Wireless resource scheduling method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a wireless resource scheduling method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring service association data between user equipment and a base station; according to the service association data, predicting a service demand between the user equipment and the base station, and generating a target radio resource scheduling policy; the target radio resource scheduling policy is used for indicating the allocation of radio resources in the communication process of the user equipment and the base station. By adopting the method, the wireless resource utilization rate can be improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a wireless resource scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In wireless communication systems, resource allocation directly affects network performance, especially in high-traffic and high-real-time business scenarios. In the remote control scenario of the Industrial Internet, services often have requirements such as low latency and high reliability, which rely on the accuracy and dynamic adjustment capabilities of resource allocation to achieve.

[0003] However, existing resource allocation technologies are usually based on fixed rules or static strategies. This static allocation method leads to low resource utilization, insufficient spectrum utilization, and inability to adapt to dynamic changes in user needs. Especially under high load or large fluctuations in business demand, system throughput and service quality will be affected.

[0004] Therefore, in the related art, there is a problem of low wireless resource utilization. Summary of the invention

[0005] Based on this, it is necessary to provide a wireless resource scheduling method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve wireless resource utilization in response to the above technical problems.

[0006] In a first aspect, the present application provides a wireless resource scheduling method, including:

[0007] Acquiring service association data between user equipment and base station;

[0008] The service demand between the user equipment and the base station is predicted according to the service association data, and a target wireless resource scheduling strategy is generated; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

[0009] In one of the embodiments, the service-related data includes at least one of wireless link status data, network status data, service status data and user status data.

[0010] In one of the embodiments, predicting the service demand between the user equipment and the base station according to the service association data and generating a target wireless resource scheduling strategy includes:

[0011] Inputting the wireless link status data, the network status data, the service status data and the user status data into a pre-trained scheduling strategy generation model, and outputting the target wireless resource scheduling strategy;

[0012] The target wireless resource scheduling strategy is the pre-trained scheduling strategy generation model, which predicts the service demand between the user equipment and the base station based on the wireless link status data, the network status data, the service status data and the user status data to generate the wireless resource scheduling strategy.

[0013] In one embodiment, the step of inputting the wireless link status data, the network status data, the service status data, and the user status data into a pre-trained scheduling strategy generation model and outputting the target wireless resource scheduling strategy includes:

[0014] Determining a real-time radio link status between the user equipment and the base station;

[0015] The target wireless resource scheduling strategy is generated according to the predicted service rate demand data and / or the real-time wireless link status.

[0016] In one of the embodiments, determining the real-time radio link status between the user equipment and the base station includes:

[0017] extracting, according to the radio link state data, a channel feature corresponding to a channel between the user equipment and the base station;

[0018] The real-time wireless link status is determined according to the channel characteristics.

[0019] In one of the embodiments, the service status data includes a service type corresponding to the service, the target wireless resource scheduling strategy includes a first strategy, and the generating of the target wireless resource scheduling strategy according to the predicted service rate requirement data and / or the real-time wireless link status includes:

[0020] Determine the service demand priority corresponding to the service type; the service demand priority is used to characterize the urgency corresponding to the service type;

[0021] The first strategy is generated according to the service demand priority and the service rate demand data; the first strategy is used to allocate corresponding resource scheduling priorities to the service.

[0022] In one of the embodiments, the target wireless resource scheduling strategy further includes a second strategy, wherein generating the target wireless resource scheduling strategy according to the predicted service rate demand data and / or the real-time wireless link status includes:

[0023] The second strategy is generated according to the real-time wireless link status and the service rate requirement data; the second strategy is used to adjust the resource block allocation of the service.

[0024] In one of the embodiments, the target wireless resource scheduling strategy further includes a third strategy, wherein the target wireless resource scheduling strategy is generated according to the predicted service rate demand data and / or the real-time wireless link status, including:

[0025] The third strategy is generated according to the real-time wireless link state; the third strategy includes a high-order modulation and coding strategy or a low-order modulation and coding strategy; the real-time wireless link state corresponding to the high-order modulation and coding strategy is better than the real-time wireless link state corresponding to the low-order modulation and coding strategy.

