Beam determination method, device, electronic device and computer readable storage medium

Abstract

The embodiment of the present application provides a beam determination method, device, electronic device and computer-readable storage medium, the method comprising: obtaining service distribution data of each set area of ​​a cell; determining the beam corresponding to the cell according to the service distribution data of each set area. Based on the solution provided by the embodiment of the present application, the flexibility of the beam required by the cell is achieved, the communication performance of hot spots with large traffic volume is improved, and the user experience of the hot spots is improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular, to a beam determination method, device, electronic device, and computer-readable storage medium. Background Art

[0002] The wireless communication system transmits data via wireless beams. The set of all beams used by the base station for beam measurement and data transmission is called beambook, and the number of beams in the beambook is the beambook size. The beambook management scheme in the existing system is: all base stations in the network use a fixed beambook, and within the beambook, the angle distribution of the beam is generally uniform or approximately uniform. The above beambook management scheme in the prior art needs to be further optimized. Summary of the invention

[0003] The purpose of the present application is to provide a beam determination method, device, electronic device and computer-readable storage medium. Based on this method, the existing beam management solution is optimized.

[0004] In a first aspect, an embodiment of the present application provides a beamforming method, the method comprising:

[0005] Obtaining service distribution data for each set area of ​​the cell;

[0006] According to the service distribution data of each set area, the beam corresponding to the cell is determined.

[0007] In a second aspect, an embodiment of the present application provides a beam determination device, the device comprising:

[0008] A service data acquisition module, used to acquire service distribution data of each set area of ​​the cell;

[0009] The beam determination module is used to determine the beam corresponding to the cell according to the service distribution data of each set area.

[0010] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory: wherein the memory is used to store a computer program; and the processor is used to execute the method shown in the first aspect above when executing the computer program stored in the memory.

[0011] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method shown in the first aspect above is implemented.

[0012] The beneficial effects of the technical solution provided by the present application are as follows: the solution provided by the embodiment of the present application can realize the flexible selection of the beam required by the cell based on the business distribution data of the cell. Compared with the existing solution, the solution provided by the embodiment of the present application can not only improve the communication performance of the hotspot area with large business volume and improve the user experience of the hotspot area, but also avoid the waste of beam resources under the premise of ensuring the communication performance of the non-hotspot area, thereby optimizing the existing beam management method. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in describing the embodiments of the present application.

[0014] Figure 1 A schematic diagram showing a beam radiation direction;

[0015] Figure 2 A schematic diagram showing the HPBW of a beam;

[0016] Figure 3 A schematic diagram showing the beam area (set area) of a cell;

[0017] Figure 4a A schematic diagram of the flow chart of the existing beam determination method is shown;

[0018] Figure 4b A schematic diagram of beam distribution in an existing beambook is shown;

[0019] Figure 5 A schematic diagram of coverage effect based on an existing beam management solution is shown;

[0020] Figure 6 A schematic diagram of a process flow of a beam determination method provided in an embodiment of the present application is shown;

[0021] Figure 7 A schematic diagram of the beam coverage effect based on the solution provided in the embodiment of the present application is shown;

[0022] Figure 8a A schematic diagram of a process flow of a beam determination method in an embodiment of the present application is shown;

[0023] Figure 8b A schematic diagram showing the principle of a beam determination method in an embodiment of the present application is shown;

[0024] Fig. 9 A schematic diagram showing a flow chart of a business distribution data prediction method in an example of the present application is shown;

[0025] Fig.10aA schematic diagram showing the relationship between the number of beams and service distribution data in an example of the present application is shown;

[0026] Fig.10b A schematic diagram showing the relationship between the number of beams and service distribution data in another example of the present application is shown;

[0027] Fig.11a A schematic diagram showing coverage information of a beam area in an example of the present application;

[0028] Fig.11b Shows Fig.11a Schematic diagram of the horizontal beam width and vertical beam width of the beam area shown in;

[0029] Fig.12 A schematic diagram showing a candidate beam subset with different beam widths in an example of the present application;

[0030] Fig.13a A schematic diagram of a beam subset in an example of the present application is shown in FIG.

[0031] Fig.13b A schematic diagram of each beam region included in a joint region in an example of the present application is shown in FIG.

[0032] Fig.13c Shows Fig.13b Schematic diagram of the beam in the joint region shown in;

[0033] Fig.14 A schematic diagram showing the received power of a wide beam and a narrow beam signal is shown;

[0034] Fig.15a , Fig.15b and Fig.15c Schematic diagrams of three different application scenarios in the simulation experiment of the present application are respectively shown;

[0035] Fig.16a , Fig.16b and Fig.16c Schematic diagrams of cumulative distribution function curves of user throughput in three different application scenarios in the simulation experiment of the present application are respectively shown;

[0036] Fig.17 A schematic diagram of the structure of a beam determination device provided in an embodiment of the present application is shown in FIG.

[0037] Fig.18 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0038] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0039] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0040] In order to better understand the solutions provided by the embodiments of the present application, the relevant technologies and technical terms involved in the present application are first briefly explained below.

[0041] In 5G systems, especially in the A6G (above 6GHz) frequency band, due to cost and antenna array size limitations, analog beams are used for link transmission in the system. The characteristics of the beam directly affect the strength of the received signal, thereby affecting system coverage and user performance. By designing the phase offset of each antenna element of the transmit / receive antenna, the system can use analog beams with different beam widths, horizontal angles, and vertical angles. The analog beams are used for transmission through TDM (time-division multiplexing).

[0042] In a communication system, each beam is combined with a set of spatial properties { θ, HPBW h , HPBW v} corresponds to, such as Figure 1 In the schematic diagram of the beam radiation direction of the antenna array shown in , x, y, and z are three directions of the three-dimensional coordinate system, where r represents the beam radiation direction. The horizontal angle of the maximum radiation direction of the beam, and θ represents the vertical angle of the maximum radiation direction of the beam. HPBW (half-power beam width) is the half-power beam width, also known as the 3dB (decibel) beam width, which is the beam width between two points where the power in the direction of maximum radiation of the beam drops by half (3dB), such as Figure 2 As shown in , wherein HPBW includes HPBW h and HPBW v , HPBW h HPBW stands for horizontal half-power beam width, which can be called the horizontal width of the beam. It is an important indicator reflecting the horizontal width of the beam. v Indicates the vertical half-power beam width, which can be called the vertical width of the beam. It is an important indicator reflecting the width of the beam in the vertical direction. θ, HPBW h , HPBW h}The parameter value is determined by the antenna array element phase.

[0043] Beam width: refers to the coverage of the beam, which can also be called beam coverage, including the beam width in the horizontal direction (horizontal dimension) and the beam width in the vertical direction (vertical dimension). The beam width in the horizontal dimension is also the coverage angle of the horizontal dimension, which is the HPBW described in the previous article. h , the vertical beam width is also the vertical coverage angle, which is the HPBW described above v For example, if the angular coverage range of a beam's horizontal dimension is 10° to 20°, then the beam width of the beam's horizontal dimension is 10°.

[0044] The setting area, which will also be referred to as beam area in the following description, is the area corresponding to the horizontal angle coverage range and vertical angle coverage range of the beam used by the UE (User Equipment) for the current beam measurement / reporting. It is customized or configured by the base station. A cell usually includes several setting areas. The coverage ranges of different setting areas may be the same or different.

[0045] like Figure 3In the schematic diagram of the beam area shown in , for the beam area 1 shown in the figure, 1 is the identifier of the set area, and the beam area 1 refers to an area in which the horizontal coverage angle range of the cell is [0°, 13°] (the corresponding horizontal dimension width of the beam area is 13°-0°=13°), and the vertical coverage angle range is [84°, 96°] (the corresponding vertical dimension width of the beam area is 96°-84°=12°). The beam area 1 is the coverage range of the beam with sequence number 1 used for the current measurement / reporting.

[0046] The coverage range information of the set area, which can also be referred to as beam area information, refers to information that can determine the horizontal coverage angle range and the vertical coverage angle range of the set area, i.e., the beam area. The beam area information can be explicit information, for example, the horizontal start angle and end angle, and the vertical start angle and end angle of the beam area. For example, Figure 3 For the beam area 1 shown in the figure, its beam area information includes: the horizontal starting angle is 0°, the horizontal ending angle is 13°, the vertical starting angle is 84°, and the vertical ending angle is 96°; the beam area information may also be implicit information, such as the horizontal center point angle and the vertical center point angle of the beam area, as well as the horizontal coverage angle size (i.e., the horizontal dimension width) and the vertical coverage angle size (vertical dimension width). For example, for the above-mentioned beam area 1, its beam area information may also include: the horizontal center point angle is 6.5°, the vertical center point angle is 90°, the horizontal coverage angle size is 13°, and the vertical coverage angle size is 12°.

[0047] In the current beam management scheme, the beambook of each cell is usually determined in the design phase and generally does not change after the design is completed. In addition, the coverage angles of the beams in the beambook set are also evenly or approximately evenly distributed. Figure 4a , a flow chart of an existing beam selection method is shown in FIG. As shown in the figure, the general flow of the method is: first, according to the beambook size restriction information and the beam coverage range of the cell (i.e., the horizontal coverage range and vertical coverage range of the cell, such as the horizontal and vertical angle ranges shown in the figure) requirements (usually determined according to the network coverage scenario of each operator), the beambook size of the cell, as well as the number of beams in the horizontal dimension and the number of beams in the vertical dimension (the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction in the antenna array, determined according to the beambook size restriction and the possible beam widths supported by the antenna array) are determined, and then the position of each beam (i.e., the horizontal angle) is calculated based on the principle of evenly distributing the beams within the beam coverage range of the cell. and vertical angle θ) and beam width.

[0048] As an example, Figure 4b , a schematic diagram of beam distribution in an existing beambook is shown in FIG. As shown in the figure, the horizontal dimension coverage angle range (the horizontal angle range shown in the figure) corresponding to the beambook in the schematic diagram is [-120°, 120°], and the vertical dimension coverage angle range (the vertical angle range shown in the figure) is [-12°, 12°]. Each ellipse in the figure represents a beam, and the size of the ellipse represents the coverage range of the corresponding beam. The coverage angles of the beams in the beambook are evenly distributed. It can be seen from the figure that the number of beams arranged in the horizontal direction in the figure is 16, and the number of beams arranged in the vertical direction is 4. Then the HPBW of each beam in the beambook is h 240° / 16 or 15°, HPBW v is 24° / 4, or 6°, and the The set of is {±7.5,±22.5,…}, and the set of θ is {±3°,±9°}.

[0049] It can be seen that the existing beam management scheme does not identify the service distribution in the cell. Therefore, the prior information about the service distribution in the cell is not considered when selecting the bean, and it is impossible to select the beam for the cell scenario to flexibly generate the beambook. However, in actual applications, the service distribution within the cell coverage is usually not uniform. Using the fixed beambook with uniform beam distribution determined by the existing traditional method in a cell with uneven service distribution will lead to the following problems:

[0050] In areas with low business density, i.e. low load areas, beam utilization is low; while in hotspots, i.e. areas with high business density, the density of existing beams (the number of beams in a set area) cannot meet user needs. Therefore, the traditional beam management solution with fixed beambook cannot flexibly select beams according to different business distributions in the cell, cannot enhance coverage in hotspots, cannot provide higher system performance for hotspots, and will lead to low beam utilization in areas with low business density, resulting in waste of resources. Figure 5A schematic diagram of beam coverage effect based on an existing management solution is shown in FIG. The largest elliptical area in the figure represents the coverage range of a cell (i.e., a base station), and the beams in each beam area of ​​the cell are evenly distributed. However, in actual applications, area A1 in the figure is a hotspot area, i.e., a high-load service area, and area A2 is a low-load area. However, based on the existing solution, the beam density of hotspot area A1 and low-load area A2 is the same, which will result in poor coverage effect in area A1 and poor user communication effect, while beam resources will be wasted in area A2. It can be seen that the existing beam management solution needs to be further optimized.

[0051] In view of the problems existing in the prior art, the embodiments of the present application provide a beam determination method, device, electronic device and computer-readable storage medium. The scheme proposed in the present application can use the historical data of cell service distribution to predict the cell service distribution, and adaptively select beams for areas with different service densities according to the predicted service distribution to form a beambook for the cell. Through this scheme, more beams with narrower widths can be selected for hotspot areas, so as to bring coverage gain to hotspot areas by using beams with higher density and narrower widths, and fewer beams with wider widths can be selected for low-load areas to improve beam utilization efficiency and maintain coverage, thereby ensuring communication performance in low-load areas.

