Slice resource configuration method and apparatus, electronic device, and storage medium

Abstract

The application relates to the technical field of wireless communication, in particular to a slice resource configuration method and device, electronic equipment and a storage medium, wherein the slice resource configuration method comprises the following steps: acquiring a coverage grid set of a light RedCap terminal; determining one or more occupied cells of the RedCap terminal and the average coverage intensity of the RedCap terminal according to the coverage grid set; when the average coverage intensity meets a first preset condition and the occupied cells are all normal cells, performing service capability checking on the occupied cells to determine a service checking result; and performing slice resource configuration on the occupied cells according to the service checking result, so as to solve the technical problem of low slice resource configuration efficiency in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, and particularly relates to a slice resource configuration method and device, electronic equipment and storage medium. BACKGROUND

[0002] 5G Reduced Capability (RedCap) terminals are designed to meet the needs of medium-speed and high-speed Internet of Things. The 5G RedCap terminals fully inherit the network characteristics of 5G, including the capabilities of slice, 5G QoS Identifier (5QI) acceleration, etc. The network deployment and use cost are reduced by weakening the terminal module function. Compared with full-function modules, RedCap modules generally have lower network bandwidth requirements, and the network is more likely to meet the bandwidth requirements.

[0003] For the slice and Physical Resource Block (PRB) resource reservation configuration requirements of RedCap terminals, manual on-site testing is mainly used to confirm the resident cell and required slice resources, and then manual configuration is performed in the network management. The efficiency is low, and there are problems of inaccurate and incomplete evaluation. Once there is network optimization adjustment, on-site testing needs to be performed again, and the cost and efficiency are difficult to meet the business delivery requirements. SUMMARY

[0004] The present application aims to at least solve one of the technical problems in the related art to some extent.

[0005] To this end, a first object of the present application is to provide a slice resource configuration method to achieve efficient slice resource configuration.

[0006] A second object of the present application is to provide a slice resource configuration device.

[0007] A third object of the present application is to provide an electronic equipment.

[0008] A fourth object of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objects, a slice resource configuration method is provided in the first aspect of the present application, comprising:

[0011] obtaining a coverage grid set of a Reduced Capability (RedCap) terminal;

[0012] determine one or more occupied cells of the RedCap terminal and an average coverage intensity of the RedCap terminal according to the coverage grid set;

[0013] perform a service capability check on the occupied cells in response to the average coverage intensity satisfying a first preset condition and the occupied cells all being normal cells, to determine a service check result;

[0014] perform slice resource configuration on the occupied cells according to the service check result.

[0015] To achieve the above object, a second aspect embodiment of the present application provides a slice resource configuration device, comprising:

[0016] a first obtaining module configured to obtain a coverage grid set of a lightweight RedCap terminal;

[0017] a second obtaining module configured to determine one or more occupied cells of the RedCap terminal and an average coverage intensity of the RedCap terminal according to the coverage grid set;

[0018] a third obtaining module configured to perform a service capability check on the occupied cells in response to the average coverage intensity satisfying a first preset condition and the occupied cells all being normal cells, to determine a service check result;

[0019] a configuration module configured to perform slice resource configuration on the occupied cells according to the service check result.

[0020] To achieve the above object, a third aspect embodiment of the present application provides an electronic device, comprising a processor and a memory connected with the processor in communication;

[0021] the memory stores computer execution instructions;

[0022] the processor executes the computer execution instructions stored in the memory to implement the method according to the first aspect embodiment.

[0023] To achieve the above object, a fourth aspect embodiment of the present application provides a computer readable storage medium, which stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method according to the first aspect embodiment.

[0024] To achieve the above object, a fifth aspect embodiment of the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the method according to the first aspect embodiment.

[0025] The slice resource configuration method, device, electronic equipment and storage medium provided by the application, by acquiring the coverage grid set of the RedCap terminal, the occupied cell and the average coverage intensity are determined, which provides an accurate basis for subsequent slice resource configuration of the occupied cell, when the average coverage intensity meets the first preset condition and the occupied cell is all normal cell, the service capability of each occupied cell is checked to obtain the service check result, the service check result can reflect the resource capability of the occupied cell, and the slice resource configuration is performed according to the service check result, which can improve the resource configuration accuracy, avoid excessive occupied resources affecting the actual business, and effectively improve the slice resource configuration efficiency.

[0026] Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following and / or can be learned by practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0027] The above and / or additional aspects and advantages of the application will become apparent and be readily understood from the following description, taken in conjunction with the accompanying drawings, in which:

[0028] Figure 1 A flowchart of a slice resource configuration method provided by an embodiment of the application;

[0029] Figure 1A A geographic grid rendering schematic diagram provided by an embodiment of the application;

[0030] Figure 2 A flowchart of a method for acquiring a coverage grid set provided by an embodiment of the application;

[0031] Figure 3 A flowchart of a method for acquiring an average coverage intensity provided by an embodiment of the application;

[0032] Figure 4 A flowchart of a method for determining the cell type of an occupied cell provided by an embodiment of the application;

[0033] Figure 4A A schematic diagram of constructing a Delone triangle net provided by an embodiment of the application;

[0034] Figure 4B A schematic diagram of selecting a neighboring base station provided by an embodiment of the application;

[0035] Figure 4C A schematic diagram of the relationship between the occupied cells provided by an embodiment of the application;

[0036] Figure 5 A flowchart of a method for configuring slice resources for an occupied cell provided by an embodiment of the application;

[0037] Figure 6 FIG. 1 is a flowchart of another slice resource configuration method provided by an embodiment of the present disclosure.

[0038] Figure 7 FIG. 1 is a structural diagram of a slice resource configuration device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] Embodiments of the present application are described in detail below with reference to the accompanying drawings. The embodiments described below are examples for explaining the present application and are not to be construed as limiting the present application.

[0040] The slice resource configuration method, device, electronic equipment and storage medium of the embodiments of the present application are described below with reference to the accompanying drawings.

[0041] Figure 1 FIG. 1 is a flowchart of a slice resource configuration method provided by an embodiment of the present application. As shown in FIG. 1, the method comprises the following steps: Figure 1

[0042] S101, obtaining a coverage grid set of a lightweight RedCap terminal.

[0043] In some implementations, gridding is a process of gridding and presenting an area, for example, taking an area range of 50*50 meters as a grid area, and the 5G coverage intensity in different grids is different. Optionally, gridding can be performed according to a geographic information system (GIS), for example, Figure 1A FIG. 1 is a geographic gridding diagram.

[0044] The coverage grid of the lightweight (Reduced Capability, RedCap) terminal is a grid in the coverage range of the RedCap terminal. In some implementations, the use area of the RedCap terminal can be determined based on business requirements, and the grids intersecting with the use area are taken as the coverage grid of the RedCap terminal, and all the coverage grids constitute the coverage grid set.

[0045] S102, determining one or more occupied cells of the RedCap terminal and the average coverage intensity of the RedCap terminal according to the coverage grid set.

[0046] ​Optionally, the occupied cells of each coverage grid can be acquired, wherein the occupied cells of each coverage grid can be one or more, or zero. According to the occupied cells of each coverage grid, the occupied cells corresponding to the coverage grid set, that is, one or more occupied cells of the RedCap terminal, are determined.