[0026] In a second aspect, the present application further provides a wireless resource scheduling device, including:

[0027] An acquisition module, used to acquire service association data between user equipment and a base station;

[0028] A generation module is used to predict the service demand between the user equipment and the base station according to the service association data, and generate a target wireless resource scheduling strategy; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

[0029] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the above method are implemented.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0031] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0032] The above-mentioned wireless resource scheduling method, device, computer equipment, computer-readable storage medium and computer program product obtain the service association data between the user equipment and the base station; based on the service association data, the service demand between the user equipment and the base station is predicted to generate a target wireless resource scheduling strategy; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

[0033] In this way, the future service demand between the user equipment and the base station is dynamically predicted through the service association data between the user equipment and the base station, so as to generate a target wireless resource scheduling strategy for indicating the allocation of wireless resources during the communication between the user equipment and the base station, so as to realize the dynamic adjustment of the scheduling strategy, optimize the spectrum utilization, avoid potential network congestion and insufficient bandwidth, meet the needs of high real-time services, and improve the utilization rate of wireless resources by analyzing the service association status and predicting the service demand in real time. The wireless resource allocation scheme based on fixed rules or static strategies in the related technology is solved, which leads to low utilization rate of wireless resources, difficulty in responding to channel changes in real time, insufficient use of spectrum, and inability to adapt to dynamic changes in user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A schematic diagram of a flow chart of a wireless resource scheduling method in an embodiment;

[0036] Figure 2 A schematic diagram of a flow chart of steps for outputting a target wireless resource scheduling strategy in an embodiment;

[0037] Figure 3 A schematic diagram of a flow chart of yet another wireless resource scheduling method in an embodiment;

[0038] Figure 4 is a flow chart of a wireless resource scheduling method in another embodiment;

[0039] Figure 5 is a structural block diagram of a wireless resource scheduling device in an embodiment;

[0040] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0043] In one embodiment, Figure 1 As shown, a wireless resource scheduling method is provided, which can be applied to a computer device. It can be understood that the computer device can be a terminal, a server, or a system including a terminal and a server, such as a wireless communication system. This embodiment is illustrated by applying the method to a wireless communication system, and the method includes the following steps:

[0044] Step S110: Acquire service association data between the user equipment and the base station.

[0045] The service-associated data may refer to data associated with a service between a user equipment (UE) and a base station.

[0046] In some embodiments, the service-associated data includes at least one of wireless link status data, network status data, service status data, and user status data.

[0047] The wireless link status data refers to data used to represent the wireless link status.

[0048] The network status data refers to data used to represent the network status.

[0049] The business status data refers to data used to represent the business status.

[0050] The user status data refers to data used to represent the user status.

[0051] In a specific implementation, a wireless communication system (hereinafter referred to as the system) can obtain service-related data between a user device and a base station. Further, the system can collect service-related data between the user device and the base station in real time in each time slot.

[0052] Step S120: predicting the service demand between the user equipment and the base station according to the service association data, and generating a target wireless resource scheduling strategy.

[0053] The target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

[0054] Among them, in wireless communication systems, resource allocation directly affects network performance. Reasonable spectrum, time and power allocation can improve the overall throughput of the system and ensure the user's quality of service (QoS). Especially in high-traffic and high-real-time business scenarios, resource allocation becomes more important.

[0055] The service requirement may be a service rate, specifically a transmission rate required by the current service.

[0056] The prediction of business demand may include at least one of the prediction of communication bandwidth, the prediction of latency, and the prediction of network jitter.

[0057] The service between the user equipment and the base station may refer to the service interacted and transmitted between the user equipment and the base station. For example, the service may include data collection and monitoring tasks, equipment control tasks, fault detection tasks, etc.

[0058] In a specific implementation, the system can predict the service demand between the user equipment and the base station based on the service-related data collected in real time to generate a target wireless resource scheduling strategy.

[0059] The system can input the real-time collected business-related data into the pre-trained AI (Artificial Intelligence) model, and dynamically predict the business needs between user equipment and base stations in the future through deep learning algorithms to generate target wireless resource scheduling strategies.

[0060] In this way, AI technology can be used to predict future business needs and adjust scheduling strategies in advance to avoid potential network congestion and insufficient bandwidth.

[0061] The future period of time may refer to a preset time period after the current time.

[0062] In the above-mentioned wireless resource scheduling method, the service association data between the user equipment and the base station is obtained; based on the service association data, the service demand between the user equipment and the base station is predicted to generate a target wireless resource scheduling strategy; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

[0063] In this way, the future service demand between the user equipment and the base station is dynamically predicted through the service association data between the user equipment and the base station, so as to generate a target wireless resource scheduling strategy for indicating the allocation of wireless resources during the communication between the user equipment and the base station, so as to realize the dynamic adjustment of the scheduling strategy, optimize the spectrum utilization, avoid potential network congestion and insufficient bandwidth, meet the needs of high real-time services, and improve the utilization rate of wireless resources by analyzing the service association status and predicting the service demand in real time. The wireless resource allocation scheme based on fixed rules or static strategies in the related technology is solved, which leads to low utilization rate of wireless resources, difficulty in responding to channel changes in real time, insufficient use of spectrum, and inability to adapt to dynamic changes in user needs.

[0064] In one embodiment, the service demand between the user equipment and the base station is predicted based on the service association data, and a target wireless resource scheduling strategy is generated, including: inputting the wireless link status data, network status data, service status data and user status data into a pre-trained scheduling strategy generation model, and outputting the target wireless resource scheduling strategy.