[0052] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems will be described in detail with reference to the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0053] Figure 6 A schematic flow chart of a beam determination method provided by an embodiment of the present application is shown. As shown in the figure, the method may include the following steps:

[0054] Step S110: Acquire service distribution data of each set area of ​​the cell;

[0055] Step S120: Determine the beam corresponding to the cell according to the service distribution data of each set area.

[0056] The service distribution data of the set area refers to data that can reflect the service distribution of the area of ​​the cell, and the data can specifically refer to the service volume or the service density. In practical applications, since the coverage areas of different beam areas may be the same or different, in order to more reasonably select beams for each beam area, as an optional method, the service distribution data can be the service density of the beam area, and the service density can be determined based on the service volume and the coverage area of ​​the beam area.

[0057] When the service distribution data adopts service density, the service density may be a service volume per unit area or a relative service density. For example, for a set area, the service density of the set area may be obtained by dividing the service volume of the area by the coverage area of ​​the area. In this case, the service density is the service volume per unit area. The service density of the set area may also be obtained by dividing the service volume of the area by a reference area (the reference area may be the coverage area of ​​any set area of ​​the cell or any set area). In this case, the service density is a relative service density.

[0058] In addition, it should be noted that the service distribution data specifically refers to the service distribution data of which service parameters or service parameters, which can be configured according to actual needs, and can be the service distribution data of one service parameter, or can be the characterization data of the service distribution data of multiple service parameters. Among them, the service parameter refers to a parameter that can reflect the communication quality or communication performance, which can include but is not limited to the throughput, the number of connected UEs, the amount of cached data (such as the amount of cached data to be transmitted), and other parameters.

[0059] Based on the solution provided by the present application, since the beam of the cell is flexibly determined according to the business distribution data of each set area of ​​the cell, it can adapt well to the business volume distribution of the cell, so that the beam density of the business hotspot area, that is, the business high-load area, is higher, and the coverage performance of the hotspot area is improved, and the beam density of the business low-load area is lower. It can avoid the waste of beam resources while ensuring the communication performance of the low-load area, realize the adaptive selection of beam based on business distribution, and realize the flexible management of beam.

[0060] In practical applications, in order to more objectively evaluate whether a set area is a high-load area or a low-load area, the above-mentioned service distribution data may specifically be the service distribution data after normalization processing, that is, the above-mentioned service density.

[0061] In an optional embodiment of the present application, obtaining service distribution data of each set area of ​​a cell includes:

[0062] Obtaining area-related information of the cell;

[0063] The service distribution data of each set area of ​​the cell is determined according to the area related information of the cell.

[0064] In the embodiment of the present application, the area-related information of the cell refers to the information about the area covered by the cell, which may refer to the information about the service distribution of each set area of ​​the cell that can affect or may affect the cell. The specific information included can be configured or adjusted according to the actual application scenario. As an optional method, the area-related information of the cell may include environmental data and / or location information of the cell.

[0065] Among them, environmental data may include but are not limited to time, date, weather, events, etc., wherein events refer to events that may affect the business, such as concerts, competitions, etc. The granularity of the division of time, date, weather and other information can be configured and adjusted according to demand. In this scheme, the specific method of determining the business distribution data of each set area of ​​the cell based on the area-related information of the cell is not limited in the embodiment of the present application. For example, statistical analysis can be performed on the historical area-related information of each cell and the historical business distribution data of each set area of ​​the corresponding cell, and a mapping relationship between the area-related information and the business distribution data is established based on the analysis results. When it is necessary to determine the current business distribution data of each set area of ​​the cell, the corresponding business distribution data can be found from the mapping relationship based on the current area-related information of the cell.

[0066] As another optional method for predicting business distribution data, in order to improve the objectivity of the prediction, an AI (Artificial Intelligence) algorithm with learning ability can be used to predict business distribution data, that is, business prediction can be performed through a business prediction model.

[0067] Specifically, in an optional embodiment of the present application, determining the service distribution data of each set area of ​​the cell according to the area related information of the cell may include:

[0068] According to the area-related information of the cell, the business distribution data of each set area is predicted through the business prediction model.

[0069] Optionally, the business prediction model can be trained in the following ways:

[0070] Acquire training samples, wherein the training samples include sample area related information of cells of each category and sample service distribution data of each set area of ​​the cell corresponding to the sample area related information of each category;

[0071] The initial prediction model is trained based on the sample area related information of each category until the predicted business distribution data of each category output by the initial prediction model and the sample business distribution data corresponding to the category meet the preset conditions, and the prediction model at the end of the training is used as the business prediction model.

[0072] The sample region related information of each category may include one or more types of region information belonging to the same category.

[0073] In practical applications, the sample area related information may specifically be historical area related information of the cell, which may include but is not limited to the location of the cell, and / or historical environmental data of the cell, etc., and the sample business distribution data may be historical business distribution data corresponding to the historical area related information. In order to train the initial prediction model, each type of sample area related information may be annotated with a corresponding category label, which characterizes the sample business distribution data of each set area of ​​the cell corresponding to the sample area related information of that type. During training, the classified sample area related information is used as the input of the model, and the output of the model is the predicted business distribution data. The model parameters are continuously updated and optimized according to the predicted business distribution data and the corresponding business distribution data in the sample to obtain the final business prediction model.

[0074] Among them, the model architecture based on the business prediction model is not limited in the embodiment of the present application. For example, an SVM (Support Vector Machine) model can be used, or other models can be used. The input of the model is the area-related information of the cell, and the output is the business distribution data of each set area of ​​the predicted cell.

[0075] In an optional embodiment of the present application, obtaining training samples may specifically include:

[0076] Acquire each initial sample data, wherein one piece of initial sample data includes initial area related information of a cell and initial service distribution data of the cell under the initial related information, wherein the initial service distribution data of a cell includes service distribution data of each set area of ​​the cell;

[0077] Determine the category of the initial service distribution data of the cell in each piece of initial sample data, and obtain the classification result of each piece of initial service distribution data;

[0078] Based on the classification results of each initial service distribution data, the initial area related information of the cell corresponding to each initial service distribution data is marked with a corresponding category label to obtain the related information of each sample area;

[0079] Based on each initial business distribution data belonging to the same category, sample business distribution data corresponding to sample historical area related information of the same category is obtained.

[0080] Each piece of initial sample data may be historical data of a cell obtained by statistics, such as historical environmental data of the cell and historical business distribution data of each set area of ​​the corresponding cell. In order to better train the model, the initial area related information and the corresponding initial business distribution data in the initial sample data may be classified first, and the model may be trained based on the classified data.

[0081] When classifying, the classification algorithm can be used to classify the acquired initial business distribution data (business distribution data of each set area of ​​the cell), and the initial area related information corresponding to each initial business distribution data can be classified based on the classification results of each initial business distribution data. Since each category of the classified initial business distribution data can include multiple initial business distribution data, and multiple initial business distribution data may correspond to multiple initial area related information, multiple area related information may correspond to the same classification mark, and the sample business distribution data corresponding to the sample area related information of each category can be obtained based on the initial business distribution data of the category, such as the average value, or weighted average value, of the initial business distribution data of the category, or other data fusion methods, to obtain the sample business distribution data corresponding to the category, thereby establishing a corresponding relationship between the sample area related information of each category and the corresponding sample business distribution data. Among them, the classification algorithm can be selected according to the needs, such as the Pearson correlation coefficient algorithm (also known as the Pearson association classification algorithm) can be used.

[0082] As an example, assume that the vector corresponding to the initial business distribution data of the cell included in one initial sample data can be expressed as [1.5, 1.7, 2.9, 0, 33], and the vector corresponding to the initial business distribution data of the cell included in another initial sample data can be expressed as [3, 3, 3, 3, 3], where the number of elements in the vector is the number of set areas contained in the cell, and the value of each element is the value used to characterize the business distribution data of each set area. When determining whether the business distribution data of the two cells belong to the same category, it can be determined based on the correlation between the two vectors, such as determining whether the business distribution data of the two cells belong to the same category through the Pearson correlation classification algorithm.

[0083] After completing the classification of the initial sample data, the relevant information of each sample area with classification marks, i.e., classification labels, can be used as the input of the model to train the model. The model parameters can be updated based on the predicted service distribution data of the cell output by the model and the sample service distribution data of the corresponding category. The model that meets the training end conditions will be used as the service prediction model.

[0084] In an optional embodiment of the present application, if the initial service distribution data of the cell includes service distribution data corresponding to at least two service parameters, determining the category of the initial service distribution data in each piece of initial sample data includes:

[0085] For any two pieces of initial sample data, for each service parameter, respectively determine the correlation between the service distribution data of the cells corresponding to the service parameter in the two pieces of initial sample data;

[0086] Based on the correlation corresponding to each service parameter in the two pieces of initial sample data, determining whether the initial service distribution data of the cells in the two pieces of initial sample data are of the same category;

[0087] Accordingly, based on each initial business distribution data belonging to the same category, sample business distribution data corresponding to sample historical area related information of the same category is obtained, including:

[0088] Based on the initial service distribution data of each service parameter belonging to the same category, sample service distribution data corresponding to the area related information of the same category is obtained.

[0089] As can be seen from the foregoing description, the service distribution data of a cell can be service data that can characterize multiple service parameters, that is, for each initial area-related information, the initial service distribution data of the cell can include initial service distribution data of multiple service parameters. In practical applications, in order to improve the objectivity of model prediction and enable the service distribution data predicted by the model to more objectively reflect the actual service distribution of the cell, for the initial service distribution data of the cell under each area-related information, the initial service distribution data corresponding to multiple different service parameters can be selected as the basic data for model training. At this time, when the initial service distribution data of the cell corresponding to each area-related information (multiple service distribution data corresponding to multiple service parameters) is classified, for the initial service distribution data of the cell corresponding to any two area-related information (which can be two area-related information of the same cell or two area-related information of different cells), it can be based on the data correlation of the initial service distribution data of the cell corresponding to each service parameter under the two area-related information to comprehensively determine whether the initial service distribution data of the cell corresponding to the two area-related information belongs to the same category.

[0090] For example, there are two types of service parameters, and for each type of area-related information, the initial service distribution data of the cell corresponding to the area-related information includes the service distribution data corresponding to the two parameters. When determining whether the initial service distribution data of two cells are of the same type, the correlation of the two distribution data under each service parameter can be calculated respectively, and then based on the correlation corresponding to the two service parameters, it is determined whether the initial service distribution data of the two areas are of the same type.

[0091] As an optional method, when determining whether the initial business distribution data of the cells in two initial sample data are of the same category based on the correlation corresponding to each business parameter, it is possible to determine whether the two initial business distribution data in the two initial sample data are of the same category based on the correlation of the business distribution data of the cells corresponding to each business parameter of the cells in the two initial sample data and the weight corresponding to each business parameter.

[0092] Since different business parameters may have different effects on communication performance in actual applications, that is, the importance of each business parameter may be different, based on this, the weight corresponding to each business parameter can be configured, and the correlation corresponding to each business parameter can be weightedly integrated to obtain the correlation between the business distribution data of the two cells, thereby determining whether the business distribution data of the two cells can be divided into the same category, and whether the area-related information corresponding to the business distribution data of the two cells belongs to the same category.

[0093] The specific method of obtaining the sample business distribution data corresponding to the regional related information of the same category based on the initial business distribution data of each business parameter belonging to the same category is not limited in the embodiment of the present application. For example, the initial business distribution data of each business parameter of the same category may be averaged or weighted fused.

[0094] After obtaining the service distribution data of each set area of ​​the cell, the beam of each set area of ​​the cell can be flexibly determined based on the service distribution data to obtain the beambook of the cell.

[0095] It should be noted that, in actual applications, when the service distribution data of a cell is represented by service data of multiple service parameters, it is also possible to separately determine the service distribution data of each set area of ​​the cell corresponding to each service parameter, and determine the beam of the set area based on the service distribution data of each set area corresponding to each service parameter. For example, based on the determined service distribution data of the set area corresponding to the service parameter, new service distribution data that can characterize the service distribution data of each service parameter of the cell can be determined according to preset rules, such as averaging or weighted averaging the service distribution data of each service parameter to obtain new service distribution data, and determining the beam of the set area based on the new service distribution data.

