Base station control methods, devices, electronic equipment and storage media

By acquiring base station operation information for scenario and service analysis, identifying candidate adjustment information and filtering basic adjustment information, the problem of inflexible adjustment of base station parameter configuration is solved, realizing intelligent adjustment of base station parameters and improving network stability and resource utilization.

CN123123950APending Publication Date: 2026-11-17ZHIZHU COMMUNICATION TECHNOLOGY (CHENGDU) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611378876.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-07
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

The inflexible configuration of base station parameters leads to low resource utilization, fluctuating service quality, and increased network interference, affecting network stability.

Method used

By acquiring the current base station's operational information, conducting operational scenario and service analysis, identifying candidate adjustment information, and filtering basic adjustment information based on correlations, intelligent and refined adjustment of base station parameters is achieved. The mutual influence between the current base station and related base stations is considered to avoid negative interference to surrounding base stations.

Benefits of technology

It improves the timeliness and pertinence of base station parameter adjustment, ensures the stability and performance of the overall network operation, and takes into account the operating status of associated base stations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123123950A_ABST
    Figure CN123123950A_ABST
Patent Text Reader

Abstract

This disclosure relates to a base station control method, apparatus, electronic device, and storage medium. The method includes: acquiring current operating information of the current base station; obtaining, based on the current operating information, a target scenario type and service analysis data for the current base station's corresponding operating scenario within a preset time period; determining at least one set of candidate adjustment information based on the target scenario type and service analysis data, wherein the candidate adjustment information represents candidate parameters to be adjusted for the current base station and candidate parameter values ​​corresponding to the candidate parameters to be adjusted; selecting basic adjustment information from the at least one set of candidate adjustment information based on a preset association relationship, wherein the preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each associated base station, and the influence weight represents the degree to which the operating state of the current base station affects the operating state of the corresponding associated base station; and controlling the current base station based on the basic adjustment information. Utilizing embodiments of this disclosure can improve the rationality of base station parameter adjustment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a base station control method, apparatus, electronic device and storage medium. Background Technology

[0002] As the infrastructure of mobile communication networks, base stations directly determine the coverage quality of the wireless network, user service experience, and operator maintenance costs. With the increasing diversification of communication services and the continuous growth of the user base, the operating environment and service load faced by base stations are becoming increasingly dynamic, with significant differences in service types and traffic density across different times and regions. If the parameter configuration of base stations cannot be flexibly adjusted to adapt to changing scenarios, it will lead to problems such as low resource utilization, fluctuating service quality, and even increased network interference, seriously affecting the stability of the overall network. Therefore, a base station control method is needed to meet the requirements of adapting to dynamic operating scenarios and ensuring the overall network performance. Summary of the Invention

[0003] This disclosure provides a base station control method, apparatus, electronic device, and storage medium to meet the needs of adapting to dynamic operating scenarios and ensuring the overall network performance.

[0004] According to a first aspect of the present disclosure, a base station control method is provided, comprising: Obtain the current operating information of the current base station; Based on the current operating information, the current base station is subjected to operating scenario analysis and service analysis to obtain the target scenario type and service analysis data of the current base station corresponding to the operating scenario within a preset time period; Based on the target scenario type and the service analysis data, at least one set of candidate adjustment information is determined. The candidate adjustment information represents the candidate parameters to be adjusted of the current base station and the candidate parameter values ​​corresponding to the candidate parameters to be adjusted. Based on a preset association relationship, basic adjustment information is selected from at least one set of candidate adjustment information. The preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each of the associated base stations. The influence weight represents the degree to which the operating status of the current base station affects the operating status of the corresponding associated base station. Based on the aforementioned basic adjustment information, the current base station is controlled.

[0005] According to a second aspect of the present disclosure, a base station control device is provided, comprising: The current operation information acquisition module is used to acquire the current operation information of the current base station; The information analysis module is used to perform operational scenario analysis and service analysis on the current base station based on the current operational information, and to obtain the target scenario type and service analysis data of the current base station corresponding to the operational scenario within a preset time period. The candidate adjustment information determination module is used to determine at least one set of candidate adjustment information based on the target scenario type and the service analysis data. The candidate adjustment information represents the candidate parameters to be adjusted of the current base station and the candidate parameter values ​​corresponding to the candidate parameters to be adjusted. The basic adjustment information determination module is used to filter basic adjustment information from at least one set of candidate adjustment information based on a preset association relationship. The preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each of the associated base stations. The influence weight represents the degree to which the operating status of the current base station affects the operating status of the corresponding associated base station. The base station control module is used to control the current base station based on the basic adjustment information.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method as described in any one of the first aspects above.

[0007] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided such that, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method described in any of the first aspects of the present disclosure.

[0008] According to a fifth aspect of the present disclosure, a computer program product including instructions is provided that, when run on a computer, causes the computer to perform the method described in any of the first aspects of the present disclosure.

[0009] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects: By acquiring the current operational information of the base station, a comprehensive understanding of its real-time operational status can be obtained, providing an accurate data foundation for subsequent analysis. Based on this operational information, operational scenario analysis and business analysis are performed to obtain the target scenario type and business analysis data for the current base station's corresponding operational scenario within a preset time period. This allows base station parameter adjustments to match future business demand trends, rather than passively responding to the current state, thereby improving the timeliness and targeting of parameter adjustments. Based on the target scenario type and business analysis data, at least one set of candidate adjustment information is determined, enabling the generation of multiple feasible parameter adjustment schemes for different scenarios and business characteristics, ensuring the diversity and flexibility of adjustment strategies. Based on preset correlations, basic adjustment information is selected from at least one set of candidate adjustment information. When determining the adjustment scheme, the mutual influence between the current base station and its associated base stations is fully considered to avoid excessive negative interference to surrounding associated base stations due to parameter adjustments, ensuring the stability of the overall network operation. Finally, the current base station is controlled based on the basic adjustment information, achieving intelligent and refined adjustment of base station parameters. This ensures the performance improvement of the current base station while also considering the operational status of associated base stations, improving the rationality of base station parameter adjustments and guaranteeing the stability of the overall network operation.

