Optimization processing method and device for 5G private network interference, server and storage medium

Abstract

The embodiment of the invention provides an optimization processing method and device for 5G private network interference, a server and a storage medium. The method comprises the following steps: receiving noise data of a 5G private network cell sent by an air interface resource monitoring probe; obtaining a 5G private network interference cell according to the noise data of the 5G private network cell; the 5G private network interference cell carries interference index data; if it is judged that an interference optimization process is triggered according to the interference index data, obtaining a 5G private network interference type through an interference type identification model; if the 5G private network interference type is inter-system interference, obtaining all terminal identifiers under a 5G private network interference cell; based on the end-to-end sensing data and the wireless measurement data of each terminal, obtaining all terminal identifiers with degraded performance; through a tabu search algorithm, determining interference sources of all terminal identifiers with degraded performance; and performing optimization processing on the interference source according to a pre-constructed interference optimization knowledge graph. The time for positioning the interference source is reduced, and the optimization efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to an optimization processing method, apparatus, server, and storage medium for 5G private network interference. Background Art

[0002] 5G private network interference refers to the phenomenon that occurs during the operation of a 5G private network and has an adverse impact on normal communication signals. These interferences will reduce network performance and affect the user experience. A 5G private network cell is a basic unit in a 5G private network and is a wireless communication area divided according to communication requirements.

[0003] Currently, the existing technology mainly relies on operation and maintenance personnel to locate interference sources with the help of frequency scanning tools. After determining the interference sources, the operation and maintenance personnel give optimization suggestions and then perform optimization processing.

[0004] However, manually locating and optimizing interference sources increases the time to locate interference sources on the one hand and reduces the optimization efficiency on the other hand. Summary of the Invention

[0005] The optimization processing method, apparatus, server, and storage medium for 5G private network interference provided in the embodiments of this application are used to achieve the effect of reducing the time to locate interference sources and improving the optimization efficiency.

[0006] In a first aspect, an optimization processing method for 5G private network interference provided in an embodiment of this application includes: receiving noise data of a 5G private network cell sent by an air interface resource monitoring probe; obtaining a 5G private network interference cell according to the noise data of the 5G private network cell, where the 5G private network interference cell carries interference index data; determining whether to trigger an interference optimization process for the 5G private network interference cell according to the interference index data; if it is determined that the interference optimization process is triggered, inputting the noise data of the 5G private network cell into an interference type recognition model to output a 5G private network interference type; if the 5G private network interference type is inter-system interference, obtaining all terminal identifiers under the 5G private network interference cell; obtaining end-to-end perception data and radio measurement data of each terminal according to each terminal identifier; obtaining all terminal identifiers with deteriorated performance from all terminal identifiers according to the end-to-end perception data and radio measurement data of each terminal; determining interference sources of all terminal identifiers with deteriorated performance through a tabu search algorithm according to the radio measurement data; and performing optimization processing on the interference sources according to a pre-constructed interference optimization knowledge graph.

[0007] In a possible implementation manner, obtaining 5G private network interference cells according to the noise data of 5G private network cells includes: clustering the noise data of 5G private network cells in the time domain to obtain time domain features and 5G private network interference cells that are continuously interfered; clustering the noise data of 5G private network cells in the frequency domain to obtain spectral features; clustering the 5G private network interference cells that are continuously interfered according to the spectral features to obtain 5G private network interference cells interfered by different interference sources; for 5G private network cells with the same time domain features and spectral features among the 5G private network interference cells interfered by different interference sources, performing density clustering in the spatial dimension to identify 5G private network interference cell clusters, so as to obtain 5G private network interference cells; where the 5G private network interference cell clusters include at least one 5G private network interference cell.

[0008] In a possible implementation manner, judging whether to trigger the interference optimization process of 5G private network interference cells according to interference index data includes: obtaining the average received interference noise and the interference duration from the interference index data; if the average received interference noise is greater than the preset average received interference noise threshold, the interference duration exceeds the preset time threshold, and the number of 5G private network interference cells in the 5G private network interference cell cluster to which the 5G private network interference cell belongs is greater than the preset number threshold, it is determined that the interference optimization process of 5G private network interference cells is triggered.

[0009] In a possible implementation manner, inputting the noise data of 5G private network cells into an interference type recognition model to output the 5G private network interference type includes: inputting the noise data of 5G private network cells into the interference type recognition model, and the interference type recognition model outputs the 5G private network interference type through a cross-validation method.

[0010] In a possible implementation manner, determining the interference sources of all terminal identifiers with deteriorated performance according to wireless measurement data through a tabu search algorithm includes: constructing an initial solution space of the interference sources; calculating the evaluation score of each solution in the initial solution space according to the wireless measurement data and an evaluation function; obtaining the current solution of the initial solution space according to the evaluation score of each solution; iteratively executing the following steps for the current solution until the iteration termination condition is reached; generating multiple neighborhood solutions based on the current solution; selecting the neighborhood solution with the best evaluation score from the multiple neighborhood solutions as the latest current solution according to the evaluation function; determining the location information corresponding to the latest current solution as the interference sources of all terminal identifiers with deteriorated performance.