[0096] Correspondingly, when predicting the business distribution data of each set area of ​​the cell through the business prediction model, it is also possible to train corresponding business prediction models for each business parameter separately. If the business parameters include two types, the business prediction model corresponding to each business parameter can be trained based on the training samples corresponding to each business parameter, or the model parameters corresponding to each business parameter can be trained. Based on the business prediction model or model parameters corresponding to each business parameter, the business distribution data of each set area corresponding to each business parameter can be obtained.

[0097] In an optional embodiment of the present application, in the above step S110, determining the beam corresponding to the cell according to the service distribution data of each set area includes:

[0098] Determine the total number of beams required for each set area based on the business distribution data of each set area;

[0099] Determine the width of the beam required for each set area according to the total number of beams required for each set area;

[0100] Based on the width of the beam required for each set area, each beam of each set area is determined from the candidate beam set.

[0101] In an optional embodiment of the present application, for a set area, determining the width of the beam required for the set area according to the total number of beams required for the set area includes:

[0102] Determine the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction of the set area according to the total number of beams required for the set area and the ratio information of the beams arranged in the horizontal direction and the beams arranged in the vertical direction of the set area;

[0103] The width of the beam required for the set area is determined according to the coverage information of the set area, the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction of the set area.

[0104] Among them, it can be known from the above description that the beam width required for each set area includes the horizontal beam width (ie, horizontal beam width) and vertical beam width (ie, vertical beam width) required for the set area.

[0105] Since the arrangement direction of the beam includes vertical arrangement and horizontal arrangement, after determining the total number of beams required for each set area, the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction required for the set area can be determined according to the ratio of the beams arranged in the horizontal direction to the beams arranged in the vertical direction (which can be referred to as the ratio of the number of vertical and horizontal beams), and the beam width required for the set area can be further determined according to the set area information of each set area, that is, the width of the beam in the horizontal dimension required for the set area is determined according to the angle coverage of the horizontal dimension of the set area and the number of beams arranged in the horizontal direction, and the width of the beam in the vertical dimension required for each set area is determined according to the angle coverage of the vertical dimension of each set area and the number of beams arranged in the vertical direction. After determining the width of the beam required for each set area, the beam of each set area can be determined from the candidate beams to obtain the beambook of the cell.

[0106] It should be noted that the ratio information of the beams arranged in the horizontal direction and the beams arranged in the vertical direction can be directly the ratio of the number of vertical and horizontal beams, or other information that can be used to determine the ratio, such as information on the number of horizontal beams and the number of vertical beams that can represent the beam area.

[0107] In an optional embodiment of the present application, for a set area, based on the beam width required for the set area, each beam of the set area is determined from a candidate beam set, including:

[0108] Determine, based on the beam width required for the set area, candidate beams for the set area from the candidate beam set;

[0109] Based on the distance between each candidate beam and the set area, each beam of the set area is determined from each candidate beam of the set area.

[0110] The candidate beam set refers to all beams in the system, and the beams contained in the beambook of each cell are all beams in the set. For a set cell, after determining the required beam width for each set area of ​​the cell, all beams in each set area can be selected from all candidate beams in the system according to the required beam width, thereby generating the beambook of the cell. Specifically, for a set area, all beams in the set area can be screened out according to the beam width of the beam required for the set area and the beam width of the beam in the candidate beam set.

[0111] As an optional solution, for each set area, when determining the beam of the set area, some candidate beams can be firstly selected from the candidate beam set based on the beam width of the beam required by the set area, and then the beams of the set area can be selected based on the distance between each candidate beam and the set area.

[0112] Among them, it is clear to those skilled in the art that the distance from the beam to the set area refers to the distance from the beam to the center of the set area, and the specific calculation method of the distance from one beam to another is the existing technology, which can be specifically determined based on the direction vector of the center position of the beam and the center point vector of the set area.

[0113] In an optional embodiment of the present application, the candidate beam set includes candidate beam subsets divided according to beam widths; in this case, for a set area, based on the beam width required for the set area, determining the candidate beams of the set area from the candidate beam set may specifically include:

[0114] Based on the beam width of the set area and the beam width corresponding to each candidate beam subset, a target beam subset corresponding to the set area is determined from each candidate beam subset, and each beam in the target beam subset is used as each candidate beam of the set area.

[0115] As an optional solution, the candidate beam set of the system may include multiple beam subsets, and the beam subsets may be divided according to beam widths, that is, the system supports multiple candidate beam subsets with different beam widths. In this case, based on the beam width required for each set area, firstly, according to the beam width of each candidate beam subset, a candidate beam subset for selecting each set area may be determined from each candidate beam subset, and then the final beam of each set area may be determined from the determined target candidate beam subset. Specifically, for a set area, the candidate beam subset whose beam width is closest to the beam width of the set area may be used as the target candidate beam subset for the application area.

[0116] It should be noted that, for each candidate beam subset, the beam width of the beam subset refers to a width used to characterize the beam width of each beam included in the subset. The representation method of the beam width of the candidate beam subset is not limited in the embodiment of the present application. For example, when each beam is divided into different beam subsets, the beam width corresponding to each subset can be configured, and each beam is divided into a subset of corresponding width according to the beam width of each beam and the beam width of each subset. At this time, the beam width of each subset can be a pre-configured beam width, or the beam width of the subset can be determined according to the beam widths of all beams divided into the subset, such as determining the average of the beam widths of all beams divided into the subset as the beam width of the beam subset.

[0117] In an optional embodiment of the present application, for a set area, based on the beam width required for the set area, each beam of the set area is determined from a candidate beam set, including:

[0118] If the total number of beams required for the set area is less than the first set value, the set area and the adjacent set areas of the set area are taken as a joint area, and each beam of the joint area is determined from the candidate beam set based on the beam width required for the joint area.

[0119] The first setting value may be configured as required, for example, may be set to 1.

[0120] In order to better improve the utilization rate of beams, when the number of beams required for a set area is less than a set value, multiple (including two) adjacent set areas can be treated as a joint area. At this time, the beam width required for a joint area is determined based on the beam widths required for each set area included in the joint area. Specifically, the beam width selected for the joint area can be the largest beam width among the beam widths required for each set area included in the joint area to ensure the coverage effect of each beam area, or it can be the beam width selected by each set area included in the joint area, that is, the beam width of the joint area includes multiple beam widths.

[0121] It is understandable that when the candidate beam set includes multiple candidate beam subsets, the target candidate beam subset corresponding to the joint region can be determined from each candidate beam subset based on the beam width required for the joint region, and then each beam of the joint region is determined from the subset based on the distance between each beam in the target candidate beam subset and the joint region. Wherein, for a set region whose required total number of beams is less than a first set value, the adjacent set region of the set region may be any one or more set regions adjacent to the set region, or may be an adjacent set region determined according to a certain rule, such as an adjacent region whose required total number of beams is also less than the first set value.

[0122] It should also be noted that, in the embodiment of the present application, two set areas being adjacent may mean that the area coverage (which may be horizontal and / or vertical) of the two set areas are adjacent, or that the distance between the two set areas (such as the distance between the center point vectors of the two set areas) meets preset conditions, such as being less than the set distance. It is also possible to determine which set areas are adjacent areas based on preconfigured rules.

[0123] In an optional embodiment of the present application, based on the beam width required by the joint region, each beam of the joint region is determined from a candidate beam set, including:

[0124] Determining a beam width required for the combined area based on beam widths required for each of the set areas included in the combined area;

[0125] Determine candidate beams for the joint region from the candidate beam set based on the beam width required for the joint region;

[0126] Based on the distances between each candidate beam and each set area included in the joint area, each beam of the joint area is determined from each candidate beam.

[0127] The beam width required for the joint region is determined based on the beam widths required for each of the set regions included in the joint region. Specifically, the beam width required for the joint region may be the largest beam width required for each of the set regions included in the joint region, or may be each beam width required for each of the set regions included in the joint region. When each beam width required for each of the set regions included in the joint region is used as the beam width required for the joint region, each candidate beam of the joint region determined from the candidate beam set includes each candidate beam determined from the candidate beam set based on each beam width required for each of the set regions included in the joint region. For example, a joint region includes two set regions, the beam width selected for one of the set regions is width A, and the beam width required for the other set region is width B. The beam width required for the joint region may be the larger of width A and width B, or may include width A and width B.

[0128] The principle of determining each beam of a set area described above is the same as that of determining each beam of a set area. When determining each beam of a joint area, each candidate beam of the joint area may be determined first, and then based on the above distance, each final beam of the joint area may be screened out from each candidate beam, wherein the distance of a beam to a joint area may be determined based on the distance of the beam to each set area included in the joint area, such as the sum of the distances of the beam to each set area included in the joint area, that is, a sum distance, the maximum value or minimum value of the distances of the beam to each set area included in the joint area, or an average value, etc. Similarly, when the candidate beam set includes multiple subsets, each candidate beam of the joint area may be each beam in the target candidate beam subset determined according to the beam width required by the joint area.

[0129] In an optional embodiment of the present application, the joint area may satisfy at least one of the following:

[0130] The total number of beams required for each set area included in the joint area is the same;

[0131] The beam widths required for each set area included in the joint area are the same;

[0132] The total number of beams required by each of the set areas included in the joint area is less than the first set value;

[0133] The sum of the total number of beams required by all the set areas included in the joint area is less than the second set value.

[0134] That is to say, when determining the set areas included in the joint area, the determination may be based on at least one of the beam width required by each set area and the total number of beams. Wherein, when the beam widths required by each set area included in the joint area are the same, the beam width required by the joint area may be directly determined as the beam width required by the set areas included therein. It is understood that the second set value is not less than the first set value, and optionally, the second set value may be equal to the first set value.

[0135] In an optional embodiment of the present application, for a set area, determining the total number of beams required for the set area according to the business distribution data of the set area includes at least one of the following:

[0136] Determine the total number of beams required for the set area according to the service distribution data of the set area and the mapping relationship between the pre-configured service distribution data and the number of beams;

[0137] The total number of beams required for the set area is determined according to the business distribution data of the set area and at least one of the following information:

[0138] The total service data distribution of all set areas of the cell, the size of the cell's beambook, the set value of the minimum number of beams in the set area, and the set value of the maximum number of beams in the set area.

[0139] As an optional solution, the total number of beams required for each set area can be determined through a pre-configured business volume mapping relationship. Specifically, different business distribution data can be mapped to a beam quantity. After the business distribution data of each set area is determined, the corresponding beam quantity can be found through the mapping relationship. The beam quantity refers to the total number of beams required for the set area.

[0140] In addition, due to limited system resources, the size of the beambook of each cell is restricted, and the number of beams that can be used in each set area may be restricted, that is, the set value of the maximum number of beams mentioned above. In order to ensure the coverage effect of each set area, each set area can also be set with a minimum number of beams, that is, the set value of the minimum number of beams mentioned above. Therefore, when determining the total number of beams required for each set area of ​​a cell, in addition to considering the business distribution data of the set area, the total business data distribution of all set areas of the cell to which the set area belongs, the size of the beambook, the set value of the minimum number of beams of the set area, the set value of the maximum number of beams of the set area and other factors can also be considered, so as to determine all beams of each area as reasonably as possible based on the business distribution data of each set area on the premise of meeting some restrictions specified by the system.

[0141] In an optional embodiment of the present application, the ratio of the beams arranged in the horizontal direction to the beams arranged in the vertical direction of each set area is preconfigured; or, is determined by any of the following methods:

[0142] Determine, according to the coverage information of each set area, the ratio of the beams arranged in the horizontal direction to the beams arranged in the vertical direction of each set area;

[0143] According to the coverage information of all the set areas of the cell, the ratio of the beams arranged in the horizontal direction to the beams arranged in the vertical direction of each set area is determined.

[0144] In actual applications, the ratio of the number of vertical and horizontal beams can be system configured or determined based on other configuration information. The other configuration information can be information reflecting the width or ratio of the vertical and horizontal beams, such as the vertical and horizontal beam widths that the antenna system can support, or information reflecting the number or ratio of vertical and horizontal beams in a set area, such as coverage area information of a set area. For different application scenarios, the method for determining the ratio of the number of vertical and horizontal beams in each set area can be configured according to actual needs. In addition, the ratio of the number of vertical and horizontal beams in different set areas can be the same or different.

[0145] Based on the above-mentioned optional beam determination schemes provided in the embodiments of the present application, it is possible to adaptively select beams for set areas with different business densities, realize flexible determination of the cell's beambook, and select more beams with narrower widths for hotspot areas according to the business distribution data of each set area, thereby improving the coverage gain of the hotspot areas. It is possible to select fewer beams with wider widths for low-load areas, thereby improving beam utilization efficiency and ensuring coverage of low-load areas.