[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0012] Figure 1 This is a flowchart illustrating a base station control method according to an exemplary embodiment; Figure 2 This is a schematic diagram illustrating a process of inputting current operating information into a preset base station analysis model to perform operating scenario analysis and service analysis on the current base station, thereby obtaining target scenario type and service analysis data, according to an exemplary embodiment. Figure 3 This is a schematic diagram illustrating a process for determining at least one set of candidate adjustment information based on target scenario type and business analysis data, according to an exemplary embodiment. Figure 4 This is a schematic diagram illustrating a process for selecting basic adjustment information from at least one set of candidate adjustment information based on a preset association relationship, according to an exemplary embodiment. Figure 5 This is a schematic diagram illustrating a process for controlling the current base station based on target adjustment information, according to an exemplary embodiment. Figure 6 This is a schematic diagram illustrating a process for performing revenue analysis on basic adjustment information based on business analysis data and current operating information, and determining target adjustment information from the basic adjustment information, according to an exemplary embodiment. Figure 7 This is a block diagram of a base station control device according to an exemplary embodiment; Figure 8 This is a block diagram illustrating an electronic device for base station control according to an exemplary embodiment. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0014] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar different contents and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0015] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0016] Figure 1 This is a flowchart illustrating a base station control method according to an exemplary embodiment, such as... Figure 1 As shown, this base station control method is used in electronic devices such as servers in a base station and includes the following steps.

[0017] Step S101: Obtain the current operating information of the current base station.

[0018] In a specific embodiment, a base station is a radio transceiver device in a mobile communication network that connects user terminals to the network. The current base station is a communication base station currently undergoing parameter adjustment and control. The current operating information can characterize the real-time operating status, service load, resource configuration and occupancy, and channel environment quality of the current base station. For example, the current operating information may include at least one of the following: the current service load of the current base station (such as downlink / uplink throughput, number of online users, number of RRC connections), resource utilization (such as time-frequency resource utilization, power resource utilization, and channel resource utilization), signal quality indicators (such as reference signal received power (RSRP), signal-to-interference-plus-noise ratio (SINR), and reference signal received quality (RSRQ), currently operating radio configuration parameters (such as transmit power, antenna downtilt angle, subframe ratio, and modulation and coding strategy), and the current values ​​of various performance indicators of the current base station (such as latency, access success rate, handover success rate, dropped call rate, bit error rate, and coverage area).

[0019] Step S103: Based on the current operating information, perform operating scenario analysis and service analysis on the current base station to obtain the target scenario type and service analysis data of the current base station's corresponding operating scenario within a preset time period.

[0020] In one specific embodiment, the preset time period is a pre-set time window for performing operational scenario analysis and service analysis on the current base station. For example, the preset time period can be the next 6 hours, the next 24 hours, or the next week, etc. This application does not limit the specific duration of the preset time period and can flexibly configure it according to actual service needs and adjustment precision.

[0021] In a specific embodiment, the target scenario type characterizes the type of operating scenario in which the current base station is located within a preset time period. For example, it can be a high-load scenario, a low-load scenario, or a tidal scenario. Among them, a high-load scenario refers to a scenario in which the service load of the current base station is continuously higher than a preset load threshold within a preset time period; a low-load scenario refers to a scenario in which the service load of the current base station is continuously lower than a preset load threshold within a preset time period; and a tidal scenario refers to a scenario in which the service load of the current base station exhibits a clear time-varying pattern within a preset time period.

[0022] In a specific embodiment, the service analysis data characterizes the service development trend and service composition characteristics of the current base station within a preset time period. For example, the service analysis data may include at least one of the following: service analysis volume, service type distribution ratio, service change trend, and user distribution information. The service analysis volume is the analysis value of the total amount of services carried by the current base station within the preset time period; the service type distribution ratio reflects the percentage of various services (such as telephone and SMS services, video services, web browsing services, IoT services, etc.) in the total service volume within the preset time period; the service change trend reflects the direction and rate of increase or decrease in service volume within the preset time period; and the user distribution information reflects the spatial distribution of users served by the current base station within the preset time period.

[0023] In a specific embodiment, the above-mentioned analysis of the operating scenario and services of the current base station based on the current operating information, to obtain the target scenario type and service analysis data of the current base station's corresponding operating scenario within a preset time period, includes: Input the current operating information into the preset base station analysis model to perform operating scenario analysis and service analysis on the current base station, and obtain the target scenario type and service analysis data.

[0024] In the above embodiments, by inputting the current operating information into the preset base station analysis model for operating scenario analysis and service analysis, the efficiency and accuracy of the analysis are improved. This allows the determination of subsequent candidate adjustment information to simultaneously take into account the operating scenario characteristics of the current base station and the actual service needs, providing a more accurate and comprehensive basis for parameter adjustment decisions.

[0025] In one specific embodiment, the preset base station analysis model includes a first feature extraction layer, a discard layer, a second feature extraction layer, an attention layer, a scene classification layer, and a service analysis layer.

[0026] Specifically, the first feature extraction layer is used to perform initial temporal feature extraction on the input current operating information and output a first vector. For example, the first feature extraction layer can be a first LSTM unit layer containing a preset number of LSTM neurons to capture long-term temporal dependencies and periodic business patterns in the current operating information. For example, the number of LSTM neurons in the first feature extraction layer can be 64. This application does not limit the number of neurons in the first feature extraction layer and can flexibly configure it according to the computing resources of the base station and the model accuracy requirements.

[0027] The dropout layer is used to randomly discard the first vector output by the first feature extraction layer. For example, the dropout layer can use the Dropout mechanism to randomly discard some neuron outputs in the first vector with a preset probability, generating a second vector with the same dimension, to prevent model overfitting. This application does not limit the preset probability and can be flexibly configured according to the computing resources of the base station and the accuracy requirements of the model.

[0028] The second feature extraction layer is used to further compress and abstract the second vector after the discard layer, outputting a third vector. For example, the second feature extraction layer can be a second LSTM unit layer containing a predetermined number of LSTM neurons, used to further extract more discriminative feature representations based on the temporal features extracted by the first feature extraction layer. For example, the number of LSTM neurons in the second feature extraction layer can be 32, and the number of LSTM neurons in the second feature extraction layer is less than the number of LSTM neurons in the first feature extraction layer, to achieve feature dimension compression.