[0011] In a possible implementation manner, the formula for calculating the evaluation score of each solution in the initial solution space according to the wireless measurement data and the evaluation function is:

[0012]

[0013] In the formula, Indicates the evaluation score, Indicates the number of interference indicators in the wireless measurement data, Indicates the weight of the Indicates the th interference indicator.

[0014] In a possible implementation manner, before receiving the noise data of the 5G private network cell sent by the air interface resource monitoring probe, it further includes: performing clustering analysis on the historical interference indicator data, historical end-to-end perception data, and historical wireless measurement data to obtain historical interference types; constructing an interference optimization knowledge graph according to the historical interference types and the optimization processing means of the historical interference types.

[0015] In a second aspect, an embodiment of the present application provides an optimization processing device for 5G private network interference, including:

[0016] A receiving module, configured to receive the noise data of the 5G private network cell sent by the air interface resource monitoring probe;

[0017] A first obtaining module, configured to obtain a 5G private network interference cell according to the noise data of the 5G private network cell; wherein the 5G private network interference cell carries interference indicator data;

[0018] A judgment module, configured to judge whether to trigger an interference optimization process for the 5G private network interference cell according to the interference indicator data;

[0019] An output module, configured to, if it is determined that the interference optimization process is triggered, input the noise data of the 5G private network cell into the interference type recognition model to output the 5G private network interference type;

[0020] A second obtaining module, configured to obtain all terminal identifiers under the 5G private network interference cell if the 5G private network interference type is inter-system interference;

[0021] A third obtaining module, configured to obtain the end-to-end perception data and wireless measurement data of each terminal according to each terminal identifier;

[0022] A fourth obtaining module, configured to obtain all terminal identifiers with deteriorated performance from all terminal identifiers according to the end-to-end perception data and wireless measurement data of each terminal;

[0023] A determination module, configured to determine the interference sources of all terminal identifiers with deteriorated performance through a tabu search algorithm according to the wireless measurement data;

[0024] An optimization module, configured to perform optimization processing on the interference sources according to the pre-constructed interference optimization knowledge graph.

[0025] In a third aspect, an embodiment of the present application provides a server, including: a memory, a processor;

[0026] The memory stores computer-executable instructions;

[0027] The processor executes the computer-executable instructions stored in the memory, such that the processor performs the above first aspect and / or various possible implementation manners of the first aspect.

[0028] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0029] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect and / or various possible implementation manners of the first aspect.

[0030] The optimization processing method, device, server and storage medium for 5G private network interference provided by the embodiments of the present application obtain 5G private network interference cells and interference indicators carried by the 5G private network interference cells according to the noise data of 5G private network cells; if it is determined that an interference optimization process is triggered according to the interference indicator data, then obtain the 5G private network interference type; if the 5G private network interference type is inter-system interference, then obtain all terminal identifiers under the 5G private network interference cell. Based on end-to-end perception data and radio measurement data, obtain all terminal identifiers with degraded performance; through a tabu search algorithm, determine the interference sources of all terminal identifiers with degraded performance, and perform optimization processing on the interference sources according to the interference optimization knowledge graph. Without manual intervention, on the one hand, the time for locating interference sources is reduced, and on the other hand, the optimization efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings here are incorporated into the description and constitute a part of this description, showing embodiments consistent with the present application, and are used together with the description to explain the principles of the present application.

[0032] Figure 1 It is a schematic diagram of the scenario of the optimization processing method for 5G private network interference provided by the embodiments of the present application;

[0033] Figure 2 It is a schematic flowchart of the optimization processing method for 5G private network interference provided by the embodiments of the present application;

[0034] Figure 3 It is a schematic structural diagram of the optimization processing device for 5G private network interference provided by the embodiments of the present application;

[0035] Figure 4 It is a schematic structural diagram of the server provided by the embodiments of the present application.

[0036] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by reference to specific embodiments. Detailed Description of the Embodiments

[0037] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0038] Figure 1 It is a schematic diagram of the scenario of the optimization processing method for 5G private network interference provided by the embodiments of the present application. As Figure 1 shown, the server provided by this embodiment includes: a receiving device 101, a processor 102, and a display device 103.

[0039] It can be understood that the structure schematically shown in the embodiments of the present application does not constitute a specific limitation on the optimization processing method for 5G private network interference. In some other feasible embodiments of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or have different component arrangements, which can be specifically determined according to the actual application scenario and will not be limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0040] In the specific implementation process, the receiving device 101 can be an input / output interface or a communication interface, and can receive the noise data of the 5G private network cell sent by the air interface resource monitoring probe.

[0041] The processor 102 can perform a series of processes on the noise data of the 5G private network cell to optimize the interference source.

[0042] The display device 103 can be used to display the optimization processing result.

[0043] It should be understood that the above processor can be implemented by the processor reading instructions in the memory and executing the instructions, or can be implemented by a chip circuit.

[0044] In addition, the network architecture and service scenarios described in the embodiments of this application are for more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those of ordinary skill in the art can know that with the evolution of the network architecture and the emergence of new service scenarios, the technical solutions provided by the embodiments of this application are equally applicable to similar technical problems.

