RedCap terminal access shunting system and method based on decision tree model

Abstract

The invention discloses a RedCap terminal access shunting system and method based on a decision tree model, and the system comprises a central control unit which is used for collecting network state information reported by each base station, and the network state information comprises key indexes including the number of users, the radio bearer RB utilization rate and the RRC access success rate; the plurality of base stations are used for executing the instruction of the central control unit and adjusting the on or off states of RedCap functions of the base stations and adjacent cells so as to optimize network resource allocation; and the decision tree model is arranged in the central control unit and is used for intelligently analyzing the network state information data and sending an instruction to the base station according to an analysis result so as to adjust the starting state of the RedCap function. By monitoring the network state in real time and intelligently evaluating and dynamically adjusting the RedCap function enabling state of the cells near the congested cell, the network load is balanced, the resource allocation is optimized, the network congestion can be effectively relieved, and the overall performance of the network is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communication networks, and in particular to a RedCap terminal access distribution system and method based on a decision tree model. Background Art

[0002] RedCap, a 5G technology defined by the 3GPP standardization organization, is designed specifically for the Internet of Things and aims to meet the needs of medium- and high-speed IoT applications by reducing equipment complexity and cost.

[0003] RedCap technology is optimized in terms of bandwidth, power consumption, antenna design and cost, effectively balancing the capabilities of 5G large bandwidth, high speed, wide connection and low latency, and meeting the differentiated industry networking needs. RedCap significantly reduces terminal complexity and cost by cutting some advanced functions, while retaining the key characteristics of 5G networks such as high reliability, low latency and large capacity.

[0004] Although RedCap technology shows great potential in the field of IoT, the following problems still exist in the current 5G network deployment:

[0005] The activation status of the RedCap function mostly relies on static configuration, which is difficult to adapt to the large-scale access of RedCap terminals and dynamically changing network loads. This static management method is prone to cause network congestion during peak network loads, affecting user experience and overall network performance;

[0006] Specifically, static configuration cannot dynamically adjust the number of RedCap terminal accesses and bandwidth resources according to real-time changes in network load, and thus cannot effectively address network congestion issues.

[0007] To this end, the present application specifically proposes a RedCap terminal access diversion system and method based on a decision tree model to solve the above-mentioned technical problems, thereby further improving network performance and realizing intelligent and dynamic management of RedCap terminals. Summary of the invention

[0008] The main purpose of the present invention is to provide a RedCap terminal access diversion system and method based on a decision tree model, which monitors the network status in real time, intelligently evaluates and dynamically adjusts the RedCap function activation status of cells near congested cells to balance the network load and optimize resource allocation, thereby effectively alleviating network congestion, improving the overall network performance and user experience, and solving the technical problems raised in the background technology. The system dynamic management can dynamically adjust the access quantity and bandwidth resources of the RedCap terminal according to the real-time changes in the network load, ensuring the reasonable allocation and efficient utilization of network resources. At the same time, the system dynamic management can also improve the user experience, reduce the probability of network congestion, and improve the overall network performance.

[0009] The present invention adopts the following technical solutions to solve the above technical problems:

[0010] The RedCap terminal access diversion system based on the decision tree model includes:

[0011] The central control unit is used to collect network status information reported by each base station. The network status information includes key indicators such as the number of users, radio bearer RB utilization, and RRC access success rate;

[0012] Multiple base stations are used to execute the instructions of the central control unit and adjust the on or off status of the RedCap function of themselves and neighboring cells to optimize network resource allocation;

[0013] The decision tree model is set in the central control unit and is used to intelligently analyze the network status information data and send instructions to the base station according to the analysis results to adjust the activation status of the RedCap function.

[0014] Preferably, the decision tree model is internally used to set a congestion alarm threshold, a congestion release threshold, a decision threshold, an adaptive user threshold, an adaptive RB utilization threshold, and an adaptive RRC access success rate threshold.