[0047] In some implementations, the coverage intensity of each coverage grid can be acquired, and the average value of the coverage intensity of all coverage grids in the coverage grid set is taken as the average coverage intensity of the RedCap terminal. Optionally, the coverage intensity in this embodiment can be the Reference Signal Receiving Power (RSRP).

[0048] Optionally, the signal intensity of the MR sampling point can be determined according to the Measurement Report (MR), which is one of the main bases for evaluating the quality of the wireless environment, and refers to the data transmitted every 480 ms on the service channel. The MR can be rendered through the uplink and downlink signal intensity distribution to present the network coverage weak blind area, and can be acquired from the network management system (network management system for short). The MR sampling point can be a User Equipment (UE), and based on the MR, at least the cell corresponding to the position of each MR sampling point and the signal intensity of the MR sampling point can be acquired.

[0049] Further, the number of all MR sampling points in each coverage grid can be counted according to the MR, and the average value of the signal intensity of all MR sampling points is calculated as the coverage intensity of the coverage grid. According to the average value of the coverage intensity of all coverage grids, the average coverage intensity of the RedCap terminal is determined.

[0050] S103, in response to the average coverage intensity satisfying the first preset condition and the occupied cells being all normal cells, performing a service capability check on the occupied cells to determine a service check result.

[0051] In some implementations, the first preset condition can be set as a set value, for example, the minimum received signal intensity of the RedCap terminal. When the average coverage intensity of the RedCap terminal is greater than or equal to the minimum received signal intensity of the RedCap terminal, it is determined that the average coverage intensity of the RedCap terminal satisfies the first preset condition, that is, the condition of the coverage grid can satisfy the deployment of the RedCap terminal set this time.

[0052] Further, the cell type of each occupied cell is acquired, the cell type including a normal cell and an abnormal cell, and the premise of network resource configuration of the occupied cell is that the occupied cell must be stable and cannot be a cell with existing abnormal indicators or complaints and other problems, so the cell type of the occupied cell needs to be determined, and the slice resource configuration is performed when all the occupied cells are normal cells. Alternatively, the cell utilization, the average uplink rate and the average downlink rate of the occupied cell can be acquired as characteristic indicators of the occupied cell, and the characteristic indicators are input into a pre-trained classification model to output the cell type of the occupied cell.

[0053] When the average coverage intensity meets the first preset condition and all the occupied cells are normal cells, it is indicated that the current network condition is good, and the service capability of the occupied cell can be checked and the slice resource configuration is performed; correspondingly, if the average coverage intensity does not meet the first preset condition and / or the occupied cell has an abnormal cell, it is indicated that the current network condition does not meet the requirement, and the current network problem needs to be solved before the analysis is performed again until the network condition is good, and the service capability of the occupied cell is checked.

[0054] In some implementations, the service capability check can be a slice resource check of the occupied cell to determine whether the support of the occupied cell for the slice exceeds the quantity limit, for example, to determine the number of slice resources supported by the occupied cell and the number of slice resources configured by the occupied cell, to calculate the number of slice resources supported by the occupied cell and the number of slice resources configured by the occupied cell, to obtain the number of slice resources configurable by the occupied cell, and if the number of slice resources configurable by the occupied cell is greater than or equal to the number of slice resources required by the RedCap terminal, it is indicated that the current occupied cell meets the slice resource configuration condition.

[0055] In some implementations, the service capability check can also include a check on the remaining capacity of the occupied cell, the remaining capacity being the cell uplink capacity and the cell downlink capacity of the occupied cell, and if the cell uplink capacity and the cell downlink capacity are both greater than or equal to zero, it is indicated that the network capacity of the occupied cell meets the slice resource configuration condition; therefore, the slice resource check and the network remaining capacity check of each occupied cell are performed to determine the service check result of the occupied cell.

[0056] S104, performing slice resource configuration on the occupied cell according to the service check result.

[0057] In some implementations, if the service inspection result indicates that the slice resource and the remaining capacity of the occupied cell meet the slice resource configuration condition, the slice resource configuration is performed on the occupied cell, and if the service inspection result indicates that the slice resource and / or the remaining capacity of the occupied cell does not meet the slice resource configuration condition, it is indicated that the current occupied cell is not suitable for direct slice resource deployment, the service inspection result of the current occupied cell is reported and fed back, and other methods are used to analyze the occupied cell in detail to determine the slice resource configuration strategy.

[0058] Optionally, the slice resource configuration method can perform 5G Quality of Service Identifier (5QI) configuration for the card number used by the RedCap terminal. The 5QI configuration of the card number mainly configures the 5QI level corresponding to the user card number. In this embodiment, high-level Guaranteed Bit Rate (GBR) 5QI is used to detect network capability, and 5QI=3 or 5QI=4 is preferably used to realize priority scheduling of network resources, ensure that the user card number can smoothly and maximally temporarily occupy network resources, simulate the allocation of Prioritised Bit Rate (PBR) network resources during slice protection, and avoid excessive occupation of existing To Business (ToB) business resources to cause additional complaints when the terminal appears abnormal or fault light.

[0059] In this embodiment, the coverage grid set of the RedCap terminal is obtained, and the occupied cells and the average coverage intensity are determined according to the coverage grid set, thereby providing an accurate basis for subsequent slice resource configuration of the occupied cells. It is determined whether the average coverage intensity meets the first preset condition and whether the occupied cells are all normal cells, thereby determining the network condition. When the average coverage intensity meets the first preset condition and the occupied cells are all normal cells, the service capability of each occupied cell is checked, thereby determining the service inspection result of each occupied cell. The service inspection result can reflect the resource capability that can be configured for each occupied cell, avoid excessive occupation of resources to cause complaints, perform slice resource configuration according to the service inspection result, improve the accuracy of resource configuration, avoid affecting the actual business of users, and reduce the time cost and improve the efficiency of slice resource configuration.

[0060] On the basis of the above-mentioned embodiments, Figure 2 A flowchart of a method for obtaining a coverage grid set provided by an embodiment of the present application is shown in FIG. Figure 2 As shown in the figure, the method comprises the following steps:

[0061] S201, obtaining the measurement report (MR) reported by the RedCap terminal.

[0062] In some implementations, the measurement report (MR) can be measured by the RedCap terminal in a service process and periodically reported to the network management system, and the MR can be requested from the network management system.

[0063] S202, projecting the MR sampling points of the RedCap terminal based on the MR to determine the candidate grid where the MR sampling points are projected.

[0064] In some implementations, the relevant information of each MR sampling point can be parsed according to the MR, and the relevant information at least includes the identity document (Identity Document, ID) of the occupied cell, the longitude and latitude of the MR sampling point, and the signal strength of the MR sampling point. Therefore, the MR sampling point can be projected on the electronic map according to the longitude and latitude of the MR sampling point to determine the grid where the MR sampling point actually falls, that is, to determine the candidate grid where the MR sampling point is projected; wherein the longitude and latitude of the MR sampling point is calculated by the base station according to the timing advance (Timing Advance, TA) value and the angle of arrival (Angle of Arrival, AOA) to calculate the user equipment position, without the need for terminal capability support.

[0065] S203, determining the use area of the RedCap terminal according to the RedCap terminal demand information.

[0066] In some implementations, the RedCap terminal demand information can be input by the customer or other front-end service personnel. The demand information can include the use area of the RedCap terminal, the uplink bandwidth demand, the downlink bandwidth demand, the number of receiving antennas, and the minimum received signal strength, etc. Therefore, the use area of the RedCap terminal can be determined based on the input demand information.