[0029] The attention layer is used to perform feature weighted fusion of the second and third vectors. For example, the attention layer can use the attention mechanism to assign different weight coefficients to the second and third vectors respectively, so as to highlight the feature dimensions that are more important to the classification and business analysis of the current base station operation scenario and suppress the influence of redundant or noisy features, thereby obtaining a weighted feature vector.

[0030] The scene classification layer can include a fully connected layer and a classification activation function, which is used to map the weighted feature vector to the classification result corresponding to the preset running scene type.

[0031] The service analysis layer may include a fully connected layer and a regression activation function, which are used to map the weighted feature vector to the service analysis data of the current base station within a preset time period.

[0032] In a specific embodiment, such as Figure 2 As shown above, the current operating information is input into a preset base station analysis model to perform operating scenario analysis and service analysis on the current base station, obtaining target scenario type and service analysis data, including: Step S201: Input the current running information into the first feature extraction layer to extract temporal features and obtain the first vector.

[0033] In a specific embodiment, the above-mentioned inputting the current running information into the first feature extraction layer for temporal feature extraction to obtain the first vector may include: First, arranging the current running information according to a preset time step to form a multi-dimensional temporal feature sequence; then, using this multi-dimensional temporal feature sequence as input, inputting it frame by frame into the first feature extraction layer in chronological order; then, at each time step, the first feature extraction layer performs feature calculation based on the input data of the current time step and the hidden state passed from the previous time step through its internal gating structure, and outputs the hidden state vector corresponding to the current time step; finally, concatenating the hidden state vectors output by the first feature extraction layer at all time steps in chronological order to obtain the first vector.

[0034] Step S203: Input the first vector into the dropout layer for random dropout processing to obtain the second vector.

[0035] In a specific embodiment, the above-mentioned input of the first vector into the dropout layer for random dropout processing to obtain the second vector may include: inputting the first vector into the dropout layer, the dropout layer randomly sampling each feature value in the first vector according to a preset dropout probability to determine the feature positions that need to be zeroed; then, setting the sampled feature values ​​in the first vector to zero, and scaling the unsampled feature values; finally, combining all the feature values ​​after zeroing and scaling to obtain the second vector.

[0036] Step S205: Input the second vector into the second feature extraction layer for feature compression to obtain the third vector.

[0037] In a specific embodiment, the above-mentioned inputting the second vector into the second feature extraction layer for feature compression to obtain the third vector may include: inputting the second vector into the second feature extraction layer, the second feature extraction layer processing the input sequence sequentially step by step through its internal recurrent units, receiving the second vector at the current time step and combining it with the hidden state at the previous time step for nonlinear transformation; since the number of neurons in the second feature extraction layer is less than that in the first feature extraction layer (e.g., reduced from 64 neurons to 32 neurons), it automatically maps high-dimensional features to low-dimensional space during the step-by-step processing, realizing the compression and abstraction of feature information; after processing for a complete time step, a feature representation with lower dimension and more concise semantics is output, which is the third vector.

[0038] Step S207: Input the second and third vectors into the attention layer for feature weighting to obtain a weighted feature vector.

[0039] In a specific embodiment, the above-mentioned input of the second vector and the third vector into the attention layer for feature weighting to obtain a weighted feature vector may include: inputting the second vector as the query vector and the third vector as the key vector and value vector into the attention layer; the attention layer first calculates the similarity score between the query vector and the key vector to obtain the attention weight distribution; then it performs a weighted summation of the weight distribution and the value vector, so that the value vector part with high relevance to the query vector receives greater weight, while the weight of the part with low relevance is suppressed; finally, it outputs a fused feature representation with weights redistributed through the attention mechanism, which is the weighted feature vector.

[0040] Step S209: Input the weighted feature vector into the scene classification layer to perform operational scene analysis on the current base station and obtain the target scene type.

[0041] In a specific embodiment, the above-mentioned inputting the weighted feature vector into the scene classification layer to analyze the operating scene of the current base station and obtain the target scene type may include: inputting the weighted feature vector into the scene classification layer, the scene classification layer performing a linear mapping on the weighted feature vector through its internal weight matrix to obtain the classification score corresponding to each preset operating scene category; then, normalizing each classification score to obtain the probability value corresponding to each preset operating scene category; finally, determining the preset operating scene category whose probability value meets the preset conditions as the operating scene corresponding to the current base station to obtain the target scene type.

[0042] Step S211: Input the weighted feature vector into the service analysis layer to perform service analysis on the current base station and obtain service analysis data.

[0043] In a specific embodiment, the above-mentioned input of the weighted feature vector into the service analysis layer to perform service analysis on the current base station and obtain service analysis data may include: inputting the weighted feature vector into the service analysis layer, the service analysis layer performing linear transformation and nonlinear activation on the weighted feature vector through its internal fully connected network, mapping it to an output dimension equal to the number of preset service analysis indicators; each output neuron corresponds to a service analysis indicator (such as the traffic volume, number of users, resource load, etc. in the future period), and after processing by the activation function, outputting continuous numerical results, which are the service analysis data.

[0044] In the above embodiments, the preset base station analysis model extracts temporal features from the current operating information through the first feature extraction layer, which can fully capture the state change patterns of the current base station in the time dimension. Then, the discard layer performs random discarding, which effectively reduces the model's over-reliance on specific features and enhances the model's generalization ability. Subsequently, the second feature extraction layer performs feature compression, extracting more representative key features from redundant temporal features. Then, the attention layer weights the features, enabling the model to adaptively focus on feature dimensions that are more important to the analysis of the current base station. Finally, the weighted feature vectors are input into the scenario classification layer and the service analysis layer respectively to complete the operation scenario analysis and service analysis, thereby improving the accuracy and reliability of the analysis results.

[0045] Step S105: Based on the target scenario type and business analysis data, determine at least one set of candidate adjustment information.