[0015] A RedCap terminal access diversion method based on a decision tree model includes the following specific steps:

[0016] S1. System deployment and initialization: Install and configure the central control unit and multiple base stations, ensure smooth communication between the central control unit and multiple base stations, deploy the decision tree model in the central control unit, and set initial parameters and thresholds to build the RedCap terminal access diversion system based on the decision tree model;

[0017] S2. Data collection and preprocessing: The base station regularly reports network status information to the central control unit, and the central control unit preprocesses the collected data to ensure data quality;

[0018] S3. Decision tree model evaluation: When a congestion alarm occurs in the preset RedCap cell, the decision tree model evaluation is triggered. The decision tree model performs evaluation according to the preset decision logic based on the collected network status information;

[0019] S4. Instruction generation and transmission: According to the evaluation results of the decision tree model, the central control unit generates corresponding instructions and sends the instructions to the target base station. The base station executes the instructions and adjusts the enabled state of the RedCap function;

[0020] S5. Monitoring and feedback: The system continuously monitors changes in network status and adjusts the parameters and thresholds of the decision tree model in a timely manner based on the monitoring results to optimize the decision effect;

[0021] S6. Documentation and archiving: Record the process and results of each decision tree model evaluation, as well as the corresponding instruction generation and sending records.

[0022] Preferably, the step of performing evaluation according to a preset decision logic in step S3 includes: first determining the number of users, then determining RB utilization, and finally considering evaluation factors including RRC access success rate and geographical location.

[0023] Preferably, in the step S4, when the base station executes instructions and adjusts the enabled state of the RedCap function, the central control unit preferentially turns on the RedCap function of high-priority non-preset neighboring cells according to the judgment result of the decision tree model to distribute the load.

[0024] Preferably, in the step S4, when the base station executes instructions and adjusts the enabled state of the RedCap function, if the high priority cell is unavailable or congested, medium priority and low priority cells are considered in turn to gradually expand the coverage of the RedCap function.

[0025] Preferably, in the step S4, the base station executes the instruction and adjusts the enabled state of the RedCap function to have a process of closing the neighboring cell RedCap, which specifically includes:

[0026] Set the release threshold value, which is lower than the congestion alarm threshold, to determine whether the preset RedCap cell has returned to normal;

[0027] When the status of a preset RedCap cell drops below the release threshold, the system checks for RedCap users in non-preset neighboring cells;

[0028] If there is no RedCap user, turn off the RedCap function of the corresponding neighboring area.

[0029] Preferably, the decision tree model includes:

[0030] The root node is used to determine whether the proportion of RedCap terminals in the congestion alarm cell exceeds the decision threshold. If so, it enters branch 1 for evaluation. If not, it ends the evaluation and does not enable the neighboring cell RedCap function.

[0031] Branch 1, which contains decision variables 1 and 2 to consider the number of users and resource utilization;

[0032] Decision variable 1: the number of users in the neighboring area. The number of users determines whether to enable the RedCap function. If the number of users exceeds the adaptive user threshold, the function is disabled. If the number of users does not exceed the adaptive user threshold, the function is enabled.

[0033] Decision variable 2: RB wireless resource utilization rate, which evaluates the resource shortage degree. If it exceeds the adaptive RB utilization rate threshold, it will not be enabled; if it does not exceed the threshold, it will continue.

[0034] Preferably, when the number of users and the RB utilization rate are both moderate or low, the decision tree model has branch 2, and decision variable 3 exists in branch 2 to consider network performance;

[0035] Decision variable 3: RRC access success rate, evaluates network access performance. If it is lower than the adaptive RRC access success rate threshold, it will not be enabled. If it exceeds, it will continue.

[0036] Preferably, when the RRC access success rate is moderate or high, the decision tree model has branch 3, and decision variables 4 and decision variables 5 exist in branch 3 with geographic location and historical data;

[0037] Decision variable 4: Geographic location, the priority is determined according to importance, among which important geographical locations are determined with high priority, and general geographical locations enter the decision variable 5 for judgment;

[0038] Decision variable 5: Historical data. The cell priority is evaluated based on recent congestion conditions and historical performance. If congestion has occurred within 3 days, it is set to low priority, and if congestion has not occurred within 3 days, it is set to medium priority.