[0067] For example, the RedCap terminal demand information can refer to Table 1 below. Table 1 includes the number of each RedCap terminal and the demand information corresponding to each RedCap terminal. The demand information includes the uplink bandwidth demand, the downlink bandwidth demand, the number of receiving antennas, the minimum received signal strength, and the use area.

[0068] Table 1

[0069]

[0070] S204, determining the candidate grid with location overlap with the use area as the coverage grid of the RedCap terminal to obtain a set of coverage grids.

[0071] It can be understood that the candidate grid can be marked in the electronic map, and according to the position of the use area of the RedCap terminal on the electronic map, the candidate grid with the position overlap with the use area can be determined as the coverage grid of the RedCap terminal, so as to ensure that the coverage grid has an overlap area with the use area of the RedCap terminal, and improve the accuracy of subsequent analysis based on the coverage grid set.

[0072] In this embodiment, the corresponding candidate grid is determined according to the projection of the MR sampling point, the use area of the RedCap terminal is determined, the candidate grid with the intersection with the use area is determined as the coverage grid to obtain the coverage grid set, and it is ensured that each grid in the coverage grid set is a grid covered by the RedCap terminal, thereby improving the accuracy of subsequent analysis based on the coverage grid set and reducing the coverage grid screening cost.

[0073] On the basis of the above-mentioned embodiments, Figure 3 A flowchart of an average coverage intensity acquisition method provided by the embodiments of the present application is shown in FIG. 1. Figure 3 As shown in the figure, the method comprises the following steps:

[0074] S301, determining a target MR sampling point in a coverage grid, and determining an average first coverage intensity of the coverage grid according to the measurement information of the target MR sampling point.

[0075] It can be understood that the projection position of each MR sampling point can be acquired according to the MR, and therefore the candidate grid corresponding to each MR sampling point can be determined; after the coverage grid set is screened out, for each coverage grid, the target MR sampling point in the coverage grid is acquired, and the signal intensity of the MR sampling point is determined according to the measurement information of the target MR sampling point, that is, the related information of the MR sampling point in the MR. Exemplarily, as shown in Table 2 below, Table 2 comprises each MR sampling point and its related information, that is, the MR sampling point ID, the longitude, the latitude, the corresponding occupied cell ID (5G cell ID) and the signal intensity.

[0076] Table 2

[0077]

[0078] Further, the number of sampling points in each coverage grid can be counted, the average value of the signal intensities of all sampling points in the coverage grid can be calculated as the average first coverage intensity of the coverage grid. Exemplarily, as shown in Table 3 below, Table 3 comprises each coverage grid ID, the number of sampling points in each coverage grid, the corresponding occupied cell ID set (5G cell ID set) and the average first coverage intensity.

[0079] Table 3

[0080]

[0081] S302, the average first coverage intensity is corrected according to the RedCap terminal demand information to obtain the second coverage intensity of the coverage grid.

[0082] In some implementations, the RedCap terminal has reduced performance, and the reduction in the number of receiving antennas will cause the received signal to be weaker, so the above-obtained average first coverage grid is corrected to determine a more accurate coverage intensity of the coverage grid.

[0083] Optionally, the correction calculation of the second coverage intensity can be:

[0084]

[0085] wherein R redcap_fix represents the second coverage intensity of the corrected coverage grid; R represents the average first coverage intensity; redcap rx represents the number of receiving antennas of the RedCap terminal, and the value is the minimum value of the minimum number of receiving antennas in the set of all RedCap terminals, which is obtained from the RedCap terminal demand information; phone rx represents the number of receiving antennas of the conventional terminal, and in the present embodiment, phone rx = 4.

[0086] Exemplary illustration, as shown in Table 4, Table 4 includes each coverage grid ID, the number of sampling points in each coverage grid, the corresponding occupied cell ID set (5G cell ID set), the average first coverage intensity and the corrected second coverage intensity.

[0087] Table 4

[0088]

[0089] S303, according to the second coverage intensity of the coverage grid to determine the average coverage intensity of the RedCap terminal.

[0090] Obtain the average value of the second coverage intensity of all coverage grids in the coverage grid set corresponding to the RedCap terminal as the average coverage intensity of the RedCap terminal.

[0091] Further, in combination with the demand information corresponding to each RedCap terminal, the minimum required received signal strength, uplink bandwidth requirement, downlink bandwidth requirement, coverage grid ID set, occupied cell ID set (5G cell ID set), usage area, and corresponding average coverage strength corresponding to each RedCap terminal can be determined. As shown in Table 5, the average coverage strength of the RedCap terminal in Table 5 is obtained by averaging the second coverage strength of each coverage grid in the coverage grid ID set, and the 5G cell ID set, that is, the occupied cell set that the RedCap terminal can occupy, is obtained by summarizing the 5G cells associated with each coverage grid.

[0092] Table 5

[0093]

[0094]

[0095] In this embodiment, according to the signal strength of the MR sampling point, the average first coverage strength of the coverage grid where the MR sampling point is located is determined. In order to improve the accuracy of the coverage strength, the average first coverage strength is corrected based on the number of receiving antennas to obtain a more accurate second coverage strength. Then, according to the more accurate second coverage strength of each coverage grid, the average value is calculated to obtain the average coverage strength of the RedCap terminal. The accuracy of the average coverage strength is higher and the adaptability is stronger.

[0096] On the basis of the above-mentioned embodiments, Figure 4 A flowchart for determining the cell type of an occupied cell is provided in the embodiments of the present application. As shown in Figure 4 The method comprises the following steps:

[0097] S401, input the characteristic data of the occupied cell into the pre-trained target classifier, and output the cell type of the occupied cell from the target classifier.

[0098] Currently, operators generally deploy Deep Packet Inspection (DPI) systems, network management systems, complaint systems, soft probe systems, and hard probe systems, and can monitor the performance of the cell from each system. Therefore, the indicators and services in the cell in the network can be statistically analyzed for abnormalities in the past week. In this embodiment, 15 minutes is taken as a period, the indicators of the occupied cell in each period are obtained as the characteristic data of the occupied cell, and whether the occupied cell is an abnormal cell is determined according to the characteristic data. In this embodiment, if any indicator is abnormal in a period, the occupied cell is determined to be an abnormal cell in the period. If there is no indicator in a certain occupied cell, it is determined that the indicator of the occupied cell is not abnormal.

[0099] As shown in Table 6, Table 6 includes each occupied cell ID and the characteristic data of each occupied cell in a period (15 minutes).

[0100] Table 6

[0101]

[0102] Wherein, the time refers to the start time of the statistical period, the antenna height, the antenna tilt angle, the cell timing advance (TA) mean value, the radio resource control (RRC) connection maximum number, the cell utilization rate, the cell user uplink average rate, the cell user downlink average rate and the cell uplink average interference level and other characteristic data can be determined from each system, and the average station spacing can be calculated based on the Taylor polygon algorithm.

