Model training method, parameter adjustment method, device and equipment for shared base station

Abstract

The present application provides a model training method, a parameter adjustment method, device and equipment for a shared base station, the model training method comprising: obtaining multiple training samples, the training samples including sample service indicators of the sample base station; obtaining label data corresponding to the sample service indicators, the label data being used to represent the expected configuration parameters corresponding to the sample base station; inputting the training samples into the target network model to obtain the training output configuration parameters; and obtaining the trained target network model according to the expected configuration parameters and the training output configuration parameters. In the embodiment of the present application, the sample service indicators of the sample base station are used as training samples, and the expected configuration parameters of the sample base station are used as label data. The trained target network model can be used to adjust the configuration parameters of the shared base station, so that the signal level of the shared base station after adjusting the configuration parameters is consistent for users of different communication operators, thereby improving the configuration efficiency of the shared base station configuration parameters.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a model training method, a parameter adjustment method, a device and equipment for a shared base station. Background Art

[0002] In order to achieve rapid and full coverage of network services, operators began to share base stations. Under the shared base station model, network speed, network coverage and network bandwidth can be quickly increased. In addition, network performance can be greatly improved.

[0003] Among them, shared base stations have different service effects for users of different operators. For example, the shared base station provided by operator A has better service effects for users of operator A, and worse service effects for users of operator B. For the above problems, the current method is to manually adjust the configuration parameters of the shared base station multiple times until the service effects of the shared base station for users of different operators are consistent. This method has the problem of low efficiency, which in turn affects the sharing progress and scale of shared base stations. Summary of the invention

[0004] The present application provides a model training method, a parameter adjustment method, device and equipment for a shared base station to solve the problem of low efficiency in the prior art of manually adjusting the configuration parameters of a shared base station multiple times.

[0005] In a first aspect, the present application provides a model training method, comprising:

[0006] Acquire multiple training samples, where the training samples include sample service indicators of sample base stations;

[0007] Obtaining label data corresponding to the sample service indicator, where the label data is used to indicate the expected configuration parameters corresponding to the sample base station;

[0008] Input the training samples into the target network model to obtain the training output configuration parameters;

[0009] According to the expected configuration parameters and the training output configuration parameters, the target network model is adjusted until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model.

[0010] In one embodiment of the present application, the sample base station includes: a sample shared base station, the sample shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator; the expected configuration parameters are configuration parameters of the sample shared base station when the signal levels of the first device and the second device are consistent.

[0011] In one embodiment of the present application, the sample base station includes: a first sample base station, the first sample base station is used to serve a first device of a first communications operator, and the expected configuration parameters are configuration parameters of the first sample base station when the signal level of the first device is greater than a first signal level threshold and the signal level of a second device of a second communications operator is less than a second signal level threshold, and the first signal level threshold is greater than the second signal level threshold.

[0012] In one embodiment of the present application, the sample base station includes: a second sample base station, the second sample base station is used to serve a second device of a second communications operator, and the expected configuration parameters are configuration parameters of the second sample base station when the signal level of the second device is greater than a third signal level threshold and the signal level of the first device of the first communications operator is less than a fourth signal level threshold, and the third signal level threshold is greater than the fourth signal level threshold.

[0013] In a second aspect, the present application provides a method for adjusting parameters of a shared base station, wherein the shared base station is used to serve a first device of a first communications operator and a second device of a second communications operator. The method for adjusting parameters of a shared base station comprises: obtaining a first service indicator of the shared base station; inputting the first service indicator into a target network model trained by any one of the items in the first aspect to obtain target configuration parameters, wherein the target network model is used to determine that the configuration parameters of the shared base station are target configuration parameters, and when the shared base station configures the target configuration parameters, the signal level of the first device is consistent with the signal level of the second device; and adjusting the configuration parameters of the shared base station according to the target configuration parameters.

[0014] In one embodiment of the present application, before obtaining the first service indicator of the shared base station, it also includes: obtaining the second service indicator of the current base station; determining the target score of the current base station based on the second service indicator using an entropy weight algorithm; and determining that the current base station is a shared base station based on the target score.

[0015] In one embodiment of the present application, the current base station is determined to be a shared base station based on the target score, including: determining the priority level at which the current base station can be shared based on the target score and the score threshold; if the priority level is greater than the level threshold, determining the current base station to be a shared base station.

[0016] In a third aspect, the present application provides a model training device, comprising:

[0017] A first acquisition module is used to acquire a plurality of training samples, where the training samples include sample service indicators of sample base stations;

[0018] A second acquisition module is used to acquire label data corresponding to the sample service indicator, where the label data is used to represent the expected configuration parameters corresponding to the sample base station;

[0019] The input module is used to input the training samples into the target network model to obtain the training output configuration parameters;

[0020] The adjustment module is used to adjust the target network model according to the expected configuration parameters and the training output configuration parameters until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model.

