Method and device for adjusting high-load sector and electronic equipment

Abstract

The invention discloses a method and a device for adjusting a high-load sector and electronic equipment. The method comprises the following steps: determining a target high-load sector in a target operator network; the scene type of the target high-load sector is determined at least based on a high-load sector wide table, and the high-load sector wide table is used for quantifying the network performance of the target operator; an adjustment strategy corresponding to the scene type of the target high-load sector is determined according to the knowledge graph, and the adjustment strategy is used for adjusting network parameters of the target high-load sector; and adjusting the network parameters of the target high-load sector by adopting an adjustment strategy. The technical problem that the utilization efficiency of network resources is low due to the fact that the adjustment means of the high-load sector depends on manual intervention, the response speed is low, and the requirements of different high-load scenes cannot be effectively met is solved.

Description

Technical Field

[0001] The present application relates to the field of wireless communications, and in particular to a method, device, and electronic device for adjusting a high-load sector. Background Art

[0002] With the rapid development of mobile communications technology, the number of 4G or 5G network users and service traffic has exploded, and the problem of high sector load in hotspot areas has become increasingly prominent. High load not only leads to degraded network performance, such as network congestion, reduced user access success rates, and deteriorating service quality, but can also trigger large-scale user complaints, seriously impacting network operators' service quality and user satisfaction. Related technologies for optimizing high-load sectors rely on regular manual inspections or passive responses to user complaints. They lack a regular, data-driven intelligent management and control process, resulting in slow response times and insufficient real-time network monitoring capabilities. Manual responses cannot keep up with service demands. Parameter adjustments and network configuration changes require manual operations, making it difficult to quickly alleviate network congestion, impacting user service experience, and failing to effectively address the needs of diverse high-load scenarios, resulting in inefficient network resource utilization.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a method, device and electronic device for adjusting high-load sectors, so as to at least solve the technical problem that the adjustment means of high-load sectors rely on manual intervention, have slow response speed, and cannot effectively meet the needs of different high-load scenarios, resulting in low efficiency of network resource utilization.

[0005] According to one aspect of an embodiment of the present application, a method for adjusting a high-load sector is provided, including: determining a target high-load sector within a target operator network; determining a scenario type of the target high-load sector based at least on a high-load sector wide table, wherein the high-load sector wide table is used to quantify the network performance of the target operator; determining an adjustment strategy corresponding to the scenario type of the target high-load sector based on a knowledge graph, wherein the adjustment strategy is used to adjust network parameters of the target high-load sector; and adjusting the network parameters of the target high-load sector using the adjustment strategy.

[0006] According to some embodiments of the present application, a high-load sector-wide table is constructed in the following manner, including: collecting network performance data of the target operator network at every preset collection period, wherein the network performance data includes at least the utilization rate of physical resource blocks, the number of wireless resource control connections, and network traffic data; and constructing a high-load sector-wide table based on the network performance data of all preset collection periods.

[0007] According to some embodiments of the present application, the scenario type of the target high-load sector is determined at least based on the high-load sector wide table, including: determining the sector that meets the preset high load requirements in the high-load sector wide table as the target high-load sector, wherein the preset high load requirements are that the utilization rate of the physical resource block is greater than or equal to the first preset threshold, the traffic load ratio is greater than or equal to the second preset threshold, and the average number of wireless resource control connections is greater than or equal to the third preset threshold; determining the scenario type of the target high-load sector whose high load duration meets the first time period indicated by the preset scenario division rule as the first scenario type; determining the scenario type of the target high-load sector that meets the sudden high load requirement indicated by the preset scenario division rule as the second scenario type, wherein the sudden high load requirement is that the sector load is greater than the fourth preset threshold in the second time period, the first time period is greater than the second time period, and the sector load is at least one of the following: the utilization rate of the physical resource block, the traffic load ratio, and the number of wireless resource control connections; determining the scenario type of the target high-load sector in the target operator network corresponding to the preset date in the future preset time period corresponding to the target timestamp as the third scenario type, wherein the preset date at least includes holidays.

[0008] According to some embodiments of the present application, an adjustment strategy corresponding to the scenario type of the target high-load sector is determined based on the knowledge graph, including: for the target high-load sector of the first scenario type, the adjustment strategy is determined based on the knowledge graph to use a load balancing strategy to adjust the network parameters of the target high-load sector, wherein the first scenario type is a long-term high-load scenario; for the target high-load sector of the second scenario type, the adjustment strategy is determined based on the knowledge graph to use a real-time alarm method to adjust the network parameters of the target high-load sector, wherein the second scenario type is a sudden high-load scenario; for the target high-load sector of the third scenario type, the adjustment strategy is determined based on the knowledge graph to use a pre-expansion method to adjust the network parameters of the target high-load sector, wherein the third scenario type is a foreseeable high-load scenario, the long-term high-load scenario corresponds to the target high-load sector with continuous high load, the sudden high-load scenario corresponds to the target high-load sector with instantaneous load changes resulting in high load, and the foreseeable high-load scenario corresponds to the target high-load sector with predicted high load.

[0009] According to some embodiments of the present application, a load balancing strategy is adopted to adjust the network parameters of the target high-load sector, including: collecting user complaint data, industrial parameter data, co-construction and sharing data and diversion ratio data at preset collection periods, wherein the industrial parameter data at least includes base station location and antenna parameters, the co-construction and sharing data is used to indicate the cooperation information between the operator corresponding to the high-load sector and other operators, and the diversion ratio data is used to reflect the load distribution of different frequency bands; constructing a resource scheduling table based on user complaint data, industrial parameter data, co-construction and sharing data and diversion ratio data, wherein the resource scheduling table is used to indicate a list of resources available for scheduling; determining the load balancing strategy corresponding to the target high-load sector based on the resource scheduling table, wherein the load balancing strategy includes an adjustment method for the network parameters of the high-load sector; adjusting the network parameters of the target high-load sector based on the load balancing strategy.

[0010] According to some embodiments of the present application, the network parameters of the target high-load sector are adjusted in a real-time alarm manner, including: generating alarm information, wherein the alarm information at least includes the network performance data of the target high-load sector and network parameter adjustment suggestions; pushing the alarm information to the client of the operation and maintenance personnel, and adjusting the network parameters of the target high-load sector according to the response instructions of the client.