[0146] As an example, Figure 7 A schematic diagram of the coverage effect of a beam of a cell determined based on the beam provided in an embodiment of the present application is shown in the figure. As shown in the figure, the beam areas (i.e., set areas) within the coverage range of the cell shown in the figure, the beam areas belonging to the hotspot area and the high-load area shown in the figure, and the beam areas belonging to the low-load area are shown in the figure. Based on the solution provided in the embodiment of the present application, the number of beams of each beam area of ​​the cell can be determined based on the business distribution data of each beam area, and when the bean width required for each beam area is further determined, as shown in the figure, more narrow beams can be allocated to each beam area in the hotspot area, so that the area can obtain better coverage performance, and fewer wide beams can be allocated to the beam area in the low-load area, thereby improving beam utilization and ensuring coverage of the low-load area.

[0147] In order to better illustrate the solution provided by the present application, the principle and effect of the solution of the present application are further described below in conjunction with a specific embodiment. It should be noted that the implementation method described in the specific embodiment is only an optional implementation method of the present application, and the limitation of the specific implementation method of each step should not constitute a limitation on the multiple optional implementation methods of the solution of the present application. In this embodiment, the set area of ​​the cell is called the beam area.

[0148] In this embodiment, the region-related information of the beam region is described by taking the environmental data of the beam region as an example. Figure 8a A schematic diagram of a beam determination method provided in this embodiment is shown. Figure 8b The schematic diagram of the embodiment principle of each step of the method is shown in FIG. Figure 8a As shown in , the method may include the following steps:

[0149] Step 1: Based on historical environmental data and historical service distribution classification tags, use AI (i.e., service prediction model) to predict cell service distribution;

[0150] Step 2: Calculate the number of beams required for each beam area of ​​the cell based on the predicted cell service distribution data;

[0151] Step 3: According to the determined beam quantity and coverage information of each beam area in the cell, the beam width of each beam area is determined, including the horizontal beam width and the vertical beam width;

[0152] Step 4: Select all beams in all beam areas according to the determined beam quantity and beam width of each beam area in the cell, thereby generating the beambook of the cell.

[0153] Combine the following Figure 8b , the optional implementation methods of the above steps are described in detail.

[0154] Step 1: Train a service prediction model based on historical environment data and corresponding service distribution data to predict the service distribution data of the cell through the model, corresponding to Figure 8b The business forecasting steps shown in .

[0155] Among them, the business prediction model can specifically adopt a classification model, for example, an SVM model can be used to predict the category to which the business distribution data of each beam area of ​​the cell belongs through the classification model. The business distribution data of this category is the business distribution data of the beam area. The business prediction model can also be a model that directly outputs the business distribution data of each beam area. In this example, the business prediction model is taken as a classification model, and the output of the model is the category of the business distribution data of each beam area.

[0156] In order to train the classification model, it is first necessary to obtain training samples. In this embodiment, the training samples can be obtained through the historical environment data of the cell (initial area related information) and the corresponding historical service distribution data (ie, initial service distribution data).

[0157] Among them, historical environmental data may include but are not limited to time, date, weather, events, etc., and historical service distribution data information includes the service volume information of each beam area of ​​the cell under specific historical environmental data. The service volume information can be reflected through parameters (i.e., service parameters) such as the average throughput in the beam area, the number of users accessing or transmitting services, and the amount of cached data (the amount of data to be transmitted), which can be one parameter or a combination of multiple parameters.

[0158] Specifically, a classification algorithm can be used to classify historical business distribution data, and its corresponding historical environmental data can be classified and marked. For example, the Pearson correlation algorithm can be used to obtain the classification of historical business distribution data through correlation operations between the historical business distribution data vectors of the cell measured at different times, and based on the classification results of the historical business distribution data, the corresponding historical environmental data can be classified and marked, and the classified and marked historical environmental data can be used as reference samples, i.e., training samples, to train the classification model. After obtaining the trained classification model, based on the trained model, the environmental data at a certain point in the future or time period can be used as input to predict the business distribution data of all beam areas in the cell at that certain point in the future or time period.

[0159] Fig. 9 FIG. 2 shows a training business prediction model provided by the present embodiment, and a schematic diagram of the principle of predicting business distribution data based on the trained model. The several historical environment data shown in the figure are: {core business district, Friday, 18:30, sunny, weekday, ...}, {residential area, Monday, 18:00, cloudy, weekday, ...}, {core business district, Tuesday, 18:30, sunny, weekday, ...}, and each type of historical environment data corresponds to the historical business distribution data of each beam area of ​​the cell under the environment data, such as {core business district, Friday, 18:3 0, sunny day, weekday, ...} The business distribution data corresponding to this environmental data is business distribution i; the historical business distribution data is classified by the classification algorithm, and the corresponding historical environmental data is classified and marked. As shown in the figure, through the classification algorithm, business distribution i and business distribution k are divided into the same category. Therefore, business distribution i and business distribution k and their corresponding historical environmental data belong to the same classification mark m, and the historical environmental data corresponding to business distribution j belongs to the classification mark n, and the sample business distribution data of the category corresponding to each category of environmental data can be determined based on the business distribution data corresponding to each classification mark.

[0160] After completing the classification of the data, the classification model (the business prediction module shown in the figure) can be trained based on the classified data. During training, the input of the model is the historical environmental data of each category, and the output is the category of the business distribution data predicted by the model. The difference between the business distribution data predicted by the model and the sample business distribution data can be used to determine whether the model training is complete. For example, it can be determined by the loss function corresponding to the model. The value of the loss function represents the difference between the business distribution data predicted by the model and the corresponding sample business distribution data.

[0161] After obtaining the trained classification model, for the environmental data of the community at a certain moment in the future, such as the environmental data of {core business district, Friday, 18:30, sunny, weekday} shown in the figure, the environmental data is input into the trained classification model, and the model predicts the business data distribution of each beam area corresponding to the environmental data of the community.

[0162] The following is an example to illustrate the model training process.

[0163] In this example, each initial sample data includes a historical environmental data α (initial environmental data) of the cell and historical business distribution data β (initial business distribution data) of the cell under the conditions corresponding to the historical environmental data. During training, each business distribution data can be represented by a vector of business distribution data.

[0164] As can be seen from the previous description, the historical environment data α can include various environmental information that affects the business distribution of the cell. The historical environment data can be characterized by setting different parameters, such as time parameters (such as 1 for daytime and 0 for nighttime), date parameters (such as 1 to 7 for Monday to Sunday), weather parameters (such as 1 for sunny days, 2 for rainy days, 3 for cloudy days, and 4 for snowy days), holiday parameters (such as 1 for yes and 2 for no), and other possible parameters (such as emergency labels such as concerts and football matches). The historical environment data can be a combination of one or more parameters. For a certain type of parameter, it can be further refined. For example, for rainy days, the rainfall parameter can be added.

[0165] The historical service distribution data β contains a vector that can characterize the service distribution of each beam area of ​​the cell. It can be specifically characterized by service parameters such as throughput, number of connected UEs, and amount of cached data. Assuming that the cell supports N beam areas, the beam service distribution data of the cell can be obtained by T = {T 1 ,T 2 ,…,T k ,…,T N} indicates that, where T k (t) represents the service distribution data of the kth (1≤k≤N) beam area at time t. Assume that S k (t) represents the area covered by the kth beam area at time t, and S′ is the area covered by the reference beam area (also called the benchmark beam area), that is, the reference area area, which is a constant. Taking the system throughput as an example, the service distribution data of the kth beam area at time t after normalization can be expressed by the following expression (1) or expression (2):

[0166]

[0167]

[0168] Among them, the sequence {T′ 1 (t),T′ 2 (t),T′ 3 (t),…,T′ k (t),…,T′ N (t)} represents the service distribution information of all beam areas. It can be understood that in practical applications, if the service distribution data is represented by multiple service parameters, then T′ k (t) represents the service distribution data represented by each service parameter of the k-th beam area at time t.

[0169] After the above preprocessing of the business distribution data, a multi-dimensional business information classification algorithm (such as a Pearson-based correlation classification algorithm) can be used to classify the historical business distribution data. The classification expression based on the Pearson-based correlation classification algorithm can be:

[0170]

[0171] Wherein, ρ represents the correlation between the historical service distribution data of two vectorized cells (the historical service distribution data of all beam areas of the cell; if multiple service parameters are used, the historical service distribution data of all beam areas of the cell corresponding to each service parameter), BT represents the type of service parameters used. For example, if the service parameters include throughput, number of connected UEs, and cached service volume, the value of BT is 3, and ω i represents the weights of different i-th business parameters. The weights of the above three business parameters can be divided into 0.3, 0.5 and 0.2. PCC i represents the correlation factor (correlation) of the historical service distribution data of the cell corresponding to the two vectors of the i-th service parameter (the historical service distribution data of the service parameter of all beam areas of the cell), PCC i The expression can be expressed as:

[0172]

[0173] Where N represents the number of beam areas contained in the cell, β R,i,j , β E,i,j Represents two historical service distribution data corresponding to the i-th service parameter of the j-th beam area of ​​the two cells R and E respectively.

[0174] When it is necessary to explain, R and E may be the same cell or different cells.

[0175] By using the above expression (4), the correlation between the service distribution data of the two cells corresponding to each service parameter can be calculated. Based on expression (3), the correlation between the two historical service distribution data can be calculated. If |ρ| is greater than the set threshold, such as greater than 0.5, it means that the two historical service distribution data corresponding to R and E belong to the same category.

[0176] As an example, for two cells, assume that cell A includes 5 beam areas and cell B also includes 5 beam areas. At a certain moment, corresponding to service parameter 1, the normalized service distribution data of the 5 beam areas of cell A are a and 11 、a 12 、a 13 、a 14 、a 15 , the normalized service distribution data of the five beam areas of cell B are b 11 、b 12 、b 13 、b 14 、b 15 , corresponding to service parameter 2, the normalized service distribution data of the 5 beam areas of cell A are a 21 、a 22 、a 23 、a 24 、a 25 , the normalized service distribution data of the five beam areas of cell B are b 21 、b 22 、b 23 、b 24 、b 25 , when determining whether the service distribution data of cell A and cell B at this moment are of the same category, the correlation between the service distribution data of the two cells corresponding to service parameter 1 can be calculated based on the above formula (4). Specifically, for service parameter 1, i=1, N=5 in formula (4), R and E correspond to cell A and cell B, β R,i,j and β E,i,j The service distribution data of the jth beam area corresponding to the service parameter 1 of the cell A and the cell B, respectively, if j=1, corresponds to a 11 and b 11 After the correlations of the service distribution data of cell A and cell B corresponding to the two service parameters are calculated respectively by formula (4), it can be determined based on formula (3) whether the service distribution data of cell A and cell B belong to the same category.

[0177] Based on this solution, the classification of the historical business distribution data of each cell can be completed, and the corresponding historical environmental data can be classified and marked according to the classification results of the business distribution data. The classified and marked historical environmental data can be used as sample environmental data in the training samples. For each type of environmental data after classification and marking, the sample business distribution data corresponding to this type of environmental data can be determined based on all the historical business distribution data corresponding to this type of environmental data. The classified and marked historical environmental data and the corresponding sample business distribution data can be used as training samples for the subsequent business prediction model, and the training of the model can be completed based on the training samples. After the training is completed, when the business distribution data needs to be predicted, the environmental data of the acquired cell can be input into the model, and the business distribution data of each beam area of ​​the cell under the environmental data can be obtained based on the output of the model.

[0178] like Figure 8b In the service prediction steps shown in , it is assumed that the beam areas included in a cell include beam area 1, beam area 2, ... (indicated by ellipsis in the figure), beam area k, beam area k+1, beam area k+2, beam area k+3, ... (indicated by ellipsis in the figure), for each beam area of ​​the cell, after obtaining the area-related information of the cell (such as historical environmental data), the service distribution data of each beam area of ​​the cell can be obtained based on the trained service prediction model, as shown in Figure 8b As shown in , the service distribution data of beam area k, beam area k+1, beam area k+2, and beam area k+3 (the services shown in the figure) can be expressed as T k , T k+1 , T k+2 , T k+3 .

[0179] Step 2: Based on the predicted service distribution data of each beam area in the cell, calculate the number of beams required to cover each beam area in the cell, corresponding to Figure 8b The steps for calculating the number of beams shown in can be specifically determined based on the service information (service distribution data of each beam area) and the limitation of the beambook size of the cell.