[0021] In one embodiment of the present application, the sample base station includes: a sample shared base station, the sample shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator; the expected configuration parameters are configuration parameters of the sample shared base station when the signal levels of the first device and the second device are consistent.

[0022] In one embodiment of the present application, the sample base station includes: a first sample base station, the first sample base station is used to serve a first device of a first communications operator, and the expected configuration parameters are configuration parameters of the first sample base station when the signal level of the first device is greater than a first signal level threshold and the signal level of a second device of a second communications operator is less than a second signal level threshold, and the first signal level threshold is greater than the second signal level threshold.

[0023] In one embodiment of the present application, the sample base station includes: a second sample base station, the second sample base station is used to serve a second device of a second communications operator, and the expected configuration parameters are configuration parameters of the second sample base station when the signal level of the second device is greater than a third signal level threshold and the signal level of the first device of the first communications operator is less than a fourth signal level threshold, and the third signal level threshold is greater than the fourth signal level threshold.

[0024] In a fourth aspect, the present application provides a parameter adjustment device for a shared base station, where the shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator, and the parameter adjustment device for the shared base station includes:

[0025] An acquisition module, used to acquire a first service indicator of a shared base station;

[0026] An input module, used to input the first service indicator into the target network model obtained by training according to claim 8 to obtain target configuration parameters, the target network model is used to determine the configuration parameters of the shared base station as the target configuration parameters, when the shared base station configures the target configuration parameters, the signal level of the first device is consistent with the signal level of the second device;

[0027] The adjustment module is used to adjust the configuration parameters of the shared base station according to the target configuration parameters.

[0028] In one embodiment of the present application, the parameter adjustment device of the shared base station further includes:

[0029] A service indicator acquisition module, used to acquire a second service indicator of the current base station;

[0030] A first determination module is used to determine a target score of the current base station using an entropy weight algorithm according to the second service indicator;

[0031] The second determination module is used to determine, according to the target score, that the current base station is a shared base station.

[0032] In one embodiment of the present application, the second determination module is specifically used to: determine the priority level of the current base station that can be shared according to the target score and the score threshold; if the priority level is greater than the level threshold, determine that the current base station is a shared base station.

[0033] In a fifth aspect, the present application provides an electronic device, including:

[0034] at least one processor; and

[0035] a memory communicatively connected to at least one processor; wherein,

[0036] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the electronic device to execute any model training method in the first aspect of the present application or any shared base station parameter adjustment method in the second aspect.

[0037] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the model training method of any one of the first aspects of the present application or the parameter adjustment method of any one of the shared base stations of the second aspect.

[0038] In the seventh aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the model training method of any one of the first aspects of the present application or the parameter adjustment method of any one of the shared base stations of the second aspect.

[0039] The present application provides a model training method, a parameter adjustment method, device and equipment for a shared base station, the model training method comprising: obtaining a plurality of training samples, the training samples comprising a sample service indicator of a sample base station; obtaining label data corresponding to the sample service indicator, the label data being used to represent the expected configuration parameters corresponding to the sample base station; inputting the training samples into a target network model to obtain training output configuration parameters; adjusting the target network model according to the expected configuration parameters and the training output configuration parameters until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model. In the embodiment of the present application, the sample service indicator of the sample base station is used as a training sample, and the expected configuration parameters of the sample base station are used as label data, and the trained target network model can be used to adjust the configuration parameters of the shared base station, so that the signal level of the shared base station after adjusting the configuration parameters is consistent for users of different communication operators, thereby improving the configuration efficiency of the shared base station configuration parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the description of the prior art. Obviously, the drawings described below are some of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A schematic diagram of a scenario for the model training method provided in this application;

[0042] Figure 2 A flowchart of the steps of a model training method provided in this application;

[0043] Figure 3 A schematic diagram of the structure of the target network model provided for this application;

[0044] Figure 4 A flowchart of the steps of a parameter adjustment method for a shared base station provided in this application;

[0045] Figure 5 A schematic diagram of the structure of a model training device provided in this application;

[0046] Figure 6 A schematic diagram of the structure of a parameter adjustment device for a shared base station provided in this application;

[0047] Figure 7 A schematic diagram of the hardware structure of the electronic device provided in this application.

[0048] The above drawings have shown that the present application is clear, and a more detailed description will be given later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application for those skilled in the art by reference. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be described clearly and completely in conjunction with the drawings in this application. Obviously, what is described is a part of this application, not all of it. Based on this application, all other things obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0050] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the application described herein can be implemented in an order other than those illustrated or described herein.