[0103] In some implementations, a Delaunay triangular network can be constructed with all network base stations as endpoints. In this embodiment, one base station corresponds to one cell, so for each occupied cell of the RedCap terminal, the corresponding point in the Delaunay triangular network can be determined. When constructing the Delaunay triangular network with base stations as endpoints, regardless of where the network is started, the same result will be obtained eventually, that is, the network has uniqueness, which guarantees the consistency and stability of the analysis result. The construction principle of the Delaunay triangular network includes that the circumcircle of each Delaunay triangle does not contain any other points in the plane (base stations in this embodiment), which is called the empty circumcircle property of the Delaunay triangular network; the diagonal of the convex quadrilateral formed by two adjacent triangles does not increase the minimum angle of the six internal angles after mutual exchange.

[0104] In the Delaunay triangular network, the other base stations directly connected to the target base station are the first circle neighboring base stations of the target base station, and the average distance of the target base station to all base stations within the first circle in geographical position is the average station spacing of the target base station, as shown in Figure 4A The Delaunay triangular network is constructed based on the discrete base station point diagram, as shown in Figure 4B Taking any base station in the Delaunay triangular network as a target base station, the neighboring base stations within the first circle are obtained, and the average value of the distance of all base stations within the first circle is calculated to obtain the average station spacing corresponding to the target base station. In this way, for each occupied cell in the RedCap terminal, the base station corresponding to the occupied cell in the Delaunay triangular network is taken as a target base station, and the average station spacing of the target base station is determined according to the Delaunay triangular network.

[0105] In some implementations, the training process of the target classifier can include:

[0106] (1) Select an abnormal cell sample in historical data, and determine a normal cell sample according to the abnormal cell sample.

[0107] In some implementations, a normal cell sample can be selected as a normal cell directly connected to a center point of each abnormal cell sample in a Delaunay triangulation network. The Delaunay triangulation network includes all base stations in the network, that is, all cell samples, so that the abnormal cell samples in the Delaunay triangulation network can be determined, and a normal cell directly connected to each abnormal cell sample as a center point can be selected as a normal cell sample. This avoids the imbalance of machine learning samples caused by too few abnormal cells, which affects the model effect. The adjacent normal cells of the abnormal cells are used as normal cell samples to achieve the balance of sample points and improve the effect of subsequent model training.

[0108] (2) Update the first feature data of the abnormal cell sample and the second feature data of the normal cell sample according to the handover relationship between the cells in the historical data.

[0109] It can be understood that users will move between different base stations, so that the base station accessed by the user will be switched from one base station to another. The switching process of the base station accessed by the user is the handover relationship between cells. In this embodiment, the graph attention mechanism is used to represent the handover relationship between cells, as shown in FIG. 1. Wherein A, B, C and D constitute the nodes of the graph, and the handover relationship constitutes the edges of the graph. There are bidirectional handover relationships (AB, AC) and unidirectional handover relationships (DC). The cell feature data is updated based on the proportion of the number of handovers between cells, so as to avoid the interference of weakly related and unrelated cell features. Figure 4C

[0110] Optionally, for any feature data of any abnormal cell sample, the update formula of the feature data is:

[0111]

[0112] Wherein, represents the updated first feature data; cell j represents the first feature data before updating; T all represents the total number of hand-in times in all handover relationships; T i represents the number of times that the current abnormal cell sample j is handed in; n represents the number of adjacent cells of all hand-in times of the current abnormal cell sample j; cell i represents the feature data of the cell sample i having the hand-in relationship.

[0113] ​Based on the above feature data update formula, the first feature data of the abnormal cell sample and the second feature data of the normal cell sample are updated. For example, assuming that cell j Five cells with hand-in relationship are collected in the cell, and the hand-in times are shown in Table 7:

[0114] Table 7

[0115]

[0116] cell j The calculation method of the cell feature data update is as follows:

[0117]

[0118] (3) Training the classifier according to the updated first feature data, the second feature data, the first label of the abnormal cell sample and the second label of the normal cell sample to obtain the target classifier.

[0119] In some implementations, the first label of the abnormal cell sample and the second label of the normal cell sample are obtained, wherein the first label and the second label are used to represent the cell type of the corresponding cell sample, for example, the first label of the abnormal cell sample is no or 0, indicating that the cell type of the cell sample is abnormal, and the second label of the normal cell sample is yes or 1, indicating that the cell type of the cell sample is normal.

[0120] Further, the updated first feature data, the second feature data, the first label of the abnormal cell sample and the second label of the normal cell sample can be summarized to obtain Table 8 below, which includes each cell sample, the updated feature data corresponding to the cell sample and the label.

[0121] Table 8

[0122]

[0123] Further, the classifier can use a support vector machine algorithm with a polynomial kernel function. Support vector machine is a kind of machine learning algorithm, which can convert feature data to high-dimensional space and find the optimal decision boundary in the new space to achieve good classification. The support vector machine used in the present embodiment can be obtained from the machine learning algorithm library SKlearn, and a support vector machine (Support Vector Machine, SVM) classifier is created, the kernel function is set to a polynomial kernel, the order is 3, the penalty parameter C is 1.0, i.e. svm=SVC(kernel='poly',degree=3,C=1.0,random_state=1).

[0124] The SVM classifier capable of classifying cell types is obtained by training the SVM classifier through the abnormal cell samples and the normal cell samples, so as to determine whether each occupied cell is a normal cell according to the pre-trained target SVM classifier to judge the cell types of the occupied cells in each time period.

[0125] In the embodiment, the Delaunay triangulation network is constructed with the whole network cells as end points, the corresponding average inter-station distance is determined according to the connection relationship between the cells, the normal cell samples are screened based on the abnormal cell samples in the Delaunay triangulation network, so that the sample types are more balanced, a more accurate target classifier is trained, the periodic characteristic data of the sample cells are obtained, the characteristic data are updated according to the switching relationship between the cells, the target classifier is pre-trained with the updated characteristic data to obtain a target classifier with higher accuracy and stronger adaptability, the cell types of each occupied cell are identified according to the target classifier, and accurate classification is realized.

[0126] On the basis of the above embodiment, Figure 5 A flowchart for configuring slice resources of an occupied cell is provided in the embodiment of the disclosure. As shown in the figure, Figure 5 The method comprises the following steps:

[0127] S501, determine the uplink capacity prediction value and the downlink capacity prediction value of the occupied cell.

[0128] In some implementations, before determining the uplink capacity prediction value and the downlink capacity prediction value of the occupied cell, the number of slices supported by each occupied cell, the number of configured slices of the occupied cell, and the number of required slices of the occupied cell can be obtained; in response to the number of supported slices being greater than or equal to the sum of the number of configured slices and the number of required slices, the uplink capacity prediction value and the downlink capacity prediction value of the occupied cell are determined according to the pre-trained capacity prediction model.

[0129] Optionally, the number of slices supported by the occupied cell can be denoted as C_slice, and a typical value of C_slice is 256 slices; the number of configured slices of the occupied cell is denoted as C_used, and the number of required slices of the occupied cell is denoted as C_slice_need, and in this embodiment, C_slice_need = 1; whether the occupied cell satisfies the following condition is determined according to C_slice, C_used and C_slice_need: C_slice-C_used-C_slice_need≥0, that is, the number of supported slices C_slice is greater than or equal to the sum of the number of configured slices C_used and the number of required slices C_slice_need, and in response to the occupied cell satisfying the above condition C_slice-C_used-C_slice_need≥0, the uplink capacity prediction value and the downlink capacity prediction value of the occupied cell are determined according to the pre-trained capacity prediction model.