[0045] 5G private network interference refers to the phenomenon that occurs during the operation of a 5G private network and has an adverse impact on normal communication signals. These interferences will reduce network performance and affect the user experience. A 5G private network cell is a basic unit in a 5G private network and is a wireless communication area divided according to communication requirements. Currently, the prior art mainly relies on operation and maintenance personnel to locate interference sources with the help of frequency scanning tools. After determining the interference sources, the operation and maintenance personnel give optimization suggestions and then perform optimization processing. However, manually locating and optimizing interference sources increases the time to locate interference sources on the one hand and reduces the optimization efficiency on the other hand.

[0046] To solve the above technical problems, the following technical concept is proposed in this application: Considering that manually locating and optimizing interference sources will increase the time to locate interference sources and reduce the optimization efficiency. The inventor thought of automatically completing the location and optimization of interference sources. Based on end-to-end perception data and wireless measurement data, the interference sources are determined through a tabu search algorithm, and the interference sources are optimized according to the interference optimization knowledge graph. Without human intervention, on the one hand, the time to locate interference sources is reduced, and on the other hand, the optimization efficiency is improved. According to the noise data of 5G private network cells, 5G private network interference cells and the interference indicators carried by the 5G private network interference cells are obtained; if it is determined that the interference optimization process is triggered according to the interference indicator data, the 5G private network interference type is obtained; if the 5G private network interference type is inter-system interference, all terminal identifiers under the 5G private network interference cell are obtained. Based on end-to-end perception data and wireless measurement data, all terminal identifiers with degraded performance are obtained; through a tabu search algorithm, the interference sources of all terminal identifiers with degraded performance are determined, and the interference sources are optimized according to the interference optimization knowledge graph. Without human intervention, on the one hand, the time to locate interference sources is reduced, and on the other hand, the optimization efficiency is improved.

[0047] The following uses specific embodiments to elaborate in detail on the technical solutions of this application and how the technical solutions of this application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0048] Figure 2 For the flow diagram of the optimization processing method for 5G private network interference provided by the embodiments of this application, as Figure 2 shown, the method includes:

[0049] S201: Receive the noise data of the 5G private network cell sent by the air interface resource monitoring probe.

[0050] Among them, the 5G private network cell is a basic unit in the 5G private network and is a wireless communication area divided according to communication requirements.

[0051] In this embodiment, the air interface resource monitoring probe is installed on both sides of the base station. Using its built-in sensors or interfaces with the base station equipment, it can monitor the wireless signal environment of the 5G private network cell in real time and collect the noise data of the 5G private network cell.

[0052] Optionally, the collected noise data of the 5G private network cell can be the received interference power (RIP) data of the physical resource block (PRB) of the uplink of the 5G private network cell. Among them, in the 5G network, each cell is divided into multiple PRBs.

[0053] S202: Obtain the 5G private network interfering cell according to the noise data of the 5G private network cell; among them, the 5G private network interfering cell carries interference index data.

[0054] Among them, each 5G private network cell is divided into multiple PRBs, and there are 273 PRBs in total in the 5G private network cell. The RIP data of the PRBs of the 5G private network cell is comprehensively analyzed in the time domain, frequency domain and spatial domain, and abnormal data is removed to obtain reasonable and credible standardized data.

[0055] Specifically, step S202 includes S2021 to 2024:

[0056] 2021: Cluster the noise data of the 5G private network cell in the time domain to obtain the time domain characteristics and the continuously interfered 5G private network interfering cell.

[0057] In this embodiment, the air interface resource monitoring probe will collect the noise data of the 5G private network cell at a certain time interval, and this time interval can be selected between 1 minute and 15 minutes. Different granularities are selected to meet the requirements of data real-time and accuracy in different scenarios. For example, in a scenario where the interference situation changes rapidly, a granularity of 1 minute may be selected to obtain data more timely; while in a scenario where the interference is relatively stable, a granularity of 15 minutes can not only ensure the acquisition of effective data but also reduce the pressure of data processing.

[0058] In this embodiment, uplink noise can cause changes in RIP data. By analyzing the RIP data collected at different time points, the uplift intensity of RIP data caused by uplink noise can be determined. For example, if the RIP value continuously increases and the increase amplitude is large within a certain period of time, it indicates that the uplink noise has a strong interference on the cell, resulting in a large uplift intensity of RIP. Specifically, through time-domain clustering, the noise data of 5G private network cells are clustered in the time domain to find 5G private network cells that are continuously interfered with.

[0059] 2022: Cluster the noise data of 5G private network cells in the frequency domain to obtain spectral characteristics.

[0060] Among them, the spectral characteristics refer to the distribution characteristics of noise data at different frequencies. Interferences generated by different interference sources will show different patterns in the frequency domain. For example, some interferences may be concentrated in a specific frequency range, forming a sharp spectral peak; while some interferences may be evenly distributed within a relatively wide frequency range. By analyzing the intensity distribution of the noise data and extracting these unique patterns, the spectral characteristics of the interference can be identified.

[0061] 2023: According to the spectral characteristics, cluster the 5G private network interference cells that are continuously interfered with to obtain 5G private network interference cells interfered by different interference sources.