[0051] In addition, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, product, or apparatus.

[0052] The inventors found that at present, different communication operators are vigorously carrying out 5G co-construction and sharing, jointly building a 5G network, and jointly promoting 5G network deployment to achieve 5G coverage in various regions. However, there are many difficulties in 5G co-construction and sharing. For example, due to the different QoS (Quality of Service) strategies of different communication operators and the differences in the coverage of shared base stations, the signal quality of mobile devices corresponding to different communication operators serving shared base stations may vary greatly.

[0053] In the related art, when determining whether the configuration parameters of a shared base station will cause large differences in the signal quality of mobile devices corresponding to different communication operators, the method adopted is that after a user complains about the network quality, the user's complaint work order is sent to the roadside staff and dial-up test staff in the corresponding area, so that the roadside staff and dial-up test staff measure the network quality indicators of the area to which the complaining user belongs, and then the analysis staff analyzes the measurement data, and through manual verification of a large amount of QoS policies, DT (road test) data, MR (measurement report) data, network cfg. (configuration) files, PM (network performance indicators) and other data, a comprehensive assessment is made on the inconsistent signal levels of mobile devices of different communication operators, and then the configuration parameters of the shared base station are adjusted.

[0054] In the above-mentioned related technologies, the method of judging the inconsistent signal levels of mobile devices of different communication operators requires the participation of workers of multiple trades, which is inefficient, inaccurate, and has a high error rate. In addition, communication operators are required to invest a lot of human resources in data docking, process communication, data extraction and analysis, etc. Due to the large number of personnel involved and the large number of management links, the differences in the levels of analysis staff, the lag in interaction time, the limited communication between staff, the lack of human resources and the lack of acquired data, and the different evaluation tendencies of different communication operators, a series of problems have led to the judgment results of the inconsistent signal levels of mobile devices of different communication operators not meeting the actual problems, which further leads to the network quality of shared base stations being unable to meet the needs of users of different communication operators.

[0055] Furthermore, the sharing of base stations is also determined by human judgment, such as "a certain site can be shared", "some sites in a certain area can be shared", "this is a special scenario, there are no shared resources", etc. The lack of a unified evaluation system has also seriously hindered the progress and scale of base station sharing.

[0056] The model training method provided in the embodiment of the present application uses the sample service indicators of the sample base stations as training samples and the expected configuration parameters of the sample base stations as label data. The target network model obtained by training can be used to adjust the configuration parameters of the shared base stations, so that the signal levels of the shared base stations after the adjustment of the configuration parameters are consistent for users of different communication operators, thereby improving the configuration efficiency of the shared base station configuration parameters.

[0057] Before introducing the model training method provided in this application, the application scenarios of the model training method are briefly introduced.

[0058] For example, Figure 1 A schematic diagram of a scenario of the model training method provided in the present application, such as Figure 1As shown, the scenario includes a sample base station 11, a first device A and a second device B in an area 12 served by the sample base station 11, and a management device 13. The first device A is a device corresponding to the first communication operator, the second device B is a device of the second communication operator, and the sample base station 11 can be a device provided by the first communication operator or the second communication operator. If the sample base station 11 is a shared base station, the service indicators of the sample base station 11 currently serving the first device A and the second device B are sent to the management device 13 as sample service indicators, and then the parameters of the sample base station are adjusted so that the configuration parameters of the sample base station when the signal levels of the first device A and the second device B are consistent are sent to the management device 13 as expected configuration parameters. The management device 13 uses the sample service indicators uploaded by multiple sample base stations 11 as training samples, and uses the expected configuration parameters as label data to train the target network model to obtain a trained target network model. When the management device 13 receives the target service indicator sent by other shared base stations, the target service indicator can be input into the target network model to obtain the target configuration parameters of the other shared base stations. The target configuration parameters of the other shared base stations can make the signal levels of the first device A and the second device B consistent when the other shared base stations serve the first device A and the second device B.

[0059] Combine the following Figure 1 For application scenarios, refer to Figure 2 To describe the model training method according to the exemplary embodiment of the present application. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0060] Figure 2 This is a flow chart of the model training method provided in the present application. The model training method specifically includes the following steps:

[0061] S201, obtaining multiple training samples.