[0065] The target wireless resource scheduling strategy is a pre-trained scheduling strategy generation model, which predicts the service demand between the user equipment and the base station according to the wireless link status data, the network status data, the service status data and the user status data, and generates the wireless resource scheduling strategy.

[0066] Among them, the pre-trained scheduling strategy generation model is a trained AI model.

[0067] The wireless link status data includes at least one of a reference signal received power (RSRP), a signal to interference plus noise ratio (SINR), and a spectrum efficiency.

[0068] Among them, the reference signal received power reflects the signal strength of the wireless link and helps evaluate the reliability of the communication link.

[0069] Among them, SINR (Signal to Interference plus Noise Ratio) indicates signal quality and ensures link stability in noisy and interfering environments.

[0070] Among them, spectrum efficiency describes the effective data transmission capacity per unit spectrum bandwidth and is used to determine the utilization level of spectrum resources.

[0071] Among them, the network status data can be used to characterize the delay and network congestion of the wireless network.

[0072] The service status data may include at least one of the service type, rate requirement, and service priority of the user equipment.

[0073] The service type of the user equipment may refer to a service type corresponding to the service. In an Internet remote control scenario, the service may refer to a control task, and the service type may also refer to a control instruction type.

[0074] The business types may include critical tasks (such as critical control tasks: emergency stop signals) and ordinary tasks (such as ordinary monitoring tasks: status reports).

[0075] The service priority corresponds to the business type and can be used to indicate the priority of serving different business types. The service priority corresponding to the critical task is higher than the service priority corresponding to the common task.

[0076] Among them, rate requirement: evaluate the communication bandwidth requirement based on the complexity of the control task and the size of the data packet.

[0077] The user status data may include at least one of device location information and connection status.

[0078] Among them, device location information: For mobile industrial equipment, location data is collected in real time to evaluate changes in signal strength.

[0079] Among them, connection status: monitors the connection quality between the device and the network, such as the disconnection rate or the number of reconnections.

[0080] In a specific implementation, when the system predicts the service demand between the user device and the base station based on the service-related data and generates a target wireless resource scheduling strategy, the wireless link status data, network status data, service status data and user status data can be input into a pre-trained scheduling strategy generation model. The pre-trained scheduling strategy generation model predicts the service demand between the user device and the base station based on the wireless link status data, network status data, service status data and user status data to generate a target wireless resource scheduling strategy.

[0081] The technical solution of this embodiment inputs wireless link status data, network status data, service status data and user status data into a pre-trained scheduling strategy generation model, and outputs a target wireless resource scheduling strategy; the target wireless resource scheduling strategy is a pre-trained scheduling strategy generation model, which predicts the service demand between the user equipment and the base station based on the wireless link status data, network status data, service status data and user status data, and generates a wireless resource scheduling strategy.

[0082] In this way, the pre-trained scheduling strategy generation model can analyze the channel status in real time according to the input wireless link status data, network status data, service status data and user status data to dynamically predict future service needs, so as to dynamically adjust the scheduling strategy and more accurately generate the target wireless resource scheduling strategy, thereby reducing network congestion when multiple services are concurrent, and improving resource utilization.

[0083] In one embodiment, Figure 2 As shown, wireless link status data, network status data, service status data and user status data are input into a pre-trained scheduling strategy generation model, and a target wireless resource scheduling strategy is output, including the following steps:

[0084] Step S210: determining the real-time radio link status between the user equipment and the base station.

[0085] The real-time link status may be used to represent the real-time status of the wireless link between the user equipment and the base station.

[0086] In a specific implementation, when wireless link status data, network status data, service status data and user status data are input into a pre-trained scheduling strategy generation model and a target wireless resource scheduling strategy is output, the pre-trained scheduling strategy generation model can determine the real-time wireless link status between the user device and the base station based on the input data.

[0087] Step S220: generating a target wireless resource scheduling strategy according to the predicted service rate demand data and / or the real-time wireless link status.

[0088] The service rate requirement data may refer to the transmission rate required by the service, including potential changes in uplink and downlink service rates.

[0089] In a specific implementation, the pre-trained scheduling strategy generation model can predict the service rate demand data in the process of predicting the service demand between the user equipment and the base station based on the input data. The service rate demand data provides data support for the adjustment of the subsequent scheduling strategy, ensuring that the system can give priority to important services under resource constraints. In this way, the pre-trained scheduling strategy generation model can generate a target wireless resource scheduling strategy based on the predicted service rate demand data and / or the real-time wireless link status.