[0130] Optionally, the pre-trained capacity prediction model can include an uplink capacity prediction model and a downlink capacity prediction model, the uplink capacity prediction model is used to obtain the uplink capacity prediction value, and the downlink capacity prediction model is used to obtain the downlink capacity prediction value.

[0131] In some implementations, a cell feature is constructed by network indicators and basic network structure indicators of all cells in the network, and the average rate (full bandwidth) of the network management indicators of the uplink and downlink users is used as a label, two neural network models, that is, an uplink capacity prediction model and a downlink capacity prediction model, are constructed respectively, and the average rate (full bandwidth) of the uplink and downlink users is predicted respectively, and the average rate (full bandwidth) of the uplink and downlink users is used as an equivalent peak capacity indicator of the cell, and this kind of conservative prediction method can improve the stability of the algorithm.

[0132] Optionally, the features and labels used to train the uplink capacity prediction model and the downlink capacity prediction model are mainly obtained by calculation or network management indicators, as shown in Table 9, and Table 9 includes common features of each occupied cell, uplink model features, downlink model features, uplink model labels and downlink model labels.

[0133] Table 9

[0134]

[0135] It can be understood that, when training the uplink capacity prediction model, pre-training is performed based on the common features, the uplink model features and the uplink model labels, and when training the downlink capacity prediction model, pre-training is performed based on the common features, the downlink model features and the downlink model labels, thereby obtaining the pre-trained uplink capacity prediction model and the pre-trained downlink capacity prediction model. In this embodiment, the uplink capacity prediction model and the downlink capacity prediction model are both neural network models, the neural network input layer is connected to the features (common features and uplink model features / downlink model features), 1 hidden layer is set, which is a full connection layer with 10 neurons, each neuron is connected to the features of the previous layer and has a perception weight W=(w1, w2, …, wn), and also has an offset b, and the output layer is the predicted cell capacity, and all parameters are obtained through neural network model iterative learning.

[0136] Currently, not all cell indicators in the network have the uplink and downlink user average rate (full bandwidth) indicator, which can only be counted through network management when there are fully scheduled users in the cell. In this embodiment, the cell features and labels with this indicator are used for model training, and the subsequent time period indicators of all cells in the network can be predicted through the pre-trained neural network model. After predicting and summarizing the uplink capacity and downlink capacity of the occupied cells, as shown in Table 10, the uplink capacity prediction value and the downlink capacity prediction value of all occupied cells are included.

[0137] Table 10

[0138]

[0139] S502, according to the uplink capacity prediction value and the downlink capacity prediction value, respectively determining the uplink residual capacity and the downlink residual capacity of the occupied cell as the service check result.

[0140] The network capacity of the cell needs to carry the reserved slice resources, GBR type services, basic service demands of ToC users, etc., and also needs to carry the newly added RedCap service, so the uplink residual capacity or downlink residual capacity of the occupied cell can be calculated by the following formula:

[0141] cell_ca_left=cell_ca-cell_prb_pre-cell_gbr-cell_nongbr-cell_redcap

[0142] cell ca left = cell ca - cell prb pre - cell gbr - cell nongbr - cell redcap

[0143] Further, the upper limit of the capacity of the occupied cell that can be used for ToB services can also be obtained, and the specific calculation is as follows:

[0144] cell config gbr = cell ca - cell prb pre - cell gbr - cell nongbr

[0145] Wherein, cell config gbr represents the upper limit of the capacity of the occupied cell that can be used for ToB services.

[0146] In some implementations, the calculation method of cell prb pre can be:

[0147] cell prb pre = cell prb pre nb / cell prb av * cell ca

[0148] Wherein, cell prb pre nb represents the sum of the number of all reserved PRBs of the occupied cell, which is obtained by network management statistics; cell prb av represents the number of all available PRBs of the occupied cell, which is obtained by network management statistics.

[0149] In some implementations, the calculation method of cell nongbr can be:

[0150] cell nongbr = user nongbr nb * user pre

[0151] Wherein, user nongbr nb represents the number of non-GBR users who are not guaranteed bit rate, which can be obtained from the wireless network management; user pre represents the minimum guaranteed rate of each nongbr user, which is set to user pre = 0.3 Mbps.

[0152] In some implementations, the calculation method of cell redcap can be:

[0153]

[0154] wherein c redcap need k represents the bandwidth requirement of the RedCap terminal that the occupied cell needs to carry, which is from the sum of the bandwidths of the RedCap terminals associated with the occupied cell in Table 5; k represents the index of the occupied cell; cell_sdm represents the spatial division multiplexing factor of the occupied cell, which is obtained by the radio network management, and in this embodiment, the equivalent capacity is amplified in combination with the number of spatial division multiplexing layers of the cell, and a certain wireless capacity equivalent margin is considered, which can improve the stability of system calculation.

[0155] The uplink residual capacity and the downlink residual capacity of the occupied cell are obtained based on the uplink residual capacity or the downlink residual capacity of the occupied cell, and the uplink residual capacity and the downlink residual capacity of the occupied cell are taken as the service checking result of the occupied cell.

[0156] S503, performing slice resource configuration on the occupied cell according to the service checking result.

[0157] In some implementations, if the service checking result indicates that the uplink residual capacity and the downlink residual capacity of all occupied cells are greater than or equal to zero, it is determined that the current network capacity meets the basic condition, and the slice resource configuration can be performed; correspondingly, if the service checking result indicates that the current network capacity does not meet the basic condition, more detailed evaluation needs to be performed on the slice resource configuration of each occupied cell.

[0158] In some implementations, when the business check result meets the basic condition, slice configuration can be performed for the occupied cell that the RedCap terminal may occupy, and 5QI configuration can be performed for the card number used by the RedCap terminal; the slice resource is mainly to configure the slice ID on the cell, and the slice ID is automatically generated by the orchestration system according to the rules; the 5QI configuration of the card number is mainly to configure the 5QI level corresponding to the user card number, and this embodiment adopts high-level GBR 5QI to detect network capability, and recommends using 5QI=3 or 5QI=4 to realize the priority scheduling of network resources and ensure that the user card number can smoothly and maximally temporarily occupy network resources, simulate the allocation of cell PRB network resources during slice guarantee, and simulate the network resources that should be occupied by the user RedCap terminal when working normally in this way. For example, as shown in Table 11, Table 11 is a network resource configuration table in this embodiment, wherein the GBR value is configured according to the uplink bandwidth requirement and downlink bandwidth requirement field in the requirement information of the RedCap terminal, the maximum bit rate (MBR) is configured according to the minimum cell_config_gbr of the occupied cell in the occupied cell ID set corresponding to each RedCap terminal, and the MBR represents the upper limit of the GBR service rate, so as to avoid excessive occupation of existing ToB type business resources when the terminal abnormally or fails, and cause additional complaints.

[0159] Table 11

[0160]

[0161] The network resources can be configured according to the above Table 11, after the network configuration is completed, the RedCap terminal user can be notified to open the card and the terminal is online, after the terminals are all online, further enter the business joint debugging stage, and confirm the reserved proportion of the slice PRB resource by observing the stable business and the network resource usage.

[0162] Optionally, observation data in use of the RedCap terminal can be obtained; it is judged whether the observation data meets a preset condition; in response to the observation data meeting the preset condition, slice PRB reserved resources of each actual occupied cell corresponding to the RedCap terminal are determined according to the slice group uplink PRB occupation number and the slice group downlink PRB occupation number.