[0062] Among them, the training samples include sample service indicators of sample base stations. Specifically, the sample service indicators include five categories of indicators. Specifically: coverage class, load class, quality class, interference class and user perception class. Among them, the coverage class includes: the proportion of downlink RSRP less than -110 (%), the average level of uplink physical shared channel (PUSCH) RSRP (dBm), and the proportion of ultra-long (>1KM) TA (%). The load class includes: the average occupancy rate of single-board CPU (%), the average number of users, the average utilization rate of uplink PRB (%), and the average utilization rate of downlink PRB (%). The quality class includes: CQI (channel quality indication) excellent rate (%), cell service rate (%), connection rate (%), drop rate (%), 5G backflow 4G ratio (%). The interference class includes: the average value of uplink interference noise received per PRB (dBm). The user perception category includes: the average uplink rate (Mbps) of user equipment in the cell, the average downlink rate (Mbps) of user equipment in the cell, the average uplink MCS (modulation and coding strategy) and the average downlink MCS.

[0063] In addition, the sample service indicator is the data generated when the sample base station uses the current configuration parameter service.

[0064] In the present application, one training sample corresponds to a sample service indicator of a sample base station. In the embodiment of the present application, multiple training samples are required to train the target network model.

[0065] S202, obtaining label data corresponding to the sample service indicator.

[0066] The tag data is used to represent the expected configuration parameters corresponding to the sample base station.

[0067] In an optional embodiment, the sample base station includes: a sample shared base station, the sample shared base station is used to serve a first device of a first communications operator and a second device of a second communications operator; the expected configuration parameters are configuration parameters of the sample shared base station when the signal levels of the first device and the second device are consistent.

[0068] Specifically, the expected configuration parameter refers to that when the configuration parameter of the sample base station is adjusted from the current configuration parameter to the expected configuration parameter, the signal level of the first device and the signal level of the second device are consistent.

[0069] In an optional embodiment, the sample base station also includes: a first sample base station, the first sample base station is used to serve a first device of a first communications operator, and the expected configuration parameters are configuration parameters of the first sample base station when the signal level of the first device is greater than a first signal level threshold and the signal level of a second device of a second communications operator is less than a second signal level threshold, and the first signal level threshold is greater than the second signal level threshold.

[0070] Specifically, the expected configuration parameter refers to the configuration parameter of the first sample base station when the configuration parameter of the sample base station is adjusted from the current configuration parameter to the expected configuration parameter, so that the signal level of the first device is greater than the first signal level threshold, and the signal level of the second device of the second communication operator is less than the second signal level threshold. Among them, if the signal level is 0, 0.2, 0.4, 0.6, 0.8 and 1, the signal level 0 indicates no signal, the signal level 0.2 indicates an extremely weak signal, the signal level 0.4 indicates a relatively weak signal, the signal level 0.6 indicates a relatively strong signal, the signal level 0.8 indicates a strong signal, and the signal level 1 indicates an extremely strong signal. In the embodiment of the present application, the signal level can be determined based on the call effect and network effect of the first device and the second device.

[0071] Exemplarily, the first signal level threshold may be 0.6, and the second signal level threshold may be 0.2.

[0072] Among them, the sample base stations include: a second sample base station, the second sample base station is used to serve the second device of the second communication operator, and the expected configuration parameters are the configuration parameters of the second sample base station when the signal level of the second device is greater than the third signal level threshold and the signal level of the first device of the first communication operator is less than the fourth signal level threshold, and the third signal level threshold is greater than the fourth signal level threshold.

[0073] Exemplarily, the third signal level threshold may be 0.6, and the fourth signal level threshold may be 0.2.

[0074] In addition, in the embodiment of the present application, the training samples and expected configuration parameters corresponding to the sample sharing base station can be used as data for training the target network model. The training samples and expected configuration parameters corresponding to the first sample base station or the second sample base station can be used as data for testing the target network model after training.

[0075] S203, input the training samples into the target network model to obtain training output configuration parameters.

[0076] Among them, the structure of the target neural network is BP neural network (back propagation), which is a multi-layer feedforward neural network trained according to the error back propagation algorithm. In addition, the BP neural network is divided into two stages: forward propagation and error back propagation. During forward propagation, the Sigmoid activation function is used to calculate the training output configuration parameters, and then the gradient descent method is used for back propagation according to the difference between the training output configuration parameters and the expected configuration parameters to update the model parameters of the target network model.

[0077] Specifically, refer to Figure 3, the target network model includes an input layer 31, a hidden layer 32 and an output layer 33. The input layer 31 includes a plurality of input nodes (A1 to An), n is an integer greater than 1, and each input node inputs different sample data in the training sample. The hidden layer 32 includes a plurality of hidden nodes (B1 to Bm), m is an integer greater than 1, and the data output by the input layer 31 enters the hidden layer 32. The output layer 33 includes a plurality of output nodes (C1 to Cp), p is an integer greater than or equal to 1, and the data output by the hidden layer 32 enters the output layer, and the training output configuration parameters are output after being processed by the output layer.