[0011] According to some embodiments of the present application, the network parameters of the target high-load sector are adjusted in a pre-expansion manner, including: predicting the network performance data of the target high-load sector of the third scenario type on a preset date to obtain predicted network performance data; determining an expansion strategy based on the predicted network performance data, and adjusting the network parameters of the target high-load sector based on the expansion strategy.

[0012] According to some embodiments of the present application, the knowledge graph is constructed in the following manner: after the network parameters of each target high-load sector are adjusted, the adjustment results corresponding to the target high-load sector are updated to the preset fields of the high-load sector wide table; the knowledge graph is constructed at least based on the high-load sector wide table, wherein the adjustment results include at least solutions and abnormal causes, wherein the abnormal causes are the reasons that cause the sector to become a high-load sector, and the knowledge graph is used to associate all target high-load sectors and the adjustment results of the target high-load sectors.

[0013] According to another aspect of an embodiment of the present application, a high-load sector adjustment device is also provided, including: a first determination module, used to determine a target high-load sector within a target operator network; a second determination module, used to determine the scenario type of the target high-load sector based at least on a high-load sector wide table, wherein the high-load sector wide table is used to quantify the network performance of the target operator; a third determination module, used to determine an adjustment strategy corresponding to the scenario type of the target high-load sector based on a knowledge graph, wherein the adjustment strategy is used to adjust the network parameters of the target high-load sector; and an adjustment module, used to adjust the network parameters of the target high-load sector using the adjustment strategy.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a program is stored. When the program is running, the device where the non-volatile storage medium is located is controlled to execute the above high-load sector adjustment method.

[0015] According to another aspect of an embodiment of the present application, an electronic device is provided, including: a memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the above high-load sector adjustment method is executed when the program is running.

[0016] According to another aspect of an embodiment of the present application, a computer program product is further provided, including computer instructions, which implement the above high-load sector adjustment method when executed by a processor.

[0017] In an embodiment of the present application, a target high-load sector within a target operator network is determined; the scenario type of the target high-load sector is determined at least based on a high-load sector wide table, wherein the high-load sector wide table is used to quantify the network performance of the target operator; an adjustment strategy corresponding to the scenario type of the target high-load sector is determined based on a knowledge graph, wherein the adjustment strategy is used to adjust the network parameters of the target high-load sector; the network parameters of the target high-load sector are adjusted using the adjustment strategy, and the adjustment strategy corresponding to the scenario type of the target high-load sector is determined through the knowledge graph, and then the network parameters of the target high-load sector are adjusted using the adjustment strategy for different types of target high-load sectors, thereby achieving targeted processing for the needs of different high-load scenarios without relying on manual intervention, thereby improving the response speed, and thereby solving the technical problem that the adjustment means of the high-load sector rely on manual intervention, have slow response speed, and cannot effectively meet the needs of different high-load scenarios, resulting in low efficiency in network resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing a method for adjusting a high-load sector according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a method for adjusting a high-load sector according to an embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of a knowledge graph provided according to an embodiment of the present application;

[0022] Figure 4 This is a structural diagram of an adjustment device for a high-load sector provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0024] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject the automated decision results; if the user chooses to reject, the expert decision-making process will be entered.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] In the related art, it relies on manual periodic inspections or passive responses to user complaints, lacks a set of normalized, data-driven intelligent management and control processes, has slow response speeds, insufficient real-time network monitoring capabilities, and manual response speeds cannot keep up with business needs. Parameter adjustments and changes to network configurations require manual operations, making it difficult to quickly alleviate network congestion, affecting user service experience, and unable to effectively respond to the needs of different high-load scenarios. Therefore, there is a technical problem that the means of adjusting high-load sectors relies on manual intervention, has slow response speeds, and cannot effectively respond to the needs of different high-load scenarios, resulting in inefficient network resource utilization. In order to solve this problem, relevant solutions are provided in the embodiments of the present application, which are described in detail below.

[0027] According to an embodiment of the present application, an embodiment of a method for adjusting a high-load sector is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal for implementing a method for adjusting a high-load sector. Figure 1 As shown, the computer terminal 10 may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the high-load sector adjustment method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned high-load sector adjustment method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0033] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for adjusting a high-load sector. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] like Figure 2FIG. 1 is a flow chart of a method for adjusting a high-load sector according to an embodiment of the present application, including:

[0035] Step S202: Determine a target high-load sector in a target operator network (for example, a 4G network or a 5G network of a target operator, where the target operator is an operator that needs to perform high-load sector adjustment).

[0036] Step S204: determining a scenario type of the target high-load sector based at least on a high-load sector width table, wherein the high-load sector width table is used to quantify the network performance of the target operator.

[0037] In the technical solution provided in step S204, the high-load sector-wide table is constructed in the following manner, including: collecting network performance data of the target operator network at every preset collection period, specifically collecting network performance data of each cell of the target operator network (a cell is the basic unit constituting a mobile communication network, responsible for providing wireless connection services to mobile devices within a specified geographical range), and constructing a high-load sector-wide table based on the network performance data of all preset collection periods, wherein the network performance data at least includes the utilization rate of the physical resource block (Physical Resource Block UtilizationRate, referred to as PRB) (including the PRB utilization rate in the uplink and downlink directions, reflecting the utilization of the frequency domain and time domain resources allocated to user data transmission in the cell, which is a key indicator for measuring the degree of cell resource tension), radio resource control (Radio Resource Control Connection Network performance data also includes key performance indicators (KPIs), such as the cell's access success rate, call drop rate, and handover success rate, which are important indicators of cell service quality. Measurement Report (MR) data contains information such as signal strength and quality between the base station and user terminals, which is crucial for RF optimization and coverage adjustment. Call Detail Record (CDR) data records detailed information about calls and data services, including start and end time, service type, duration, and data volume. It is valuable for analyzing user behavior and optimizing resource allocation. Deep Packet Inspection (DPI) data provides more detailed traffic information, such as application type, protocol, and traffic direction, which is crucial for refined network management and optimizing user experience.