[0046] In one specific embodiment, candidate adjustment information represents the candidate parameters to be adjusted for the current base station and the corresponding candidate parameter values. The candidate parameters to be adjusted are the configuration parameters that the current base station can adjust, and the candidate parameter values ​​are the specific values ​​corresponding to the candidate parameters. For example, the candidate parameters to be adjusted may include at least one of transmit power parameters, antenna parameters, resource scheduling parameters, handover parameters, and load balancing parameters.

[0047] The transmit power parameter is used to control the signal transmission strength of the current base station. For example, the transmit power parameter may include the reference signal power, the maximum transmit power, etc.

[0048] Antenna parameters are used to control the antenna radiation characteristics of the current base station. For example, antenna parameters may include antenna tilt angle, azimuth angle, beamwidth, etc.

[0049] Resource scheduling parameters are used to control the current base station's wireless resource allocation strategy. For example, resource scheduling parameters may include bandwidth allocation ratio, uplink and downlink time slot ratio, etc.

[0050] Handover parameters are used to control the handover behavior of user equipment between the current base station and neighboring base stations. For example, handover parameters may include handover threshold, handover hysteresis value, etc.

[0051] Load balancing parameters are used to control the service load distribution strategy of the current base station. For example, load balancing parameters may include load balancing thresholds, user access control parameters, etc.

[0052] If at least one set of candidate adjustment information is two sets of candidate adjustment information, then the first set of candidate adjustment information can characterize the candidate parameters to be adjusted, including cell transmit power and antenna electronic downtilt angle, wherein the candidate parameter value corresponding to cell transmit power is 46dBm and the candidate parameter value corresponding to antenna electronic downtilt angle is 6°.

[0053] The second set of candidate adjustment information can characterize the candidate parameters to be adjusted, including cell transmit power and antenna electronic downtilt angle. The candidate parameter value corresponding to cell transmit power is 43dBm, and the candidate parameter value corresponding to antenna electronic downtilt angle is 3°.

[0054] In a specific embodiment, such as Figure 3 As shown, based on the target scenario type and business analysis data, at least one set of candidate adjustment information is identified, including: Step S301: Based on the target scene type and the preset mapping relationship, determine the candidate parameters to be adjusted.

[0055] In a specific embodiment, the preset mapping relationship represents the preset parameters to be adjusted corresponding to various preset operating scenario types.

[0056] Step S303: Based on business analysis data, determine the parameter value range corresponding to each candidate parameter to be adjusted.

[0057] In a specific embodiment, determining the parameter value range corresponding to each candidate parameter to be adjusted based on service analysis data may include: determining the adjustment direction of each candidate parameter to be adjusted according to the deviation direction between the service analysis volume in the service analysis data and the current service volume of the current base station; then, based on the adjustment direction and combined with the proportion of each service type reflected by the service type distribution ratio in the service analysis data, determining the adjustment range of the candidate parameter to be adjusted; finally, based on the current value of each candidate parameter to be adjusted, determining the upper limit and lower limit of the value corresponding to each candidate parameter to be adjusted according to the adjustment direction and adjustment range, and determining the value interval formed by the upper limit and lower limit as the parameter value range corresponding to the candidate parameter to be adjusted.

[0058] If the volume of business analysis is higher than the current volume, it indicates a future growth trend in business. In this case, the candidate parameters to be adjusted need to be adjusted in the direction of capacity expansion or enhancement. This applies when the candidate parameters to be adjusted include cell transmit power, resource block allocation ratio, antenna electronic downtilt angle, and maximum number of users accessing the network. The cell transmit power is adjusted to increase in order to expand coverage or improve signal strength; the resource block allocation ratio is adjusted to increase the spectrum resources available for user scheduling; the antenna electronic downtilt angle is adjusted to decrease in order to extend coverage distance or enhance signal strength at distant points; and the maximum number of users accessing the network is adjusted to increase in order to allow more users to access the network simultaneously.

[0059] Conversely, when the service analysis volume in the service analysis data is less than the current service volume of the current base station, i.e. the deviation direction is a decrease in service volume, the adjustment direction of each candidate parameter to be adjusted is opposite to the above.

[0060] Furthermore, once the adjustment direction is determined, if high-traffic services (such as video services) account for a relatively high proportion of the business type distribution, then even if the business analysis volume is slightly higher than the current business volume, a significant expansion adjustment is needed to ensure user experience; if low-speed services (such as IoT services) dominate the business type distribution, then even if the business analysis volume is significantly higher than the current business volume, only a small adjustment is needed to meet the demand.

[0061] For example, taking candidate parameters to be adjusted, including cell transmit power and maximum number of users, as an example, assuming the current traffic volume of the base station is 100Mbps, and the traffic analysis volume in the traffic analysis data is 150Mbps, the traffic analysis volume is higher than the current traffic volume, indicating a future growth trend in traffic. In this case, the adjustment direction for both cell transmit power and maximum number of users is to increase. The traffic type distribution ratio in the traffic analysis data shows that video traffic accounts for 60%, web browsing accounts for 30%, and IoT traffic accounts for 10%, indicating a high proportion of high-bandwidth traffic. Therefore, the adjustment range for cell transmit power is determined to be 20%, and the adjustment range for maximum number of users is determined to be 15%. In the current operating information of the base station, the current value of cell transmit power is 40dBm, and the current value of maximum number of users is 200. Based on the direction of increase and their respective adjustment ranges, the upper limit of the cell transmission power is 40×(1+20%)=48dBm, the lower limit is 40dBm, and the parameter value range is [40dBm, 48dBm]; the upper limit of the maximum number of users accessing the network is 200×(1+15%)=230, the lower limit is 200, and the parameter value range is [200,230].

