Data processing method and device, computer device and storage medium

Abstract

The application relates to a data processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a simulation measurement data set and an existing network measurement data set; determining a frequency domain difference value and a time domain difference value between the simulation measurement data set and the existing network measurement data set, and determining a total difference value between the existing network measurement data set and the simulation measurement data set according to the frequency domain difference values and the time domain difference values; and in the case that the total difference value is greater than or equal to a preset total difference value threshold, optimizing the simulation measurement data set to obtain a target simulation measurement data set. The method can improve the accuracy of the target simulation measurement data set.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] During the construction and optimization of base stations, to ensure that the network meets user experience requirements under various service scenarios, operators typically need to evaluate signal strength, interference conditions, and service performance at different locations in the measurement area based on a large amount of existing network measurement data, thereby determining the base station layout and configuration parameters. However, in actual measurement processes, only a portion of the existing network measurement dataset in the measurement area can usually be obtained. Therefore, it is necessary to generate simulated measurement datasets for the remaining parts of the measurement area through data processing methods, and determine the base station layout and configuration parameters based on the simulated measurement datasets and the existing network measurement datasets.

[0003] Current data processing methods use path loss models in simulation tools to calculate simulation parameter vectors containing base station transmit power, antenna model, and terrain propagation model loss parameters, thus obtaining simulated measurement datasets.

[0004] However, current data processing methods, which rely solely on path loss models to calculate simulated measurement datasets, lack sufficient accuracy, resulting in low precision of the simulated measurement datasets. Therefore, a method to optimize simulated measurement datasets is urgently needed. Summary of the Invention

[0005] Therefore, it is necessary to provide a data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0006] In a first aspect, this application provides a data processing method, including:

[0007] Obtain the simulated measurement dataset and the live network measurement dataset;

[0008] Determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences;

[0009] If the total difference is greater than or equal to a preset total difference threshold, the simulated measurement dataset is optimized to obtain the target simulated measurement dataset.

[0010] In one embodiment, determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset includes:

[0011] For each indicator in the simulated measurement dataset, the corresponding real measurement data sequence is determined in the live network measurement dataset.

[0012] The frequency domain difference between the simulated measurement data sequence and the real measurement data sequence under the specified index is determined based on the frequency domain difference algorithm.

[0013] The time-domain difference between the simulated measurement data sequence and the real measurement data sequence under the specified index is determined by using a time-domain coefficient algorithm and dynamic programming.

[0014] In one embodiment, determining the frequency domain difference between the simulated measurement data sequence and the real measurement data sequence under the index according to the frequency domain difference algorithm includes:

[0015] Perform a discrete Fourier transform on the actual measurement data sequence under the aforementioned index to obtain the true frequency domain characteristics of the actual measurement data sequence;

[0016] Perform a discrete Fourier transform on the simulated measurement data sequence of the index to obtain the simulated frequency domain characteristics of the simulated measurement data sequence;

[0017] According to the frequency domain difference algorithm, the real frequency domain features and the simulated frequency domain features are processed to obtain the frequency domain difference.

[0018] In one embodiment, determining the time-domain difference between the simulated measurement data sequence and the real measurement data sequence under the specified index using a time-domain coefficient algorithm and dynamic programming includes:

[0019] A local distance matrix is ​​constructed based on the simulated measurement data sequence and the real measurement data sequence;

[0020] The bending distance is determined in the local distance matrix by dynamic programming; the bending distance characterizes the similarity between the real measurement data sequence and the simulated measurement data sequence after a moderately nonlinear transformation along the time axis.

[0021] According to the time-domain coefficient algorithm, the real measurement data sequence and the simulated measurement data sequence are processed to obtain the time-domain correlation value between the real measurement data sequence and the simulated measurement data sequence;

[0022] The time-domain difference of the index is determined based on the time-domain correlation value and the bending distance.

[0023] In one embodiment, determining the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences includes:

[0024] The comprehensive difference of the indicators is determined based on the frequency domain difference and time domain difference of each indicator;

[0025] Based on the weights of each indicator, the comprehensive difference between each indicator is weighted to obtain the total difference between the live network measurement dataset and the simulated measurement dataset.

[0026] In one embodiment, optimizing the simulated measurement dataset to obtain a target simulated measurement dataset when the total difference is greater than or equal to a preset total difference threshold includes:

[0027] If the total difference is greater than or equal to a preset total difference threshold, update the simulation parameter vector;

[0028] An optimized simulation measurement dataset is generated using simulation tools and updated simulation parameter vectors;

[0029] Perform the steps of determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset until the total difference is less than the total difference threshold, and then determine the simulated measurement dataset as the target simulated measurement dataset.

[0030] Secondly, this application also provides a data processing apparatus, comprising:

[0031] The acquisition module is used to acquire simulated measurement datasets and live network measurement datasets;

[0032] The determination module is used to determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and to determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences;

[0033] An optimization module is used to optimize the simulated measurement dataset to obtain a target simulated measurement dataset when the total difference is greater than or equal to a preset total difference threshold.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0035] Obtain the simulated measurement dataset and the live network measurement dataset;

[0036] Determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences;

[0037] If the total difference is greater than or equal to a preset total difference threshold, the simulated measurement dataset is optimized to obtain the target simulated measurement dataset.

[0038] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0039] Obtain the simulated measurement dataset and the live network measurement dataset;

[0040] Determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences;

[0041] If the total difference is greater than or equal to a preset total difference threshold, the simulated measurement dataset is optimized to obtain the target simulated measurement dataset.

[0042] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0043] Obtain the simulated measurement dataset and the live network measurement dataset;

[0044] Determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences;

[0045] If the total difference is greater than or equal to a preset total difference threshold, the simulated measurement dataset is optimized to obtain the target simulated measurement dataset.