[0038] When constructing a high-load sector-wide table based on network performance data from all pre-set collection cycles, first standardize all data from all pre-set collection cycles to ensure consistent format and dimensions for subsequent analysis. After data standardization, clean the data to remove invalid, duplicate, or anomalous data points, such as data from network failure times within the statistical period. Aggregate the data points within each collection cycle to calculate statistical information such as the average, maximum, and minimum values ​​for each data point within the period. Design a high-load sector-wide table structure (including but not limited to fields such as timestamp, cell ID, base station ID, PRB utilization, number of RRC connections, and uplink and downlink traffic). Store network performance indicators and statistical information such as the average, maximum, and minimum values ​​for each data point within each collection cycle in the high-load sector-wide table. The high-load sector-wide table is used to quantify the target operator's network performance and store aggregated network performance data. Network performance data collected during a new pre-set collection cycle will also be updated to the high-load sector-wide table according to the above steps.

[0039] As some examples of this application:

[0040] First, create a big data analytics sharing platform. This platform is the core of the entire data processing and analysis architecture. It integrates and manages various data sources and supports real-time analysis and sharing of large-scale data. The data analytics sharing platform consists of at least two independent yet collaborative data processing centers (i.e., analysis clusters, which refer to a group of computing servers or nodes used to process and analyze data. Each cluster is responsible for different types of data analysis tasks, or provides redundancy and load balancing under high load conditions to ensure continuous and efficient data processing).

[0041] The big data analysis sharing platform collects network performance data of the target operator's network (e.g., the target operator's 4G network or 5G network) at preset collection periods (e.g., 15 minutes). For example, for physical resource block utilization, data is collected at preset collection periods, and the average physical resource block utilization of each cell within the period is recorded. For the number of radio resource control (RRC) connections, data is collected at preset collection periods, and the maximum and average number of radio resource control connected users in each cell within the recording period are recorded. For network traffic data, data is collected at preset collection periods, and uplink and downlink traffic data are collected, including the total amount of data transmission in each cell, and the average value of user uplink and downlink traffic, to reflect the total load of the cell.

[0042] The big data analysis sharing platform supports multi-source data fusion (data fusion refers to the integration of data from different sources and formats into a unified framework or data model) and builds a cross-domain integrated big data foundation (cross-domain integration refers to transcending traditional business boundaries, interconnecting data from different fields, and establishing a unified data foundation). In this scenario, communication network data is integrated with business operation data (i.e., the business operation management and billing system management domain (Business Operation Management, referred to as the BOM domain)) to achieve more precise management and optimization of network resources. It can collect a variety of analytical data (such as MR, CDR, DPI, etc.) from various types of wireless base stations in real time. By integrating the BOM domain, it can obtain a variety of analytical data such as user behavior data and business demand data, which can be combined with network performance data to provide a more comprehensive basis for resource allocation. The big data analysis sharing platform applies streaming processing technology when processing and collecting all data (streaming processing technology refers to processing continuous, real-time data streams, rather than waiting for data collection to be completed before batch analysis). By applying streaming processing technology, network data can be processed in real time, and analysis and decisions can be made immediately. In particular, when processing real-time peak traffic of hundreds of GB, the latency is maintained at 4 minutes, which shows the real-time response capability and processing efficiency of the big data analysis sharing platform and the corresponding high-load sector self-optimization system based on wireless resource orchestration. The high-load sector self-optimization system based on wireless resource orchestration for executing the method of the present application includes a data collection module, a scenario classification module, a resource optimization module, and a prediction and learning module, wherein the data collection module is used to collect network performance data, user complaint data, work parameter data, co-construction and sharing data, and diversion ratio data of the target operator network at every preset collection period, and to construct a high-load sector wide table and a resource scheduling table. The scenario classification module is used to determine the scenario type of the target high-load sector based at least on the high-load sector wide table. The resource optimization module is used to determine, based on the knowledge graph, an adjustment strategy corresponding to the target high-load sector scenario type. The adjustment strategy is used to adjust the network parameters of the target high-load sector; the network parameters of the target high-load sector are adjusted using the adjustment strategy. The prediction and learning module is used to construct a knowledge graph and predict network performance data for the target high-load sector for the third scenario type on a preset date.

[0043] The sectors that meet the preset high load requirements in the high-load sector width table are determined as target high-load sectors, wherein the preset high load requirements are that the utilization rate of the physical resource block is greater than or equal to the first preset threshold, the traffic load ratio is greater than or equal to the second preset threshold, and the average number of radio resource control connections is greater than or equal to the third preset threshold. The traffic load ratio is a key indicator in a wireless communication network to measure the relationship between the actual data traffic carried by a cell and the theoretical maximum data processing capacity of the cell. It expresses the utilization rate or load level of the cell in processing data traffic and is crucial for network resource management and optimization. The traffic load ratio is the ratio of network traffic data to the theoretical maximum traffic of the cell (the maximum data processing capacity determined according to the cell configuration (such as frequency band, bandwidth, etc.)).

[0044] As some examples of this application:

[0045] The first, second and third preset thresholds are predefined, and the three are used to identify high load conditions of physical resource block utilization, traffic load ratio and number of radio resource control connections, respectively. The data in each preset collection period of the high-load sector wide table is scanned every preset monitoring time (for example, 10 minutes), and each sector is checked to see whether the three indicators of PRB utilization, traffic load ratio and number of RRC connections reach the corresponding thresholds respectively. If so, the sector that meets the preset high load requirements is determined as the target high-load sector. The preset high load requirements are indicated in the preset rules. For example, the preset rules are as follows: for 4G networks, the preset high load requirements of 4G high-load sectors are: PRB load (ie, PRB utilization) ≥ 70% (ie, the first preset threshold) and traffic load ratio ≥ 70% (ie, the second preset threshold) and the average number of RRC connected users ≥ (bandwidth / 20MHz×400×70%) (ie, the third preset threshold). For 5G networks, the preset high load requirements for 5G high-load sectors are: PRB load ≥ 70% and traffic load ratio ≥ 70% and average number of RRC connected users ≥ (bandwidth / 100MHz × 400 × 70%). A high-load sector refers to an area in a wireless communication network where, due to a surge in the number of users, excessive data traffic, or other reasons, the wireless resources (such as spectrum, time slices, power, etc.) within the sector are close to or exceed their carrying capacity, resulting in service quality degradation and network congestion.