[0062] In this embodiment, by monitoring 273 PRBs of the 5G private network interference cells that are continuously interfered with one by one, the intensity values of the noise data on each PRB are obtained, so as to obtain the distribution of the noise data over the entire frequency band. The difference in this intensity distribution reflects the characteristics of the interference in the frequency domain. Once the spectral characteristics of each 5G interference cell are identified, the cells with similar spectral characteristics can be grouped into one category. Because cells with similar spectral characteristics are likely to be affected by the same interference source. Through the above steps, finally, the cells affected by the same interference source are grouped into one set to obtain 5G private network interference cells interfered by different interference sources.

[0063] 2024: From the 5G private network interference cells interfered by different interference sources, for the 5G private network cells with the same time-domain characteristics and spectral characteristics, perform density clustering in the spatial dimension to identify 5G private network interference cell clusters to obtain 5G private network interference cells; where the 5G private network interference cell cluster includes at least one 5G private network interference cell.

[0064] In this embodiment, the airspace dimension analysis is based on the time domain dimension and the frequency domain dimension. The objects for airspace dimension analysis are those 5G private network cells that have shown consistency in time domain characteristics and spectral characteristics. This means that these cells are similar in the time pattern of interference occurrence and the spectral characteristics of interference. Thus, it can be inferred that they may be affected by the same interference source, or there is some correlation in the interference propagation characteristics, which provides a basis for analysis from the spatial dimension.

[0065] In this embodiment, density clustering analysis is a spatial data analysis method. In the 5G private network environment, each cell is regarded as a point in space, and the spatial distribution density is calculated. In space, if the distribution of cells in a certain area is relatively dense, and these cells have similar characteristics in both time domain and spectrum, then this area is regarded as an area with a high density. The algorithm will automatically identify these high-density areas and divide them into a cluster. In this way, a set of cells that are spatially clustered and have similar interference characteristics can be found, and these sets are potential 5G private network interference cell clusters affected by the same interference source. After identifying the 5G private network interference cell clusters, an interference cell list is obtained. The interference cell list clearly lists the information of specific 5G private network interference cells belonging to each 5G private network interference cell cluster, including numbers and locations, etc.

[0066] S203: According to the interference index data, determine whether to trigger the interference optimization process for 5G private network interference cells.

[0067] Optionally, the interference index data includes but is not limited to: the average value of the interference noise detected on the 0th to 272nd PRBs, the maximum value of the interference noise detected on the 0th to 272nd PRBs, the average received interference noise per PRB, the interference intensity, and the interference duration, etc.

[0068] Specifically, from the interference index data, obtain the average received interference noise and the interference duration; if the average received interference noise is greater than the preset average received interference noise threshold, the interference duration exceeds the preset time threshold, and the number of 5G private network interference cells in the 5G private network interference cell cluster to which the 5G private network interference cell belongs is greater than the preset number threshold, then it is determined that the interference optimization process for 5G private network interference cells has been triggered.

[0069] Exemplarily, if the average received interference noise of a 5G private network interference cell is greater than -100, the interference duration exceeds 1 hour, and the number of 5G private network interference cells in the 5G private network interference cell cluster to which the 5G private network interference cell belongs is greater than 3, then it is determined that the interference optimization process for 5G private network interference cells has been triggered.

[0070] S204: If it is determined that the interference optimization process is triggered, the noise data of the 5G private network cell is input into the interference type recognition model to output the 5G private network interference type.

[0071] Specifically, the noise data of the 5G private network cell is input into the interference type recognition model, and the interference type recognition model outputs the 5G private network interference type through the cross-validation method.

[0072] In this embodiment, the 5G private network interference type is divided into intra-system interference and inter-system interference. There are obvious differences in the waveforms of the noise data of 273 PRBs in the frequency domain for different types of interference sources. The interference type recognition model judges whether the interference type is intra-system interference and inter-system interference based on the waveforms monitored on PRBs 0 to 272. If it is intra-system interference, parameter optimization is performed. If it is inter-system interference, the next external interference judgment is carried out.

[0073] In this embodiment, based on the uplink service load of the 5G private network cell and the PRB base station noise rise distribution, an interference feature model of the uplink is modeled, the PRB frequency point distribution characteristics of the interference are analyzed, an interference type recognition model is constructed, and the model performance evaluation result reaches the expected target through parameter optimization.

[0074] Optionally, the interference type recognition model can also output whether it is a 5G private network interference cell and the interference confidence level, etc. The interference type also includes system-external interference classification, inter-system interference, and inter-system external interference.

[0075] Optionally, the interference type recognition model can be mirror-packaged and directly deployed in the form of a container.

[0076] Optionally, the interference type recognition model is divided into two modes: training mode and running mode. In the training mode, model training and periodic iteration are completed, including six functions: training data import, data preprocessing, feature engineering, data modeling and model optimization, model packaging, and model release and online. In the running mode, online model inference is performed, intelligent diagnosis is carried out for the 5G private network uplink interference, and it is output whether there is uplink interference in the 5G cell and the corresponding interference type.

[0077] Optionally, the training of the interference type recognition model can be based on LightGBM: the RIP data of the PRBs with interference characteristics are stored in the database and cleaned; based on the RIP data feature analysis and interference intensity analysis of the uplink PRBs with known interference, an interference type recognition model is constructed.