[0039] It can be seen from the above technical solution that the present invention provides a RedCap terminal access diversion system and method based on a decision tree model. Compared with the prior art, the present invention has the following advantages:

[0040] 1. The present invention integrates a decision tree model in the central control unit, collects and analyzes the network status information reported by each base station in real time, automatically identifies network congestion, and can achieve the purpose of intelligent dynamic management of the RedCap function. It also continuously optimizes the decision tree model parameters through continuous monitoring and feedback mechanism, ensuring long-term efficient network operation.

[0041] 2. The present invention can accurately evaluate the network status and make the best decision by setting multi-level judgment logic in the decision tree model, thereby guiding the base station to dynamically turn on or off the RedCap function of the adjacent cell, effectively dispersing the network load, alleviating congestion, ensuring the reasonable allocation of network resources under different load conditions, and improving the stability and response speed of network services.

[0042] 3. The decision tree model of the present invention can more finely match network resources with actual needs by incorporating geographic priority and historical data analysis into the decision-making process, ensuring the stability and efficiency of RedCap services in high-priority areas.

[0043] 4. In the case of limited resources, the decision tree model of the present invention reasonably allocates the activation of RedCap functions through a priority sorting mechanism, maximizes the use of limited RedCap license resources, and thus maximizes the deployment of redcap applications by utilizing limited license resources when the operator's RedcapLicense resources are limited, thereby improving the overall performance of the network and user experience.

[0044] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easy to understand through the following description. Of course, it is not necessary to achieve all of the advantages described above simultaneously for any product implementing the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0046] Figure 1 It is a schematic diagram of the overall structure of the system of the present invention;

[0047] Figure 2 A schematic diagram of threshold setting of the decision tree model of the present invention;

[0048] Figure 3 It is a schematic diagram of the overall process of the method of the present invention;

[0049] Figure 4 It is a schematic diagram of the decision judgment logic of the decision tree model of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] In the embodiment, see Figures 1 to 4 .

[0052] like Figure 1 The RedCap terminal access distribution system based on the decision tree model proposed in the embodiment of the present invention includes a central control unit and multiple base stations, wherein the central control unit collects and analyzes the network status information reported by each base station, uses the decision tree model to perform intelligent evaluation, and sends instructions to the base station according to the evaluation results to adjust the activation status of the RedCap function;

[0053] Furthermore, the central control unit in the system architecture is the core of the system, responsible for collecting network status information reported by each base station (including key indicators such as the number of users, radio bearer RB (Radio Bearer) utilization, RRC (Radio Resource Control) access success rate), and at the same time, intelligently analyzing these network status information data through the built-in decision tree model, and sending instructions to the base station based on the analysis results to flexibly adjust the activation status of the RedCap function;

[0054] At this time, the base station is responsible for executing the instructions of the central control unit and adjusting the on or off status of the RedCap function of itself and the neighboring cells to optimize the allocation of network resources;

[0055] And at this time, if Figure 2 As shown, the decision tree model is used to set a congestion alarm threshold, a congestion release threshold, a decision threshold, an adaptive user threshold, an adaptive RB utilization threshold, and an adaptive RRC access success rate threshold.

[0056] In summary, the system integrates a decision tree model in the central control unit, and automatically identifies network congestion by collecting and analyzing the network status information reported by each base station in real time. It can then intelligently evaluate and dynamically adjust the RedCap function activation status of cells near the congested cells, thereby achieving the purpose of intelligent dynamic management of the RedCap function, balancing network load, optimizing resource allocation, and effectively alleviating network congestion, improving the overall network performance and user experience, and realizing intelligent and dynamic management of RedCap terminals. At the same time, it continuously optimizes the decision tree model parameters through continuous monitoring and feedback mechanisms to ensure long-term efficient network operation.