[0046] There are multiple ways to implement the scenario type of the target high-load sector based at least on the high-load sector wide table. For example, the scenario type of the target high-load sector whose high load duration meets the first time period indicated by the preset scenario division rule is determined as the first scenario type; the scenario type of the target high-load sector that meets the sudden high load requirement indicated by the preset scenario division rule is determined as the second scenario type, wherein the sudden high load requirement is that the sector load is greater than the fourth preset threshold in the second time period, the first time period is greater than the second time period, and the sector load is at least one of the following: the utilization rate of the physical resource block, the traffic load ratio, and the number of wireless resource control connections; the scenario type of the target high-load sector in the target operator network corresponding to the preset date in the future preset time period corresponding to the target timestamp is determined as the third scenario type, wherein the preset date at least includes holidays.

[0047] As some examples of this application:

[0048] Categorizing data in the high-load sector-wide table into different scenario types is a key step in achieving intelligent network optimization. By analyzing the data in the high-load sector-wide table and using pre-set scenario classification rules and thresholds, high-load sectors are identified and classified into long-term high load (the first scenario type), sudden high load (the second scenario type), and foreseeable high load (the third scenario type).

[0049] The data within each preset collection period of the high-load sector wide table is scanned at preset monitoring intervals (e.g., 10 minutes). The preset scenario classification rules include at least a first scenario type and a second scenario type classification rule. Specifically, the scenario type of a target high-load sector whose high load duration meets the first time period indicated by the preset scenario classification rule (e.g., 5 consecutive days in a week) is determined as the first scenario type, where the high load duration is the duration of time that the preset high load requirement is continuously met. The scenario type of a target high-load sector that meets the sudden high load requirement indicated by the preset scenario classification rule is determined as the second scenario type. The sudden high load requirement is that the sector load exceeds a fourth preset threshold (e.g., 70%) within the second time period (e.g., a single day). The sector load is at least one of the following: physical resource block utilization, traffic load ratio, and number of radio resource control connections. If the sector load rapidly exceeds the fourth preset threshold within a short period of time, identification of the sudden high load scenario type is triggered. For example, one preset scenario classification rule is that the scenario type of a target high-load sector experiencing high load for 5 consecutive days in a week is determined as the first scenario type. The sudden increase in sector load to more than 70% (four preset thresholds) on a certain day (i.e., the second time period) is a sudden high-load scenario type. For the target high-load sector of the third scenario type, the scenario type of the target high-load sector in the target operator network corresponding to the preset date within the future preset time period (e.g., the next 15 days) corresponding to the target timestamp (the timestamp of the monitoring moment, i.e., the current timestamp) is determined to be the third scenario type. The implementation process is as follows: the sector in the target operator network corresponding to the preset date within the future preset time period (e.g., the next 15 days) corresponding to the future target timestamp (the timestamp of the monitoring moment, i.e., the current timestamp) is determined as the target high-load sector, and the scenario type of the target high-load sector is determined to be the third scenario type.

[0050] Step S206: Determine an adjustment strategy corresponding to the scenario type of the target high-load sector based on the knowledge graph, wherein the adjustment strategy is used to adjust network parameters of the target high-load sector.

[0051] The knowledge graph is constructed in the following way: after the network parameters of each target high-load sector are adjusted, the adjustment results corresponding to the target high-load sector are updated to the preset fields of the high-load sector wide table; the knowledge graph is constructed at least based on the high-load sector wide table, wherein the adjustment results include at least solutions and abnormal causes, and the knowledge graph is used to associate all target high-load sectors and the adjustment results of the target high-load sectors.

[0052] In the technical solution provided in step S206, there are multiple ways to implement the adjustment strategy corresponding to the scenario type of the target high-load sector determined based on the knowledge graph. For example: for the target high-load sector of the first scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by adopting a load balancing strategy, wherein the first scenario type is a long-term high-load scenario; for the target high-load sector of the second scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by adopting a real-time alarm method, wherein the second scenario type is a sudden high-load scenario; for the target high-load sector of the third scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by adopting a pre-expansion method, wherein the third scenario type is a foreseeable high-load scenario, the long-term high-load scenario corresponds to the target high-load sector with continuous high load, the sudden high-load scenario corresponds to the target high-load sector with instantaneous load changes resulting in high load, and the foreseeable high-load scenario corresponds to the target high-load sector with predicted high load. The preset dates include at least holidays, and may also include pre-set special dates (eg, large-scale cultural festivals, important meeting dates, etc.).

[0053] Long-term high-load scenarios are highly persistent and occur in densely populated and active areas. Sudden high-load scenarios are highly instantaneous, with sudden load changes, often triggered by unpredictable events. These scenarios rely on real-time alerts and rapid parameter adjustments. Predictable high-load scenarios are highly predictable and based on historical data and event predictions. They are suitable for pre-allocating resources before a preset date and preparing for capacity expansion. Related technologies for long-term high-load scenarios rely on manual proactive inquiries or passive problem discovery through user complaints. This lacks a regularized management and control process, resulting in fragmented optimization solutions and a lack of closed-loop management, leading to frequent recurring problems. Resource allocation in high-load sectors relies on experience and lacks data-driven, precise decision-making. Sudden traffic in high-load scenarios cannot be monitored in real time, resulting in delayed alert mechanisms and slow manual response times. Network parameter adjustments in high-load sectors rely on manual operations, making it difficult to quickly alleviate congestion. For predictable high-load scenarios, predictions rely on single-dimensional data (such as historical traffic) without comprehensively considering factors such as holidays, weather, and special events, resulting in low prediction accuracy. Irrational allocation of capacity expansion resources can easily lead to resource waste or insufficient support. The method of the present application can solve the above problems very well. It determines the adjustment strategy corresponding to the scenario type of the target high-load sector based on the knowledge graph, wherein the adjustment strategy is used to adjust the network parameters of the target high-load sector. For the target high-load sector of the first scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by adopting a load balancing strategy. For the target high-load sector of the second scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by adopting a real-time alarm method. For the target high-load sector of the third scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by adopting a pre-expansion method. Through the knowledge graph, historical optimization cases and solutions are mapped into structured information to realize intelligent recommendation of similar adjustment solutions. The method of the present application can adopt corresponding optimization strategies for different types of high-load scenarios, effectively improving the efficiency and intelligence level of network operation and maintenance, and significantly improving user perception and network performance.