[0090] The technical solution of this embodiment determines the real-time wireless link status between the user equipment and the base station; generates a target wireless resource scheduling strategy based on the predicted service rate demand data and / or the real-time wireless link status. In this way, the service rate demand data predicted based on the wireless link status data, network status data, service status data and user status data provides data support for the subsequent adjustment of the wireless resource scheduling strategy, ensuring that the system can give priority to important services under resource constraints. At the same time, by analyzing the real-time wireless link status, the adjustment of the wireless resource scheduling strategy can be guided more accurately.

[0091] In one embodiment, determining the real-time wireless link status between the user equipment and the base station includes: extracting channel characteristics corresponding to the channel between the user equipment and the base station according to the wireless link status data; and determining the real-time wireless link status according to the channel characteristics.

[0092] In a specific implementation, the pre-trained scheduling strategy generation model can extract the channel characteristics corresponding to the channel between the user equipment and the base station based on the input wireless link status data during the process of determining the real-time wireless link status between the user equipment and the base station; the channel characteristics can characterize the quality of the wireless link between the user equipment and the base station, so that the real-time wireless link status can be determined based on the channel characteristics.

[0093] The technical solution of this embodiment extracts the channel characteristics corresponding to the channel between the user equipment and the base station according to the wireless link status data; and determines the real-time wireless link status according to the channel characteristics. In this way, the quality of the wireless link between the user equipment and the base station can be accurately judged by the channel characteristics extracted from the wireless link status data, thereby more accurately determining the real-time wireless link status between the user equipment and the base station.

[0094] In one embodiment, the service status data includes the service type corresponding to the service; the target wireless resource scheduling strategy includes a first strategy, which generates a target wireless resource scheduling strategy based on the predicted service rate requirement data and / or the real-time wireless link status, including: determining the service demand priority corresponding to the service type; the service demand priority is used to characterize the urgency corresponding to the service type; the first strategy is generated based on the service demand priority and the service rate requirement data; the first strategy is used to allocate corresponding resource scheduling priority to the service.

[0095] In actual applications, the first strategy can be named as a resource scheduling priority allocation strategy, which is used to allocate corresponding resource scheduling priorities to different services.

[0096] The business demand priority is used to characterize the urgency of the business type.

[0097] The service types may also include delay-sensitive tasks and delay-insensitive tasks.

[0098] Among them, the business demand priority of delay-sensitive tasks is higher than the business demand priority of delay-insensitive tasks.

[0099] In a specific implementation, the target wireless resource scheduling strategy includes a first strategy. In the process of generating the target wireless resource scheduling strategy, the pre-trained scheduling strategy generation model can generate a first strategy for allocating corresponding resource scheduling priorities to different services according to the service demand priority corresponding to the service type and the predicted service rate demand data, so that the system can adjust the current resource scheduling priority for the service according to the first strategy.

[0100] Specifically, different resource scheduling priorities can be dynamically assigned to services based on service demand priorities and service rate demand data to ensure that critical tasks or delay-sensitive tasks are given priority in resource competition. For example, the resource scheduling priority of delay-sensitive tasks is higher than that of delay-insensitive tasks.

[0101] For another example, suppose that a remote surgery is being performed in a medical IoT system. For high resource scheduling priority allocation: the transmission of control instructions for surgical instruments is the most critical business, and its business demand priority is the highest. From the perspective of business rate requirements, the operating instructions for controlling surgical instruments are complex, and the data packet size is moderate but requires extremely low latency and high bandwidth to ensure the accuracy of the operation. Therefore, this type of business will be assigned the highest resource scheduling priority, such as a resource scheduling priority of 1. When allocating resources, network resources will give priority to meeting the needs of this type of business to ensure the timely and accurate transmission of surgical instructions.

[0102] As for the medium resource scheduling priority allocation: In this medical Internet of Things system, the transmission of patient vital signs (such as heart rate, blood pressure, etc.) data is relatively important, but slightly inferior to surgical instrument control. Its business demand priority is medium. From the perspective of business rate requirements, the data packets of vital signs data are relatively small, the transmission frequency is high, and the bandwidth requirements are not as high as those of surgical instrument control, but a certain real-time guarantee is also required. Therefore, the resource scheduling priority can be allocated to 2. When allocating resources, resources will be reasonably allocated to it after high-priority services, such as ensuring a certain bandwidth and low latency, so that medical staff can monitor patients' vital signs in a timely manner.

[0103] For low resource scheduling priority allocation: In the administrative office system within the hospital, such as file transfer (non-urgent medical files) and other services, the business demand priority is low. The control tasks of these file transfers are simple, and the data packet size may be large (such as large documents), but the real-time requirements are not high. The resource scheduling priority can be allocated to 3. When allocating resources, resources will be considered for such services only after the resource requirements of high-priority and medium-priority services are met, and a certain degree of delay and lower bandwidth guarantee may be allowed.

