A method and apparatus for processing a 5G signal, an electronic device, and a readable medium

Abstract

Embodiments of the present application provide a 5G signal processing method and device, electronic equipment and readable medium. The method comprises: receiving a 5G signal state message when the device accesses a 5G network; inputting the 5G signal state message into a preset neural network model to determine the splitting parameters output by the neural network model; dividing the 5G signal into at least one frequency band sub-signal stream based on the splitting parameters; assigning weights to the at least one frequency band based on the splitting parameters; and integrating the at least one frequency band sub-signal stream into a complete signal stream based on the weights of the frequency bands and sending the complete signal stream to a downstream device. Thus, the 5G signal can be more accurately split and processed, and the efficiency of 5G signal transmission can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of signal processing, in particular to a 5G signal processing method, a 5G signal processing device, an electronic device and a computer readable medium. BACKGROUND

[0002] With the rapid development of 5G technology, the demand for high-speed and low-latency communication is increasing, especially in application scenarios such as intelligent transportation, industrial automation and remote medical treatment. The stability and efficiency of signal transmission are required to be higher. The existing signal splitting technology mostly uses fixed algorithms to process and transmit signals, which cannot effectively cope with the interference brought by environmental changes and the diversity of signal characteristics. In the traditional splitting method, the signal is usually simply divided into multiple sub-signals, which has obvious shortcomings in spectrum utilization and processing efficiency. SUMMARY

[0003] The embodiments of the present application provide a 5G signal processing method, device, electronic device and computer readable storage medium to solve the problem of improving the transmission efficiency of 5G signals.

[0004] The embodiments of the present application disclose a 5G signal processing method, which comprises:

[0005] In the case of device accessing 5G network, receiving 5G signal state message;

[0006] Inputting the 5G signal state message into a preset neural network model to determine the splitting parameter output by the neural network model;

[0007] Based on the splitting parameter, the 5G signal is divided into at least one frequency band sub-signal stream;

[0008] Based on the splitting parameter, the at least one frequency band is allocated a weight;

[0009] Based on the weight of the frequency band, the at least one frequency band sub-signal stream is integrated into a complete signal stream and sent to the downstream device.

[0010] Optionally, the step of receiving 5G signal state message in the case of device accessing 5G network comprises:

[0011] In the case of device accessing 5G network, receiving at least one of signal strength, signal spectrum distribution, noise level and signal delay as 5G signal state message.

[0012] Optionally, the step of inputting the 5G signal state message into a preset neural network model to determine the splitting parameter output by the neural network model comprises:

[0013] Input at least one of the signal strength, the signal spectrum distribution, the noise level, and the signal delay into a preset neural network model, obtain a beam splitting parameter output by the neural network model.

[0014] Optionally, the beam splitting parameter comprises a spectrum division strategy.

[0015] The step of dividing the 5G signal into at least one frequency band sub-signal stream based on the beam splitting parameter comprises:

[0016] Based on the spectrum division strategy, the 5G signal is decomposed in time domain and frequency domain to obtain at least one frequency band sub-signal stream.

[0017] Optionally, the step of assigning a weight to the at least one frequency band based on the beam splitting parameter comprises:

[0018] Extracting frequency characteristics and time domain variation trends in the at least one frequency band sub-signal stream;

[0019] Assigning a weight to the at least one frequency band based on the beam splitting parameter, the frequency characteristics and the time domain variation trends in the at least one frequency band sub-signal stream.

[0020] Optionally, the step of extracting the frequency characteristics and the time domain variation trends in the at least one frequency band sub-signal stream comprises:

[0021] At least one computing thread is used to extract the frequency characteristics and the time domain variation trends in the at least one frequency band sub-signal stream.

[0022] Optionally, the method further comprises:

[0023] Detecting at least one of the signal strength, the signal spectrum distribution, the noise level, and the signal delay of the output complete signal stream, and adjusting the model parameters in the neural network model.

[0024] Embodiments of the present application also provide a 5G signal processing device, the device comprising:

[0025] A state receiving module is configured to receive a 5G signal state message when a device accesses a 5G network.

[0026] A beam splitting parameter determining module is configured to input the 5G signal state message into a preset neural network model, and determine a beam splitting parameter output by the neural network model.