[0078] in, Figure 3 In the above example, the training samples are preprocessed to obtain the input data X = (x1, x2, ..., x n ) T , where x i Input the corresponding input node A i , i ranges from 1 to n. Wk=(w k1 , w k2 ,…,w km ) is the connection weight between the kth hidden node in the hidden layer 32 and the input layer 31. Wo = (w1, w2, ..., w m ) is the connection weight between the output layer 33 and the hidden node. Ho=(h1,h2,…,h m ) is the output value of each hidden node in the hidden layer. B=(b1,b2,…,b m ) is the threshold value corresponding to each hidden node. bo is the threshold value of each output node in the output layer. Then the output of the hidden layer is Ho = f1(w k xb k ), where f1 is the activation function (Sigmoid) of the hidden layer 32. The training output configuration parameter of the output layer output is O=f2(w o H o -b o ), where f2 is the activation function (Sigmoid) of the output layer 33.

[0079] S204, adjusting the target network model according to the expected configuration parameters and the training output configuration parameters until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold, thereby obtaining a trained target network model.

[0080] Among them, adjusting the target network model is essentially adjusting the model parameters of the target network model. Specifically, when the difference between the expected configuration parameters and the training output configuration parameters is greater than the threshold, the connection weights between the hidden nodes and the input layer, the connection weights between the output layer and the hidden nodes, the thresholds of each hidden node, and the thresholds of each output node are adjusted through back propagation. Until the difference between the expected configuration parameters and the training output configuration parameters is less than the threshold, the trained target network model is obtained.

[0081] The model training method provided in the present application includes: obtaining multiple training samples, the training samples include sample service indicators of sample base stations; obtaining label data corresponding to the sample service indicators, the label data is used to represent the expected configuration parameters corresponding to the sample base stations; inputting the training samples into the target network model to obtain the training output configuration parameters; adjusting the target network model according to the expected configuration parameters and the training output configuration parameters until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model. In the embodiment of the present application, the sample service indicators of the sample base stations are used as training samples, and the expected configuration parameters of the sample base stations are used as label data. The trained target network model can be used to adjust the configuration parameters of the shared base stations, so that the signal levels of the shared base stations after adjusting the configuration parameters are consistent for users of different communication operators, thereby improving the configuration efficiency of the shared base station configuration parameters.

[0082] Figure 4 A flow chart of the steps of the parameter adjustment method of a shared base station provided in the present application. The shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator, and the parameter adjustment method of the shared base station specifically includes the following steps:

[0083] S401: Obtain a first service indicator of a shared base station.

[0084] Before obtaining the first service indicator of the shared base station, the method also includes: obtaining the second service indicator of the current base station; determining the target score of the current base station using an entropy weight algorithm based on the second service indicator; and determining that the current base station is a shared base station based on the target score.

[0085] Specifically, the current base station is a non-shared base station. The base station only serves the first communication operator or the second communication operator. The second service indicators of the current base station include: three categories of indicators, namely load, throughput and perception. Among them, the load includes: single-user perception rate, number of online activated users and wireless resource utilization. Throughput includes: three high user traffic (GB), single-cell downlink traffic (GB), "720p+video traffic (GB)" and "71080p+video traffic (GB)". Perception includes: game freeze rate (%) and video freeze rate (%).

[0086] Exemplarily, the single-user perception rate refers to {the total throughput of downlink data sent by the cell PDCP (radio network layer and transport network layer) layer minus the downlink PDCP throughput transmitted in the last TTI that makes the buffer empty} / (the data transmission duration after deducting the last TTI (transmission time interval) that makes the downlink buffer empty) / {1000}. The number of online activated users refers to the average number of activated users. The wireless resource utilization rate refers to the average number of downlink PRBs (physical resource modules) used / the number of downlink available PRBs / {0.9} / {0.6} / {0.5}*{100}. The three high user traffic refers to high ARPU (revenue) user traffic, high DOU (monthly Internet traffic per household) and high terminal user traffic. The single-cell downlink traffic (GB) refers to the total throughput of downlink data sent by the cell PDCP layer / ({1000}*{1000}*{1000}.

[0087] In the embodiment of the present application, entropy is a measure of uncertain data. The larger the amount of data, the higher the recognizability and the smaller the entropy. Conversely, the smaller the amount of data, the greater the entropy. The present application introduces an entropy weight algorithm to uniformly score the second service indicators of each base station, and determines the base station that can be used as a shared base station based on the target score of the final base station. It is also possible to perform scoring calculations on base stations and key base stations recommended by communication operators.