[0104] In the technical solution of this embodiment, the service status data includes the service type corresponding to the service, and the target wireless resource scheduling strategy includes a first strategy, which determines the service demand priority corresponding to the service type; the service demand priority is used to characterize the urgency corresponding to the service type; the first strategy is generated according to the service demand priority and the service rate demand data; the first strategy is used to allocate the corresponding resource scheduling priority to the service. In this way, according to the priority of the service demand and the predicted service rate demand, different resource scheduling priorities are dynamically allocated, which can ensure that key services are given priority in resource competition, avoid excessive allocation of resources for low-rate demand services and low-demand priority services, and improve service quality while avoiding resource waste.

[0105] In one embodiment, the target wireless resource scheduling strategy also includes a second strategy, which generates a target wireless resource scheduling strategy based on predicted service rate demand data and / or real-time wireless link status, including: generating a second strategy based on real-time wireless link status and service rate demand data; the second strategy is used to adjust resource block allocation of the service.

[0106] In actual applications, the second strategy can be named as a resource block allocation strategy, which is used to allocate corresponding resource blocks to different services.

[0107] In a specific implementation, when the model generates a target wireless resource scheduling strategy based on the predicted service rate demand data and / or the real-time wireless link status, a second strategy for adjusting the resource block allocation of the service can be generated based on the real-time wireless link status and the service rate demand data. Thus, the system can adjust the current resource block allocation for the service based on the second strategy.

[0108] Among them, when the real-time wireless link status indicates that the wireless link is in good condition, more resource blocks can be allocated to increase the transmission rate; when the real-time wireless link status indicates that the wireless link is in a worse condition, resource blocks can be reasonably allocated to stabilize service transmission. For example, if the condition of the wireless link is too bad, no matter how many resources are allocated, the performance improvement is not obvious. In this case, more resources can be allocated to other users or services to improve the overall performance of the system. In this way, the real-time wireless link status and service rate demand data can be analyzed to achieve adaptive allocation of resources, ensuring that network performance can still be optimized when the link condition fluctuates.

[0109] For example, in a smart factory environment, there are industrial robot control services, environmental monitoring sensor data transmission services, and equipment status monitoring data transmission services. The industrial robot control service is a key service that requires high transmission rates and low latency to ensure precise control, and its service rate requirements are the highest. The environmental monitoring sensor data transmission service (such as temperature and humidity sensors) has a small data packet and has a slightly lower real-time requirement. The equipment status monitoring data transmission service (such as the power of the equipment, the operating time, etc.) has requirements in between.

[0110] When the wireless link is in good condition, 70% of the resource blocks can be allocated to the industrial robot control service, 20% of the resource blocks to the equipment status monitoring data transmission service, and 10% of the resource blocks to the environmental monitoring sensor data transmission service. This can fully utilize the good link to ensure efficient and accurate control of the industrial robot, while also taking into account the normal development of other services.

[0111] When allocating under the condition of link deterioration, such as when a large number of metal equipment moves or electromagnetic interference occurs in the factory, the link condition deteriorates. Due to link interference, it is difficult to ensure accurate control of the industrial robot control business even if more resource blocks are added. At this time, 40% of the resource blocks can be allocated to the industrial robot control business to try to maintain its basic operation and avoid dangerous actions of the robot. 30% of the resource blocks are allocated to the equipment status monitoring data transmission business, because equipment status monitoring is more important for timely detection of equipment failures and other situations, and there is still room for performance improvement when the link deteriorates. The remaining 30% of the resource blocks are allocated to the environmental monitoring sensor data transmission business, which can ensure the overall performance of the system in the case of link deterioration and give priority to the normal operation of services that are not very sensitive to link quality.

[0112] In some embodiments, if the state of the wireless link is good, the corresponding resource block size can be allocated according to the order of the service rate requirements of each service, that is, the service rate requirement and the resource block size are positively correlated. In the case of deterioration of the link state, it is also necessary to determine the allocation of corresponding resource blocks for different services based on the actual situation.

[0113] In the technical solution of this embodiment, the target wireless resource scheduling strategy also includes a second strategy, which is generated according to the real-time wireless link status and service rate demand data; the second strategy is used to adjust the resource block allocation of the service. In this way, by real-time monitoring of link status data combined with service rate demand forecast data, resources can be allocated more accurately. In addition, by real-time monitoring of link status and adjusting resource block allocation, service interruption caused by insufficient resources or deterioration of link quality can be prevented in advance, thereby improving network stability.

[0114] In one embodiment, the target wireless resource scheduling strategy also includes a third strategy, which generates the target wireless resource scheduling strategy based on the predicted service rate demand data and / or the real-time wireless link status, including: generating the third strategy based on the real-time wireless link status; the third strategy includes a high-order modulation and coding strategy or a low-order modulation and coding strategy; the real-time wireless link status corresponding to the high-order modulation and coding strategy is better than the real-time wireless link status corresponding to the low-order modulation and coding strategy.