[0163] In some implementations, the network performance index is observed after the terminal is online to confirm that the network usage is in a steady state, and a week is usually taken as an index observation period, that is, the index data in a week is taken as the observation data in use of the RedCap terminal; it is further judged whether the observation data meets the following preset conditions:

[0164] (1) There is no RedCap terminal user complaint related to this analysis in T period and T+1 period;

[0165] (2) Extract the traffic information of the RedCap terminal through the billing system, and the change of the traffic of each terminal is within the threshold (Threshold, TH) compared with the T period and the T+1 period. In this embodiment, the TH value is 5%;

[0166] (3) Analyze the actual occupied wireless cell set cell_real of the RedCap terminal through the DPI technology. The cell_real has n_real cells, and there is no new cell compared with the T period and the T+1 period.

[0167] (4) The traffic distribution of each terminal in the occupied cell is basically consistent.

[0168] In some implementations, the network management indicators "slice group uplink PRB occupation number" and "slice group downlink PRB occupation number" corresponding to the slice ID of each occupied cell in the cell_real cell set can be extracted through network management. Taking the slice group uplink PRB occupation number as an example, the cell_real cell set will take n_real occupied cell indicators to form an n_real-dimensional vector. The similarity of the two vectors is compared by using the Pearson correlation coefficient. Compared with the T period and the T+1 period, if the correlation coefficient is greater than or equal to P_TH, it is considered that the vectors are related. The value range of the Pearson correlation coefficient is -1 to 1. -1 represents negative correlation, 0 represents no correlation, and 1 represents positive correlation. In this embodiment, P_TH is set to 0.7.

[0169] Optionally, the calculation formula of the Pearson correlation coefficient is:

[0170]

[0171] Wherein, ρ(X,T) represents the Pearson correlation coefficient between vector X and vector Y; σX represents the standard deviation of vector X; σY represents the standard deviation of vector Y; cov(X,Y) represents the covariance between vector X and vector Y.

[0172] Further, based on the above method of analyzing the slice group uplink PRB occupation number, the Pearson correlation coefficient of the slice group downlink PRB occupation number is calculated in the T period and the T+1 period. When the uplink and downlink traffic distribution in the T+1 period and the T period are similar, it is considered that the traffic of each terminal in the occupied cell has basically entered a steady state, and it can be considered that the network situation at this time is consistent with the daily normal use. At this time, the slice PRB reserved resources of each occupied cell should be configured, and the maximum value of the "slice group PRB occupation number" in the T period and the T+1 period is taken. It can be understood that the uplink PRB reserved resource value and the downlink PRB reserved resource value are obtained by the same method.

[0173] As shown in Table 12, the slice group uplink PRB occupation number and the slice group downlink PRB occupation number of each occupied cell in the T period and the T+1 period are exemplarily illustrated. When the uplink and downlink traffic distribution in the T+1 period and the T period are similar, the slice PRB reserved resources configured by the occupied cell are the maximum value of the slice group PRB occupation number in the T period and the T+1 period; that is, the slice group uplink PRB occupation number of the occupied cell 460-00-12639628-91 is 12, the slice group downlink PRB occupation number is 3; the slice group uplink PRB occupation number of the occupied cell 460-00-12639628-91 is 6, the slice group downlink PRB occupation number is 3; the slice group uplink PRB occupation number of the occupied cell 460-00-12639628-91 is 3, and the slice group downlink PRB occupation number is 2.

[0174] Table 12

[0175]

[0176] Further, after the traffic of each terminal in the occupied cell enters a steady state, the PRB reserved resources of the slice, the cell slice ID resources and the 5QI resources can also be configured according to the network usage; it can be understood that the cell_real cell set is the actual occupied cell set, the configured slice ID of the non-cell_real cell set is deleted to avoid invalid occupation of the slice ID to the cell slice configuration number; the 5QI value of the card number corresponding to the RedCap terminal is adjusted to the level of the ordinary card to avoid subsequent improper occupation of the network and to recover the 5QI network resources; and each occupied cell of the RedCap terminal is configured according to the slice group uplink PRB occupation number and the slice group downlink PRB occupation number of each occupied cell obtained above.

[0177] In the embodiment, the slice resources of the occupied cell are obtained, the uplink capacity prediction value and the downlink capacity prediction value are obtained by the capacity prediction model when the number of slice resources meets the preset condition, the uplink capacity prediction model is trained based on the common feature, the uplink model feature and the uplink model label, the downlink capacity prediction model is trained based on the common feature, the downlink model feature and the downlink model label, the capacity prediction value is predicted based on the uplink capacity prediction model and the downlink capacity prediction model, the accuracy of obtaining the uplink capacity prediction value and the downlink capacity prediction value is improved, the uplink residual capacity and the downlink residual capacity are calculated according to the uplink capacity prediction value and the downlink capacity prediction value, the slice configuration is performed when the residual capacity meets the preset condition, the observation data is obtained after the slice configuration to observe, the network performance is detected, the slice PRB reserved resources are configured after the observation service is stable, and the slice resources are recovered, thereby avoiding invalid occupation of the cell slice configuration, improving the resource configuration efficiency and accuracy, and reducing the cost of configuration calculation.

[0178] Figure 6 Another flowchart of a slice resource configuration method provided by an embodiment of the present disclosure is shown in FIG. 6. As shown in the figure, the method comprises the following steps: Figure 6

[0179] S601, obtaining a measurement report (MR) reported by a RedCap terminal.

[0180] In the embodiment of the present disclosure, the implementation method of step S601 can be realized by any one of the embodiments of the present disclosure, and here it is not limited, nor will it be elaborated again.

[0181] S602, projecting the MR sampling points of the RedCap terminal based on the MR, and determining the candidate grid where the MR sampling points are projected.

[0182] In the embodiment of the present disclosure, the implementation method of step S602 can be realized by any one of the embodiments of the present disclosure, and here it is not limited, nor will it be elaborated again.

[0183] S603, determining the use area of the RedCap terminal according to the RedCap terminal requirement information.

[0184] In the embodiment of the present disclosure, the implementation method of step S603 can be realized by any one of the embodiments of the present disclosure, and here it is not limited, nor will it be elaborated again.

[0185] S604, determining the candidate grid that has a location overlap with the use area as the coverage grid of the RedCap terminal, to obtain a coverage grid set.

[0186] In the embodiment of the present disclosure, the implementation method of step S604 can be realized by any one of the embodiments of the present disclosure, and here it is not limited, nor will it be elaborated again.

[0187] S605, determining a target MR sampling point in the coverage grid, and determining the average first coverage intensity of the coverage grid according to the measurement information of the target MR sampling point.

[0188] In the embodiment of the present disclosure, the implementation method of step S605 can be realized by any one of the embodiments of the present disclosure, and here it is not limited, nor will it be elaborated again.

[0189] S606, correcting the average first coverage intensity according to the RedCap terminal requirement information to obtain a second coverage intensity of the coverage grid.

[0190] ​In the embodiments of the present disclosure, the implementation method of step S606 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0191] S607, determining the average coverage intensity of the RedCap terminal according to the second coverage intensity of the coverage grid.

[0192] In the embodiments of the present disclosure, the implementation method of step S607 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0193] S608, inputting the feature data of the occupied cell into the pre-trained target classifier, and outputting the cell type of the occupied cell by the target classifier.