[0046] The aforementioned data processing method, apparatus, computer equipment, storage medium, and computer program product acquire simulated measurement datasets and live network measurement datasets. The simulated measurement datasets contain simulated measurement data sequences for each indicator; the live network measurement datasets contain actual measurement data sequences for each indicator. The method determines the frequency domain difference and time domain difference between each simulated measurement data sequence and each actual measurement data sequence. Based on the frequency domain difference and the time domain difference, it determines the total difference between the live network measurement data and the simulated measurement data. If the total difference is greater than or equal to a preset total difference threshold, the method optimizes the simulated measurement dataset and executes the steps of determining the frequency domain difference and time domain difference between each simulated measurement data sequence and each actual measurement data sequence until the total difference is less than the total difference threshold. This method determines the total difference between the live network measurement dataset and the simulated measurement dataset from both time and frequency domain perspectives. When the total difference is greater than or equal to the total difference threshold, the method optimizes the simulated measurement dataset, making it continuously approach the actual live network measurement dataset until the total difference is less than the total difference threshold. At this point, the difference between the target simulation measurement dataset and the existing network measurement dataset is small, which improves the accuracy of the target simulation measurement dataset and, consequently, the accuracy of the data processing method. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating a data processing method in one embodiment;

[0048] Figure 2 This is a flowchart illustrating the process of determining the time-domain difference and the frequency-domain difference in one embodiment;

[0049] Figure 3 This is a flowchart illustrating the process of determining the frequency domain difference in one embodiment;

[0050] Figure 4 This is a flowchart illustrating the process of determining the time-domain difference in one embodiment;

[0051] Figure 5 This is a flowchart illustrating the process of determining the total difference in one embodiment;

[0052] Figure 6 This is a flowchart illustrating the process of determining a target simulation measurement dataset in one embodiment;

[0053] Figure 7 This is a schematic diagram of the architecture of a data processing method in an exemplary embodiment;

[0054] Figure 8 This is a structural block diagram of a data processing device in one embodiment;

[0055] Figure 9This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] In one embodiment, such as Figure 1 As shown, a data processing method is provided. This application embodiment uses the application of this method to a computer device as an example for illustration. This application embodiment does not limit the execution device for data processing, and includes the following steps 102 to 106:

[0058] Step 102: Obtain the simulated measurement dataset and the live network measurement dataset.

[0059] In implementation, the computer equipment is pre-configured with simulation tools. The computer equipment acquires simulation parameter vectors and uses the simulation tools to simulate these vectors, obtaining a simulated measurement dataset. Then, the computer equipment acquires the live network measurement dataset.

[0060] Specifically, the simulation parameter vector includes base station transmit power, antenna model, and terrain propagation model parameters. The simulation parameter vector... As shown in the following formula (1):

[0061] =( ,…)(1)

[0062] In the above formula (1), This refers to the base station's transmit power, typically measured in units of 1000 kJ / m². (decibels and milliwatts). The antenna model can also be represented as , indicating the horizontal angle and vertical angle Antenna gain (unit: dBi (unit of power gain)). Gain variations in different directions can be described using antenna patterns or gain coefficients. These are the parameters for the terrain propagation model, mainly referring to the various coefficients in the path loss formula, such as the path loss index. Standard deviation of shadow fading Scattering and fading characteristics, etc. Common models used in actual simulations include COST231 (an empirical model for predicting radio wave propagation path loss), Okumura-Hata (an empirical propagation model), or the 3GPP (Third Generation Partnership Project) standard model. The simulation parameter vector is pre-set in the computer device. The computer device obtains the simulation vector parameters based on the simulation vector model. Then, the computer device inputs the simulation vector parameters into the simulation tool, which generates a simulated measurement dataset. The computer device then obtains the live network measurement dataset. Both the simulated and live network measurement datasets contain measurement data sequences for each indicator. The simulated measurement dataset contains simulated measurement data sequences for each indicator, while the live network measurement dataset contains actual measurement data sequences for each indicator. In one example, the indicators are the reference signal received power indicator, the reference signal received quality indicator, and the signal-to-interference-plus-noise ratio indicator. That is, the simulated measurement dataset contains simulated measurement data sequences for the reference signal received power indicator, the reference signal received quality indicator, and the signal-to-interference-plus-noise ratio indicator. The live network measurement dataset contains actual measurement data sequences for the reference signal received power indicator, the reference signal received quality indicator, and the signal-to-interference-plus-noise ratio indicator.

[0063] In an exemplary embodiment, before installing base stations in the area to be measured, the administrator needs to measure the area to obtain a large amount of measurement data, thereby determining the layout and configuration parameters of the base stations based on the measurement data. However, due to terrain or the coverage signal of other base stations, only a portion of the existing network measurement dataset in the area to be measured can be obtained. The administrator then inputs the existing network measurement dataset into a computer device, allowing the computer device to acquire the dataset. The computer device then displays a simulation parameter vector template. This template includes the initial base station transmit power, the initial antenna model, and various initial terrain propagation models. The computer device obtains the base station transmit power input by the administrator based on the initial base station transmit power, and the antenna model input by the administrator based on the initial antenna model. The computer device determines the terrain propagation model from each initial terrain propagation model and obtains the terrain propagation model parameters input by the administrator for that model. Then, the computer device constructs a simulation parameter vector based on the base station transmit power, antenna model, and terrain propagation model parameters, and inputs this vector into a preset simulation tool to obtain a simulated measurement dataset. The set of indicators in the simulated measurement dataset and the existing network measurement dataset is: m∈{RSRP, RSRQ, SINR}. RSRP is the reference signal received power, RSRQ is the reference signal received quality, and SINR is the signal-to-interference-plus-noise ratio. The actual measurement data sequence of each indicator in the current network measurement dataset is shown in the following formula (2):

[0064] (2)

[0065] In the above formula (2), Indicators The actual measurement data sequence, The measurement time refers to when the actual measurement data sequence was obtained. To measure the total cycle.

