traffic value data, and identify the peak analysis period

[0156] In the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0158] The above has detailed one embodiment of the present invention, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for analyzing wireless communication operation and maintenance data, characterized in that, It includes the following steps: In all sub - regions of the wireless communication operation and maintenance area, perform high - frequency similarity analysis on the historical business traffic value data for each period, and construct a first set from the data analyzed for each period; The process of obtaining the first set is as follows: Set an analysis period composed of multiple periods. For any period in the same analysis period; judge the similarity of each period by the Chebyshev distance method, construct a fourth set based on the similarity results; obtain all different sub - regions included in all fourth sets, and calculate the proportion of the occurrence times of each sub - region; Obtain all sub - regions with an occurrence proportion greater than or equal to the occurrence proportion threshold, and construct the first set for this period; Perform distance analysis on the first set of each period, and construct a second set through the distance analysis results; The process of obtaining the second set is as follows: for each first set, calculate the distances between any two analysis sub-regions in the first set and construct an Euclidean distance matrix; calculate the average value jz and the standard deviation bz of the non-zero elements in the Euclidean distance matrix. If , then it is marked as an adjacent analysis sub-region combination, where α is a proportionality coefficient. Perform impact analysis on the sub - regions in the second set, construct a third set through the impact analysis results, and perform impact range analysis on the sub - regions in the third set to obtain key sub - regions; The process of obtaining the third set is as follows: Perform data analysis on the sub - regions in the second set to obtain relevant impact degree values, obtain the combinations of sub - regions in the second set with values greater than the relevant impact degree threshold, and mark them as the third set; The process of obtaining key sub - regions is as follows: Combine the non - repeating sub - regions in the third set and mark them as sub - regions to be marked and analyzed; traverse all combinations of sub - regions in the third set and mark each sub - region, respectively count the number of times each sub - region is marked, calculate the ratio with the number of sub - regions to be marked and analyzed to obtain the marking times ratio; mark the analysis sub - regions with a marking times ratio greater than or equal to the marking times ratio threshold as key sub - regions.

2. The method for analyzing wireless communication operation and maintenance data according to claim 1, wherein The process of obtaining the relevant impact degree value is as follows: Calculate the proportion of the number of periods in which the sub - region combination in the second set appears in the first set, and obtain the sub - region similarity proportion; Calculate the ratio of the distance value of the sub - region combination in the second set to the judgment distance threshold to obtain the sub - region distance ratio; Calculate the relevant characterization value of the sub - region combination in the second set; For each period, use the mutual information correlation coefficient to calculate the relevant degree value of the change in business traffic value data between two sub - regions; Perform mean processing on the relevant degree values corresponding to all analysis periods in the same period, and then perform mean processing on the relevant degree means of all analysis periods to obtain the relevant characterization value; Calculate the relevant impact degree value through the sub - region similarity proportion, sub - region distance ratio, and relevant characterization value.

3. A method for analyzing wireless communication operation and maintenance data according to claim 1, characterized in that It also includes: Construct a business traffic prediction model through the historical business traffic value data of key sub - regions, predict the business traffic value data, and identify the peak analysis period.

4. A method for analyzing wireless communication operation and maintenance data according to claim 3, characterized in that, The process of obtaining the identified peak analysis period is as follows: Construct a business traffic prediction model for each key analysis sub - region and obtain a sequence of business traffic prediction value data; Calculate the proportion of the number of business traffic prediction values greater than the business traffic limit; Calculate the difference between all business traffic prediction values greater than the business traffic limit and the business traffic limit respectively, perform mean processing, and then calculate the ratio with the business traffic limit to obtain the high business traffic degree value; Calculate the proportion of the number of high service traffic values and the high service traffic degree value to obtain a peak characterization value, and mark the analysis period corresponding to the key analysis sub-region greater than the peak characterization threshold as the peak analysis period.

5. A wireless communication operation and maintenance data analysis system, characterized in that, The system is used to execute the method described in any one of claims 1-4 above. The system includes: Similarity recognition module: In all sub-regions of the wireless communication operation and maintenance area, perform high-frequency similarity analysis on the service traffic value data of each historical period, and construct a first set from the data analyzed in each period; Distance recognition module: Perform distance analysis on the first set of each period, and construct a second set through the distance analysis results; Influence and key recognition module: Perform influence analysis on the sub-regions in the second set, construct a third set through the influence analysis results, and perform influence range analysis on the sub-regions in the third set to obtain key sub-regions.

Images