[0088] In addition, the entropy weight algorithm is specifically as follows: each data X1, X2, ..., Xk of the second service indicator is standardized to obtain standardized data Y1, Y2, ..., Yk. Among them, j is 1 to k, min(X i ) refers to X1, X2, …, X k The smallest data, max(X m ) refers to X1, X2, …, X k The information entropy corresponding to the second service indicator in, Among them, if P j =0, then define According to information entropy, determine each data X1, X2, ..., X k The corresponding information entropies are E1, E2, ..., E k . Then we get the weights corresponding to each data: i ranges from 1 to k in sequence.

[0089] For example, referring to Table 1, the weight values ​​corresponding to the three types of indicators and the weights corresponding to the data in each type of indicator are obtained by the above method. The sum of the weights of the data under each type of indicator is 100%. The sum of the weights of various indicators is 100%.

[0090] Specifically, based on each type of indicator, the weight corresponding to each data under the indicator can be calculated, and then the weight of each type of indicator can be calculated.

[0091] Table 1

[0092]

[0093] Among them, referring to Table 2, which is the entropy value corresponding to each data, the score corresponding to each indicator can be calculated according to the sum of the product of the weight corresponding to each data and the corresponding entropy value, and then the target score of the current base station can be obtained according to the sum of the product of the weight corresponding to each indicator and the score corresponding to the indicator.

[0094] For example, if the entropy value corresponding to the single-user perception rate is 100, the entropy value corresponding to the number of online activated users is 60, and the entropy value corresponding to the wireless resource utilization rate is 30, then the score corresponding to the load is S1 = 28.26% * 100 + 35.25% * 60 + 36.49% * 30, which is 60.357. If the entropy value corresponding to the three-high user traffic is 60, the entropy value corresponding to the single-cell downlink traffic is 30, the entropy value corresponding to the 720p + video traffic is 100, and the entropy value corresponding to the 1080p + video traffic is 60, then the score corresponding to the throughput is S2 = 23.59% * 60 + 22% * 30 + 29.65% * 100 + 24.76% * 60, which is 65.26. If the entropy value corresponding to the game jam rate is 60, and the entropy value corresponding to the video jam rate is 30, then the score corresponding to the perception is S3 = 50% * 60 + 50% * 30, which is 45. Then the target score of the previous base station S = 50%*S1+40%*S2+10%*S3, which is 60.78.

[0095] In an embodiment of the present application, entropy values ​​corresponding to reference value intervals of multiple data may be pre-set to further determine a target score for the current base station, so as to accurately determine whether the current base station can be used as a shared base station.

[0096] Table 2

[0097]

[0098] Further, according to the target score, determining the current base station as a shared base station includes: determining a priority level at which the current base station can be shared according to the target score and a score threshold; if the priority level is greater than the level threshold, determining the current base station as a shared base station.

[0099] Exemplarily, if the target score is greater than or equal to 60 points, the current base station is determined to be a non-shared base station. If the target score is greater than or equal to 50 points and less than 60 points, the current base station is determined to be a negotiable shared base station. If the target score is greater than or equal to 40 points and less than 50 points, the current base station is determined to be a shareable base station. If the target score is greater than or equal to 30 points and less than 40 points, the current base station is determined to be a priority shared base station.

[0100] S402: Input the first service indicator into the target network model obtained by any of the above training to obtain target configuration parameters.

[0101] The target network model is used to determine the configuration parameters of the shared base station as target configuration parameters. When the shared base station configures the target configuration parameters, the signal level of the first device is consistent with the signal level of the second device.

[0102] S403: Adjust the configuration parameters of the shared base station according to the target configuration parameters.

[0103] In the embodiment of the present application, the target network model can be used to adjust the configuration parameters of the shared base station, so that the signal level of the shared base station after adjusting the configuration parameters is consistent for users of different communication operators, thereby improving the configuration efficiency of the shared base station configuration parameters. In addition, the entropy weight algorithm can also be used to determine whether the current base station can be shared, thereby promoting the sharing progress and scale of the shared base station.

[0104] Figure 5 This is a structural block diagram of the model training device 50 provided in the present application. Figure 5 As shown, the model training device 50 provided in the present application includes: a first acquisition module 51, a second acquisition module 52, an input module 53 and an adjustment module 54. Among them:

[0105] A first acquisition module 51 is used to acquire a plurality of training samples, where the training samples include sample service indicators of sample base stations;

[0106] A second acquisition module 52 is used to acquire label data corresponding to the sample service indicator, where the label data is used to represent the expected configuration parameters corresponding to the sample base station;

[0107] An input module 53 is used to input the training samples into the target network model to obtain the training output configuration parameters;

[0108] The adjustment module 54 is used to adjust the target network model according to the expected configuration parameters and the training output configuration parameters until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model.