[0066] The simulated measurement data sequence for each indicator in the simulated measurement dataset is shown in the following formula (3):

[0067] , t=1,2,…,T(3)

[0068] In the above formula (3), Indicators The simulated measurement data sequence, The measurement time refers to when the actual measurement data sequence was obtained. The simulation parameter vector is the vector corresponding to the simulated measurement data sequence, that is, it is composed of the simulation parameter vector. The generated sequence of simulated measurement data. To measure the total cycle.

[0069] In an optional embodiment, to facilitate alignment and comparison, it is necessary to ensure that the real measurement data sequence and the simulated measurement data sequence are at the same time scale or at least have the same sampling rate. If the sampling rates are different, interpolation or downsampling can be performed on either the real or simulated measurement data sequence to obtain a consistent sampling sequence length.

[0070] Optionally, the simulation tool may be, but is not limited to, OMNeT++ (an object-oriented modular discrete event simulation environment) or Network Simulator 3 (a discrete event network simulator). This application embodiment does not limit the simulation tool.

[0071] Step 104: Determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each frequency domain difference and each time domain difference.

[0072] The simulated measurement dataset contains simulated measurement data sequences for each indicator (measurement indicator). The live network measurement dataset contains actual measurement data sequences for each indicator (measurement indicator).

[0073] In implementation, the computer equipment determines the frequency domain difference and time domain difference between the simulated measurement data sequence and the actual measurement data sequence for each indicator. Then, based on the frequency domain difference and time domain difference of each indicator, the computer equipment determines the comprehensive difference of that indicator, and determines the total difference based on the comprehensive difference of all indicators.

[0074] Specifically, for each indicator, the computer equipment determines the actual measurement data sequence and the simulated measurement data sequence under that indicator. Then, based on a frequency domain difference algorithm, the computer equipment determines the frequency domain difference between the actual and simulated measurement data sequences under that indicator. Next, based on a time domain coefficient algorithm and dynamic programming, the computer equipment determines the time domain difference between the simulated and actual measurement data sequences under that indicator. Finally, based on the time domain difference and the frequency domain difference, the computer equipment determines the comprehensive difference between the actual and simulated measurement data sequences under that indicator. The computer equipment then performs a weighted average of the comprehensive differences for each indicator to obtain the total difference between the live network measurement dataset and the simulated measurement dataset.

[0075] Step 106: If the total difference is greater than or equal to the preset total difference threshold, optimize the simulated measurement dataset to obtain the target simulated measurement dataset.

[0076] In implementation, a total difference threshold is pre-set in the computer equipment. The computer equipment determines whether the total difference is less than the total difference threshold. If the total difference is greater than or equal to the total difference threshold, the computer equipment optimizes the simulation parameter vector and generates an optimized simulated measurement dataset based on the optimized simulation parameter vector. Then, the computer equipment continues to execute step 104 above until the total difference is less than the total difference threshold. The computer equipment then determines the simulated measurement dataset as the target simulated measurement dataset.

[0077] In an optional embodiment, if the total difference is less than a total difference threshold, the computer device directly determines the simulated measurement dataset as the target simulated measurement dataset and the simulation parameter vector corresponding to the simulated measurement dataset as the target simulation parameter vector. Administrators then determine the location and parameters of the base station based on the target simulation parameter vector, the target simulated measurement dataset, and the existing network measurement dataset.

[0078] Optionally, the total difference threshold is determined according to the optimization requirements. This application embodiment does not limit the total difference threshold.

[0079] In the aforementioned data processing method, the total difference between the live network measurement dataset and the simulated measurement dataset is determined from both time and frequency domain perspectives. If the total difference is greater than or equal to a threshold, the simulated measurement dataset is optimized to continuously approximate the actual live network measurement dataset until the total difference falls below the threshold. At this point, the difference between the target simulated measurement dataset and the live network measurement dataset is small, improving the accuracy of the target simulated measurement dataset and thus enhancing the accuracy of the data processing method.

[0080] In one embodiment, such as Figure 2As shown, the specific processing steps for determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset in step 104 include steps 202 to 206. Wherein:

[0081] Step 202: For the simulated measurement data sequence of each indicator in the simulated measurement dataset, determine the actual measurement data sequence corresponding to the simulated measurement data sequence in the live network measurement dataset.

[0082] The simulated measurement dataset contains simulated measurement data sequences for each indicator, while the live network measurement dataset contains actual measurement data sequences for each indicator.

[0083] In implementation, the computer equipment determines the actual measurement data sequence of each indicator in the live network measurement dataset for the simulated measurement data sequence in the simulated measurement dataset, and identifies the actual measurement data sequence as the actual measurement data sequence corresponding to the simulated measurement data sequence.

[0084] In one exemplary embodiment, the simulated measurement dataset includes a simulated measurement data sequence of a reference signal received power index, a simulated measurement data sequence of a reference signal received quality index, and a simulated measurement data sequence of a signal-to-interference-plus-noise ratio (SNR) index. For the simulated measurement data sequence of the reference signal received power index, the computer device determines the actual measurement data sequence of the reference signal received power index from the actual measurement dataset and identifies this actual measurement data sequence as the actual measurement data sequence corresponding to the simulated measurement data sequence. Similarly, for the simulated measurement data sequence of the reference signal received quality index, the computer device determines the actual measurement data sequence of the SNR index from the actual measurement dataset and identifies this actual measurement data sequence as the actual measurement data sequence corresponding to the simulated measurement data sequence.