[0115] Among them, the third strategy can be named as Modulation and Coding Scheme (MCS).

[0116] In a specific implementation, when the model generates a target wireless resource scheduling strategy based on predicted service rate demand data and / or real-time wireless link status, it can generate a third strategy based on the real-time wireless link status; the third strategy includes a high-order modulation and coding strategy or a low-order modulation and coding strategy; the real-time wireless link status corresponding to the high-order modulation and coding strategy is better than the real-time wireless link status corresponding to the low-order modulation and coding strategy.

[0117] That is, when the real-time wireless link status indicates that the link state of the wireless link is good, the third strategy is a high-order modulation and coding strategy; when the real-time wireless link status indicates that the link state of the wireless link is deteriorating, the third strategy is a low-order modulation and coding strategy. Thus, the system can adjust the current modulation and coding strategy for the service according to the third strategy.

[0118] Specifically, the system may obtain a current modulation and coding strategy corresponding to the service; and when the current modulation and coding strategy is different from the generated third strategy, the current modulation and coding strategy is adjusted to the third strategy.

[0119] For example, when the real-time wireless link status indicates that the link state of the wireless link is good, the output third strategy is a high-order modulation and coding strategy. If the current modulation and coding strategy is a low-order modulation and coding strategy, the system can adjust the current modulation and coding strategy to a high-order modulation and coding strategy to improve spectrum efficiency. When the real-time wireless link status indicates that the link state of the wireless link is deteriorating, the output third strategy is a low-order modulation and coding strategy. If the current modulation and coding strategy is a high-order modulation and coding strategy, the system can adjust the current modulation and coding strategy to a low-order modulation and coding strategy to enhance the robustness of the link and ensure the reliability of data transmission.

[0120] In the technical solution of this embodiment, the target wireless resource scheduling strategy also includes a third strategy, which is generated according to the real-time wireless link status; the third strategy includes a high-order modulation and coding strategy or a low-order modulation and coding strategy; the real-time wireless link status corresponding to the high-order modulation and coding strategy is better than the real-time wireless link status corresponding to the low-order modulation and coding strategy. In this way, according to the real-time wireless link status, the modulation and coding strategy is dynamically adjusted, which enables network resources to be more accurately allocated to each service, and not only can the modulation and coding strategy be adjusted more flexibly, but also the utilization rate of wireless resources can be effectively improved.

[0121] In one embodiment, Figure 3 As shown, a flow chart of a wireless resource scheduling method is provided, which can be applied to the remote control scenario of the industrial Internet. The services in this scenario have the characteristics of low latency and high reliability. According to the dynamic changes of uplink and downlink conditions and service needs in the wireless communication network, the artificial intelligence model is used to predict future service needs, adjust the resource allocation strategy in real time, and improve resource utilization efficiency and service quality assurance. The system for implementing the wireless resource scheduling method mainly includes four modules (units): data acquisition module (unit), AI analysis and service prediction module (unit), dynamic scheduling strategy adjustment module (unit), and feedback optimization module (unit).

[0122] Data acquisition unit:

[0123] The system collects service-related data between the user equipment (UE) and the base station in each time slot, mainly including: wireless link status data, service status data, user status data, and network status data.

[0124] The data acquisition module is responsible for storing these data and transmitting them to the AI ​​model (pre-trained scheduling strategy generation model) in real time for subsequent analysis.

[0125] AI Analysis and Business Forecasting Unit:

[0126] Construction of AI model: A model combining convolutional neural network (CNN) and recurrent neural network (RNN) is adopted. CNN is used to extract high-dimensional channel features, while RNN is used to capture the timing characteristics of historical link changes.

[0127] The wireless link state data may also include historical wireless link timing data, which may refer to wireless link state data collected within a preset time period before the current time. The RNN may extract timing features of historical link changes based on the input historical wireless link timing data.

[0128] In this way, through channel characteristics and link characteristics, combined with network status data, service status data and user status data, the service demand between user equipment and base station can be predicted more accurately, and the accuracy of the predicted service rate demand data can be improved. Therefore, by analyzing the channel status in real time and predicting the service rate demand, the scheduling strategy can be dynamically adjusted, the spectrum utilization can be optimized, and the problems of low resource allocation efficiency and difficulty in real-time response to channel changes in wireless communication systems in related technologies can be solved.

[0129] Business prediction: The business-related data collected in real time is input into the AI ​​model, and the business demand in the future is predicted through deep learning algorithms, including potential changes in uplink and downlink business rates.

[0130] Dynamic scheduling strategy adjustment unit:

[0131] Used to generate at least one target wireless resource scheduling strategy among the first strategy, the second strategy and the third strategy. For specific limitations, please refer to the specific limitations of a wireless resource scheduling method above.