[0078] S205: If the 5G private network interference type is inter-system interference, all terminal identifiers under the 5G private network interference cell are obtained.

[0079] S206: Obtain the end-to-end perception data and radio measurement data of each terminal according to each terminal identifier.

[0080] Optionally, the end-to-end perception data includes rate, latency, and jitter, etc.

[0081] Optionally, the radio measurement report metrics include Reference Signal Receiving Power (RSRP), Received Signal Strength Indicator (RSSI), and Signal to Interference Noise Ratio (SINR), etc.

[0082] S207: Obtain the identifiers of all terminals with degraded performance from all terminal identifiers according to the end-to-end perception data and radio measurement data of each terminal.

[0083] In this embodiment, the end-to-end perception data can, from the perspective of the actual user experience, understand the specific impact of interference on the use of the 5G private network. For example, a decrease in rate will make users feel significantly slow when downloading files or watching videos; an increase in latency may cause delays and jitters in real-time communication, seriously affecting the communication quality; and jitter will bring a very poor experience to users in scenarios such as gaming and streaming media playback.

[0084] In this embodiment, by analyzing and comparing the end-to-end perception data and radio measurement data, it is determined whether the perception performance of each terminal has deteriorated. For example, if the download rate of a certain terminal is significantly lower than the normal level, the latency increases greatly, and jitters occur frequently, and at the same time, the indicators such as RSRP, SINR, and RSRQ in its radio measurement report also perform poorly, then it can be considered that the perception performance of this terminal has deteriorated. For example, when interference increases, SINR will decrease, resulting in a reduction in data transmission efficiency and affecting the perception performance of the terminal.

[0085] S208: Determine the interference sources of the identifiers of all terminals with degraded performance through a tabu search algorithm according to the radio measurement data.

[0086] Among them, the tabu search algorithm is a heuristic search algorithm aimed at solving combinatorial optimization problems. In the scenario of wireless signal interference source localization, by continuously exploring the solution space, using a tabu list to avoid repeated searches, and jumping out of the local optimal solution with a certain strategy, the interference source location can be efficiently found.

[0087] In this embodiment, in the customer's private network, there are various private network scenarios, and the services carried by the terminals in each private network scenario are grouped and managed according to customer requirements. Therefore, the interference sources can be determined through the tabu algorithm.

[0088] Specifically, step S208 includes S2081 to S2087:

[0089] S2081: Construct the initial solution space of the interference source.

[0090] Specifically, determine the range of the area where the interference source may exist. Combine all possible positions of the interference source within this range to form the initial solution space. Optionally, each solution can be represented as a coordinate point or a set of related parameters, representing a possible hypothesis of the interference source position.

[0091] S2082: According to the wireless measurement data, calculate the evaluation score of each solution in the initial solution space according to the evaluation function.

[0092] Among them, the evaluation function is the key to measuring the quality of each solution.

[0093] Specifically, according to the wireless measurement data, the formula for calculating the evaluation score of each solution in the initial solution space according to the evaluation function is:

[0094]

[0095] In the formula, represents the evaluation score, represents the number of interference indicators in the wireless measurement data, represents the weight of the th interference indicator, represents the

[0096] S2083: According to the evaluation score of each solution, obtain the current solution of the initial solution space.

[0097] In this embodiment, the smaller the SINR value, the greater the interference intensity. The current solution of the initial solution space can be obtained according to the evaluation score standard preset by the user.

[0098] S2084: Iteratively execute the following steps on the current solution until the iteration termination condition is reached.

[0099] Specifically, step S2084 includes Sa to Sb:

[0100] Sa: Based on the current solution, generate multiple neighborhood solutions.

[0101] Optionally, the neighborhood solutions can be generated based on the swap operation or the move operation.

[0102] Sb: According to the evaluation function, select the neighborhood solution with the best evaluation score from the multiple neighborhood solutions as the latest current solution.

[0103] In this embodiment, the current solution is added to the taboo list to avoid repeated search.

[0104] In this embodiment, a solution with a slightly worse evaluation score is accepted with a certain probability to jump out of the local optimum. During the search process, the algorithm may fall into a local optimum. A local optimum refers to a situation where within a certain local area, the evaluation function value of this solution is the best, but from the perspective of the entire solution space, it is not the global optimum. For example, in a complex interference environment, the algorithm may fall into a local area where the interference situation is relatively good but not the actual location of the interference source. To jump out of the local optimum, the algorithm will accept a solution with a slightly worse evaluation score with a certain probability. Specifically, when selecting a new current solution, not only the solution with the best evaluation function value is considered, but neighboring solutions with an evaluation score slightly worse than the current optimum solution are accepted with a pre-set probability. In this way, the algorithm has more opportunities to explore different regions of the solution space; as the iteration progresses, the probability value gradually decreases, and the algorithm gradually converges to the vicinity of the possible optimum solution.

[0105] S2087: Determine the location information corresponding to the latest current solution as the interference source of all terminals with deteriorated performance.