[0180] Specifically, the number of beams required to cover each beam area, i.e., the total number of beams, can be calculated based on the predicted traffic volume in each beam area (that is, traffic distribution data, which can be referred to as predicted traffic volume) and the beambook size of the cell. In practical applications, due to resource constraints, the beambook size is limited, and the calculation method for the number of beams required for each beam area usually has the following characteristics:

[0181] 1) The number of beams should be a monotonically increasing function of the business volume. The relationship between business volume and the number of beams can be linear or nonlinear.

[0182] 2) The total number of beams in all beam areas in the cell should not be greater than the maximum value supported by the cell beambook;

[0183] 3) To avoid coverage gaps and ensure coverage effects, the number of beams in each beam region should be no less than the set minimum number of beams, i.e., the set value of the minimum number of beams in the beam region. The minimum number of beams in the beam region is determined by the maximum beam width supported by the system. For example, if the maximum beam width supported by the system can cover 4 beam regions, then the set value of the minimum number of beams can be 1 / 4.

[0184] The optional implementation methods of this step are described below with reference to several specific examples.

[0185] Example 1

[0186] There is a linear relationship between the number of beams required for each beam area and the predicted traffic volume of the beam area, and the number of beams is proportional to the traffic volume, such as Fig.10a The diagram shows the relationship between the number of beams and the predicted traffic volume. In the diagram, the horizontal axis represents the predicted traffic volume, and the vertical axis represents the number of beams selected by the beam area. As an optional method, the number of beams required for each beam area can be determined by the following expression:

[0187]

[0188] Among them, m k is the number of beams corresponding to the calculated beam region k, P is the total size of the beambook limit of the cell, T k is the predicted traffic volume of beam region k, is the total traffic volume of all beam areas, α k is the minimum number of beams for the set beam region k. The minimum number of beams corresponding to each beam region can be the same value or different values, which can be configured or agreed upon by the system. For example, if the maximum beam width supported by the system can cover 4 beam regions, the minimum number of beams corresponding to each beam region is the same. k =1 / 4.

[0189] Example 2

[0190] There is a nonlinear relationship between the number of beams required for each beam area and the predicted traffic volume of the beam area, and the number of beams is proportional to the traffic volume, such as Fig.10b The diagram of the relationship between the number of beams and the predicted traffic volume shown in FIG. 1 is an optional method, and the number of beams required for each beam area can be determined by the following expression:

[0191]

[0192] Among them, m k is the number of beams corresponding to the calculated beam region k, T k is the predicted traffic volume of beam area k, α k is the minimum number of beams in the set beam region k. k It is the maximum number of beams of beam region k, that is, the setting value of the maximum number of beams of beam region k. Similarly, the maximum number of beams corresponding to each beam region can be the same value or different values. As described above, the sum of the setting values ​​of the maximum number of beams corresponding to all beam regions in a cell is not greater than the total size of the beambook limit of the cell.

[0193] Example 3

[0194] The number of beams required for each beam area can be determined by the business volume mapping relationship. For example, a certain range of business volume is mapped to a beam number. The system can pre-store a mapping relationship table of business volume and beam number. For example, as shown in Table 1, each business volume range corresponds to a beam number. For each beam area, after determining the predicted business volume of each beam area, the number of beams required for each beam area can be determined by the mapping relationship. For example, assuming that the predicted business volume of a beam area is greater than A1 and not greater than A2, the number of beams required for the beam area is 1 / 2.

[0195] Table 1

[0196]

[0197]

[0198] like Figure 8b In the schematic diagram shown, the numbers of beams required for beam region k, beam region k+1, beam region k+2, and beam region k+3 are 6, 1, 0.5, and 0.5, respectively.

[0199] Step 3: Determine the horizontal and vertical beam widths of each beam area based on the number of beams and coverage information of each beam area in the cell, corresponding to Figure 8b The steps for determining beam width are shown in .

[0200] In this step, the horizontal and vertical beam widths of each beam area are determined according to the number of beams of each beam area, the coverage information of each beam area, and other configuration information calculated in step 2. Assuming that the cell includes N beam areas, the input information in this step includes the number of beams required by each of the N beam areas (e.g., the set m of the number of beams required by the N beam areas can be expressed as m={m 1 ,m 2 ,…,m k ,…,m N}, where m i (1≤i≤N) represents the number of beams required for the i-th beam region), coverage information of each beam region (for example, the set of coverage information of N beam regions can be expressed as A={A 1 ,A 2 ,…,A k ,…,A N}, where A i (1≤i≤N) represents the coverage information required by the i-th beam area), and other configuration information of each beam area (such as the number ratio information of the horizontal dimension and the vertical dimension, etc.); the output information is the horizontal beam width and the vertical beam width of each beam area. For example, the set (H, V) of the horizontal beam width and the vertical beam width of all beam areas of a cell can be expressed as:

[0201]

[0202] in, (1≤i≤N) represents the horizontal beam width of the i-th beam region, Represents the vertical beam width of the i-th beam region.

[0203] Among them, other configuration information refers to information that can be used to determine the ratio of beams arranged in the horizontal direction and beams arranged in the vertical direction of each beam area, that is, information that can reflect the vertical and horizontal beam widths or the beam width ratio, or information that can reflect the number or number ratio of vertical and horizontal beams in the beam area, such as the vertical and horizontal beam widths that the antenna system can support, or the vertical and horizontal beam number ratio of the system parameter configuration.

[0204] In practical applications, the ratio of the number of beams in the horizontal dimension and the vertical dimension can be the same or different for each beam area of ​​a cell, and the ratio can be preconfigured or calculated in real time. For a preconfigured ratio, the ratio can be a preset ratio or selected from a set of preset ratios. For a case where there is only one preset ratio, the ratio of the number of beams in the horizontal dimension and the vertical dimension for all beam areas is the same.

[0205] For the case of selecting from a preset ratio set, each beam region can be the same or different. If the ratio of the number of beams in the horizontal dimension and the number of beams in the vertical dimension of each beam region is set to be the same, the ratio can be determined jointly according to the horizontal dimension and the vertical dimension width in the coverage information of all beam regions. As an optional method, it can be determined in the following way:

[0206] Calculate the sum of the horizontal widths of the coverage information of all beam areas, set it as Total_BW_h, calculate the sum of the vertical widths of the coverage area information of all beams, set it as Total_BW_v, and find the ratio closest to Total_BW_h / Total_BW_v in the candidate ratio set. This ratio is the required ratio of the number of horizontal and vertical beams.

[0207] If the ratio of the number of beams in the horizontal dimension and the number of beams in the vertical dimension of each beam region is set to be different, the ratio of each beam region can be determined according to the horizontal dimension and the vertical dimension width in the coverage information of each beam region. As an optional method, it can be determined in the following way:

[0208] For each beam region, calculate the horizontal width of the coverage information of the beam region With vertical width The ratio of Find the ratio that matches The closest ratio is the ratio of the number of beams in the horizontal dimension to the number of beams in the vertical dimension of the beam area.

[0209] For the case where the ratio is calculated in real time, similarly, each beam area can be the same or different. If the ratio of the number of beams in the horizontal dimension and the number of beams in the vertical dimension of each beam area is set to be the same, the ratio can be determined based on the horizontal dimension and the vertical dimension width in the coverage information of all beam areas. As an optional method, it can be determined in the following way:

[0210] Calculate the sum of the horizontal widths of the coverage information of all beam regions, set it as Total_BW_h, calculate the sum of the vertical widths of the coverage information of all beam regions, set it as Total_BW_v, then the required ratio of the number of horizontal and vertical beams is Total_BW_h / Total_BW_v.

[0211] If the ratio of the number of beams in the horizontal dimension to the number of beams in the vertical dimension of each beam area is set to be different, the ratio of each beam area is determined according to the horizontal dimension and vertical dimension width in the coverage information of each beam area, that is, the ratio of the number of beams in the horizontal dimension to the vertical dimension of the beam area is

[0212] After determining the number of beams required for each beam area, the number of beams in the horizontal and vertical dimensions of each beam area can be calculated based on the other configuration information mentioned above, and then the horizontal and vertical beam widths of the beam area can be calculated respectively based on the calculated number of beams in the horizontal and vertical dimensions and the coverage information of the beam area, wherein the beams in each beam area can be distributed uniformly or non-uniformly.

[0213] The optional implementation methods of this step are described below with reference to several specific examples. It should be noted that in the following examples, the ratio of the number of beams in the horizontal dimension and the vertical dimension of the above-mentioned beam area is described by taking the configured ratio as an example. However, as can be seen from the previous description, the ratio can be pre-configured or calculated in real time.

[0214] Example 1

[0215] In this example, the horizontal beam width and vertical beam width of each beam area can be determined according to the beam quantity of each beam area, the coverage information of the beam area, and the ratio of the horizontal and vertical beam numbers of the configured beam area calculated in step 2. As can be seen from the foregoing description, for the ratio of the horizontal and vertical beam numbers of each beam area, each beam area can be the same or different, and the ratio can be a preset ratio or selected from a preset ratio set.

[0216] Specifically, firstly, the number of horizontal and vertical beams of each beam region is calculated according to the number of beams of each beam region calculated according to step 2 and the ratio of the number of horizontal and vertical beams configured. The product of the number of horizontal beams and the number of vertical beams is equal to the number of beams of the beam region.

[0217] For each beam region, assume that the ratio of the number of beams in the horizontal dimension to the number of beams in the vertical dimension of the beam region is preconfigured, and let the ratio of the number of beams in the horizontal dimension to the number of beams in the vertical dimension be X:Y. For a beam region k, assume that the total number of beams in the beam region k calculated in step 2 is m. k , then the number of horizontal beams and vertical beams of the beam region k can be determined by the following expressions:

[0218] The number of beams in the horizontal dimension is:

[0219] The number of vertical beams is:

[0220] Among them, satisfying m k =m k_h ×m k_v .

[0221] Then, the horizontal beam width and vertical beam width of the beam area are calculated according to the calculated horizontal and vertical beam numbers and the coverage information of the beam area. Assuming that the beams of beam area k are evenly distributed, the horizontal beam width and vertical beam width of beam area k can be determined by the following method:

[0222] Horizontal beam width:

[0223] Vertical beam width:

[0224] in, and are the horizontal dimension width and vertical dimension width in the coverage information of the beam area of ​​beam area k respectively;

[0225] As an example, Fig.11a A schematic diagram of the coverage of a beam region k is shown in FIG. 1 . The elliptical region in the figure indicates the coverage information of the beam region k. As shown in the figure, the horizontal dimension width of the beam region k is The vertical width is m k Indicates the number of beams required for the area. Assume that the number of beams arranged horizontally is the number of beams in the horizontal dimension m k_h , the number of beams in the vertical dimension is m k_h ,like Fig.11b In the enlarged schematic diagram of the beam region shown in FIG, the m of the beam required for the beam region is k =20, where mk_h =5,m k_h =4, then the horizontal beam width of the beam region Vertical dimension bea width

[0226] Example 2

[0227] In this example, the horizontal and vertical beam widths of each beam region can be determined according to the number of beams of each beam region calculated in step 2, the coverage information of the beam region, and the ratio of the number of horizontal and vertical beams calculated in real time. For the optional method of calculating the ratio of the number of horizontal and vertical beams in real time, refer to the corresponding description in the previous text.

[0228] Specifically, first, the number of horizontal and vertical beams of each beam region is calculated based on the number of beams of each beam region calculated in step 2 and the ratio of the number of horizontal and vertical beams of each beam region calculated in real time. The product of the number of horizontal and vertical beams is equal to the number of beams of the beam region. Assuming that the ratio of the number of horizontal and vertical beams calculated in real time is X:Y, the total number of beams of beam region k calculated in step 2 is m k , then the number of horizontal beams and vertical beams of the beam region k can be determined by the following expressions:

[0229] The number of beams in the horizontal dimension is:

[0230] The number of vertical beams is:

[0231] Among them, satisfying m k =m k_h ×m k_v .

[0232] Then, the horizontal and vertical beam widths of the beam area k are calculated according to the calculated horizontal and vertical beam numbers and the coverage information of the beam area k. Assuming that the beams of the beam area k are evenly distributed, the horizontal and vertical beam widths of the beam area can be determined by the following method:

[0233] Horizontal beam width:

[0234] Vertical beam width:

[0235] in, and They are the horizontal and vertical widths in the coverage information of the beam area of ​​beam area k, respectively.