[0085] Step 204: Determine the frequency domain difference between the simulated measurement data sequence and the actual measurement data sequence under the specified index, based on the frequency domain difference algorithm.

[0086] In implementation, the computer equipment extracts features from the simulated and actual measurement data sequences under this indicator, obtaining the simulated frequency domain features of the simulated measurement data sequence and the actual frequency domain features of the actual measurement data sequence. Based on a frequency domain difference algorithm, the computer equipment performs data operations on the actual and simulated frequency domain features to obtain the frequency domain difference between the simulated and actual measurement data sequences under this indicator.

[0087] Specifically, the computer equipment performs a Discrete Fourier Transform (DFT) on the actual measurement data sequence under this indicator to obtain the true frequency domain features. Simultaneously, the computer equipment performs a DFT on the simulated measurement data sequence corresponding to the true measurement data sequence to obtain the simulated frequency domain features. Then, based on a frequency domain difference algorithm, the computer equipment performs data operations on the true and simulated frequency domain features to obtain the frequency domain difference between the simulated and actual measurement data sequences under this indicator.

[0088] Step 206: Determine the time-domain difference between the simulated measurement data sequence and the actual measurement data sequence under the index using the time-domain coefficient algorithm and dynamic programming.

[0089] In implementation, the computer equipment processes the simulated and actual measurement data sequences using dynamic programming to obtain the bending distance. Then, based on a time-domain coefficient algorithm, the computer equipment determines the time-domain correlation value between the simulated and actual measurement data sequences for this indicator. Therefore, the computer equipment determines the time-domain difference between the simulated and actual measurement data sequences for this indicator based on the bending distance and the time-domain correlation value.

[0090] Specifically, the computer equipment constructs a local distance matrix based on the simulated and actual measurement data sequences. Then, it determines the bending distance within this local distance matrix using dynamic programming. Next, it performs data operations on the simulated and actual measurement data sequences using a time-domain coefficient algorithm to obtain a time-domain correlation value. Finally, it fuses the time-domain correlation value and the bending distance to obtain the time-domain difference between the simulated and actual measurement data sequences.

[0091] In this embodiment, by determining the frequency domain difference and the time domain difference respectively, the simulated measurement dataset is optimized based on the time domain difference and the frequency domain difference. This ensures that the optimized simulated measurement dataset is highly consistent with the existing network measurement dataset in terms of overall energy distribution and subtle temporal characteristics, thereby improving the data alignment efficiency and accuracy of the target simulated measurement data and thus improving the accuracy of the data processing method.

[0092] In one embodiment, such as Figure 3 As shown, the specific processing procedure of step 204 includes steps 302 to 306. Wherein:

[0093] Step 302: Perform a discrete Fourier transform on the actual measurement data sequence under the index to obtain the true frequency domain characteristics of the actual measurement data sequence.

[0094] In practice, computer equipment performs a discrete Fourier transform on the actual measurement data sequence under this indicator to extract the true frequency domain features of the actual data sequence.

[0095] Specifically, the process of performing a discrete Fourier transform on the actual measurement data sequence is shown in the following formula (4):

[0096] (4)

[0097] In the above formula (4), For the actual measurement data sequence, For the actual measurement data sequence The true frequency domain characteristics. These are discrete frequency points. This is the frequency index for the frequency point. It is the total length of the actual measurement data sequence, and also the total measurement period. It is a complex exponential function in the discrete Fourier transform.

[0098] In one exemplary embodiment, the example is a computer device performing a Discrete Fourier Transform (DFT) on a sequence of actual measured data of a reference signal received power index. The computer device performs a DFT on the actual measured data sequence of the reference signal received power index according to the DFT algorithm to obtain the actual frequency domain characteristics under the reference signal received power index.

[0099] Step 304: Perform a discrete Fourier transform on the simulated measurement data sequence of the index to obtain the simulated frequency domain characteristics of the simulated measurement data sequence.

[0100] In practice, computer equipment performs a discrete Fourier transform on the simulated measurement data sequence under this indicator to extract the simulated frequency domain characteristics of the simulated measurement data sequence.

[0101] Specifically, the process of performing a discrete Fourier transform on the simulated measurement data sequence is shown in the following formula (5):

[0102] (5)

[0103] In the above formula (5), To simulate the measurement data sequence, For simulated measurement data sequences The simulated frequency domain characteristics. These are discrete frequency points. This is the frequency index for the frequency point. It is the total length of the simulated measurement data sequence, and also the total measurement period. It is a complex exponential function in the discrete Fourier transform.

[0104] In an exemplary embodiment, the reference signal received power index is used as an example. The computer device performs a Discrete Fourier Transform on the simulated measurement data sequence of the reference signal received power index according to the Discrete Fourier algorithm to obtain the simulated frequency domain characteristics under the reference signal received power index.

[0105] Step 306: Based on the frequency domain difference algorithm, perform data processing on the real frequency domain features and the simulated frequency domain features to obtain the frequency domain difference value.

[0106] In implementation, the computer equipment determines the true amplitude spectrum of the real frequency domain features and the simulated amplitude spectrum of the simulated frequency domain features based on the frequency domain difference algorithm. Then, the computer equipment determines the amplitude spectrum difference between the true amplitude spectrum and the simulated amplitude spectrum as the frequency domain difference value. The true amplitude spectrum is shown in formula (6), and the simulated amplitude spectrum is shown in formula (7).

[0107] (6)

[0108] (7)

[0109] In the above formula (6), For the true amplitude spectrum, This represents the true frequency domain characteristics. It is the real part of the square of the true frequency domain feature. This is the imaginary part of the square of the true frequency domain feature. In the above formula (7), For virtual amplitude spectrum, This represents virtual frequency domain characteristics. Let be the real part of the square of the virtual frequency domain feature. It is the real part of the square of the virtual frequency domain feature.