[0194] In the embodiments of the present disclosure, the implementation method of step S608 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0195] S609, in response to the average coverage intensity satisfying the first preset condition and the occupied cell being a normal cell, determining the uplink capacity prediction value and the downlink capacity prediction value of the occupied cell.

[0196] In the embodiments of the present disclosure, the implementation method of step S609 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0197] S610, according to the uplink capacity prediction value and the downlink capacity prediction value, respectively determining the uplink residual capacity and the downlink residual capacity of the occupied cell as the service inspection result.

[0198] In the embodiments of the present disclosure, the implementation method of step S610 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0199] S611, performing slice resource configuration on the occupied cell according to the service inspection result.

[0200] In the embodiments of the present disclosure, the implementation method of step S611 can be implemented by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0201] In this embodiment, the corresponding candidate grid is determined according to the projection of the MR sampling point, the use area of the RedCap terminal is determined, the candidate grid intersecting with the use area is taken as the coverage grid to obtain the coverage grid set, and the coverage grid screening cost is reduced; the average first coverage intensity of the coverage grid where the MR sampling point is located is determined according to the signal intensity of the MR sampling point, the average first coverage intensity is corrected based on the number of receiving antennas to obtain a more accurate second coverage intensity, and then the average coverage intensity of the RedCap terminal is obtained according to the more accurate second coverage intensity of each coverage grid, thereby providing an accurate basis for subsequent slice resource configuration of the occupied cell; whether the average coverage intensity meets the first preset condition and whether the occupied cell is all normal cells are determined according to the pre-trained target classifier, so as to accurately determine the network condition; when the average coverage intensity meets the first preset condition and the occupied cell is all normal cells, the service capability of each occupied cell is checked, the slice resource of the occupied cell is obtained, the uplink capacity prediction value and the downlink capacity prediction value are obtained through the capacity prediction model when the number of slice resources meets the preset condition, and the service check result obtained can reflect the configurable resource capability of each occupied cell, thereby avoiding excessive occupied resources causing complaints, the slice resource configuration is performed according to the service check result, the observation data is obtained after the slice configuration to observe, the network performance is detected, the slice PRB reserved resource configuration is performed after the observation service is stable, and the slice resource is recycled, thereby avoiding invalid occupation of the cell slice configuration, and improving the resource configuration efficiency and accuracy.

[0202] To implement the above-mentioned embodiments, the application further provides a slice resource configuration device.

[0203] Figure 7 A structural schematic diagram of a slice resource configuration device provided by the embodiments of the application is shown in FIG. 1. Figure 7 As shown in the figure, the slice resource configuration device comprises:

[0204] A first obtaining module 701 is configured to obtain a coverage grid set of a lightweight RedCap terminal.

[0205] A second obtaining module 702 is configured to determine one or more occupied cells of the RedCap terminal and the average coverage intensity of the RedCap terminal according to the coverage grid set.

[0206] A third obtaining module 703 is configured to, in response to the average coverage intensity meeting the first preset condition and the occupied cells being all normal cells, perform service capability checking on the occupied cells to determine a service check result.

[0207] A configuration module 704 is configured to perform slice resource configuration on the occupied cells according to the service check result.

[0208] Further, in a possible implementation manner of the embodiment of the present application, the first obtaining module 701 comprises:

[0209] obtaining a measurement report MR reported by the RedCap terminal;

[0210] projecting the MR sampling point of the RedCap terminal based on the MR, to determine a candidate grid where the MR sampling point is projected;

[0211] determining a use area of the RedCap terminal according to the RedCap terminal requirement information;

[0212] determining a candidate grid having a location overlap with the use area as a coverage grid of the RedCap terminal, to obtain a coverage grid set.

[0213] Further, in a possible implementation manner of the embodiment of the present application, the second obtaining module 702 comprises:

[0214] determining a target MR sampling point in the coverage grid, and determining an average first coverage intensity of the coverage grid according to the measurement information of the target MR sampling point;

[0215] correcting the average first coverage intensity according to the RedCap terminal requirement information, to obtain a second coverage intensity of the coverage grid;

[0216] determining an average coverage intensity of the RedCap terminal according to the second coverage intensity of the coverage grid.

[0217] Further, in a possible implementation manner of the embodiment of the present application, the apparatus 700 further comprises:

[0218] inputting the feature data of the occupied cell into a pre-trained target classifier, and outputting a cell type of the occupied cell by the target classifier; wherein the training process of the target classifier comprises:

[0219] selecting an abnormal cell sample in the historical data, and determining a normal cell sample according to the abnormal cell sample;

[0220] updating first feature data of the abnormal cell sample and second feature data of the normal cell sample according to the switching relationship between the cells in the historical data;

[0221] training the classifier according to the updated first feature data, the second feature data, and a first label of the abnormal cell sample and a second label of the normal cell sample, to obtain the target classifier.

[0222] Further, in a possible implementation manner of the embodiment of the present application, the apparatus 700 comprises:

[0223] The Delone triangle network is constructed with all cell samples in historical data as end points.

[0224] Each normal cell sample is selected as a center point in the Delone triangle network, and a normal cell directly connected to the center point is selected as a normal cell sample.

[0225] Further, in a possible implementation of the embodiment of the application, the third obtaining module 703 comprises:

[0226] The uplink capacity prediction value and the downlink capacity prediction value of the occupied cell are determined.

[0227] According to the uplink capacity prediction value and the downlink capacity prediction value, the uplink residual capacity and the downlink residual capacity of the occupied cell are determined as the service check result.

[0228] Further, in a possible implementation of the embodiment of the application, the third obtaining module 703 comprises:

[0229] The number of supported slices, the number of configured slices and the number of required slices of each occupied cell are obtained.

[0230] In response to the number of supported slices being greater than or equal to the sum of the number of configured slices and the number of required slices, the uplink capacity prediction value and the downlink capacity prediction value of the occupied cell are determined according to the pre-trained capacity prediction model.

[0231] Further, in a possible implementation of the embodiment of the application, the configuration module 704 further comprises:

[0232] Observation data in use of the RedCap terminal is obtained.

[0233] It is determined whether the observation data meets a preset condition.

[0234] In response to the observation data meeting the preset condition, the slice PRB reserved resources of each actual occupied cell corresponding to the RedCap terminal are determined according to the slice group uplink PRB occupation number and the slice group downlink PRB occupation number.

[0235] It should be noted that the foregoing explanation and description of the slice resource configuration method embodiment are also applicable to the slice resource configuration device of this embodiment, which will not be described here.