[0236] Example 3

[0237] In this example, the horizontal and vertical beam widths of each beam area can be determined based on the number of beams in each beam area calculated in step 2, the coverage information of the beam area, and the ratio of the number of configured horizontal and vertical beams.

[0238] Specifically, first, the number of horizontal and vertical beams of each beam region is calculated based on the number of beams of each beam region calculated in step 2 and the ratio of the number of horizontal and vertical beams configured. The sum of the number of horizontal and vertical beams is equal to the number of beams of the beam region. For a beam region k, assuming that the ratio of the number of horizontal and vertical beams configured is X:Y, the total number of beams of the beam region k calculated in step 2 is m k , then the number of horizontal beams and vertical beams of the beam region k can be determined by the following expressions:

[0239] The number of beams in the horizontal dimension is:

[0240] The number of vertical beams is:

[0241] Among them, satisfying m k =m k_h +m k_v .

[0242] Then, the horizontal and vertical beam widths are calculated based on the calculated horizontal and vertical beam numbers and the coverage information of the beam area. Assuming that the beams in beam area k are evenly distributed, the horizontal and vertical beam widths of beam area k can be determined by the following method:

[0243] Horizontal beam width:

[0244] Vertical beam width:

[0245] in, and They are the horizontal and vertical widths in the coverage information of the beam area of ​​beam area k, respectively.

[0246] Example 4

[0247] In this example, the horizontal and vertical beam widths of each beam area can be determined based on the number of beams in each beam area calculated in step 2, the coverage information of the beam area, and the ratio of the horizontal and vertical beam numbers calculated in real time.

[0248] Specifically, first, according to the number of beams in each beam region calculated in step 2 and the ratio of the horizontal and vertical beam numbers calculated in real time, the number of horizontal and vertical beams in each beam region is calculated. The product of the horizontal and vertical beam numbers is equal to the number of beams in the beam region. For a beam region k, assuming that the ratio of the horizontal and vertical beam numbers of the beam region calculated in real time is X:Y, the total number of beams in the beam region k calculated in step 2 is m k , the number of horizontal and vertical beams of the beam region k can be determined by the following expressions:

[0249] The number of beams in the horizontal dimension is:

[0250] The number of vertical beams is:

[0251] Among them, satisfying m k =m k_h +m k_v .

[0252] Then, the horizontal and vertical beam widths are calculated based on the calculated horizontal and vertical beam numbers and the coverage information of the beam area. Assuming that the beams in the beam area k are evenly distributed, the horizontal and vertical beam widths of the beam area can be determined by the following method:

[0253] Horizontal beam width:

[0254] Vertical beam width:

[0255] in, and They are the horizontal and vertical widths in the coverage information of the beam area of ​​beam area k, respectively.

[0256] like Figure 8bIn the schematic diagram shown, the number of beams required for beam area k and beam area k+1 are 6 and 1 respectively, both of which are not less than 1. The horizontal beam width and vertical beam width of the two beam areas can be determined based on the number of beams required for each and the coverage information of the beam areas. As shown in the figure, the horizontal beam width and vertical beam width of beam area k are respectively expressed as and The horizontal beam width and vertical beam width of beam region k+1 are expressed as and For beam region k+2 and beam region k+3, the number of beams required for these two beam regions is 0.5. These two regions can be used as a joint region. The horizontal beam width and vertical beam width of the joint region are shown in the figure. and These two beam regions can share the same beam.

[0257] Step 4: According to the number of beams and beam widths of each beam area in the determined cell, all beams of all beam areas are selected from the system candidate beam set or candidate beam subset to generate the beambook of the cell, corresponding to Figure 8b The steps for determining the beambook are shown in .

[0258] As can be seen from the foregoing description, when determining the beam of each beam region, the determination method may be different for different system configurations. For example, if all candidate beams of the system configuration are included in a set (i.e., the candidate beam set), all beams of each beam region may be determined from the set according to the determined beam quantity and beam width of each beam region and the beam width of the candidate beam. If all candidate beams of the system configuration are included in multiple candidate beam subsets, each subset has a different beam width, a corresponding subset may be selected from the multiple candidate beam subsets according to the beam width of each beam region and the beam width of each subset, and then beams of the corresponding beam quantity may be selected from the selected subset.

[0259] As an example, Fig.12 A schematic diagram of a candidate beam subset with different beam widths supported by the system is shown in Figure 8b), which shows three candidate beam subsets with different beam widths, which can be represented as W(H1,V1), W(H2,V2), and W(H3,V3), respectively. Each ellipse in the figure represents the horizontal beam width and vertical beam width of a beam. For example, the horizontal beam width (i.e., horizontal angle) of the subset W(H1,V1) is H1, and the vertical beam width (i.e., vertical angle) is V1. The horizontal beam width of the subset W(H2,V2) is H2, and the vertical beam width is V2. The horizontal beam width of the subset W(H3,V3) is H3, and the vertical beam width is V3.

[0260] After determining the number of beams and beam widths for each beam region in the cell, a certain criterion (such as the minimum distance criterion, which refers to the distance from the selected beam to the center of the beam region) can be used to select beams from the beam set supported by the system (candidate beam set) or a subset of the beam subset (candidate beam subset) for each beam region. All selected beams form the final beambook.

[0261] Among them, for the beam region where the required number of beams is greater than or equal to 1 (the first set value), the required number of beams can be selected from the beam set supported by the system according to certain criteria based on the determined beam width of the beam region. For the convenience of description, this method is called beambook determination method I.

[0262] For a beam region where the required number of beams is less than 1, the beam region and its adjacent regions where the number of beams is also less than 1 can be combined into a joint region, and beam selection is performed uniformly on the joint region, that is, the number of beams required for the joint region is selected from the beam set using certain criteria. For the convenience of description, this method is called beambook determination method II.

[0263] The following describes the optional implementation of this step with some examples. In these examples, the minimum distance criterion is used as the criterion for determining the beambook of each beam region, where the distance in the minimum distance criterion refers to the distance from the selected beam to the beam region. In addition, for beambook determination method II, these examples are described by taking multiple beam regions sharing one beam as an example.

[0264] Example 1

[0265] In this example, the system supports multiple candidate beam subsets with different beam widths. When determining the beam of each beam region, first determine the corresponding beam subset (i.e., candidate beam subset) for each beam region from the beam set supported by the system according to the horizontal and vertical beam widths calculated in step 3, then select the required number of beams from the determined subset, and all selected beams form the final beambook.

[0266] For beam regions with a beam number greater than or equal to 1, beambook determination method I is used, that is, the corresponding beam subset is determined based on the beam width calculated in the beam region, and then the required number of beams is selected from the beam subset based on the minimum distance criterion. For beam regions with a beam number less than 1, beambook determination method II is used, that is, beam regions with the same number of adjacent beams form a joint region, and beam selection is performed uniformly for the joint region. Because the number of beams required for each beam region in the joint region is the same, and the corresponding beam widths are also the same, the minimum distance criterion is used to select the required number of beams from the beam subset of the corresponding width.

[0267] The beambook determination method I in this example may specifically include:

[0268] Let the center point vector corresponding to beam region k be u k , that is u k The direction vector representing the center position of beam region k, the required beam width calculated for this region is in, Denote the horizontal and vertical widths of beam region k respectively. Then, the distance between each beam in the beam subset and the center point of beam region k (referred to as beam distance) can be calculated based on the dot product of the two vectors. The specific calculation method is as follows:

[0269] d n =1 / abs(u′ k × n )

[0270] Among them, w n The beam width is The beam subset The direction vector of the nth beam, u′ k Indicates u k The conjugate transpose of abs(u′ k × n ) represents u′ k× n The absolute value of the dot product of n Indicates the distance between the nth beam in the beam subset and the beam region k.

[0271] As an example, Fig.13a A subset of beams is shown in The beam subset is the beam width in the horizontal dimension and the beam width in the vertical dimension according to the beam area. It is determined that, in the schematic diagram, the set of beams circled by dotted lines is a beam subset, wherein "0" shown in the figure indicates that the corresponding beam is not selected, and "1" indicates that the corresponding beam is selected, that is, the beam is a beam in the candidate beam subset.

[0272] After completing the distances between each beam in the beam subset and the beam region k, all calculated beam distances can be sorted and m can be selected from them. k The beam with the smallest distance (the number of beams required for beam area k) is written into the beambook of the cell.

[0273] The beambook determination method II in this example may specifically include:

[0274] Let the required beam width calculated for beam region k be The joint region includes K beam regions. First, the joint beam region is determined. The joint region is composed of beam region k and adjacent regions with the same number of beams as beam region k. If a total of A regions are found (including beam region k itself), then K = min(A, 1 / m k ), that is, the number of beam regions included in the joint area is the smaller value between the number of qualified beam regions and the number of beam regions that can be covered by one beam, so as to ensure the coverage of each beam region in the joint area.

[0275] Secondly, the sum of the distances between all beams in the beam subset and the center points of each beam region can be calculated based on the dot product method. Finally, a beam corresponding to the minimum beam distance is selected and written into the beambook. The specific calculation method of the distance sum is as follows:

[0276]

[0277] Among them, w n The width is The beam subset W The direction vector of the nth beam, is the direction vector of the center point corresponding to the sth beam region in the joint beam region, Represents the center point direction vector The conjugate transpose of , s=1,2,..,K.

[0278] After calculating the distance sums corresponding to the beams in the beam subset, a beam corresponding to the minimum beam distance (distance sum) can be selected as the beam of the joint area and written into the beambook of the cell.

[0279] As an example, Fig.13b A schematic diagram of a joint region is shown in FIG. 1 . In this example, the joint region includes a number of beams less than 1 (m shown in the figure). k <1), the number of beams required for each of the four beam areas is the same, and the horizontal and vertical widths of the coverage of the four beam areas are also the same. Taking the beam area k in the upper left corner as an example, assuming that its horizontal and vertical widths are and The number of horizontal beams and vertical beams required are m respectively. k_h and m k_v , then the required horizontal beam width and vertical beam width of the joint area are as well as Then, the candidate beams required for the joint beam region can be screened out from the candidate beam set based on the width, and the beam of the joint region can be determined from the candidate beams based on the above minimum distance principle. Fig.13c It is shown in Fig.13b Schematic diagram of candidate beams of the joint region shown in the figure. The beam corresponding to "1" in the figure is the beam of the joint region selected from the candidate beam set, and the beam corresponding to "0" represents the unselected beam. The four dotted ovals shown in the figure represent the four beam regions included in the joint region.

[0280] Example 2

[0281] The difference between this example and Example 1 is that this example provides another optional implementation of beambook determination method II. In this example, for beams whose required beam number is less than 1, the joint region includes the beam region and adjacent beam regions whose beam number is also less than 1. Beam selection is performed uniformly for the joint region. Because the required beam number of each beam region in the joint region may be different, the required beam number can be selected from the beam subset of the corresponding width using the minimum distance principle.

[0282] The beambook determination method II in this example can be specifically as follows:

[0283] Let the required beam width calculated for beam region k be The joint region includes K beam regions, and the joint beam region may be determined first. In this example, the joint region may be composed of beam region k and adjacent beam regions whose beam numbers are also less than 1. The sum of the beam numbers of the joint region is required to be less than or equal to 1.

[0284] Secondly, the sum of the distances between all beams in the corresponding beam subset and the center point of each beam region is calculated based on the dot multiplication operation. The calculation method is as follows:

[0285]

[0286] Among them, w n is the direction vector of the nth beam of one or more beam subsets corresponding to all beam widths in the joint beam region, is the direction vector of the center point corresponding to the sth region in the joint beam region, express The conjugate transpose of , s=1,2,..,K.

[0287] Finally, select a beam corresponding to the minimum beam distance and write it into the beambook.

[0288] Example 3

[0289] In this example, the minimum distance criterion is used to select beams from the beam set supported by the system for each beam region, and all selected beams form the final beambook.

[0290] For beam regions where the number of beams is greater than or equal to 1, beambook determination method I is used, that is, the required number of beams is selected from the beam set supported by the system according to the minimum distance criterion.

[0291] For beam regions with a beam number less than 1, beambook determination method II is used, that is, the regions with the same number of adjacent beams form a joint region, and beam selection is performed uniformly for the joint region. The required number of beams is selected from the beam set supported by the system using the minimum sum distance criterion.