[0054] As some examples of this application:

[0055] After adjusting the network parameters for each target high-load sector, the adjustment results corresponding to the target high-load sector are updated in the high-load sector width table. A preset field is a reserved solution field, which is used to record the adjustment results for each high-load sector. The adjustment results include at least the solution (including specific measures such as RF optimization, capacity expansion plan, and parameter adjustment) and the cause of the anomaly (the reason that caused the sector to become a high-load sector). The knowledge graph can be constructed in the following way: a knowledge graph is constructed based on the high-load sector width table and resource scheduling table, and all data is extracted from the high-load sector width table and resource scheduling table to ensure data integrity and real-time performance. All data in the high-load sector width table and resource scheduling table are then divided into four categories based on indicators (such as PRB utilization, traffic, etc.), parameters (such as operating parameters, antenna azimuth, power setting, etc.), anomaly causes (such as user density surge, hardware bottleneck), and solutions. Based on this data classification, each category of data and each high-load sector identifier (each target high-load sector corresponds to a high-load sector identifier) ​​are treated as an entity node in the knowledge graph. Indicators, parameters, causes, and solutions are labeled as independent nodes, ensuring that each node represents a specific element or concept in the high-load sector wide table and resource scheduling table. Graph nodes and edges are simulated using dictionaries and lists. Dictionaries store node information, while lists represent the relationship chains between entities. For example, each high-load sector identifier serves as a primary node, while its various indicators, parameters, anomaly causes, and solutions serve as subsidiary nodes, linked to the primary node via lists. This creates a collection of nodes containing all information related to its performance, configuration, issues, and solutions. In the graph structure, relationships between entities (i.e., edges) are defined by pre-set rules or algorithms. For example, if a high-load sector adjusts its antenna azimuth, an edge links the "Antenna Azimuth" parameter node to the "RF Optimization" solution node. Similarly, if a certain indicator anomaly leads to capacity expansion, these indicator nodes are also linked to the corresponding solution nodes. Collectively, these nodes and edges form the foundational structure of the knowledge graph, where nodes represent entities and edges represent relationships between them. This knowledge graph can be stored in a single file or managed using more advanced graph database technologies for efficient query and data analysis. Once constructed, the knowledge graph can be used for intelligent decision-making, such as recommending solutions. Adjustments can then be recorded back into the knowledge graph, forming a closed learning loop. Over time, the knowledge graph will accumulate more optimization cases and experience, making it even more valuable in future network operations and maintenance.

[0056] Figure 3This is a knowledge graph schematic diagram provided according to an embodiment of the present application. The figure is an example of a part of the knowledge graph related to the target high-load sector corresponding to the high-load sector identifier 1 in the knowledge graph. Purple represents the high-load sector identifier, which is used to determine the target high-load sector and the cell and base station corresponding to the target high-load sector; blue represents the indicators of the target high-load sector corresponding to the high-load sector identifier 1 stored in the high-load sector wide table (indicators 1 to 4 in the figure), red represents parameters (parameters 1 to 3 in the figure), orange represents solutions, gray represents the cause of the abnormality, and the connecting lines of each node represent the connection relationship (the specific connection relationship is not shown in the figure).

[0057] Step S208: Using an adjustment strategy to adjust the network parameters of the target high-load sector.

[0058] As some examples of this application:

[0059] Search by scenario type based on the knowledge graph: For the target high-load sector of the first scenario type, the adjustment strategy determined based on the knowledge graph is to use a load balancing strategy to adjust the network parameters of the target high-load sector. For the target high-load sector of the second scenario type, the adjustment strategy determined based on the knowledge graph is to use a real-time alarm method to adjust the network parameters of the target high-load sector. For the target high-load sector of the third scenario type, the adjustment strategy determined based on the knowledge graph is to use a pre-capacity expansion method to adjust the network parameters of the target high-load sector. When determining the adjustment strategy corresponding to the scenario type of the target high-load sector based on the knowledge graph, you can also directly perform a keyword search on the knowledge graph and return matching nodes based on keywords (such as high-load performance, alarms, parameters, etc.). For the returned nodes, if it is a performance issue, you can obtain the same-frequency and different-frequency load conditions of the surrounding sectors and determine which solution to use: radio frequency, capacity expansion, or parameter adjustment. If it is an alarm issue, you can obtain capacity expansion and parameter adjustment solutions. If it is a site configuration, you can solve it by creating a new site.

[0060] In the technical solution provided in step S208, a load balancing strategy is adopted to adjust the network parameters of the target high-load sector, including: collecting user complaint data, industrial parameter data, co-construction and sharing data and diversion ratio data every preset collection period, wherein the industrial parameter data at least includes the base station location and antenna parameters (azimuth, tilt angle, transmission power, etc.), the co-construction and sharing data is used to indicate the cooperation information between the operator corresponding to the high-load sector and other operators, and the diversion ratio data is used to reflect the load distribution of different frequency bands; a resource scheduling table is constructed based on the user complaint data, industrial parameter data, co-construction and sharing data and diversion ratio data, wherein the resource scheduling table is used to indicate a list of resources available for scheduling; the load balancing strategy corresponding to the target high-load sector is determined based on the resource scheduling table, wherein the load balancing strategy includes the adjustment method of the network parameters of the high-load sector; and the network parameters of the target high-load sector are adjusted according to the load balancing strategy.

[0061] As some examples of this application:

[0062] User complaint data, operating parameter data, co-location and sharing data, and traffic splitting ratio data are collected at predetermined intervals. All collected data is integrated into a resource scheduling table, creating a unified data view to facilitate subsequent analysis and decision-making. The resource scheduling table must clearly list all available resources, including but not limited to adjustable antenna parameters, adjustable traffic splitting, a list of operators and equipment that can cooperate in co-location and sharing. Based on the operating parameter data, traffic splitting ratio information, and user complaints in the resource scheduling table, the rationality of current network resource allocation is evaluated and network performance issues such as uneven coverage or quality degradation are identified. Based on the analysis results, a load balancing strategy is generated for target high-load sectors. The load balancing strategy includes adjustments to network parameters for target high-load sectors, such as antenna parameter adjustments (such as changing azimuth or tilt angles), adjustments to RF parameters such as reference signal power, adjustments to traffic splitting (optimizing user allocation between different frequency bands), and dynamic reduction of coverage for high-load sectors. Based on the load balancing strategy, network parameters for target high-load sectors are adjusted to balance the load and improve overall network performance. The adjusted parameter configuration is distributed to the base stations corresponding to the target high-load sectors through the network management system or big data analysis sharing platform to ensure that the network parameter adjustment can take effect quickly in the network. In long-term high-load scenarios, some target high-load sectors will experience continuous high load due to their geographical location characteristics (such as commercial centers, residential areas, etc.) or continuously growing user demand. The expansion decision unit plays a key role in this situation. The expansion decision unit analyzes the network performance data of the historical time period and determines whether hardware or software resources need to be expanded. For example, if it is monitored that the traffic of a certain sector has increased by 30% on the 7th day compared to the 1st day in the past 7 days, and it is predicted that it will continue to increase by more than 5% in the next 24 hours, then the expansion decision unit will trigger hardware expansion (such as adding new frequencies and building new sites) or software expansion (such as improving data processing capabilities). Based on the frequency bands supported by the remote radio unit (Radio Remote Unit, RRU) model, the baseband board capabilities, and the optical port rate capabilities, dual-carrier expansion or different-frequency same-coverage cell expansion will be used to expand the frequency of the target high-load sector coverage area sites to adapt to this long-term demand growth and ensure that network resources are sufficient to support high loads.

[0063] Load balancing strategies can be combined with regional scenarios to optimize base station parameter configuration and maximize network resource utilization by optimizing inter-frequency / co-frequency neighboring cell parameters. This strategy shifts load (i.e., resources) from busier cells (those corresponding to the target high-load sector) to cells with more remaining resources. This involves adjusting the network parameters of the target high-load sector (such as the neighboring cell list, handover boundary parameters, and load balancing parameters) to shift the load from the cell corresponding to the target high-load sector to the cell with more remaining resources. Load transfer application scenarios are categorized as co-frequency neighboring cell and inter-frequency neighboring cell. Co-frequency neighboring cell optimization focuses on adjusting inter-cell handover parameters, while inter-frequency neighboring cell optimization involves optimizing interoperability parameters between different frequency bands to ensure users receive service on the most appropriate frequency band, avoid unnecessary handovers, and thus reduce network burden. For primary and secondary neighboring cells with a 50% difference in data volume or number of users, the RF optimization unit adjusts power to appropriately expand or contract coverage, ensuring a more balanced distribution of network resources across cells and improving overall network performance.

[0064] The following is an example of a load balancing strategy: Target high-load sectors with a PRB utilization rate greater than 80% for seven consecutive days are screened and prioritized based on a complaint rate greater than 0.5%. Specifically, these sectors are ranked by complaint rate from high to low. The load balancing unit then uses the inter-frequency load balancing function to adjust the network parameters of the target high-load sectors, shifting traffic from these sectors to lower-loaded neighboring cells (sectors with a PRB utilization rate less than 30%). After the adjustment, the PRB utilization rate of the target high-load sectors drops to 65%, and the terminal access success rate increases by 15%. Furthermore, for sectors with a high degree of backflow from 5G terminals on the 4G network, the following judgment rule is used to identify sectors requiring optimization: ({downlink traffic volume of 5G terminals on the 4G network} + {uplink traffic volume of 5G terminals on the 4G network}) divided by ({uplink traffic volume} + {downlink traffic volume}) > a preset value (e.g., 0.3). If the above conditions are met, it means that the service traffic of 5G terminals on the 4G network is too high, and the 4 / 5G interoperability parameters should be optimized to encourage 5G users to stay more on the 5G network and reduce the traffic pressure on the 4G network.

[0065] The network parameters of the target high-load sector are adjusted by using a real-time alarm method, including: generating alarm information, wherein the alarm information at least includes network performance data of the target high-load sector and network parameter adjustment suggestions; pushing the alarm information to the client of the operation and maintenance personnel, and adjusting the network parameters of the target high-load sector according to the response instructions of the client.

[0066] As some examples of this application:

[0067] A network optimization assurance model for sudden high-load scenarios is established. Granular monitoring is performed at a preset period (15-minute intervals) for sudden high-traffic scenarios. If the number of RRC connections in a target high-load sector exceeds a preset high-load threshold (for example, >220 for 5G networks and >250 for 4G networks) for two consecutive periods within half an hour, and the number of RRC connections in the previous period (the monitoring period preceding the two consecutive periods) did not reach the preset high-load threshold, an alarm mechanism is triggered. (Specific scenarios such as universities and high-speed rail are excluded, as these areas already have high RRC connection counts and are not subject to the high-load determination criteria). Alarm information is immediately generated, triggering real-time alerts. The alarm mechanism must be sensitive and timely, generating detailed alarm information as soon as an anomaly occurs. Alarm information should include not only network performance data (such as the number of RRC connections and changes in PRB usage), but also network parameter adjustment recommendations based on current network status and historical data (in the form of large-traffic parameter optimization scripts, including network parameter modification solutions for both 4G and 5G high-load scenarios). Alarm information is automatically pushed to the O&M personnel's client. After receiving the alarm information, the O&M personnel can quickly determine the urgency of the situation and the feasibility of the optimization suggestions. If immediate optimization is confirmed, a response instruction (including specific network parameter adjustment methods) will be issued through the client. The system adjusts the network parameters of the target high-load sectors based on the client's response instructions. For example, in 4G networks, the network parameter modification plan for high-load sectors located in high-value scenarios such as scenic spots, transportation hubs, large gathering areas, and popular shopping districts is to perform hardware expansion in the 2.1GHz frequency band, such as increasing the number of remote radio units, to increase the cell's carrier capacity and data processing capabilities. Hardware expansion can directly increase network resources, alleviate traffic pressure, and improve user experience. In hot spots with extremely high user density, such as large shopping malls or plazas, the deployment of pole micro-base stations can serve as a temporary or auxiliary expansion measure. By locally enhancing signal coverage, they can distribute traffic pressure on the main sector, thereby improving overall network performance and user experience. In 5G networks, especially in frequency-division duplex (FDD) areas, focus on sites that support holidays and high-traffic scenarios, such as rural areas or major transportation routes during the Spring Festival rush hour. At this time, the network parameter modification plan for the two types of 5G high-load scenarios includes adjusting the network parameters related to high traffic in advance based on historical data and prediction models, such as adjusting the switching threshold, to ensure the stability and efficiency of the network during high traffic periods. For high-load sites in the 3.5G frequency band, bandwidth expansion is carried out in advance, from the existing 100MHz to 200MHz, to meet high traffic demands. For example, it was monitored that the number of RRC connections in a certain scenic spot increased sharply from 150 to 300 within 15 minutes, triggering an alarm; the alarm information was pushed to the client of the operation and maintenance personnel, along with suggestions for adjusting the network parameters. After manual review, the network parameters of the target high-load sector are adjusted according to the response instructions.