[0057] It should also be noted that the system's dynamic management can dynamically adjust the access quantity and bandwidth resources of RedCap terminals according to the real-time changes in network load, ensuring the rational allocation and efficient use of network resources. At the same time, the system's dynamic management can also enhance user experience, reduce the probability of network congestion, and improve overall network performance.

[0058] On the other hand, Figure 3 and Figure 4 The present invention also discloses a RedCap terminal access diversion method based on a decision tree model, comprising the following specific steps:

[0059] S1. System deployment and initialization: Install and configure the central control unit and multiple base stations, ensure smooth communication between the central control unit and multiple base stations, deploy the decision tree model in the central control unit, and set initial parameters and thresholds (such as congestion threshold, release threshold, etc.) to build the above-mentioned RedCap terminal access diversion system based on the decision tree model;

[0060] S2. Data collection and preprocessing: The base station regularly reports network status information to the central control unit, including key indicators such as the number of users, RB utilization, and RRC access success rate. The central control unit then preprocesses the collected data, such as data cleaning and format conversion, to ensure data quality;

[0061] S3. Decision tree model evaluation: When a congestion alarm occurs in the preset RedCap cell (such as the ratio of the number of RRC users to the number of cell users exceeds the preset congestion threshold), the decision tree model evaluation is triggered. After that, the decision tree model is evaluated according to the preset decision logic based on the collected network status information (such as first determining the number of users, then determining the RB utilization rate, and finally considering the evaluation factors including the RRC access success rate and geographical location);

[0062] S4. Instruction generation and transmission: According to the evaluation results of the decision tree model, the central control unit generates corresponding instructions (such as turning on or off the RedCap function of non-preset neighboring cells), and then sends the instructions to the target base station, which executes the instructions and adjusts the activation status of the RedCap function;

[0063] S5. Monitoring and feedback: The system continuously monitors changes in network status, including the effect evaluation after the RedCap function is enabled, and then adjusts the parameters and thresholds of the decision tree model in a timely manner based on the monitoring results to optimize the decision effect;

[0064] S6. Documentation and archiving: Record the process and results of each decision tree model evaluation, as well as the corresponding instruction generation and sending records.

[0065] Therefore, when resources are limited, the decision tree model of the present invention reasonably allocates the activation of RedCap functions through a priority sorting mechanism, maximizes the use of limited RedCap license resources, and thus maximizes the deployment of redcap applications by utilizing limited license resources when the operator's RedcapLicense resources are limited, thereby improving the overall performance of the network and user experience.

[0066] Further, in step S4, the base station executes the instruction and adjusts the enabled state of the RedCap function, such as Figure 4 As shown in the figure, the adaptive management process of decision tree model judgment includes:

[0067] (1) Adaptive opening of non-preset neighboring area RedCap process

[0068] a1. When a congestion alarm occurs in the preset RedCap cell (such as the ratio of the number of RRC users to the number of cell users exceeds the preset congestion threshold), the decision tree model evaluation is triggered;

[0069] a2. The central control unit preferentially turns on the RedCap function of the high-priority non-preset neighboring area according to the decision tree model to distribute the load;

[0070] a3. If the high-priority cell is unavailable or congested, the medium-priority and low-priority cells will be considered in turn to gradually expand the coverage of the RedCap function;

[0071] (2) Adaptive closing of neighboring RedCap process;

[0072] b1. Set the release threshold value, which is lower than the congestion alarm threshold, to determine whether the preset RedCap cell has returned to normal;

[0073] b2. When the preset RedCap cell status drops below the release threshold, the system checks the number of non-preset neighboring RedCap users;

[0074] b3. If there is no RedCap user, turn off the RedCap function of the corresponding neighboring area.

[0075] In summary, by setting up multi-level judgment logic in the decision tree model, we can accurately evaluate the network status and make the best decision, thereby guiding the base station to dynamically turn on or off the RedCap function of the adjacent cell, effectively dispersing the network load, alleviating congestion, ensuring the reasonable allocation of network resources under different load conditions, and improving the stability and response speed of network services.