[0132] Feedback Optimization Unit:

[0133] Performance feedback: The relevant data of network performance (such as actual uplink and downlink rates, packet loss rate, etc.) adjusted in real time according to the target wireless resource scheduling strategy are fed back to the AI ​​model. The AI ​​model is continuously updated and optimized based on this feedback data to improve the accuracy of business prediction.

[0134] Model update: Through continuous feedback optimization, the AI ​​model can gradually improve the accuracy of its business prediction and resource allocation in the future, allowing the system to dynamically adapt in a changing wireless environment.

[0135] In this way, in the remote control scenario of the industrial Internet, through deep learning (a combination of CNN and RNN), dynamic prediction of services based on historical link data and current network status, service status, and user status, the wireless resource allocation strategy is dynamically adjusted according to the prediction results, realizing dynamic optimization and adaptive adjustment of resource allocation, avoiding potential network congestion and insufficient bandwidth, improving service quality assurance capabilities and overall transmission efficiency, providing stable bandwidth and rate support for high-priority and critical services, meeting the needs of high-real-time services, ensuring low latency and high reliability of remote control tasks, meeting their business determinism requirements, reducing network congestion when multiple services are concurrent, and improving resource utilization. In addition, through closed-loop feedback, the data after the implementation of the wireless resource allocation strategy is fed back to the AI ​​model, so that it can continuously update model parameters and generate more effective wireless resource scheduling strategies.

[0136] Thus, in industrial Internet remote control scenarios, such as intelligent manufacturing and industrial control scenarios, the industrial Internet requires real-time and reliable data communication to ensure the efficient operation of automation equipment and the coordination of production processes. For example, in remote equipment monitoring services, fault detection services, and predictive maintenance services, the delay and stability of data transmission directly affect the production efficiency and safety of the system. This method can ensure stable transmission and low latency of key services, and is particularly suitable for high-priority, time-sensitive tasks in industrial environments.

[0137] Through real-time dynamic resource allocation, data transmission in wireless networks can be optimized, delays and packet loss can be reduced, the operating efficiency of equipment and the overall throughput of production lines can be improved, and production efficiency can be improved. In addition, effective resource management and dynamic scheduling can reduce unnecessary resource waste and reduce network maintenance and operating costs. At the same time, predictive maintenance can reduce equipment failures and downtime, further saving costs.

[0138] It can be understood that this solution can also be applied to multi-user, multi-service scenarios, and resources can be allocated more accurately in multi-user, multi-service scenarios, thereby improving the overall transmission efficiency of the network and the service quality assurance capabilities of key businesses, and solving the problems of inefficient resource allocation and difficulty in real-time response to channel changes in wireless communication systems in related technologies.

[0139] In another embodiment, Figure 4 As shown, a wireless resource scheduling method is provided, which is described by taking the method applied to a computer device as an example, and includes the following steps:

[0140] Step S402: Acquire service association data between the user equipment and the base station.

[0141] Step S404: inputting the wireless link status data, network status data, service status data and user status data into a pre-trained scheduling strategy generation model to predict the service demand between the user equipment and the base station.

[0142] Step S406: extracting channel characteristics corresponding to the channel between the user equipment and the base station according to the radio link state data.

[0143] Step S408: determining the real-time wireless link status between the user equipment and the base station according to the channel characteristics.

[0144] Step S410: Generate a target wireless resource scheduling strategy according to the predicted service rate demand data and / or the real-time wireless link status.

[0145] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a wireless resource scheduling method mentioned above.

[0146] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0147] Based on the same inventive concept, the embodiment of the present application also provides a wireless resource scheduling device for implementing the wireless resource scheduling method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more wireless resource scheduling device embodiments provided below can refer to the limitations of the wireless resource scheduling method above, and will not be repeated here.

[0148] In an exemplary embodiment, Figure 5 As shown, a wireless resource scheduling device is provided, including: an acquisition module 510 and a generation module 530, wherein:

[0149] The acquisition module 510 is used to acquire service association data between the user equipment and the base station.

[0150] The generation module 520 is used to predict the service demand between the user equipment and the base station according to the service association data, and generate a target wireless resource scheduling strategy; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

[0151] In one of the embodiments, the service-related data includes at least one of wireless link status data, network status data, service status data and user status data.

[0152] In one embodiment, the generation module 520 is specifically used to input the wireless link status data, the network status data, the service status data and the user status data into a pre-trained scheduling strategy generation model, and output the target wireless resource scheduling strategy; the target wireless resource scheduling strategy is the pre-trained scheduling strategy generation model, which predicts the service demand between the user equipment and the base station based on the wireless link status data, the network status data, the service status data and the user status data, and generates a wireless resource scheduling strategy.

[0153] In one of the embodiments, the generation module 520 is specifically used to determine the real-time wireless link status between the user equipment and the base station; and generate the target wireless resource scheduling strategy based on the predicted service rate demand data and / or the real-time wireless link status.