[0062] For example, taking candidate parameters to be adjusted, including cell transmit power and antenna electronic downtilt angle, as an example, assuming the current traffic volume of the base station is 120Mbps and the traffic analysis volume in the traffic analysis data is 80Mbps, the traffic analysis volume is lower than the current traffic volume, indicating that the future traffic is decreasing. In this case, the adjustment direction of the cell transmit power is to decrease, and the adjustment direction of the antenna electronic downtilt angle is to increase (increasing the downtilt angle to reduce coverage and interference). The traffic type distribution ratio in the traffic analysis data shows that IoT traffic accounts for 70%, web browsing accounts for 20%, and video traffic accounts for 10%, with low-speed traffic accounting for a relatively high proportion. Therefore, the adjustment range of the cell transmit power is determined to be 15% (decrease), and the adjustment range of the antenna electronic downtilt angle is determined to be 10% (increase). In the current operating information of the base station, the current value of the cell transmit power is 44dBm, and the current value of the antenna electronic downtilt angle is 6 degrees. According to their respective adjustment directions and adjustment ranges, the upper limit of the cell transmission power is 44dBm, the lower limit is 44×(1-15%)=37.4dBm, and the parameter value range is [37.4dBm, 44dBm]; the upper limit of the antenna electronic downtilt angle is 6×(1+10%)=6.6 degrees, the lower limit is 6 degrees, and the parameter value range is [6 degrees, 6.6 degrees].

[0063] Step S305: Generate multiple candidate parameter values ​​within the range of parameter values ​​corresponding to each candidate parameter to be adjusted, so as to obtain at least one set of candidate adjustment information.

[0064] In a specific embodiment, generating multiple candidate parameter values ​​within the corresponding parameter value range of each candidate parameter to be adjusted to obtain at least one set of candidate adjustment information may include: for each candidate parameter to be adjusted, uniform or random sampling is performed within its corresponding parameter value range according to a preset sampling step size or sampling quantity to generate multiple candidate parameter values ​​for that parameter; then, the candidate parameter values ​​of all candidate parameters to be adjusted are cross-combined to form multiple candidate parameter combinations, each candidate parameter combination containing one candidate parameter value for each candidate parameter to be adjusted.

[0065] In the above embodiments, by determining candidate parameters to be adjusted based on the target scenario type and a preset mapping relationship, the parameters that need to be adjusted can be accurately matched for different operating scenarios, improving the targeting of parameter selection. On this basis, by determining the parameter value range corresponding to each candidate parameter to be adjusted based on service analysis data, the adjustment range of each parameter can be reasonably constrained in combination with the actual service requirements of the current base station, avoiding parameter values ​​from deviating from actual service requirements. Furthermore, by generating multiple candidate parameter values ​​within the parameter value range to obtain at least one set of candidate adjustment information, sufficient candidate schemes can be provided for subsequent interference analysis, thereby improving the reliability of the finally determined target adjustment information.

[0066] Step S107: Based on the preset correlation, basic regulation information is selected from at least one set of candidate regulation information.

[0067] In one specific embodiment, the preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each associated base station. The influence weight represents the degree to which the operating state of the current base station affects the operating state of the corresponding associated base station. The preset association relationship can be stored in the form of a matrix or graph structure, where rows and columns represent base station nodes, and the weight values ​​of matrix elements or edges are the corresponding influence weights.

[0068] For example, the preset association relationship can be constructed in two ways: one is based on the geographical topology of the base station, identifying the current base station and its physically adjacent base stations as associated base stations. Assuming the current base station is base station X, and there are three adjacent base stations around base station X: base station A, base station B, and base station C, where base station A has the largest overlap area with base station X and is the closest, base station B has a medium overlap area with base station X and is a medium distance away, and base station C has the smallest overlap area with base station X and is the farthest away. In this preset association relationship, the associated base stations include base station A, base station B, and base station C, with base station X having the largest influence weight on base station A (e.g., 0.6), a medium influence weight on base station B (e.g., 0.3), and the smallest influence weight on base station C (e.g., 0.1). This preset association relationship indicates that when base station X adjusts its operating parameters (e.g., increases its transmission power), it has the greatest impact on the operating state of base station A, followed by base station B, and the least impact on base station C.

[0069] Second, based on historical operational data, the changes in operational status indicators (such as interference level, number of handover requests, user throughput, etc.) of associated base stations before and after the current base station parameter adjustment are statistically analyzed to quantify the impact weight of the current base station on each associated base station. For example, if adjusting the parameters of the current base station significantly increases co-channel interference and handover requests of associated base stations, the impact weight of the current base station on that associated base station can be set to a higher value (e.g., 0.8); conversely, if adjusting the parameters of the current base station has almost no impact on the operational status indicators of a certain associated base station, the impact weight can be set to a lower value (e.g., 0.1).

[0070] In a specific embodiment, such as Figure 4 As shown, the basic regulatory information selected from at least one set of candidate regulatory information based on preset correlations includes: Step S401: Obtain the associated operation information corresponding to at least one associated base station.

[0071] In a specific embodiment, the detailed information related to the operation can be found in the current operation information above, and will not be repeated here.

[0072] Step S403: For each group of candidate adjustment information, an impact degree analysis is performed based on the preset correlation relationship and the associated operation information to obtain the impact degree analysis results corresponding to each group of candidate adjustment information.

[0073] In one specific embodiment, the impact degree analysis result characterizes the degree of impact that the current base station has on the operating status of at least one associated base station after applying the corresponding candidate adjustment information.

[0074] In a specific embodiment, the above-mentioned impact degree analysis of each group of candidate adjustment information based on preset correlation relationships and associated operation information to obtain the impact degree analysis result corresponding to each group of candidate adjustment information may include: for each group of candidate adjustment information, firstly, based on the candidate parameters to be adjusted and their values ​​in the group of candidate adjustment information, combined with the current operation information of the current base station, simulating the expected change in the operating state of the current base station after applying the group of candidate adjustment information; then, based on preset correlation relationships, mapping the expected change in the operating state of the current base station to each associated base station, and combined with the associated operation information of each associated base station, calculating the impact degree of the current base station on the operating state of each associated base station after applying the group of candidate adjustment information; finally, integrating the impact degrees of all associated base stations according to a preset aggregation method (such as weighted summation or taking the maximum value) to obtain the impact degree analysis result corresponding to the group of candidate adjustment information.

[0075] For example, suppose the current base station is base station X, and the three associated base stations recorded in the preset association relationship are base station A (influence weight 0.6), base station B (influence weight 0.3), and base station C (influence weight 0.1). There is currently a candidate adjustment setting: adjust the cell transmit power of base station X from the current value of 42dBm to 46dBm.