[0076] Further, such as Figure 4 As shown, the decision tree model includes:

[0077] Root node: Determine whether the proportion of RedCap terminals in the congestion alarm cell exceeds the decision threshold. If it exceeds, enter branch 1 evaluation; if it does not exceed, end the evaluation and do not enable the neighboring cell RedCap function.

[0078] Branch 1: Number of users and resource utilization:

[0079] Decision variable 1: The number of users in the neighboring area. The number of users determines whether the RedCap function needs to be enabled (if the number of users exceeds the adaptive user threshold, it will not be enabled; if it does not exceed the adaptive user threshold, it will continue to be enabled).

[0080] Decision variable 2: RB wireless resource utilization, to evaluate the resource shortage level (if it exceeds the adaptive RB utilization threshold, it will not be turned on, if it does not exceed, it will continue).

[0081] Branch 2: Network performance (when the number of users and RB utilization are both moderate or low):

[0082] Decision variable 3: RRC access success rate, to evaluate network access performance (if it is lower than the adaptive RRC access success rate threshold, it will not be enabled; if it exceeds the threshold, it will continue).

[0083] Branch 3: Geographic location and historical data (considered only when the RRC access success rate is moderate or high):

[0084] Decision variable 4: Geographic location, the priority is determined according to importance, among which important geographical locations are determined with high priority, and general geographical locations enter the decision variable 5 for judgment;

[0085] Decision variable 5: Historical data. The cell priority is evaluated based on recent congestion conditions and historical performance. If congestion has occurred within 3 days, it is set to low priority, and if congestion has not occurred within 3 days, it is set to medium priority.

[0086] Therefore, by incorporating geographic priorities and historical data analysis into the decision-making process, the decision tree model can more finely match network resources with actual needs, ensuring the stability and efficiency of RedCap services in high-priority areas.

[0087] In another embodiment provided in the present application, a computer program product containing instructions is also provided to serve as a central control unit or base station of a RedCap terminal access diversion system based on a decision tree model, which is used to build a corresponding system. When it runs on a computer, it enables the computer to implement any of the RedCap terminal access diversion methods based on a decision tree model in the above-mentioned embodiments.

[0088] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

[0089] The embodiment of the present application also provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus.

[0090] Memory, used to store computer programs;

[0091] The processor is used to implement the above-mentioned RedCap terminal access diversion system and method based on the decision tree model when executing the program stored in the memory.

[0092] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0093] The communication interface is used for communication between the above electronic device and other devices.

[0094] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0095] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0096] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0097] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0098] In addition, it should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0099] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or schemes that A and B meet at the same time. In addition, in the embodiments of the present invention, "multiple" refers to more than two. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

Claims

1. The RedCap terminal access diversion system based on the decision tree model is characterized by: include: The central control unit is used to collect network status information reported by each base station. The network status information includes key indicators such as the number of users, radio bearer RB utilization, and RRC access success rate; Multiple base stations are used to execute the instructions of the central control unit and adjust the on or off status of the RedCap function of themselves and neighboring cells to optimize network resource allocation; The decision tree model is set in the central control unit and is used to intelligently analyze the network status information data and send instructions to the base station according to the analysis results to adjust the activation status of the RedCap function.

2. The RedCap terminal access and diversion system based on the decision tree model as claimed in claim 1, characterized in that: The decision tree model is used to set a congestion alarm threshold, a congestion release threshold, a decision threshold, an adaptive user threshold, an adaptive RB utilization threshold, and an adaptive RRC access success rate threshold.