[0154] In one of the embodiments, the generating module 520 is specifically used to extract the channel characteristics corresponding to the channel between the user equipment and the base station according to the wireless link status data; and determine the real-time wireless link status according to the channel characteristics.

[0155] In one of the embodiments, the service status data includes a service type corresponding to the service, the target wireless resource scheduling strategy includes a first strategy, and the generation module 520 is specifically used to determine the service demand priority corresponding to the service type; the service demand priority is used to characterize the urgency corresponding to the service type; the first strategy is generated according to the service demand priority and the service rate requirement data; the first strategy is used to allocate corresponding resource scheduling priority to the service.

[0156] In one of the embodiments, the target wireless resource scheduling strategy also includes a second strategy, and the generation module 520 is specifically used to generate the second strategy based on the real-time wireless link status and the service rate requirement data; the second strategy is used to adjust the resource block allocation of the service.

[0157] In one embodiment, the target wireless resource scheduling strategy also includes a third strategy, and the generation module 520 is specifically used to generate the third strategy according to the real-time wireless link status; the third strategy includes a high-order modulation and coding strategy or a low-order modulation and coding strategy; the real-time wireless link status corresponding to the high-order modulation and coding strategy is better than the real-time wireless link status corresponding to the low-order modulation and coding strategy.

[0158] Each module in the above-mentioned wireless resource scheduling device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0159] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store business-related data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a wireless resource scheduling method is implemented.

[0160] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0161] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0162] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0163] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0167] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A wireless resource scheduling method, characterized in that: The method comprises: Acquiring service association data between user equipment and base station; The service demand between the user equipment and the base station is predicted according to the service association data, and a target wireless resource scheduling strategy is generated; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

2. The method according to claim 1, characterized in that The service-related data includes at least one of wireless link status data, network status data, service status data and user status data.

3. The method according to claim 2, characterized in that The predicting the service demand between the user equipment and the base station according to the service association data and generating a target wireless resource scheduling strategy includes: Inputting the wireless link status data, the network status data, the service status data and the user status data into a pre-trained scheduling strategy generation model, and outputting the target wireless resource scheduling strategy; The target wireless resource scheduling strategy is the pre-trained scheduling strategy generation model, which predicts the service demand between the user equipment and the base station based on the wireless link status data, the network status data, the service status data and the user status data to generate the wireless resource scheduling strategy.

4. The method according to claim 3, characterized in that The step of inputting the wireless link status data, the network status data, the service status data and the user status data into a pre-trained scheduling strategy generation model and outputting the target wireless resource scheduling strategy comprises: Determining a real-time radio link status between the user equipment and the base station; The target wireless resource scheduling strategy is generated according to the predicted service rate demand data and / or the real-time wireless link status.

5. The method according to claim 4, characterized in that The determining the real-time radio link status between the user equipment and the base station includes: extracting, according to the radio link state data, a channel feature corresponding to a channel between the user equipment and the base station; The real-time wireless link status is determined according to the channel characteristics.

6. The method according to claim 4, characterized in that The service status data includes a service type corresponding to the service, the target wireless resource scheduling strategy includes a first strategy, and the generating of the target wireless resource scheduling strategy according to the predicted service rate requirement data and / or the real-time wireless link status includes: Determine the service demand priority corresponding to the service type; the service demand priority is used to characterize the urgency corresponding to the service type; The first strategy is generated according to the service demand priority and the service rate demand data; the first strategy is used to allocate corresponding resource scheduling priorities to the service.

7. The method according to claim 4, characterized in that The target wireless resource scheduling strategy also includes a second strategy, wherein the target wireless resource scheduling strategy is generated according to the predicted service rate demand data and / or the real-time wireless link status, including: The second strategy is generated according to the real-time wireless link status and the service rate requirement data; the second strategy is used to adjust the resource block allocation of the service.

8. The method according to claim 4, characterized in that The target wireless resource scheduling strategy also includes a third strategy, wherein the target wireless resource scheduling strategy is generated according to the predicted service rate demand data and / or the real-time wireless link status, including: The third strategy is generated according to the real-time wireless link state; the third strategy includes a high-order modulation and coding strategy or a low-order modulation and coding strategy; the real-time wireless link state corresponding to the high-order modulation and coding strategy is better than the real-time wireless link state corresponding to the low-order modulation and coding strategy.

9. A wireless resource scheduling device, characterized in that: The device comprises: An acquisition module, used to acquire service association data between the user equipment and the base station; A generation module is used to predict the service demand between the user equipment and the base station according to the service association data, and generate a target wireless resource scheduling strategy; the target wireless resource scheduling strategy is used to indicate the allocation of wireless resources during the communication between the user equipment and the base station.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

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

Images