[0076] First, based on the candidate adjustment information (transmit power increased to 46dBm) and the current operating information of base station X, the expected changes in the operating status of base station X after the application of this adjustment are simulated and predicted: the coverage radius is expected to expand outward by about 200 meters, and the downlink reference signal received power RSRP is expected to increase by about 4dB at the coverage edge.

[0077] Next, based on the influence weights in the preset association relationships, the aforementioned expected changes in operating status are mapped to each associated base station: For base station A (weight 0.6), its associated operational information shows that the current uplink interference level is -105dBm, and its coverage area overlaps with that of base station X to the largest extent. Based on the signal enhancement in the overlapping area after the coverage expansion of base station X, it is calculated that the expected interference level of base station A will increase by approximately 8dB, and the number of handover requests is expected to increase by 15%.

[0078] For base station B (weight 0.3), its associated operational information shows a current load of 65%, and its coverage area partially overlaps with that of base station X. Calculations indicate that the expected interference level for base station B will increase by approximately 4 dB, and the number of handover requests is expected to increase by 8%.

[0079] For base station C (weight 0.1), its associated operational information shows that it is currently in a low-traffic period, and its coverage area overlaps with that of base station X to a minimum. Calculations indicate that the expected interference level for base station C will increase by approximately 1 dB, and the number of handover requests is expected to increase by 2%.

[0080] Finally, the expected impact levels of the three associated base stations are integrated using a weighted summation: Impact level analysis result = 0.6 * (interference increase of 8dB + handover increase of 15%) + 0.3 * (interference increase of 4dB + handover increase of 8%) + 0.1 * (interference increase of 1dB + handover increase of 2%). The resulting impact level analysis result for this group of candidate regulation information is a comprehensive score, which is used for subsequent comparison and screening with other candidate regulation information.

[0081] Step S405: Based on the results of the influence degree analysis, determine the basic regulation information from at least one set of candidate regulation information.

[0082] In a specific embodiment, determining the basic adjustment information from at least one set of candidate adjustment information based on the impact degree analysis results may include: selecting the candidate adjustment information corresponding to the impact degree analysis result that has the smallest impact on the operating status of at least one associated base station after the current base station applies the corresponding candidate adjustment information as the basic adjustment information.

[0083] In the above embodiments, the impact degree analysis of each group of candidate adjustment information can comprehensively assess the impact of the current base station applying different candidate adjustment information on the operating status of each associated base station. Thus, when screening basic adjustment information, not only the service needs of the current base station itself are considered, but also the impact on surrounding associated base stations are taken into account. The final basic adjustment information can meet the adjustment needs of the current base station while reducing the interference on the operating status of associated base stations, thereby improving the coordination and overall operational stability of each base station in the entire network system.

[0084] Step S109: Control the current base station based on the basic adjustment information.

[0085] In a specific embodiment, such as Figure 5 As shown, the above method also includes: Step S501: Based on business analysis data and current operating information, perform revenue analysis on the basic adjustment information and determine the target adjustment information from the basic adjustment information.

[0086] In a specific embodiment, such as Figure 6 As shown, the above-mentioned revenue analysis of basic adjustment information based on business analysis data and current operational information, and the determination of target adjustment information from the basic adjustment information, include: Step S601: Based on business analysis data and current operating information, determine the performance improvement value corresponding to each set of basic adjustment information.

[0087] In one specific embodiment, the performance improvement value represents the degree of performance improvement of the current base station on various performance indicators after applying the corresponding basic adjustment information. For example, performance indicators may include at least one of the following: throughput, latency, access success rate, handover success rate, dropped call rate, coverage, signal-to-noise ratio, and bit error rate.

[0088] In a specific embodiment, determining the performance improvement value corresponding to each set of basic adjustment information based on business analysis data and current operating information may include: for each set of basic adjustment information, using business analysis data as input scenario parameters for the simulation model corresponding to the current base station; then, substituting the candidate parameters to be adjusted and their candidate parameter values ​​in the set of basic adjustment information into the simulation model to simulate the predicted values ​​of the current base station on each performance indicator after applying the set of basic adjustment information; next, comparing the current value and predicted value of each performance indicator in the current operating information to calculate the improvement magnitude of each performance indicator (such as the percentage increase in throughput, the absolute value of the reduction in latency, the percentage increase in access success rate, etc., and taking the inverse change amount for negative indicators); finally, weighting and summing the improvement magnitudes of each performance indicator according to the preset weights corresponding to each performance indicator to obtain the performance improvement value corresponding to the set of basic adjustment information.

[0089] Step S603: Based on the current operating information, determine the resource saving value corresponding to each group of basic adjustment information.

[0090] In one specific embodiment, the resource saving value represents the degree of resource saving of the current base station on various resource indicators after applying the corresponding basic adjustment information. For example, each resource indicator may include at least one of time-frequency resources, power resources, channel resources, and bandwidth resources.

[0091] In a specific embodiment, determining the resource saving value corresponding to each set of basic adjustment information based on the current operating information may include: for each set of basic adjustment information, firstly, applying the candidate parameters to be adjusted and their candidate parameter values ​​in the set of basic adjustment information to the simulation model corresponding to the current base station, simulating the predicted occupancy value of the current base station on each resource indicator after applying the set of basic adjustment information; then, comparing the current occupancy value and the predicted occupancy value of each resource indicator in the current operating information, and calculating the saving range of each resource indicator; finally, weighting and summing the saving ranges of each resource indicator according to the preset weights corresponding to each resource indicator to obtain the resource saving value corresponding to the set of basic adjustment information.

[0092] Step S605: The performance improvement value and the resource saving value are weighted and summed to obtain the comprehensive benefit value of each set of basic adjustment information.

[0093] In a specific embodiment, the above-mentioned weighted summation of performance improvement value and resource saving value to obtain the comprehensive benefit value of each group of basic adjustment information may include: weighted summation of performance improvement value and resource saving value based on the first preset weight corresponding to the performance improvement value and the second preset weight corresponding to the resource saving value to obtain the comprehensive benefit value of each group of basic adjustment information.