3. The RedCap terminal access diversion method based on the decision tree model is characterized by: The specific steps include: S1. System deployment and initialization: installing and configuring a central control unit and multiple base stations, ensuring smooth communication between the central control unit and multiple base stations, deploying a decision tree model in the central control unit, and setting initial parameters and thresholds to construct the RedCap terminal access diversion system based on the decision tree model according to claim 2; S2. Data collection and preprocessing: The base station regularly reports network status information to the central control unit, and the central control unit preprocesses the collected data to ensure data quality; S3. Decision tree model evaluation: When a congestion alarm occurs in the preset RedCap cell, the decision tree model evaluation is triggered. The decision tree model performs evaluation according to the preset decision logic based on the collected network status information; S4. Instruction generation and transmission: According to the evaluation results of the decision tree model, the central control unit generates corresponding instructions and sends the instructions to the target base station. The base station executes the instructions and adjusts the enabled state of the RedCap function; S5. Monitoring and feedback: The system continuously monitors changes in network status and adjusts the parameters and thresholds of the decision tree model in a timely manner based on the monitoring results to optimize the decision effect; S6. Documentation and archiving: Record the process and results of each decision tree model evaluation, as well as the corresponding instruction generation and sending records.

4. The RedCap terminal access diversion method based on the decision tree model as claimed in claim 3, characterized in that: The evaluation steps performed according to the preset decision logic in step S3 include: first determining the number of users, then determining the RB utilization rate, and finally considering evaluation factors including the RRC access success rate and the geographical location.

5. The RedCap terminal access diversion method based on the decision tree model as claimed in claim 3, characterized in that: In the step S4, when the base station executes the instruction and adjusts the enabled state of the RedCap function, the central control unit preferentially turns on the RedCap function of the high-priority non-preset neighboring area according to the judgment result of the decision tree model to distribute the load.

6. The RedCap terminal access diversion method based on the decision tree model as claimed in claim 5, characterized in that: In the step S4, when the base station executes the instruction and adjusts the enabled state of the RedCap function, if the high priority cell is unavailable or congested, the medium priority and low priority cells are considered in turn to gradually expand the coverage of the RedCap function.

7. The RedCap terminal access diversion method based on the decision tree model as claimed in claim 3, characterized in that: In the step S4, the base station executes the instruction and adjusts the RedCap function to be enabled, and there is a process of closing the neighboring cell RedCap, which specifically includes: Set the release threshold value, which is lower than the congestion alarm threshold, to determine whether the preset RedCap cell has returned to normal; When the status of a preset RedCap cell drops below the release threshold, the system checks for RedCap users in non-preset neighboring cells; If there is no RedCap user, turn off the RedCap function of the corresponding neighboring area.

8. The RedCap terminal access diversion method based on a decision tree model according to any one of claims 3 to 7, characterized in that: The decision tree model includes: The root node is used to determine whether the proportion of RedCap terminals in the congestion alarm cell exceeds the decision threshold. If so, it enters branch 1 for evaluation. If not, it ends the evaluation and does not enable the neighboring cell RedCap function. Branch 1, which contains decision variables 1 and 2 to consider the number of users and resource utilization; Decision variable 1: the number of users in the neighboring area. The number of users determines whether to enable the RedCap function. If the number of users exceeds the adaptive user threshold, the function is disabled. If the number of users does not exceed the adaptive user threshold, the function is enabled. Decision variable 2: RB wireless resource utilization rate, which evaluates the resource shortage degree. If it exceeds the adaptive RB utilization rate threshold, it will not be enabled; if it does not exceed the threshold, it will continue.

9. The RedCap terminal access diversion method based on the decision tree model as claimed in claim 8, characterized in that: When the number of users and the RB utilization rate are both moderate or low, the decision tree model has branch 2, and decision variable 3 exists in branch 2 to consider network performance; Decision variable 3: RRC access success rate, evaluates network access performance. If it is lower than the adaptive RRC access success rate threshold, it will not be enabled. If it exceeds, it will continue.

10. The RedCap terminal access diversion method based on the decision tree model as claimed in claim 9, characterized in that: When the RRC access success rate is moderate or high, the decision tree model has branch 3, and decision variables 4 and 5 exist in branch 3 based on geographic location and historical data; Decision variable 4: Geographic location, the priority is determined according to importance, among which important geographical locations are determined with high priority, and general geographical locations enter the decision variable 5 for judgment; Decision variable 5: Historical data. The cell priority is evaluated based on recent congestion conditions and historical performance. If congestion has occurred within 3 days, it is set to low priority, and if congestion has not occurred within 3 days, it is set to medium priority.

Images