[0110] In an exemplary embodiment, a reference signal received power index is used as an example. The computer device processes the true frequency domain characteristics of the reference signal received power index using a frequency domain difference algorithm to obtain the true amplitude spectrum of the reference signal received power index, and processes the analog frequency domain characteristics of the reference signal received power index to obtain the analog amplitude spectrum of the reference signal received power index. Then, the computer device determines the amplitude spectrum difference between the true amplitude spectrum and the analog amplitude spectrum as the frequency domain difference value of the reference signal received power index.

[0111] In an optional embodiment, the computer device determines the frequency domain difference of the index by the L2 norm difference between the true amplitude difference and the analog amplitude difference. The smaller the frequency domain difference, the closer the true measurement data sequence and the analog measurement data sequence are in the frequency domain.

[0112] In this embodiment, by determining the frequency domain difference between the real measurement data sequence and the simulated measurement data sequence for each index, the difference between the real measurement data sequence and the simulated measurement data sequence in the frequency domain is clarified, which facilitates the subsequent determination of the total difference.

[0113] In one embodiment, such as Figure 4 As shown, the specific processing procedure of step 206 includes steps 402 to 408. Wherein:

[0114] Step 402: Construct a local distance matrix based on the simulated measurement data sequence and the real measurement data sequence.

[0115] The simulated measurement data sequence contains each simulated measurement data, while the real measurement data sequence contains real measurement data.

[0116] In practice, computer equipment determines the distance between each simulated measurement data and each real measurement data, and constructs a local distance matrix based on each distance.

[0117] Specifically, for each simulated measurement data point, the computer device determines the local distance between that simulated measurement data point and each real measurement data point. For example, the local distance is D(i,j), where D(i,j) represents... and Local distance (e.g., local distance is | ). This represents the i-th real measurement data in the real measurement data sequence. This represents the j-th simulated measurement data in the simulated measurement data sequence. Then, the computer constructs a local distance matrix D based on each local distance.

[0118] Step 404: Determine the bending distance in the local distance matrix using dynamic programming.

[0119] Among them, the bending distance characterizes the similarity between the real measurement data sequence and the simulated measurement data sequence after a moderate nonlinear transformation of the time axis.

[0120] In practice, the computer equipment uses dynamic programming to find a path with the minimum cumulative distance in the local distance matrix, and determines the cumulative distance of this path as the curvature distance. The smaller the curvature distance, the better the two sequences match after the "time axis curvature".

[0121] Specifically, in network measurement scenarios, real measurement data sequences and simulated measurement data sequences, as time-series data, often have problems such as local time offset or incomplete sampling synchronization. Simply comparing the mean squared error (MSE) point-to-point is not flexible enough. Therefore, in order to better capture the consistency of "shape" or "trend", this application uses dynamic time warping (DTW) to evaluate the gap between simulated data and live network data. The computer device determines a path with the minimum cumulative distance from the upper left corner to the lower right corner of the local distance matrix through dynamic programming, and the cumulative distance of this path is determined as the warping distance. The warping distance is shown in the following formula (8):

[0122] (8)

[0123] In the above formula (8), For the actual measurement data sequence, This is a simulated measurement data sequence. It is a dynamic time warping function. This represents the bending distance. It's an indicator. This is represented as a simulation vector parameter. The smaller the value of the bending distance, the higher the similarity between the real and simulated measurement data sequences after a moderately nonlinear transformation along the time axis; the larger the value of the bending distance, the lower the similarity between the real and simulated measurement data sequences after a moderately nonlinear transformation along the time axis.

[0124] In an exemplary embodiment, the reference signal received power index is taken as an example, corresponding to the simulated measurement data sequence. The computer device constructs a local distance matrix based on the actual measurement data sequence and the simulated measurement data sequence under the reference signal received power index, and determines the bending distance between the simulated measurement data sequence and the actual measurement data sequence under the reference signal received power index in the local distance matrix through dynamic programming.

[0125] Step 406: Based on the time-domain coefficient algorithm, perform data processing on the real measurement data sequence and the simulated measurement data sequence to obtain the time-domain correlation value between the real measurement data sequence and the simulated measurement data sequence.

[0126] In implementation, a time-domain coefficient algorithm is incorporated into the computer equipment. Based on this algorithm, the computer equipment performs data operations on the real and simulated measurement data sequences to obtain the time-domain correlation value between them. The time-domain coefficient algorithm is shown in the following formula (9):

[0127] (9)

[0128] In the above formula (9), This is the time-domain correlation value. For located in the real measurement data sequence Actual measurement data at any given moment. This is the mean of the actual measurement data in the true measurement data series. . For the simulated measurement data sequence Simulated measurement data at any given time. This is the mean of the simulated measurement data series. .like A value close to 1 indicates excellent synchronization of the rising and falling trends between the real test data sequence and the simulated measurement data sequence, meaning the correlation between the two sequences is very strong. If... A value close to 0 indicates poor synchronization of the rising and falling trends between the real test data sequence and the simulated measurement data sequence, meaning that the correlation between the two sequences is relatively poor.

[0129] In an exemplary embodiment, taking the index corresponding to the real measurement data sequence as the reference signal received power index as an example, the computer device performs data operations on the real measurement data sequence and the simulated measurement data sequence of the reference signal received power index according to the time-domain coefficient algorithm to obtain the time-domain correlation value between the real test data sequence and the simulated measurement data sequence.

[0130] Step 408: Determine the time-domain difference of the index based on the time-domain correlation value and the bending distance.