[0094] Step S607: Based on the comprehensive return value, determine the target adjustment information from the basic adjustment information.

[0095] In one specific embodiment, determining the target adjustment information from the basic adjustment information based on the comprehensive return value may include: using the basic adjustment information corresponding to the highest comprehensive return value as the target adjustment information.

[0096] In the above embodiments, by analyzing the performance improvement value and resource saving value corresponding to each set of basic adjustment information, and then weighting and summing the two to obtain the comprehensive benefit value, the target adjustment information is determined based on the comprehensive benefit value. This can take into account both service performance improvement and resource saving when determining the target adjustment information. It not only achieves effective improvement in service performance, but also avoids resource waste caused by simply pursuing performance improvement, thereby improving the comprehensive benefits of base station parameter adjustment.

[0097] In one specific embodiment, controlling the current base station based on basic adjustment information includes: Step S503: Control the current base station based on the target adjustment information.

[0098] In a specific embodiment, controlling the current base station based on the target adjustment information may include: parsing the target adjustment information into a configuration instruction executable by the current base station, and sending the configuration instruction to the parameter management module of the current base station; the parameter management module updating the corresponding candidate parameter to be adjusted in the current base station from its current value to the target parameter value according to the configuration instruction.

[0099] In the above embodiments, after selecting basic adjustment information that takes into account the impact of associated base stations from at least one set of candidate adjustment information, further performing benefit analysis on the basic adjustment information based on service analysis data and current operation information, it is possible to further select target adjustment information that has the best benefit for improving the current base station's own services from the basic adjustment information while ensuring that the impact on associated base stations is controllable. Based on the target adjustment information, the current base station is controlled, so that the parameter adjustment of the current base station not only takes into account the coordination with associated base stations, but also achieves the optimization of its own service improvement effect, thereby improving the accuracy of base station parameter adjustment and overall network performance.

[0100] Figure 7 This is a block diagram of a base station control device according to an exemplary embodiment. (Refer to...) Figure 7 The device includes: The current operation information acquisition module 710 is used to acquire the current operation information of the current base station; The information analysis module 720 is used to perform operational scenario analysis and service analysis on the current base station based on the current operational information, and to obtain the target scenario type and service analysis data of the current base station's corresponding operational scenario within a preset time period; The candidate adjustment information determination module 730 is used to determine at least one set of candidate adjustment information based on the target scenario type and service analysis data. The candidate adjustment information represents the candidate parameters to be adjusted of the current base station and the candidate parameter values ​​corresponding to the candidate parameters to be adjusted. The basic adjustment information determination module 740 is used to select basic adjustment information from at least one set of candidate adjustment information based on a preset association relationship. The preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each associated base station. The influence weight represents the degree to which the operating status of the current base station affects the operating status of the corresponding associated base station. The base station control module 750 is used to control the current base station based on basic adjustment information.

[0101] In an optional embodiment, the basic adjustment information determination module 740 includes: The associated operation information acquisition unit is used to acquire the associated operation information corresponding to at least one associated base station. The impact degree analysis result determination unit is used to perform impact degree analysis on each group of candidate adjustment information based on preset correlation and related operation information, and obtain the impact degree analysis result corresponding to each group of candidate adjustment information. The impact degree analysis result characterizes the degree of impact on the operation status of at least one related base station after the current base station applies the corresponding candidate adjustment information. The basic adjustment information determination unit is used to determine basic adjustment information from at least one set of candidate adjustment information based on the results of the influence degree analysis.

[0102] In an optional embodiment, the above-described apparatus further includes: The target adjustment information determination module is used to perform revenue analysis on the basic adjustment information based on business analysis data and current operating information, and to determine the target adjustment information from the basic adjustment information; In an optional embodiment, the base station control module 750 includes: The base station control unit is used to control the current base station based on target adjustment information.

[0103] In an optional embodiment, the target adjustment information determination module includes: The performance improvement value determination unit is used to determine the performance improvement value corresponding to each set of basic adjustment information based on service analysis data and current operation information; the performance improvement value represents the degree of performance improvement of the current base station on each performance indicator after applying the corresponding basic adjustment information; The resource saving value determination unit is used to determine the resource saving value corresponding to each set of basic adjustment information based on the current operating information; the resource saving value represents the degree of resource saving of the current base station in each resource indicator after applying the corresponding basic adjustment information; The comprehensive benefit value determination unit is used to weighted summation of performance improvement value and resource saving value to obtain the comprehensive benefit value of each set of basic adjustment information; The target adjustment information determination unit is used to determine the target adjustment information from the basic adjustment information based on the comprehensive return value.

[0104] In an optional embodiment, the candidate adjustment information determination module 730 includes: The candidate parameter determination unit is used to determine candidate parameters to be adjusted based on the target scene type and the preset mapping relationship. The preset mapping relationship represents the preset parameters to be adjusted corresponding to various preset running scene types. The parameter value range determination unit is used to determine the parameter value range corresponding to each candidate parameter to be adjusted based on business analysis data. The candidate adjustment information determination unit is used to generate multiple candidate parameter values ​​within the parameter value range corresponding to each candidate parameter to be adjusted, so as to obtain at least one set of candidate adjustment information.

[0105] In an optional embodiment, the information analysis module 720 includes: The information analysis unit is used to input the current operating information into the preset base station analysis model, perform operating scenario analysis and service analysis on the current base station, and obtain target scenario type and service analysis data.

[0106] In an optional embodiment, the preset base station analysis model includes a first feature extraction layer, a discard layer, a second feature extraction layer, an attention layer, a scene classification layer, and a service analysis layer. The aforementioned information analysis unit includes: The first vector determination subunit is used to input the current running information into the first feature extraction layer for temporal feature extraction to obtain the first vector; The second vector determination subunit is used to input the first vector into the drop-out layer for random drop-out processing to obtain the second vector; The third vector determination subunit is used to input the second vector into the second feature extraction layer for feature compression to obtain the third vector; The weighted feature vector determination subunit is used to input the second and third vectors into the attention layer for feature weighting to obtain the weighted feature vector. The scenario type determination subunit is used to input the weighted feature vector into the scenario classification layer to perform operational scenario analysis on the current base station and obtain the target scenario type. The data analysis determines the sub-unit, which is used to input the weighted feature vector into the service analysis layer to perform service analysis on the current base station and obtain service analysis data.