[0068] The network parameters of the target high-load sector are adjusted in advance by adopting a pre-expansion method, including: predicting the network performance data of the target high-load sector of the third scenario type on a preset date to obtain the predicted network performance data; determining the expansion strategy based on the predicted network performance data, and adjusting the network parameters of the target high-load sector based on the expansion strategy.

[0069] As some examples of this application:

[0070] Using prediction models (such as Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Remote Radio Unit (RRU), Convolutional Neural Network (CNN), etc. The GRU model (GRU) is used to predict the network performance data of the target sector (the target sector refers to all sectors of the target operator's network) within a preset time period (e.g., the next 24 hours) using a neural network (CNN) model (verified by mean absolute error (MAE) and root mean square error (RMSE)). The predicted network performance data is then used to determine whether the expansion trigger conditions have been met, such as if traffic growth exceeds a certain percentage or if PRB utilization is nearing saturation. If the prediction results indicate that the target operator's network is facing potential high load pressure, an expansion strategy is determined based on the predicted network performance data. The expansion strategy includes hardware or software-level expansion strategies, such as upgrading the baseband board, adjusting the antenna configuration, or enabling additional capacity for software resources. When formulating the expansion plan, effective resource utilization is also considered to avoid cost waste or idle resources caused by excessive expansion. Finally, the expansion plan is distributed to the base stations in the target high-load sector in the form of a parameter script, including hardware installation instructions and software configuration updates. Expansion hardware is deployed on-site, such as new The software parameters are updated simultaneously. After completion, network performance verification is required to ensure that the expansion meets expectations. After the expansion, network performance, including PRB utilization, RRC connection numbers, and network traffic data, is continuously monitored to verify the effectiveness of the expansion strategy. The expansion results are fed back into the knowledge graph and predictive model for iterative optimization of future predictions and policy formulation, continuously improving network resource utilization efficiency and user experience. The training dataset used to train the predictive model is constructed using the following methods: Scenario type: Transportation hubs, scenic spots, schools, and shopping districts are selected as the primary prediction scenarios. Time range: Historical network performance data is obtained from the network optimization platform, typically over a longer period, such as the past year, to cover the impact of various seasons and events. Historical network performance data is aggregated by grid type and day. This means combining data from the same grid type (such as a specific transportation hub grid) on each day to capture pattern variations across different grids and days. Based on the scenario type, corresponding data records are extracted from the aggregated data to create a separate training dataset for each scenario. This allows for more accurate modeling and prediction tailored to the specific characteristics of each scenario.Define the metrics that the prediction model needs to predict, including average physical resource block utilization (average uplink physical resource block utilization and average downlink physical resource block utilization), maximum number of radio resource control connected users, average number of RRC connected users, and packet data convergence protocol layer user plane traffic bytes (including uplink user plane traffic bytes and downlink user plane traffic bytes). Then, perform data enhancement on the training dataset. The following data features can be enhanced: weather information: including temperature, humidity, precipitation, etc.; holidays and special events: such as Spring Festival, National Day, sporting events, or concerts; user behavior data: including age distribution, weekday and weekend activity patterns, and usage frequency of specific applications (such as video and games); socioeconomic data: such as regional population density and average income level. The data of the training dataset after data enhancement includes the following fields: date, city (the specific city to which the data belongs), grid type (describing the category of the grid, such as transportation hubs, scenic spots, schools, business districts, etc.), grid name, grid group name, average uplink physical resource block utilization rate and downlink physical resource block utilization rate, maximum number of radio resource control connected users (), average number of RRC connected users (), number of uplink user plane traffic bytes and number of downlink user plane traffic bytes, month, day, reverse day (used to refine the time granularity, reverse day is only counted from the last day of the corresponding month, which day the data collection date belongs to), whether it is a holiday, weather conditions, maximum temperature, long holiday (indicating whether it is a long holiday), major events (marking whether there are major events on the date of data recording, such as sports events, concerts, etc.), number of 5G terminals (the number of 5G user devices in the grid), school winter and summer vacation conditions (marking whether the grid is on vacation when it is a school), etc. For example, during training, the input data consisted of PRB usage and traffic data for a transportation hub over the past three months, with holiday and weather labels superimposed. GRU model training was used to predict network performance data for the next 24 hours. The prediction results showed a 120% increase in traffic during the National Day holiday, enabling the early deployment of a dual-carrier capacity expansion solution. After the expansion, peak-period PRB usage stabilized below 75%, and the user complaint rate dropped by 50%.

[0071] The embodiment of the present application also provides a structural diagram of an adjustment device for a high-load sector, such as Figure 4 Shown, including:

[0072] The first determining module 402 is configured to determine a target high-load sector in a target operator network.

[0073] The second determining module 404 is configured to determine a scenario type of a target high-load sector based at least on a high-load sector-wide table, wherein the high-load sector-wide table is used to quantify the network performance of the target operator.

[0074] The third determination module 406 is used to determine an adjustment strategy corresponding to the scenario type of the target high-load sector based on the knowledge graph, wherein the adjustment strategy is used to adjust the network parameters of the target high-load sector.

[0075] The adjustment module 408 is configured to adjust the network parameters of the target high-load sector using an adjustment strategy.

[0076] It should be noted that Figure 4 The adjustment device of the high load sector is used to perform Figure 2 The adjustment method for high-load sectors is shown, so Figure 2 The relevant explanations in the adjustment method of the high-load sector also apply to the adjustment device of the high-load sector and will not be repeated here.

[0077] It should be noted that the various modules in the above-mentioned high-load sector adjustment device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0078] An embodiment of the present application further provides a non-volatile storage medium, which includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the high-load sector adjustment method in any one of the above embodiments.