[0131] In implementation, the computer equipment performs data calculations on the time-domain correlation value and bending distance according to the time-domain difference algorithm to obtain the time-domain difference of the index. The time-domain difference algorithm is shown in the following formula (10):

[0132] (10)

[0133] In the above formula (10), For time-domain difference, The bending distance, This represents the time-domain correlation value. As the weight of the bending distance, The weights are the time-domain correlation values. Used to measure the importance of bending distance; Weights used to measure time-domain correlation values; when When it is larger, The smaller the value, the easier it is to reduce the size. . It's an indicator. Represented as simulation vector parameters.

[0134] In an exemplary embodiment, taking the index corresponding to the real measurement data sequence as the reference signal received power index as an example, the computer device performs data calculations on the time domain correlation value and bending distance of the reference signal received power index according to the time domain difference algorithm to obtain the time domain difference of the reference signal received power index.

[0135] Optionally, the weights of the bending distance and the temporal correlation value can be set according to the data processing requirements. In this embodiment, the weights of the bending distance and the temporal correlation are not limited.

[0136] In this embodiment, by determining the time-domain difference between the real measurement data sequence and the simulated measurement data sequence for each indicator, the time-domain difference between the real measurement data sequence and the simulated measurement data sequence is clarified, which facilitates the subsequent determination of the total difference.

[0137] In one embodiment, such as Figure 5 As shown, the specific processing steps in step 104 for determining the total difference between the live network measurement dataset and the simulated measurement dataset based on the differences in each frequency domain and each time domain include steps 502 to 504. Wherein:

[0138] Step 502: Determine the comprehensive difference of the indicators based on the frequency domain difference and time domain difference of each indicator.

[0139] The overall difference of the indicator represents the difference between the actual measurement data series and the simulated measurement data series on that indicator. The larger the overall difference of the indicator, the greater the difference between the actual measurement data series and the simulated measurement data series on that indicator.

[0140] In implementation, the computer equipment performs weighted processing on the frequency domain difference and time domain difference of each indicator according to the comprehensive difference algorithm to obtain the comprehensive difference of the indicator. The comprehensive difference algorithm is shown in the following formula (11):

[0141] (11)

[0142] In the above formula (11), The combined difference, The weights for the time-domain differences, For time-domain difference, The weights are the frequency domain differences. This represents the frequency domain difference. It's an indicator. Represented as simulation vector parameters.

[0143] In an exemplary embodiment, the metrics are a reference signal received power metric, a reference signal received quality metric, and a signal-to-interference-plus-noise ratio (SNR) metric. The computer device performs weighted processing on the time-domain and frequency-domain differences of the reference signal received power metric using a comprehensive difference algorithm to obtain a comprehensive difference value for the reference signal received power metric. Simultaneously, the computer device performs weighted processing on the reference signal received quality metric using the same comprehensive difference algorithm to obtain a comprehensive difference value for the reference signal received quality metric. The computer device also performs weighted processing on the time-domain and frequency-domain differences of the signal-to-interference-plus-noise ratio (SNR) metric using the same comprehensive difference algorithm to obtain a comprehensive difference value for the SNR metric.

[0144] Optionally, the weights of the time-domain difference and the frequency-domain difference are determined according to the data processing requirements. This application embodiment does not limit the time-domain difference and the frequency-domain difference.

[0145] Step 504: Based on the weight of each indicator, perform weighted processing on the comprehensive difference of each indicator to obtain the total difference between the live network measurement dataset and the simulated measurement dataset.

[0146] In implementation, the computer equipment performs weighted processing on the comprehensive difference of each indicator according to the total difference function and the weight of each indicator, to obtain the total difference between the live network measurement dataset and the simulated measurement dataset. The total difference function is shown in the following formula (12):

[0147] (12)

[0148] In the above formula (12), This is the total difference. For a set of indicators, For indicators in the indicator set, As an indicator The overall difference As an indicator Weights. Optional. {RSRP, RSRQ, SINR}.

[0149] In an exemplary embodiment, the metrics are a reference signal received power metric, a reference signal received quality metric, and a signal-to-interference-plus-noise ratio (SNR) metric. The computer device performs weighted processing on the comprehensive difference of the reference signal received power metric according to its weight, obtaining a weighted comprehensive difference of the reference signal received power metric. Simultaneously, the computer device performs weighted processing on the comprehensive difference of the reference signal received quality metric according to its weight, obtaining a weighted comprehensive difference of the reference signal received quality metric, and also performs weighted processing on the comprehensive difference of the signal-to-interference-plus-noise ratio metric according to its weight, obtaining a weighted comprehensive difference of the signal-to-interference-plus-noise ratio metric.

[0150] Optionally, the weights of each indicator can be adjusted appropriately according to the business scenario and accuracy requirements. For example, the weight of the reference signal received power indicator is 0.5, the weight of the reference signal received quality indicator is 0.3, and the weight of the signal-to-interference-plus-noise ratio indicator is 0.2. This application does not limit the weights of each indicator in its embodiments.

[0151] In this embodiment, the total difference is obtained by weighting the time-domain and frequency-domain differences of each indicator, thus comprehensively evaluating network coverage, interference, and performance levels. Compared to simple single-indicator or single-evaluation methods, this data processing method exhibits higher robustness in complex environments.

[0152] In one embodiment, such as Figure 6 As shown, the specific processing procedure of step 106 includes steps 602 to 606. Wherein:

[0153] Step 602: If the total difference is greater than or equal to the preset total difference threshold, update the simulation parameter vector.

[0154] During implementation, if the total difference is greater than or equal to the preset total difference threshold, the computer device updates the simulation parameter vector.

[0155] Specifically, when the total difference is greater than or equal to a preset total difference threshold, the computer device adds the simulation parameter vector to the simulation parameter vector template and displays the simulation parameter vector template. Then, the computer device updates the simulation parameter vector based on the simulation parameter vector template to obtain the updated simulation parameter vector.