[0106] Exemplarily, taking the SINR as the measured value of the evaluation function, the specific implementation steps are as follows:

[0107] Step 1: Select an arbitrary interference scenario to set the initial "center" position, and use the difference between the SINR value of the terminals in the private network scenario and the "center" value as the judgment criterion.

[0108] Step 2: Set the calculated difference > 0 as the taboo length. During this period, the accessed scenarios will be tabooed and will not be accessed again. For each taboo period: If the SINR value of the current scenario is lower than the SINR value of the "center" position, it means that the interference in the current scenario may be more serious. At this time, update the "center" position to the current scenario. Add the original center scenario to the taboo list.

[0109] Repeat Step 2 until the scenario with the lowest SINR of the terminal group is found. Perform the same taboo algorithm judgment on all terminals in the terminal group in the scenario with the highest interference. The final "center" position obtained is the location of the interference source.

[0110] S209: Optimize the interference source according to the pre-constructed interference optimization knowledge graph.

[0111] In summary, according to the noise data of the 5G private network cell, the 5G private network interference cell and the interference indicators carried by the 5G private network interference cell are obtained; if the interference optimization process is determined to be triggered according to the interference indicator data, the 5G private network interference type is obtained; if the 5G private network interference type is inter-system interference, all terminal identifiers under the 5G private network interference cell are obtained. Based on the end-to-end perception data and wireless measurement data, all terminal identifiers with deteriorated performance are obtained; through the tabu search algorithm, the interference sources of all terminal identifiers with deteriorated performance are determined, and according to the interference optimization knowledge graph, the interference sources are optimized. Without human intervention, on the one hand, the time for locating the interference source is reduced, and on the other hand, the optimization efficiency is improved.

[0112] On the basis of the above embodiments, the process of constructing the interference optimization knowledge graph is introduced in detail as follows:

[0113] S301: Perform clustering analysis on historical interference indicator data, historical end-to-end perception data and historical wireless measurement data to obtain historical interference types;

[0114] In this embodiment, the optimization processing method and effective optimization processing results are saved to the database, including the time domain, frequency domain, and spatial domain characteristics of the noise data, as well as the wireless measurement data and end-to-end perception data of the terminal users.

[0115] S302: Construct an interference optimization knowledge graph according to the historical interference type and the optimization processing means of the historical interference type.

[0116] In this embodiment, for the historical interference type and the optimization processing means of the historical interference type, a label set for interference recognition and optimization is designed, and clustering learning is performed through an algorithm to record the interference type corresponding to each interference waveform and the optimization processing means, and an interference optimization knowledge graph is constructed.

[0117] In summary, the interference optimization knowledge graph constructed for the obtained historical interference types and the optimization processing means of the historical interference types can automatically recommend the best optimization processing means for the interference sources corresponding to each interference type, further improving the optimization efficiency.

[0118] On the basis of the above embodiments, this embodiment also provides an optimization processing system for 5G private network interference, which includes: an automatic discovery unit, an automatic analysis unit, an automatic demarcation unit, an automatic optimization unit, and an automatic iteration unit.

[0119] Among them, the automatic discovery unit is used to obtain the 5G private network interference cell according to the noise data of the 5G private network cell sent by the air interface resource monitoring probe. Among them, the interference indicator data carried by the 5G private network interference cell is obtained.

[0120] An automatic analysis unit for obtaining all terminal identifiers with degraded performance under 5G private network interference cells according to interference index data.

[0121] An automatic delimitation unit for troubleshooting all terminals with degraded performance through a tabu algorithm based on the end-to-end perception data and radio measurement data of each terminal, and delimiting the interference source;

[0122] An automatic optimization unit for outputting an optimization plan for the interference source according to a pre-constructed interference optimization knowledge graph and performing optimization processing.

[0123] An automatic iteration unit: If there is a deviation in the output optimization plan, further iterate the self-optimization ability according to the actual interference characteristics.

[0124] Optionally, the automatic discovery unit can also output the interference time of the uplink, and can also adjust the spatial range affected by the uplink and the degree of interference impact based on customer scenario requirements.

[0125] In summary, according to the noise data of 5G private network cells, obtain 5G private network interference cells and the interference indicators carried by 5G private network interference cells; if it is determined that the interference optimization process is triggered according to the interference index data, obtain the 5G private network interference type; if the 5G private network interference type is inter-system interference, obtain all terminal identifiers under the 5G private network interference cell. Based on the end-to-end perception data and radio measurement data, obtain all terminal identifiers with degraded performance; determine the interference source of all terminal identifiers with degraded performance through the tabu search algorithm, and perform optimization processing on the interference source according to the interference optimization knowledge graph. Without human intervention, on the one hand, it reduces the time to locate the interference source, and on the other hand, it improves the optimization efficiency.

[0126] Figure 3 The structural schematic diagram of the optimization processing device for 5G private network interference provided by the embodiment of the present application is as Figure 3 shown. The optimization processing device for 5G private network interference provided in this embodiment includes: a receiving module 301, a first obtaining module 302, a judging module 303, an output module 304, a second obtaining module 305, a third obtaining module 306, a fourth obtaining module 307, a determining module 308, and an optimizing module 309.