[0292] The beambook determination method I in this example may specifically include:

[0293] Let the direction vector of the center point corresponding to beam region k be u k , the distances between all beams in the beam set and the center points of the beam region k can be calculated based on the dot multiplication operation. The calculation method is as follows:

[0294] d n =1 / abs(u′ k × n )

[0295] Among them, w n is the direction vector of the nth beam in the beam set W supported by the system, u′ k Indicates u k The conjugate transpose of .

[0296] After calculating the distance between each beam in the beam set and the beam region k, all calculated beam distances can be sorted and m can be selected from them. k The beam with the smallest distance is taken as the beam of the beam area k and written into the beambook of the cell.

[0297] The beambook determination method II in this example may specifically include:

[0298] Assume that the joint region includes K beam regions. First, determine the joint beam region. In this example, the joint region consists of beam region k and adjacent regions with the same number of beams as beam region k. If a total of A regions are found (including beam region k itself), then K = min(A, 1 / m k ).

[0299] Secondly, the sum of the distances between all beams and the center points of each beam region in the beam set supported by the system is calculated based on the dot multiplication operation. The specific calculation method is as follows:

[0300]

[0301] Among them, w n is the direction vector of the nth beam in the beam set W supported by the system, is the direction vector of the center point corresponding to the sth region in the joint beam region, express The conjugate transpose of , s=1,2,..,K.

[0302] Finally, select a beam corresponding to the minimum beam distance and write it into the beambook.

[0303] Example 4

[0304] The difference between this example and Example 3 is that this example provides another optional implementation of beambook determination method II. In this example, for beams with a required beam number less than 1, the joint region includes the beam region and adjacent beam regions with a beam number also less than 1. The total number of beams required for the joint region is required to be no greater than 1. Beam selection is performed uniformly for the joint region. Because the number of beams of each beam region in the joint region may be different, the required number of beams can be selected from the beam subset of the corresponding width using the minimum distance principle.

[0305] The beambook determination method II in this example can be specifically as follows:

[0306] Assuming that the joint region includes K beam regions, the joint region is first determined, which is composed of beam region k and neighboring regions whose beam numbers are also less than 1. The sum of the beam numbers in the joint region is required to be less than or equal to 1. Secondly, based on the point multiplication operation, the sum of the distances between all beams in the beam set supported by the calculation system and the center points of each beam region can be calculated in the following way:

[0307]

[0308] Among them, w n is the direction vector of the nth beam in the beam set W supported by the system, is the direction vector of the center point corresponding to the sth region in the joint beam region, express The conjugate transpose of , s=1,2,..,K.

[0309] After calculating the sum distances corresponding to each beam in the beam set, you can select a beam corresponding to the minimum beam distance and write it into the beambook.

[0310] After determining the beams of each beam area and obtaining the beambook of the cell, data transmission services can be provided to users of the cell based on the determined beams, such as Figure 8bThe steps of applying beambook are shown in the figure. As shown in the figure, for the hot spot area, that is, beam area k, the determined 6 narrower beams are used to provide services for the beam area, thereby improving the coverage of the area. For the medium load area, that is, beam area k+1, a relatively wide beam can be used to provide services for it, and for the low load areas, that is, beam area k+1 and beam area k+2, a wider beam can be used to jointly provide services for these two beam areas, thereby realizing a solution of adaptively determining beambook according to business distribution. With this solution, the beam width and corresponding quantity in the beambook can be adjusted in real time according to changes in business. For areas with low business volume, a small number of wide beams are used for coverage to ensure system performance and coverage. For hot spots, more narrower beams are allocated to improve system performance and user experience, thereby improving beam utilization.

[0311] For beams, the shape of beams can be regarded as Sinc functions. A denser and narrower beam distribution can bring higher received signal power gain. Therefore, in hot spots, a denser and narrower beam distribution can effectively improve signal power and system capacity. Fig.14 A schematic diagram of transmission gain of a wide beam with a wider width and a narrow beam with a narrower width is shown. In the schematic diagram, the horizontal axis represents the width of the beam (horizontal angle or vertical angle), and the vertical axis represents the received power of the beam. It can be seen from the figure that compared with the wide beam, the signal received power of the narrow beam is relatively higher and the performance is better. The gain of the narrow beam shown in the figure is the receiving gain of the wide beam corresponding to the narrow beam shown in the figure, and the wider beam has a larger coverage range, which can ensure full coverage of the low-load area.

[0312] The following table shows the comparison results between the existing traditional beam management scheme and the adaptive beambook management scheme provided in the embodiment of the present application. It can be seen from the table that in the existing beam management scheme, the beams in the beambook of the cell are fixed, and it is impossible to enhance coverage according to the different service distributions of the cell. The adaptive beambook management scheme based on the embodiment of the present application can adaptively allocate beams according to the service distribution of the cell, which can better meet the actual application needs.

[0313]

[0314] In order to further illustrate the improvement of the beam determination solution provided by the present application on the system performance and hotspot performance, the following is a description of the effect of the embodiment of the present application in combination with the experimental results of performance evaluation for three different scenarios using a system-level simulation tool. The simulation assumptions are shown in the following table:

[0315]

[0316]

[0317] In this simulation experiment, the schematic diagrams of the three scenarios are as follows: Fig.15a , Fig.15b , Fig.15c As shown in the figure, in the three-dimensional coordinate axis shown in the figure, the center point position of the cell is the position shown by the black dot on the Y axis of the figure, that is, the position marked ●. In the simulation, the coverage area of ​​the three cells can be understood as a hexagon with a radius of 100 meters and a center point position. Fig.15a , Fig.15b , Fig.15c A schematic diagram of a cell is shown in FIG. 1 , in which the distance between all user coordinate points and the center point is no more than 100 m (only one cell is shown in the figure, which is a partial area of ​​one third of a hexagon). The specific scenarios are as follows:

[0318] Scenario 1: Fig.15a In the schematic diagram of Case 1 shown in FIG, 0% is located in the hotspot area, that is, 0% of the users are located in the hotspot area, that is, all users are evenly distributed in the outdoor ground, and there is no hotspot area;

[0319] Scenario 2: If Fig.15b As shown in the schematic diagram of scenario 2 (Case 2), 80% are distributed in the hotspot area (the hotspot shown in the figure), and the size of the hotspot area is 50mx15mx3m (1 floor). It can be understood that 50mx15m is the ground coverage area of ​​the hotspot area, and 3m is the height of the area, that is, 80% of the users are located in the hotspot area of ​​1 floor, 80% of the users are evenly distributed on the 1st floor, and the remaining 20% ​​of the users are distributed outside the hotspot area, which is also evenly distributed;

[0320] Scenario 3: If Fig.15c In the schematic diagram of Case 3 shown in the figure, 90% of the users are distributed in the hotspot area, and the size of the hotspot area is 50mx15mx18m (including 6 floors), that is, 90% of the users are located in the hotspot area of ​​6 floors, and the users are evenly distributed on the 1st to 6th floors. The remaining 10% of the users are distributed outside the hotspot area, which is also evenly distributed.

[0321] In all scenarios, the beambook size is 64, that is, the beambook size limit is 64.

[0322] For the above three scenarios, the existing beam management scheme and the beam determination scheme provided in the embodiment of the present application are respectively used to generate the beambook of the cell, and based on the generated beambook, the CDF (Cumulative Distribution Function) of the user throughput (i.e., UE throughput) of the microcells in the three scenarios is simulated.

[0323] Fig.16a The figure shows a schematic diagram of the simulation results of scenario 1. The dotted line in the figure shows the simulation results of the existing solution, and the solid line shows the simulation results of the embodiment of the present application. The horizontal axis in the figure shows the user throughput in Mbps (Million bits per second), and the vertical axis shows the cumulative distribution function value. At a fixed CDF point, the larger the user throughput, the better the performance. Fig.16a It can be seen that at the same CDF point, compared with the existing solution, the user throughput based on the solution of the embodiment of the present application has been greatly improved, and the beam coverage gain is better.

[0324] The following table shows the cell performance comparison results of the existing solution and the solution of the present application in scenario 1:

[0325]

[0326] It can be seen from the table that in scenario 1, by adopting the solution of the embodiment of the present application, a suitable beam can be selected for a certain coverage area, thereby obtaining an improvement of about 30% in the average cell throughput performance. Although there is no hotspot area in this scenario, because the users are distributed on the ground, those beams with relatively large vertical angles basically have no business. Through the method of the embodiment of the present application, more beams can be distributed in areas with relatively low vertical angles or more in the horizontal dimension, and fewer and wider beams can be used to cover areas with relatively high vertical angles, thereby improving the utilization of beams and improving system performance.

[0327] Fig.16b The simulation result schematic diagram of scenario 2 is shown in FIG. 1 . Similarly, the dotted line in the figure represents the simulation result of the existing solution, and the solid line represents the simulation result of the embodiment of the present application. Fig.16b It can be seen that at the same CDF point, compared with the existing solution, the user throughput based on the solution of the embodiment of the present application has been greatly improved, and the beam coverage gain is better.

[0328] The following table shows the simulation comparison results of the cell performance of the existing solution and the solution of the present application in scenario 2:

[0329]

[0330] By adopting the solution of the embodiment of the present application, the hotspot area can adopt a higher density and narrower width beam number, thereby improving the received signal strength of users in the hotspot area. For scenario 2, because 80% of the services are concentrated in the hotspot area, the higher density and narrower width beam can better cover the hotspot area. From the simulation evaluation results of the table, it can be seen that compared with the existing solution, when the solution of the embodiment of the present application is adopted, the hotspot area can obtain an average performance gain of 36.6%, and the overall performance of the cell is also significantly improved.

[0331] Fig.16c The simulation result schematic diagram of scenario 3 is shown in FIG. 1 . Similarly, the dotted line in the figure represents the simulation result of the existing solution, and the solid line represents the simulation result of the embodiment of the present application. Fig.16c It can be seen that at the same CDF point, compared with the existing solution, the user throughput based on the solution of the embodiment of the present application has been greatly improved, and the beam coverage gain is better. Fig.16a , Fig.16b , Fig.16c It can be seen that compared with the existing solution, the solution of the embodiment of the present application brings greater gains for hot spots where the service distribution is more concentrated. The following table shows the simulation comparison results of the cell performance of the existing solution and the solution of the present application in scenario 3:

[0332]

[0333]

[0334] Similar to scenario 2, based on the solution of the embodiment of the present application, the hotspot area adopts a higher density and narrower width beam number, which can effectively improve the received signal strength of users in the area. In scenario 3, 90% of the services are in the hotspot area, and the hotspot area has a larger vertical distribution, and denser beams can obtain higher gains. The evaluation results show that by adopting the solution of the present invention, the hotspot area can obtain a performance gain of more than 40%, and the overall performance of the cell is also significantly improved.

[0335] Based on Figure 6 Based on the same principle as the method shown in , the embodiment of the present application also provides a beam determination device, such as Fig.17 As shown in , the beam determination device includes a service data acquisition module 110 and a beam determination module 120, wherein:

[0336] The service data acquisition module 110 is used to acquire service distribution data of each set area of ​​the cell;

[0337] The beam determination module 120 is used to determine the beam corresponding to the cell according to the service distribution data of each set area.

[0338] The beam determination device may specifically be a device arranged on the base station side, the device may be a part of the base station, or may be an independent beam management device that communicates with the base station.

[0339] Optionally, the beam determination module 120 is specifically configured to:

[0340] Determine the total number of beams required for each set area based on the business distribution data of each set area;

[0341] Determine the width of the beam required for each set area according to the total number of beams required for each set area;

[0342] Based on the width of the beam required for each set area, each beam of each set area is determined from the candidate beam set.

[0343] Optionally, for a set area, when the beam determination module 120 determines the width of the beam required for the set area according to the total number of beams required for the set area, it is specifically configured to:

[0344] Determine the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction of the set area according to the total number of beams required for the set area and the ratio information of the beams arranged in the horizontal direction and the beams arranged in the vertical direction of the set area;

[0345] The width of the beam required for the set area is determined according to the coverage information of the set area, the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction of the set area.

[0346] Optionally, for a set area, when the beam determination module 120 determines each beam of the set area from the candidate beam set based on the beam width required by the set area, it is specifically configured to:

[0347] Determine, based on the beam width required for the set area, candidate beams for the set area from the candidate beam set;

[0348] Based on the distance between each candidate beam and the set area, each beam of the set area is determined from each candidate beam of the set area.