[0236] In the embodiments of the present application, the corresponding candidate grid is determined according to the projection of the MR sampling point, the use area of the RedCap terminal is determined, the candidate grid intersecting with the use area is taken as the coverage grid to obtain the coverage grid set, and the coverage grid screening cost is reduced; the average first coverage intensity of the coverage grid where the MR sampling point is located is determined according to the signal intensity of the MR sampling point, the average first coverage intensity is corrected based on the number of receiving antennas to obtain a more accurate second coverage intensity, and then the average coverage intensity of the RedCap terminal is obtained according to the more accurate second coverage intensity of each coverage grid, thereby providing an accurate basis for subsequent slice resource configuration of the occupied cell; whether the average coverage intensity meets the first preset condition and whether the occupied cell is all normal cells are determined according to the pre-trained target classifier, so as to accurately determine the network condition; when the average coverage intensity meets the first preset condition and the occupied cell is all normal cells, the service capability of each occupied cell is checked, the slice resource of the occupied cell is obtained, the uplink capacity prediction value and the downlink capacity prediction value are obtained through the capacity prediction model when the number of slice resources meets the preset condition, and the service check result obtained can reflect the configurable resource capability of each occupied cell, thereby avoiding excessive occupied resources causing complaints, performing slice resource configuration according to the service check result, and observing the observation data after the slice configuration to realize the detection of network performance, performing slice PRB reserved resource configuration after observing the stable service, and recycling the slice resource, thereby avoiding invalid occupation of the cell slice configuration, and improving the resource configuration efficiency and accuracy.

[0237] To achieve the above-mentioned embodiments, the present application further provides an electronic device, comprising a processor and a memory connected with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to realize the method provided by the foregoing embodiments.

[0238] To achieve the above-mentioned embodiments, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to realize the method provided by the foregoing embodiments.

[0239] To achieve the above-mentioned embodiments, the present application further provides a computer program product, comprising a computer program, which is executed by the processor to realize the method provided by the foregoing embodiments.

[0240] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the present application comply with relevant laws and regulations and do not violate public order and good customs.

[0241] It is important to note that user's personal information should be collected for legitimate and reasonable uses of the entity and not shared or sold outside of those legitimate uses. Further, such collection / sharing should occur after the user is informed of and individually agrees to the purposes for which the personal information is being collected and shared. Additionally, appropriate measures and / or steps should be taken to safeguard and secure access to such personal information data and ensure that other users with access to the personal information data adhere to the entity's privacy policies and procedures. Thus, the entity can provide users with the opportunity to individually or collectively manage their personal information data by requesting access to and / or modifying or deleting such personal information data.

[0242] The present application contemplates that user selective blocking of use or access of personal information data can be provided. That is, the present disclosure contemplates that hardware and / or software elements can be provided to prevent or block access to such personal information data. For example, in the case of collection of personal information data, the present technology can provide users with control over how their personal information data is shared by the entity or used, through customization of

[0243] In the preceding embodiments descriptions, the description referring to the terms “one embodiment”, “some embodiments”, “an example”, “a specific example”, or “some examples” etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. Furthermore, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples, without contradiction.

[0244] In addition, the terms “first”, “second”, etc. are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with “first”, “second” can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of “plurality” is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0245] Any process or method descriptions or any other descriptions in flow diagrams or otherwise described herein can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions (or steps) and / or can be implemented in hardware or software, including both general and special purpose systems. It should also be understood that each flow diagram and / or detailed description of steps is merely illustrative and explanatory, and that the order of the steps can be varied, including the order of the steps can be reversed, unless otherwise specifically stated, and that some steps can be omitted, unless otherwise specifically stated. The scope of embodiments of the present application encompasses these and other possible variations.

[0246] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, a processor-based system, or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or a combination thereof. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus or device. The computer readable medium can specifically be, but is not limited to, the following: an electronic connection (electronic apparatus) having one or more wires, a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disk read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium upon which the program can be printed, because the program can be electronically obtained, for example, by optically scanning the paper or other medium, then

[0247] It should be understood that portions of the application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or a combination thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0248] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing relevant hardware, and the programs can be stored in a computer readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0249] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0250] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for configuring slice resources, characterized in that, include: Obtain the set of overlay grids for the lightweight RedCap endpoint; The RedCap terminal's one or more occupied cells and the RedCap terminal's average coverage strength are determined based on the coverage grid set. When the average coverage strength meets the first preset condition and all the occupied cells are normal cells, a service capability check is performed on the occupied cells to determine the service check result. Based on the results of the business inspection, the occupied cell is allocated slice resources.

2. The method according to claim 1, characterized in that, The acquisition of the coverage grid set of the lightweight RedCap terminal includes: Obtain the measurement report MR reported by the RedCap terminal; Based on the MR, the MR sampling points of the RedCap terminal are projected to determine the candidate grid where the MR sampling point projection is located; The usage area of ​​the RedCap terminal is determined based on the RedCap terminal demand information; Candidate grids that overlap with the area of ​​use are identified as overlay grids for the RedCap terminal, thus obtaining the set of overlay grids.

3. The method according to claim 2, characterized in that, The process of determining the average coverage strength of the RedCap terminal includes: Identify the target MR sampling point within the coverage grid, and determine the average first coverage intensity of the coverage grid based on the measurement information of the target MR sampling point; The average first coverage strength is corrected based on the RedCap terminal demand information to obtain the second coverage strength of the coverage grid; The average coverage strength of the RedCap terminal is determined based on the second coverage strength of the coverage grid.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: The feature data of the occupied cell is input into a pre-trained target classifier, which outputs the cell type of the occupied cell; wherein, the training process of the target classifier includes: Select abnormal cell samples from historical data, and determine normal cell samples based on the abnormal cell samples; Based on the handover relationships between cells in historical data, update the first feature data of the abnormal cell samples and the second feature data of the normal cell samples; The target classifier is obtained by training a classifier based on the updated first feature data, second feature data, first label of the abnormal cell sample, and second label of the normal cell sample.

5. The method according to claim 4, characterized in that, The step of determining normal cell samples based on the abnormal cell samples includes: Using all cell samples from the historical data as endpoints, construct the Denello triangulation; Using each of the abnormal cell samples in the De Nero triangulation as the center point, the normal cells directly connected to the center point are selected as the normal cell samples.

6. The method according to claim 1, characterized in that, The step of performing a service capability check on the occupied cell and determining the service check result includes: Determine the predicted uplink capacity and predicted downlink capacity of the occupied cell; Based on the predicted uplink capacity and the predicted downlink capacity, the remaining uplink capacity and the remaining downlink capacity of the occupied cell are determined respectively, and used as the service inspection result.

7. The method according to claim 6, characterized in that, Determining the predicted uplink capacity and predicted downlink capacity of the occupied cell includes: Obtain the number of slices supported by each occupied cell, the number of slices already configured in the occupied cell, and the number of slices required by the occupied cell; In response to the fact that the number of supported slices is greater than or equal to the sum of the number of configured slices and the number of required slices, the uplink capacity prediction value and downlink capacity prediction value of the occupied cell are determined according to the pre-trained capacity prediction model.

8. The method according to any one of claims 1-3, characterized in that, After configuring slice resources for the occupied cell based on the service inspection results, the method further includes: Acquire observation data during the use of the RedCap terminal; Determine whether the observed data meets the preset conditions; In response to the observation data meeting preset conditions, the slice PRB reserved resources for each actual occupied cell corresponding to the RedCap terminal are determined based on the uplink PRB occupancy count and the downlink PRB occupancy count of the slice group.

9. A slice resource allocation device, characterized in that, include: The first acquisition module is used to acquire the set of overlay grids of the lightweight RedCap terminal; The second acquisition module is used to determine one or more occupied cells of the RedCap terminal and the average coverage strength of the RedCap terminal based on the coverage grid set; The third acquisition module is used to perform a service capability check on the occupied cells and determine the service check result when the average coverage strength meets the first preset condition and all the occupied cells are normal cells. The configuration module is used to configure slice resources for the occupied cell based on the service inspection results.

10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-8.

Images