[0127] The receiving module 301 is used to receive the noise data of 5G private network cells sent by the air interface resource monitoring probe;

[0128] The first obtaining module 302 is used to obtain 5G private network interference cells according to the noise data of 5G private network cells; where the 5G private network interference cells carry interference index data;

[0129] A judgment module 303, configured to determine whether to trigger an interference optimization process for a 5G private network interference cell according to interference index data;

[0130] An output module 304, configured to, if it is determined that the interference optimization process is triggered, input the noise data of the 5G private network cell into an interference type recognition model to output the 5G private network interference type;

[0131] A second acquisition module 305, configured to, if the 5G private network interference type is inter-system interference, acquire all terminal identifiers under the 5G private network interference cell;

[0132] A third acquisition module 306, configured to acquire the end-to-end perception data and radio measurement data of each terminal according to each terminal identifier;

[0133] A fourth acquisition module 307, configured to acquire all terminal identifiers with deteriorated performance from all terminal identifiers according to the end-to-end perception data and radio measurement data of each terminal;

[0134] A determination module 308, configured to determine the interference source of all terminal identifiers with deteriorated performance through a tabu search algorithm according to the radio measurement data;

[0135] An optimization module 309, configured to perform optimization processing on the interference source according to a pre-constructed interference optimization knowledge graph.

[0136] In a possible implementation manner, the first acquisition module 302 is specifically configured to: perform clustering on the noise data of the 5G private network cell in the time domain to obtain time domain features and the 5G private network interference cell continuously affected by interference; perform clustering on the noise data of the 5G private network cell in the frequency domain to obtain spectrum features; according to the spectrum features, perform clustering on the 5G private network interference cell continuously affected by interference to obtain 5G private network interference cells affected by different interference sources; perform density clustering on the 5G private network cells with the same time domain features and spectrum features in the spatial dimension from the 5G private network interference cells affected by different interference sources to identify 5G private network interference cell clusters so as to obtain 5G private network interference cells; where the 5G private network interference cell cluster includes at least one 5G private network interference cell.

[0137] In a possible implementation manner, the judgment module 303 is specifically configured to: acquire the average received interference noise and the interference duration from the interference index data; if the average received interference noise is greater than a preset average received interference noise threshold, the interference duration exceeds a preset time threshold, and the number of 5G private network interference cells in the 5G private network interference cell cluster to which the 5G private network interference cell belongs is greater than a preset number threshold, it is determined that the interference optimization process for the 5G private network interference cell is triggered.

[0138] In a possible implementation manner, the output module 304 is specifically configured to: input the noise data of the 5G private network cell into an interference type recognition model, and the interference type recognition model outputs the 5G private network interference type through a cross-validation method.

[0139] In a possible implementation manner, the determination module 308 is specifically configured to: construct an initial solution space of the interference source; calculate the evaluation score of each solution in the initial solution space according to the wireless measurement data and an evaluation function; obtain the current solution of the initial solution space according to the evaluation score of each solution; iteratively execute the following steps on the current solution until the iteration termination condition is reached; generate a plurality of neighborhood solutions based on the current solution; select the neighborhood solution with the best evaluation score from the plurality of neighborhood solutions as the latest current solution according to the evaluation function; determine the position information corresponding to the latest current solution as the interference source of all terminal identifiers with deteriorated performance.

[0140] In a possible implementation manner, the formula for calculating the evaluation score of each solution in the initial solution space according to the wireless measurement data and the evaluation function is:

[0141]

[0142] In the formula, represents the evaluation score, represents the number of interference indicators in the wireless measurement data, represents the weight of the th interference indicator, represents the

[0143] th interference indicator.

[0144] The optimization processing device for 5G private network interference provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0145] Figure 4 It is a schematic structural diagram of a server provided in an embodiment of the present application. As Figure 4 shown, the server provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. Among them, the processor 401, the memory 402, and the communication component 403 are connected through a bus 404.

[0146] In a specific implementation process, at least one processor 401 executes computer-executable instructions stored in a memory 402, so that at least one processor 401 executes the above-mentioned method.

[0147] For the specific implementation process of the processor 401, reference may be made to the above method embodiments, and their implementation principles and technical effects are similar, so they will not be elaborated here in this embodiment.

[0148] In the above embodiments, it should be understood that the processor may be a central processing unit (Central Processing Unit, CPU for short), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or by a combination of hardware and software modules in the processor.

[0149] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0150] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0151] This application also provides a computer program product, including a computer program, which implements the above-mentioned method when executed by a processor.

[0152] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the above-mentioned method is implemented.

[0153] The above-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The readable storage medium may be any available medium accessible by a general-purpose or special-purpose computer.

[0154] An exemplary readable storage medium is coupled to the processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium may also be a component of the processor. The processor and the readable storage medium may be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium may also exist as discrete components in a device.

[0155] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other may be indirect couplings or communication connections through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

[0156] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] In addition, the functional units in various embodiments of the present invention may be integrated in a processing unit, may also exist separately physically for each unit, or two or more units may be integrated in one unit.

[0158] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, and other various media that can store program codes.

[0159] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, and other various media that can store program codes.