[0109] In one embodiment of the present application, the sample base station includes: a sample shared base station, the sample shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator; the expected configuration parameters are configuration parameters of the sample shared base station when the signal levels of the first device and the second device are consistent.

[0110] In one embodiment of the present application, the sample base station includes: a first sample base station, the first sample base station is used to serve a first device of a first communications operator, and the expected configuration parameters are configuration parameters of the first sample base station when the signal level of the first device is greater than a first signal level threshold and the signal level of a second device of a second communications operator is less than a second signal level threshold, and the first signal level threshold is greater than the second signal level threshold.

[0111] In one embodiment of the present application, the sample base station includes: a second sample base station, the second sample base station is used to serve a second device of a second communications operator, and the expected configuration parameters are configuration parameters of the second sample base station when the signal level of the second device is greater than a third signal level threshold and the signal level of the first device of the first communications operator is less than a fourth signal level threshold, and the third signal level threshold is greater than the fourth signal level threshold.

[0112] The model training device provided in this application is used to perform the above Figure 2 The technical solutions in the corresponding methods have similar implementation principles and technical effects, which will not be repeated here.

[0113] Figure 6 The shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator, such as Figure 6 As shown, the parameter adjustment device 60 of the shared base station provided in the present application includes: an acquisition module 61, an input module 62 and an adjustment module 63. Among them:

[0114] An acquisition module 61 is used to acquire a first service indicator of a shared base station;

[0115] An input module 62, configured to input the first service indicator into the target network model obtained by training according to claim 8 to obtain a target configuration parameter, wherein the target network model is used to determine the configuration parameter of the shared base station as the target configuration parameter, and when the shared base station configures the target configuration parameter, the signal level of the first device is consistent with the signal level of the second device;

[0116] The adjustment module 63 is used to adjust the configuration parameters of the shared base station according to the target configuration parameters.

[0117] In one embodiment of the present application, the parameter adjustment device of the shared base station further includes:

[0118] A service indicator acquisition module (not shown), configured to acquire a second service indicator of the current base station;

[0119] A first determination module (not shown), configured to determine a target score of the current base station using an entropy weight algorithm according to the second service indicator;

[0120] The second determination module (not shown) is used to determine, according to the target score, that the current base station is a shared base station.

[0121] In one embodiment of the present application, the second determination module is specifically used to: determine the priority level of the current base station that can be shared according to the target score and the score threshold; if the priority level is greater than the level threshold, determine that the current base station is a shared base station.

[0122] The parameter adjustment device of the shared base station provided in this application is used to perform the above Figure 4 The technical solutions in the corresponding methods have similar implementation principles and technical effects, which will not be repeated here.

[0123] Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 of the present application may include: at least one processor 71 ( Figure 7 Only one processor is shown); and a memory 72 in communication with at least one processor. The memory 72 stores instructions that can be executed by at least one processor 71, and the instructions are executed by at least one processor 71 so that the electronic device 70 can execute the technical solution in any of the aforementioned methods.

[0124] Optionally, the memory 72 can be independent or integrated with the processor 71.

[0125] When the memory 72 is a device independent of the processor 71 , the electronic device 70 further includes a bus 73 for connecting the memory 72 and the processor 71 .

[0126] The electronic device provided in the present application can execute the technical solution of any of the aforementioned methods, and its implementation principles and technical effects are similar, which will not be repeated here.

[0127] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the technical solution in any of the aforementioned methods.

[0128] The present application provides a computer program product, including a computer program, which implements the technical solution in any of the aforementioned methods when executed by a processor.

[0129] The present application also provides a chip, including: a processing module and a communication interface, and the processing module can execute the technical solution in the aforementioned method.

[0130] Furthermore, the chip also includes a storage module (such as a memory), the storage module is used to store instructions, the processing module is used to execute the instructions stored in the storage module, and the execution of the instructions stored in the storage module enables the processing module to execute the technical solution in the aforementioned method.

[0131] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0132] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0133] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0134] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0135] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device.

[0136] Finally, it should be noted that the above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above, ordinary technicians in this field should understand that they can still modify the above-mentioned technical solutions, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. A model training method, characterized in that: include: Acquire a plurality of training samples, wherein the training samples include sample service indicators of sample base stations; Acquire label data corresponding to the sample service indicator, where the label data is used to represent the expected configuration parameters corresponding to the sample base station; Inputting the training samples into the target network model to obtain training output configuration parameters; According to the expected configuration parameters and the training output configuration parameters, the target network model is adjusted until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model; The sample base station includes: a sample shared base station, the sample shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator; the expected configuration parameter is a configuration parameter of the sample shared base station when the signal levels of the first device and the second device are consistent, wherein the signal level is determined according to the call effect and network effect of the first device and the second device; The training samples and expected configuration parameters corresponding to the sample sharing base station are used as data for training the target network model.