[0156] In an exemplary embodiment, the computer device displays a simulation vector parameter template with added simulation parameter vectors. This simulation vector parameter template includes base station transmit power, antenna model, and terrain propagation model. The computer device obtains the base station transmit power input by the administrator and updates the base station transmit power based on the input, resulting in a new transmit power. The computer device obtains the antenna model input by the administrator and updates the antenna model based on the input, resulting in a new antenna model. Then, the computer device obtains the terrain propagation model and terrain propagation model parameters input by the user and updates the terrain propagation model and terrain propagation model parameters according to the input, resulting in a new terrain propagation model and terrain propagation model parameters. The computer device then constructs an updated simulation parameter vector using the new base station transmit power, the new antenna model, the new terrain propagation model, and the terrain propagation model parameters.

[0157] In an optional embodiment, the computer device updates the simulation parameter vector using a specific optimization algorithm to obtain the updated simulation parameter vector. The specific optimization algorithm may include, for example, gradient descent, genetic algorithm, particle swarm optimization, Bayesian optimization, etc.

[0158] Step 604: Generate an optimized simulation measurement dataset using simulation tools and the updated simulation parameter vector.

[0159] In practice, the computer equipment inputs the updated simulation parameter vector into the simulation tool, which then generates an optimized simulation measurement dataset.

[0160] Step 606: Perform the steps of determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset until the total difference is less than the total difference threshold, and then determine the simulated measurement dataset as the target simulated measurement dataset.

[0161] In implementation, the computer device performs the steps of determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset until the total difference is less than a preset total difference threshold. The computer device then determines the simulated measurement dataset as the target simulated measurement data and the simulation parameter vector corresponding to the target simulated measurement data as the target simulation parameter vector. Specifically, determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset is step 104 described above. The specific processing procedure of step 104 has been described in detail in the above embodiments and will not be repeated here.

[0162] In this embodiment, when the total difference is greater than or equal to a total difference threshold, the simulated measurement dataset is optimized so that it continuously approaches the actual live network measurement dataset until the total difference is less than the total difference threshold. At this point, the difference between the target simulated measurement dataset and the live network measurement dataset is small, improving the accuracy of the target simulated measurement dataset and thus improving the accuracy of the data processing method.

[0163] In one exemplary embodiment, Figure 7 This is a schematic diagram of the architecture of a data processing method in an exemplary embodiment. For example... Figure 7 As shown, the computer device acquires a simulated measurement dataset and a live network measurement dataset. The simulated measurement dataset contains simulated measurement data sequences for the RSRP, RSRQ, and SINR indices. The live network measurement dataset contains actual measurement data sequences for the RSRP, RSRQ, and SINR indices. The computer device extracts time-series and frequency-domain features from both datasets. Then, the computer device compares the time-series features of the simulated and live network measurement datasets, and also compares their frequency-domain features to obtain a total difference. The computer device then determines whether the total difference is less than a preset threshold. If the total difference is greater than or equal to the preset threshold, the computer device optimizes the simulated measurement dataset and extracts both time-series and frequency-domain features until the total difference is less than the threshold. The computer device then designates the simulated measurement dataset as the target simulated measurement dataset.

[0164] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0165] Based on the same inventive concept, this application also provides a data processing apparatus for implementing the data processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more data processing apparatus embodiments provided below can be found in the limitations of the data processing method described above, and will not be repeated here.

[0166] In one exemplary embodiment, such as Figure 8 As shown, a data processing apparatus 800 is provided, including: an acquisition module 801, a determination module 802, and an optimization module 803, wherein:

[0167] The acquisition module 801 is used to acquire the simulated measurement dataset and the live network measurement dataset.

[0168] The determination module 802 is used to determine the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, and to determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each frequency domain difference and each time domain difference.

[0169] The optimization module 803 is used to optimize the simulated measurement dataset to obtain the target simulated measurement dataset when the total difference is greater than or equal to the preset total difference threshold.

[0170] In an exemplary embodiment, the determining module 802 includes a first determining submodule and a second determining submodule. The first determining submodule includes:

[0171] The third determination submodule is used to determine the actual measurement data sequence corresponding to the simulated measurement data sequence in the live network measurement dataset for each indicator in the simulated measurement dataset.

[0172] The fourth determination submodule is used to determine the frequency domain difference between the simulated measurement data sequence and the real measurement data sequence under the index based on the frequency domain difference algorithm.

[0173] The fifth determination submodule is used to determine the time-domain difference between the simulated measurement data sequence and the actual measurement data sequence under the index through time-domain coefficient algorithm and dynamic programming.

[0174] In one exemplary embodiment, the fourth determining submodule includes:

[0175] The first transformation submodule is used to perform discrete Fourier transform on the real measurement data sequence under the index to obtain the real frequency domain characteristics of the real measurement data sequence.

[0176] The second transformation submodule is used to perform discrete Fourier transform on the simulated measurement data sequence of the index to obtain the simulated frequency domain characteristics of the simulated measurement data sequence.

[0177] The first processing submodule is used to process the real frequency domain features and simulated frequency domain features according to the frequency domain difference algorithm to obtain the frequency domain difference value.

[0178] In one exemplary embodiment, the fifth determining submodule includes:

[0179] The first construction submodule is used to construct a local distance matrix based on the simulated measurement data sequence and the real measurement data sequence.

[0180] The sixth submodule determines the curvature distance in the local distance matrix using dynamic programming. The curvature distance characterizes the similarity between the real and simulated measurement data sequences after a moderately nonlinear transformation along the time axis.

[0181] The second processing submodule is used to process the real measurement data sequence and the simulated measurement data sequence according to the time-domain coefficient algorithm to obtain the time-domain correlation value between the real measurement data sequence and the simulated measurement data sequence.

[0182] The seventh determination submodule is used to determine the time-domain difference of the index based on the time-domain correlation value and the bending distance.