[0160] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for optimizing 5G private network interference, characterized in that: Applicable to servers, including: Receive noise data of 5G private network cells sent by air interface resource monitoring probes; According to the noise data of the 5G private network cell, a 5G private network interference cell is obtained; wherein the 5G private network interference cell carries interference index data; According to the interference indicator data, determine whether to trigger the interference optimization process of the 5G private network interference cell; If it is determined that the interference optimization process is triggered, the noise data of the 5G private network cell is input into the interference type identification model to output the 5G private network interference type; If the 5G private network interference type is inter-system interference, obtain all terminal identifiers under the 5G private network interference cell; According to each terminal identifier, obtain end-to-end sensing data and wireless measurement data of each terminal; Acquire, from all the terminal identifiers, identifiers of all terminals with degraded performance according to the end-to-end perception data of each terminal and the wireless measurement data; Determine, according to the wireless measurement data, interference sources identified by all the terminals with degraded performance by using a taboo search algorithm; The interference source is optimized according to the pre-constructed interference optimization knowledge graph.

2. The method according to claim 1, characterized in that The obtaining, according to the noise data of the 5G private network cell, a 5G private network interference cell includes: Clustering the noise data of the 5G private network cell in the time domain to obtain time domain features and continuously interfered 5G private network interference cells; Clustering the noise data of the 5G private network cell in the frequency domain to obtain spectrum characteristics; Clustering the continuously interfered 5G private network interference cells according to the spectrum characteristics to obtain 5G private network interference cells interfered by different interference sources; From the 5G private network interference cells affected by different interference sources, the 5G private network cells with the same time domain characteristics and the spectrum characteristics are densely clustered in the spatial dimension to identify 5G private network interference cell clusters to obtain 5G private network interference cells; wherein the 5G private network interference cell cluster includes at least one 5G private network interference cell.

3. The method according to claim 2, characterized in that The determining, according to the interference indicator data, whether to trigger the interference optimization process of the 5G private network interference cell includes: Obtaining an average value of received interference noise and an interference duration from the interference indicator data; If the average value of the received interference noise is greater than the preset average value threshold of the received interference noise, the interference duration exceeds the preset time threshold, and the number of 5G private network interference cells in the 5G private network interference cell cluster to which the 5G private network interference cell belongs is greater than the preset number threshold, it is determined that the interference optimization process of the 5G private network interference cell is triggered.

4. The method according to claim 1, characterized in that: The step of inputting the noise data of the 5G private network cell into an interference type identification model to output the 5G private network interference type includes: The noise data of the 5G private network cell is input into the interference type identification model, and the interference type identification model outputs the 5G private network interference type through a cross-validation method.

5. The method according to claim 1, characterized in that: The determining, according to the wireless measurement data, the interference sources identified by all the terminals with degraded performance by means of a taboo search algorithm comprises: Construct the initial solution space of interference sources; Calculating an evaluation score of each solution in the initial solution space according to the wireless measurement data and an evaluation function; Obtaining a current solution of the initial solution space according to the evaluation score of each solution; Iteratively perform the following steps on the current solution until an iteration termination condition is reached; Based on the current solution, generate multiple neighborhood solutions; According to the evaluation function, from the plurality of neighborhood solutions, a neighborhood solution with the best evaluation score is used as the latest current solution; The location information corresponding to the latest current solution is determined as the interference source identified by all the terminals with degraded performance.

6. The method according to claim 5, characterized in that The formula for calculating the evaluation score of each solution in the initial solution space according to the wireless measurement data and the evaluation function is: In the formula, Indicates the evaluation score. represents the number of interference indicators in the wireless measurement data, Indicates The weight of the interference indicator, Indicates Interference indicator.

7. The method according to any one of claims 1 to 6, characterized in that: Before receiving the noise data of the 5G private network cell sent by the air interface resource monitoring probe, the method further includes: Perform cluster analysis on historical interference indicator data, historical end-to-end perception data, and historical wireless measurement data to obtain historical interference types; Based on the historical interference types and the optimization processing methods of historical interference types, an interference optimization knowledge graph is constructed.

8. A 5G private network interference optimization processing device, characterized in that: Applicable to servers, including: A receiving module, used to receive noise data of a 5G private network cell sent by an air interface resource monitoring probe; A first acquisition module is used to acquire a 5G private network interference cell according to the noise data of the 5G private network cell; wherein the 5G private network interference cell carries interference indicator data; A judgment module, used to judge whether to trigger the interference optimization process of the 5G private network interference cell according to the interference indicator data; An output module, configured to input the noise data of the 5G private network cell into an interference type identification model to output the 5G private network interference type if it is determined that the interference optimization process is triggered; A second acquisition module is used to obtain all terminal identifiers under the 5G private network interference cell if the 5G private network interference type is inter-system interference; A third acquisition module is used to acquire end-to-end perception data and wireless measurement data of each terminal according to each terminal identifier; A fourth acquisition module, configured to acquire, from all the terminal identifiers, identifiers of all terminals with degraded performance according to the end-to-end perception data and the wireless measurement data of the terminals; A determination module, configured to determine the interference sources identified by all the terminals with degraded performance through a taboo search algorithm according to the wireless measurement data; The optimization module is used to optimize the interference source according to a pre-built interference optimization knowledge graph.

9. A server, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when being executed by a processor.

Images