2. The model training method according to claim 1, characterized in that: The sample base station includes: a first sample base station, the first sample base station is used to serve a first device of a first communications operator, and the expected configuration parameters are configuration parameters of the first sample base station when the signal level of the first device is greater than a first signal level threshold and the signal level of a second device of a second communications operator is less than a second signal level threshold, and the first signal level threshold is greater than the second signal level threshold; wherein the training samples and expected configuration parameters corresponding to the first sample base station are used as data for the target network model completed by test training.

3. The model training method according to claim 1 or 2, characterized in that: The sample base station includes: a second sample base station, the second sample base station is used to serve a second device of a second communication operator, the expected configuration parameter is a configuration parameter of the second sample base station when the signal level of the second device is greater than a third signal level threshold and the signal level of the first device of the first communication operator is less than a fourth signal level threshold, and the third signal level threshold is greater than the fourth signal level threshold; The training samples and expected configuration parameters corresponding to the second sample base station are used as data for testing the target network model after training.

4. A parameter adjustment method for a shared base station, characterized in that: The shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator, and the parameter adjustment method of the shared base station includes: Obtaining a first service indicator of a shared base station; Inputting the first service indicator into the target network model obtained by training according to any one of claims 1 to 3 to obtain target configuration parameters, wherein the target network model is used to determine that the configuration parameters of the shared base station are target configuration parameters, and when the shared base station configures the target configuration parameters, the signal level of the first device is consistent with the signal level of the second device; According to the target configuration parameters, the configuration parameters of the shared base station are adjusted.

5. The parameter adjustment method of a shared base station according to claim 4, characterized in that: Before obtaining the first service indicator of the shared base station, the method further includes: Acquire a second service indicator of a current base station; the current base station only serves the first communication operator or the second communication operator; the second service indicator of the current base station includes: load, throughput and perception; Determine a target score for the current base station using an entropy weight algorithm according to the second service indicator; The entropy weight algorithm is as follows: standardizing each data of the second service indicator to obtain standardized data; calculating the information entropy corresponding to the second server indicator according to the standardized data, and determining the weight corresponding to each data according to the information entropy; Calculate the score corresponding to each indicator according to the sum of the product of the weight corresponding to each data and the corresponding entropy value, and then obtain the target score of the current base station according to the sum of the product of the weight corresponding to each indicator and the score corresponding to the indicator; According to the target score, the current base station is determined to be the shared base station.

6. The parameter adjustment method of a shared base station according to claim 5, characterized in that: The determining, according to the target score, that the current base station is the shared base station includes: Determining a priority level at which the current base station can be shared according to the target score and the score threshold; If the priority level is greater than the level threshold, the current base station is determined to be the shared base station.

7. A model training device, characterized in that: include: A first acquisition module, configured to acquire a plurality of training samples, wherein the training samples include sample service indicators of sample base stations; A second acquisition module, used to acquire label data corresponding to the sample service indicator, wherein the label data is used to represent the expected configuration parameters corresponding to the sample base station; An input module, used to input the training samples into a target network model to obtain training output configuration parameters; An adjustment module, used to adjust the target network model according to the expected configuration parameters and the training output configuration parameters, until the difference between the expected configuration parameters and the training output configuration parameters is less than a threshold value, thereby obtaining a trained target network model; The sample base station includes: a sample shared base station, the sample shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator; the expected configuration parameter is a configuration parameter of the sample shared base station when the signal levels of the first device and the second device are consistent; wherein the signal level is determined according to the call effect and network effect of the first device and the second device; The training samples and expected configuration parameters corresponding to the sample sharing base station are used as data for training the target network model.

8. A parameter adjustment device for a shared base station, characterized in that: The shared base station is used to serve a first device of a first communication operator and a second device of a second communication operator, and the parameter adjustment device of the shared base station includes: An acquisition module, used to acquire a first service indicator of a shared base station; an input module, used to input the first service indicator into the target network model obtained by training according to claim 7 to obtain target configuration parameters, wherein the target network model is used to determine that the configuration parameters of the shared base station are target configuration parameters, and when the shared base station configures the target configuration parameters, the signal level of the first device is consistent with the signal level of the second device; An adjustment module is used to adjust the configuration parameters of the shared base station according to the target configuration parameters.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the electronic device can execute the model training method described in any one of claims 1 to 3 or the parameter adjustment method of the shared base station described in any one of claims 4 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the model training method described in any one of claims 1 to 3 or the parameter adjustment method of a shared base station described in any one of claims 4 to 6.

Images