[0079] An embodiment of the present application further provides an electronic device, which includes a processor, and the processor is used to run a program, wherein the method for adjusting the high-load sector in any one of the above embodiments is executed when the program is running.

[0080] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the high-load sector adjustment method in any one of the above embodiments.

[0081] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0083] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0084] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0086] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adjusting a high-load sector, characterized in that: include: Identify target high-load sectors within the target operator's network; determining a scenario type of the target high-load sector based at least on a high-load sector-wide table, wherein the high-load sector-wide table is used to quantify network performance of the target operator; Determining, based on the knowledge graph, an adjustment strategy corresponding to the scenario type of the target high-load sector, wherein the adjustment strategy is used to adjust network parameters of the target high-load sector; The adjustment strategy is adopted to adjust the network parameters of the target high-load sector.

2. The method according to claim 1, characterized in that The high-load sector wide table is constructed in the following way: Collecting network performance data of the target operator's network at every preset collection period, wherein the network performance data at least includes a utilization rate of physical resource blocks, a number of radio resource control connections, and network traffic data; The high-load sector wide table is constructed based on the network performance data of all the preset collection periods.

3. The method according to claim 2, characterized in that The determining the scenario type of the target high-load sector based at least on the high-load sector wide table includes: Determining a sector in the high-load sector wide table that meets a preset high-load requirement as the target high-load sector, wherein the preset high-load requirement is that the utilization rate of the physical resource block is greater than or equal to a first preset threshold, the traffic load ratio is greater than or equal to a second preset threshold, and the average number of radio resource control connections is greater than or equal to a third preset threshold; Determining the scenario type of the target high-load sector whose high-load duration meets the first time period indicated by the preset scenario division rule as a first scenario type; Determining the scenario type of the target high-load sector that meets the sudden high-load requirement indicated by the preset scenario division rule as a second scenario type, wherein the sudden high-load requirement is that the sector load is greater than a fourth preset threshold within a second time period, the first time period is greater than the second time period, and the sector load is at least one of the following: a utilization rate of the physical resource block, the traffic load ratio, and the number of radio resource control connections; The scenario type of the target high-load sector in the target operator network corresponding to a preset date within a future preset time period corresponding to the target timestamp is determined as a third scenario type, wherein the preset date at least includes holidays.

4. The method according to claim 3, characterized in that The determining, based on the knowledge graph, an adjustment strategy corresponding to the scenario type of the target high-load sector includes: For the target high-load sector of the first scenario type, determining, based on the knowledge graph, that the adjustment strategy is to use a load balancing strategy to adjust the network parameters of the target high-load sector, wherein the first scenario type is a long-term high-load scenario; For the target high-load sector of the second scenario type, determining, based on the knowledge graph, that the adjustment strategy is to adjust the network parameters of the target high-load sector by means of real-time alarm, wherein the second scenario type is a sudden high-load scenario; For the target high-load sector of the third scenario type, the adjustment strategy is determined based on the knowledge graph to adjust the network parameters of the target high-load sector by pre-expansion, wherein the third scenario type is a foreseeable high-load scenario, the long-term high-load scenario corresponds to the target high-load sector with continuous high load, the sudden high-load scenario corresponds to the target high-load sector with instantaneous load changes resulting in high load, and the foreseeable high-load scenario corresponds to the target high-load sector with predicted high load.

5. The method according to claim 4, characterized in that The method of using a load balancing strategy to adjust the network parameters of the target high-load sector includes: Collect user complaint data, industrial parameter data, co-construction and sharing data, and split ratio data at every preset collection period, wherein the industrial parameter data includes at least base station location and antenna parameters, the co-construction and sharing data is used to indicate the cooperation information between the operator corresponding to the high-load sector and other operators, and the split ratio data is used to reflect the load distribution of different frequency bands; Constructing a resource scheduling table based on the user complaint data, the work parameter data, the co-construction and sharing data, and the diversion ratio data, wherein the resource scheduling table is used to indicate a list of resources available for scheduling; Determining the load balancing strategy corresponding to the target high-load sector according to the resource scheduling table, wherein the load balancing strategy includes an adjustment method for network parameters of the high-load sector; The network parameters of the target high-load sector are adjusted according to the load balancing strategy.

6. The method according to claim 4, characterized in that The method of adjusting the network parameters of the target high-load sector by using a real-time alarm includes: generating alarm information, wherein the alarm information includes at least network performance data of the target high-load sector and a network parameter adjustment suggestion; The alarm information is pushed to the client of the operation and maintenance personnel, and the network parameters of the target high-load sector are adjusted according to the response instruction of the client.

7. The method according to claim 4, characterized in that The method of adjusting the network parameters of the target high-load sector by pre-expansion includes: Predicting network performance data of the target high-load sector of the third scenario type on the preset date to obtain predicted network performance data; A capacity expansion strategy is determined based on the predicted network performance data, and network parameters of the target high-load sector are adjusted based on the capacity expansion strategy.

8. The method according to claim 2, characterized in that The knowledge graph is constructed in the following way: After adjusting the network parameters of each target high-load sector, updating the adjustment result corresponding to the target high-load sector into a preset field of the high-load sector wide table; A knowledge graph is constructed at least based on the high-load sector wide table, wherein the adjustment result includes at least a solution and an abnormal cause, wherein the abnormal cause is the reason why the sector becomes a high-load sector, and the knowledge graph is used to associate all the target high-load sectors and the adjustment results of the target high-load sectors.

9. An adjustment device for a high-load sector, characterized in that: include: A first determining module is configured to determine a target high-load sector within a target operator network; a second determining module, configured to determine a scenario type of the target high-load sector based at least on a high-load sector width table, wherein the high-load sector width table is used to quantify the network performance of the target operator; a third determining module, configured to determine, based on the knowledge graph, an adjustment strategy corresponding to the scenario type of the target high-load sector, wherein the adjustment strategy is used to adjust network parameters of the target high-load sector; An adjustment module is configured to adjust the network parameters of the target high-load sector by adopting the adjustment strategy.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the high-load sector adjustment method according to any one of claims 1 to 8.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the method for adjusting a high-load sector according to any one of claims 1 to 8 is executed when the program is run.

12. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the high-load sector adjustment method according to any one of claims 1 to 8 is implemented.

Images