[0107] Figure 8 This is a block diagram illustrating an electronic device for base station control according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the electronic device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a base station control method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0108] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the electronic device to which the present disclosure is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0109] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the base station control method as described in the embodiments of this disclosure.

[0110] In an exemplary embodiment, a computer-readable storage medium is also provided, wherein when the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the base station control method of the present disclosure embodiments.

[0111] In an exemplary embodiment, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform the base station control method of the present disclosure embodiments.

[0112] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0113] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0114] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A base station control method, characterized in that, The method includes: Obtain the current operating information of the current base station; Based on the current operating information, the current base station is subjected to operating scenario analysis and service analysis to obtain the target scenario type and service analysis data of the current base station corresponding to the operating scenario within a preset time period; Based on the target scenario type and the service analysis data, at least one set of candidate adjustment information is determined. The candidate adjustment information represents the candidate parameters to be adjusted of the current base station and the candidate parameter values ​​corresponding to the candidate parameters to be adjusted. Based on a preset association relationship, basic adjustment information is selected from at least one set of candidate adjustment information. The preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each of the associated base stations. The influence weight represents the degree to which the operating status of the current base station affects the operating status of the corresponding associated base station. Based on the aforementioned basic adjustment information, the current base station is controlled.

2. The method according to claim 1, characterized in that, The step of filtering basic adjustment information from at least one set of candidate adjustment information based on a preset association relationship includes: Obtain the associated operational information corresponding to at least one of the associated base stations; For each group of candidate adjustment information, an impact degree analysis is performed based on the preset correlation relationship and the associated operation information to obtain the impact degree analysis result corresponding to each group of candidate adjustment information. The impact degree analysis result characterizes the degree of impact that the current base station has on the operation status of at least one of the associated base stations after applying the corresponding candidate adjustment information. Based on the results of the influence analysis, the basic regulation information is determined from at least one set of candidate regulation information.

3. The method according to claim 1, characterized in that, The method further includes: Based on the business analysis data and the current operating information, a revenue analysis is performed on the basic adjustment information to determine the target adjustment information from the basic adjustment information; The control of the current base station based on the basic adjustment information includes: Based on the target adjustment information, the current base station is controlled.

4. The method according to claim 3, characterized in that, The step of performing revenue analysis on the basic adjustment information based on the business analysis data and the current operating information, and determining the target adjustment information from the basic adjustment information, includes: Based on the business analysis data and the current operating information, a performance improvement value corresponding to each group of basic adjustment information is determined; the performance improvement value represents the degree of performance improvement of the current base station on each performance indicator after applying the corresponding basic adjustment information. Based on the current operating information, a resource saving value is determined for each group of basic adjustment information; the resource saving value represents the degree of resource saving of the current base station in each resource indicator after applying the corresponding basic adjustment information. The performance improvement value and the resource saving value are weighted and summed to obtain the comprehensive benefit value of each group of basic adjustment information; Based on the comprehensive benefit value, the target adjustment information is determined from the basic adjustment information.

5. The method according to claim 1, characterized in that, The determination of at least one set of candidate adjustment information based on the target scenario type and the business analysis data includes: Based on the target scenario type and the preset mapping relationship, candidate parameters to be adjusted are determined. The preset mapping relationship represents the preset parameters to be adjusted corresponding to each of the various preset running scenario types. Based on the business analysis data, determine the parameter value range corresponding to each of the candidate parameters to be adjusted; Multiple candidate parameter values ​​are generated within the parameter value range corresponding to each candidate parameter to be adjusted, so as to obtain at least one set of candidate adjustment information.

6. The method according to claim 1, characterized in that, The step of performing operational scenario analysis and service analysis on the current base station based on the current operational information to obtain the target scenario type and service analysis data of the current base station's corresponding operational scenario within a preset time period includes: The current operating information is input into a preset base station analysis model to perform operating scenario analysis and service analysis on the current base station, thereby obtaining the target scenario type and the service analysis data.

7. The method according to claim 6, characterized in that, The preset base station analysis model includes a first feature extraction layer, a discard layer, a second feature extraction layer, an attention layer, a scene classification layer, and the service analysis layer. The step of inputting the current operating information into the preset base station analysis model to perform operating scene analysis and service analysis on the current base station, and obtaining the target scene type and the service analysis data, includes: The current running information is input into the first feature extraction layer for temporal feature extraction to obtain a first vector; The first vector is input into the discarding layer for random discarding to obtain the second vector; The second vector is input into the second feature extraction layer for feature compression to obtain the third vector; The second vector and the third vector are input into the attention layer for feature weighting to obtain a weighted feature vector. The weighted feature vector is input into the scene classification layer to perform operational scene analysis on the current base station and obtain the target scene type. The weighted feature vector is input into the service analysis layer to perform service analysis on the current base station and obtain the service analysis data.

8. A base station control device, characterized in that, include: The current operation information acquisition module is used to acquire the current operation information of the current base station; The information analysis module is used to perform operational scenario analysis and service analysis on the current base station based on the current operational information, and to obtain the target scenario type and service analysis data of the current base station corresponding to the operational scenario within a preset time period. The candidate adjustment information determination module is used to determine at least one set of candidate adjustment information based on the target scenario type and the service analysis data. The candidate adjustment information represents the candidate parameters to be adjusted of the current base station and the candidate parameter values ​​corresponding to the candidate parameters to be adjusted. The basic adjustment information determination module is used to filter basic adjustment information from at least one set of candidate adjustment information based on a preset association relationship. The preset association relationship represents at least one associated base station corresponding to the current base station and the influence weight between the current base station and each of the associated base stations. The influence weight represents the degree to which the operating status of the current base station affects the operating status of the corresponding associated base station. The base station control module is used to control the current base station based on the basic adjustment information.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the base station control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the base station control method as described in any one of claims 1 to 7.