[0349] Optionally, the candidate beam set includes candidate beam subsets divided according to beam widths; accordingly, when the beam determination module 120 determines the candidate beams of the set area from the candidate beam set based on the beam width required for the set area, it can be used to:

[0350] Based on the beam width of the set area and the beam width corresponding to each candidate beam subset, a target beam subset corresponding to the set area is determined from each candidate beam subset, and each beam in the target beam subset is used as each candidate beam of the set area.

[0351] Optionally, for a set area, when the beam determination module 120 determines each beam of the set area from the candidate beam set based on the beam width required for the set area, it can be used to:

[0352] If the total number of beams required for the set area is less than the first set value, the set area and the adjacent set areas of the set area are taken as a joint area, and each beam of the joint area is determined from the candidate beam set based on the beam width required for the joint area.

[0353] Optionally, when the beam determination module 120 determines each beam of the joint region from the candidate beam set based on the beam width required by the joint region, it can be used to:

[0354] Determining a beam width required for the combined area based on beam widths required for each of the set areas included in the combined area;

[0355] Determine candidate beams for the joint region from the candidate beam set based on the beam width required for the joint region;

[0356] Based on the distances between each candidate beam and each set area included in the joint area, each beam of the joint area is determined from each candidate beam.

[0357] Optionally, the joint region satisfies at least one of the following:

[0358] The total number of beams required for each set area included in the joint area is the same;

[0359] The beam widths required for each set area included in the joint area are the same;

[0360] The total number of beams required by each of the set areas included in the joint area is less than the first set value;

[0361] The sum of the total number of beams required by all the set areas included in the joint area is less than the second set value.

[0362] Optionally, the business data acquisition module 110 may be used to:

[0363] Obtaining area-related information of the cell;

[0364] The service distribution data of each set area of ​​the cell is determined according to the area related information of the cell.

[0365] Optionally, the area-related information includes environmental data and / or location information of the cell.

[0366] Optionally, when determining the service distribution data of each set area of ​​the cell according to the area-related information of the cell, the service data acquisition module 110 may be used to:

[0367] According to the area-related information of the cell, the business distribution data of each set area of ​​the cell is predicted through the business prediction model.

[0368] Optionally, the business prediction model can be trained by the model training module in the following manner:

[0369] Acquire training samples, wherein the training samples include sample area related information of cells of each category and sample service distribution data of each set area of ​​the cell corresponding to the sample area related information of each category;

[0370] The initial prediction model is trained based on the sample area related information of each category until the predicted business distribution data of each category output by the initial prediction model and the sample business distribution data corresponding to the category meet the preset conditions, and the prediction model at the end of the training is used as the business prediction model.

[0371] Optionally, when obtaining training samples, the model training module can be used to:

[0372] Acquire each initial sample data, wherein one piece of initial sample data includes initial area related information of a cell and initial service distribution data of the cell under the initial related information, wherein the initial service distribution data of a cell includes service distribution data of each set area of ​​the cell;

[0373] Determine the category of the initial service distribution data of the cell in each piece of initial sample data, and obtain the classification result of each piece of initial service distribution data;

[0374] Based on the classification results of each initial service distribution data, the initial area related information of the cell corresponding to each initial service distribution data is marked with a corresponding category label to obtain the related information of each sample area;

[0375] Based on each initial business distribution data belonging to the same category, sample business distribution data corresponding to sample historical area related information of the same category is obtained.

[0376] Optionally, if the initial service distribution data of the cell includes service distribution data corresponding to at least two service parameters, the model training module, when determining the category of the initial service distribution data in each piece of initial sample data, can be used to:

[0377] For any two pieces of initial sample data, for each service parameter, respectively determine the correlation between the service distribution data of the cells corresponding to the service parameter in the two pieces of initial sample data;

[0378] Based on the correlation corresponding to each service parameter in the two pieces of initial sample data, determining whether the initial service distribution data of the cells in the two pieces of initial sample data are of the same category;

[0379] Accordingly, when the model training module obtains the sample business distribution data corresponding to the sample historical area related information of the same category based on the initial business distribution data belonging to the same category, it can be used to:

[0380] Based on the initial service distribution data of each service parameter belonging to the same category, sample service distribution data corresponding to the area related information of the same category is obtained.

[0381] Optionally, for a set area, the beam determination module 120 determines the total number of beams required for the set area according to the service distribution data of the set area, and can be used to perform at least one of the following:

[0382] Determine the total number of beams required for the set area according to the service distribution data of the set area and the mapping relationship between the pre-configured service distribution data and the number of beams;

[0383] The total number of beams required for the set area is determined based on the business distribution data of the set area and at least one of the following information: the total business data distribution of all set areas of the cell, the size of the cell's beambook, the set value of the minimum number of beams for the set area, and the set value of the maximum number of beams for the set area.

[0384] Optionally, the ratio information of the beams arranged in the horizontal direction and the beams arranged in the vertical direction of each set area is preconfigured; or is determined by any of the following methods:

[0385] Determine, according to the coverage information of each set area, the ratio information of the beams arranged in the horizontal direction and the beams arranged in the vertical direction of each set area;

[0386] According to the coverage information of all the set areas of the cell, the ratio information of the beams arranged in the horizontal direction and the beams arranged in the vertical direction of each set area is determined.

[0387] Based on the same principles as the methods and devices provided in the embodiments of the present application, the embodiments of the present application also provide an electronic device, which includes a processor and a memory: the memory is used to store a computer program; the processor is used to execute the method provided in any embodiment of the present application when executing the computer program.

[0388] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method provided in any embodiment of the present application is implemented.

[0389] As an example, Fig.18 FIG. 4 is a schematic diagram showing a structure of an electronic device 4000 to which the solution of an embodiment of the present application is applicable. Fig.18 As shown in , the electronic device 4000 may include a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0390] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0391] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.18 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0392] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0393] The memory 4003 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the solution shown in any of the above method embodiments.

[0394] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0395] The above descriptions are only some embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A beam control method in a cell, characterized in that: include: Obtaining service distribution data of multiple beam areas in a cell; Acquire the total number of beams in each of the multiple beam areas according to the service distribution data of each beam area; According to the total number of beams in each beam area, a beam width of a beam in each beam area is obtained; Based on the total number of beams in each beam region and the beam width of a beam in each beam region, obtaining each candidate beam in each beam region from the candidate beam set; Each beam of each beam region is obtained from each candidate beam of each beam region based on the distance between the center of each candidate beam and the center of the beam region.

2. The method according to claim 1, characterized in that Get the beam width of a beam for each beam region, including: For each beam area, based on the total number of beams of the beam area obtained, coverage information of the beam area, and ratio information of beams arranged in the horizontal direction and beams arranged in the vertical direction of the beam area, obtain the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction of the beam area; Based on the coverage information of the beam area, and the number of beams arranged in the horizontal direction and the number of beams arranged in the vertical direction of the beam area, the beam width of one beam of the beam area is obtained.

3. The method according to claim 2, characterized in that For a beam region, obtaining a beam width of a beam in the beam region includes: Obtaining a horizontal beam width by dividing a horizontal beam area width included in the coverage information of the beam area by the number of beams arranged in the horizontal direction of the obtained beam area; The vertical beam width is obtained by dividing the vertical beam area width included in the coverage information of the beam area by the obtained number of beams arranged in the vertical direction of the beam area.

4. The method according to claim 1, characterized in that The obtaining, based on the distance between the center of each candidate beam and the center of the beam area, each beam of each beam area from each candidate beam of each beam area comprises: For each beam region, based on the distance between the center of the beam region and the center of each candidate beam in the beam region, each beam of the beam region is obtained from the candidate beams according to a minimum distance criterion.

5. The method according to claim 1, characterized in that The candidate beam set includes a plurality of candidate beam subsets having different beam widths; For a beam region, based on a beam width of a beam in the beam region, obtaining each candidate beam of the beam region from a candidate beam set includes: Obtaining a target beam subset of the beam area by selecting a candidate beam subset having the same beam width as a beam width of a beam of the beam area from a plurality of candidate beam subsets; Each candidate beam of the beam area is obtained from the obtained target beam subset.

6. The method according to claim 1, characterized in that Obtaining candidate beams of each beam region from the candidate beam set includes: For a beam region, based on the total number of beams in the beam region being less than a first set value, merging the beam region and one or more adjacent beam regions of the beam region as a joint beam region; Based on the beam width of the joint beam area, each candidate beam of the joint beam area is obtained from the candidate beam set.

7. The method according to claim 6, characterized in that The first setting value is 1.

8. The method according to claim 6, characterized in that The candidate beam set includes a plurality of candidate beam subsets having different beam widths; Based on the beam width of the joint beam area, obtaining each candidate beam of the joint beam area from the candidate beam set includes: Each candidate beam of the joint beam region is obtained from a subset of candidate beams having the same beam width as the joint beam region.

9. The method according to claim 8, characterized in that Get each beam in each beam region, including: Based on the distance between the center of the joint beam area and the center of each obtained candidate beam of the joint beam area, each beam of the joint beam area is obtained from the obtained candidate beams of the joint beam area.

10. The method according to any one of claims 6 to 9, characterized in that: The joint beam area satisfies at least one of the following: The total number of beams corresponding to each beam area included in the joint beam area is the same; The beam widths corresponding to the beam areas contained in the joint beam area are all the same; The total number of beams corresponding to each beam area included in the joint beam area is less than a first set value; The sum of the total number of beams corresponding to all beam areas included in the joint beam area is less than a second set value.

11. The method according to any one of claims 1 to 9, characterized in that The acquiring of service distribution data of a plurality of beam areas in a cell includes: Obtaining area-related information of the cell; According to the area-related information of the cell, the service distribution data of multiple beam areas in the cell is obtained.

12. The method according to claim 11, characterized in that The area-related information includes environmental data and / or location information of the cell.

13. The method according to claim 11, characterized in that According to the area-related information of the cell, the service distribution data of multiple beam areas in the cell is obtained, including: According to the area-related information of the cell, the service distribution data of multiple beam areas in the cell are predicted through the service prediction model.

14. The method according to claim 13, characterized in that The business prediction model is trained in the following way: Acquire training samples, wherein the training samples include sample area related information of cells of various categories and sample service distribution data of each beam area of ​​the cell corresponding to the sample area related information of each category; The initial prediction model is trained based on the sample area related information of each category until the predicted business distribution data of each category output by the initial prediction model and the sample business distribution data corresponding to the category meet preset conditions, thereby obtaining the business prediction model.

15. The method according to claim 14, characterized in that The obtaining of training samples comprises: Acquire each initial sample data, where one piece of initial sample data includes information related to an initial area of ​​a cell and initial service distribution data of the cell under the information related to the initial area, wherein the initial service distribution data of a cell includes service distribution data of multiple beam areas of the cell; Determine the category of the initial service distribution data of the cell in each piece of initial sample data, and obtain the classification result of each piece of initial service distribution data; Based on the classification results of each initial service distribution data, the initial area related information of the cell corresponding to each initial service distribution data is marked with a corresponding category label to obtain the related information of each sample area; Based on each initial business distribution data belonging to the same category, sample business distribution data corresponding to sample historical area related information of the same category is obtained.

16. The method according to claim 15, characterized in that The initial service distribution data based on the cell includes service distribution data corresponding to at least two service parameters, and the determining of the category of the initial service distribution data in each piece of initial sample data includes: For any two initial sample data, for each service parameter, respectively obtain the correlation between the service distribution data of the cells corresponding to the service parameter in the two initial sample data; For each service parameter, based on the correlation corresponding to the service parameter in the two initial sample data, determining whether the initial service distribution data of the cells in the two initial sample data are of the same category; The sample business distribution data corresponding to the sample historical area related information of the same category is obtained, including: Based on the initial business distribution data in two initial sample data belonging to the same category, the sample business distribution data corresponding to the sample historical area related information of the same category is obtained.

17. The method according to any one of claims 1 to 9, characterized in that For a beam area, determining the total number of beams in the beam area includes at least one of the following: Determine the total number of beams in the beam area according to the service distribution data of the beam area and the mapping relationship between the pre-configured service distribution data and the number of beams; Determine the total number of beams in the beam area according to the service distribution data of the beam area and at least one of the following information: The total service data distribution of all beam areas of the cell, the size of the cell's beambook, the set value of the minimum number of beams in the beam area, and the set value of the maximum number of beams in the beam area.

18. An electronic device, characterized in that: The electronic device comprises a processor and a memory: The memory is used to store a computer program, wherein the computer program includes one or more instructions; The processor is configured to execute the computer program to perform the method of any one of claims 1 to 17.

19. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 17 is implemented.

Images