[0183] In one exemplary embodiment, the second determining submodule includes:

[0184] The eighth determination submodule is used to determine the comprehensive difference of the indicators based on the frequency domain difference and time domain difference of each indicator.

[0185] The third processing submodule is used to perform weighted processing on the comprehensive difference of each indicator according to the weight of each indicator, so as to obtain the total difference between the live network measurement dataset and the simulated measurement dataset.

[0186] In one exemplary embodiment, the optimization module 803 includes:

[0187] The update submodule is used to update the simulation parameter vector when the total difference is greater than or equal to a preset total difference threshold.

[0188] The generation submodule is used to generate an optimized simulation measurement dataset using simulation tools and updated simulation parameter vectors.

[0189] The execution submodule is used to perform the steps of determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset, until the total difference is less than the total difference threshold, at which point the simulated measurement dataset is determined as the target simulated measurement dataset.

[0190] Each module in the aforementioned data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0191] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a data processing method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0192] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0193] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0194] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0195] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0196] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0197] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0198] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A data processing method, characterized in that, The method includes: Obtain the simulated measurement dataset and the live network measurement dataset; For each indicator in the simulated measurement dataset, the corresponding real measurement data sequence is determined in the live network measurement dataset. Feature extraction is performed on the simulated measurement data sequence and the real measurement data sequence to obtain the simulated frequency domain features of the simulated measurement data sequence and the real frequency domain features of the real measurement data sequence; Based on the frequency domain difference algorithm, the true amplitude spectrum of the real frequency domain feature is determined, and the simulated amplitude spectrum of the simulated frequency domain feature is determined. The amplitude spectrum difference between the real amplitude spectrum and the simulated amplitude spectrum is determined as the frequency domain difference; The time-domain difference between the simulated measurement data sequence and the real measurement data sequence under the specified index is determined by using a time-domain coefficient algorithm and dynamic programming. Based on each frequency domain difference and each time domain difference, the total difference between the live network measurement dataset and the simulated measurement dataset is determined. If the total difference is greater than or equal to a preset total difference threshold, the simulated measurement dataset is optimized to obtain the target simulated measurement dataset.

2. The method according to claim 1, characterized in that, The aforementioned indicators are the reference signal received power indicator, the reference signal received quality indicator, and the signal-to-interference-plus-noise ratio indicator.

3. The method according to claim 1, characterized in that, The step of determining the frequency domain difference between the simulated measurement data sequence and the real measurement data sequence under the specified index, based on the frequency domain difference algorithm, includes: Perform a discrete Fourier transform on the actual measurement data sequence under the aforementioned index to obtain the true frequency domain characteristics of the actual measurement data sequence; Perform a discrete Fourier transform on the simulated measurement data sequence of the index to obtain the simulated frequency domain characteristics of the simulated measurement data sequence; According to the frequency domain difference algorithm, the real frequency domain features and the simulated frequency domain features are processed to obtain the frequency domain difference.

4. The method according to claim 1, characterized in that, The step of determining the time-domain difference between the simulated measurement data sequence and the actual measurement data sequence under the specified index using a time-domain coefficient algorithm and dynamic programming includes: A local distance matrix is ​​constructed based on the simulated measurement data sequence and the real measurement data sequence; The bending distance is determined in the local distance matrix by dynamic programming; the bending distance characterizes the similarity between the real measurement data sequence and the simulated measurement data sequence after a moderately nonlinear transformation along the time axis. According to the time-domain coefficient algorithm, the real measurement data sequence and the simulated measurement data sequence are processed to obtain the time-domain correlation value between the real measurement data sequence and the simulated measurement data sequence; The time-domain difference of the index is determined based on the time-domain correlation value and the bending distance.

5. The method according to claim 1, characterized in that, The step of determining the total difference between the live network measurement dataset and the simulated measurement dataset based on each of the frequency domain differences and each of the time domain differences includes: The comprehensive difference of the indicators is determined based on the frequency domain difference and time domain difference of each indicator; Based on the weights of each indicator, the comprehensive difference between each indicator is weighted to obtain the total difference between the live network measurement dataset and the simulated measurement dataset.

6. The method according to claim 1, characterized in that, The step of optimizing the simulated measurement dataset to obtain a target simulated measurement dataset when the total difference is greater than or equal to a preset total difference threshold includes: If the total difference is greater than or equal to a preset total difference threshold, update the simulation parameter vector; An optimized simulation measurement dataset is generated using simulation tools and updated simulation parameter vectors; Perform the steps of determining the frequency domain difference and time domain difference between the simulated measurement dataset and the live network measurement dataset until the total difference is less than the total difference threshold, and then determine the simulated measurement dataset as the target simulated measurement dataset.

7. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire simulated measurement datasets and live network measurement datasets; The determination module is used to determine the corresponding real measurement data sequence in the live network measurement dataset for each indicator's simulated measurement data sequence in the simulated measurement dataset; to perform feature extraction on the simulated measurement data sequence and the real measurement data sequence to obtain the simulated frequency domain features of the simulated measurement data sequence and the real frequency domain features of the real measurement data sequence; to determine the real amplitude spectrum of the real frequency domain features and the simulated amplitude spectrum of the simulated frequency domain features according to a frequency domain difference algorithm; to determine the amplitude spectrum difference between the real amplitude spectrum and the simulated amplitude spectrum as the frequency domain difference; to determine the time domain difference between the simulated measurement data sequence and the real measurement data sequence under the indicator through a time domain coefficient algorithm and dynamic programming; and to determine the total difference between the live network measurement dataset and the simulated measurement dataset based on each frequency domain difference and each time domain difference. An optimization module is used to optimize the simulated measurement dataset to obtain a target simulated measurement dataset when the total difference is greater than or equal to a preset total difference threshold.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images