[0027] A signal dividing module is configured to divide a 5G signal into at least one frequency band sub-signal stream based on the beam splitting parameter.

[0028] a weight distribution module, configured to distribute weights to the at least one frequency band based on the beam splitting parameter;

[0029] a signal sending module, configured to integrate the sub-signal streams of the at least one frequency band into a complete signal stream based on the weights of the frequency bands, and send the complete signal stream to a downstream device.

[0030] Optionally, the state receiving module comprises:

[0031] a state message obtaining sub-module, configured to receive at least one of a signal strength, a signal spectrum distribution, a noise level, and a signal delay as a 5G signal state message in a case where the device accesses the 5G network.

[0032] Optionally, the beam splitting parameter determining module comprises:

[0033] a beam splitting parameter obtaining sub-module, configured to input at least one of the signal strength, the signal spectrum distribution, the noise level, and the signal delay into a preset neural network model, and obtain a beam splitting parameter output by the neural network model.

[0034] Optionally, the beam splitting parameter comprises a spectrum division strategy.

[0035] The signal splitting module comprises:

[0036] a sub-signal stream obtaining sub-module, configured to split the 5G signal in time domain and frequency domain based on the spectrum division strategy, and obtain sub-signal streams of at least one frequency band.

[0037] Optionally, the weight distribution module comprises:

[0038] an information extracting sub-module, configured to extract frequency characteristics and time domain variation trends in the sub-signal streams of the at least one frequency band;

[0039] a frequency band weight distribution sub-module, configured to distribute weights to the at least one frequency band based on the beam splitting parameter, the frequency characteristics, and the time domain variation trends in the sub-signal streams of the at least one frequency band.

[0040] Optionally, the information extracting sub-module comprises:

[0041] a thread extracting unit, configured to extract the frequency characteristics and the time domain variation trends in the sub-signal streams of the at least one frequency band by using at least one computing thread.

[0042] Optionally, the apparatus further comprises:

[0043] The model parameter adjustment module is configured to detect at least one of signal strength, signal spectrum distribution, noise level, and signal delay of the output complete signal stream, and adjust model parameters in the neural network model.

[0044] The embodiment of the present application also discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus.

[0045] The memory is used for storing a computer program.

[0046] The processor is used for executing the program stored on the memory, and realizes the method as described in the embodiment of the present application.

[0047] The embodiment of the present application also discloses one or more computer readable media having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method as described in the embodiment of the present application.

[0048] The embodiment of the present application has the following advantages:

[0049] The method for processing 5G signals provided by the embodiment of the present application can receive a 5G signal state message in the case of device access to a 5G network, input the 5G signal state message into a preset neural network model, determine the splitting parameters output by the neural network model, divide the 5G signal into at least one frequency band sub-signal stream based on the splitting parameters, assign weights to the at least one frequency band based on the splitting parameters, and integrate the at least one frequency band sub-signal stream into a complete signal stream based on the weights of the frequency bands and send the complete signal stream to a downstream device. Therefore, the 5G signal can be more accurately split and processed, and the efficiency of 5G signal transmission can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 is a step flowchart of the method for processing 5G signals provided in the embodiment of the present application;

[0051] Figure 2 is a structural block diagram of the processing device for 5G signals provided in the embodiment of the present application;

[0052] Figure 3 is a block diagram of the electronic device provided in the embodiment of the present application;

[0053] Figure 4 is a schematic diagram of the computer readable medium provided in the embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the above objectives, characteristics and advantages of the present application more apparent, further specific embodiments will be described in detail with reference to the accompanying drawings and specific embodiments.

[0055] Referring to Figure 1 , a step flow chart of a 5G signal processing method provided in an embodiment of the present application is shown, which can specifically include the following steps:

[0056] Step 101, in the case of device accessing 5G network, receiving 5G signal state message;

[0057] It should be noted that the device can be an upstream device, which can refer to a device located upstream of the data transmission path in the communication network. It is usually responsible for sending data to downstream devices (such as user devices, routers or switches), and performing data processing, encoding, modulation and transmission. The upstream device can be various types of network devices, servers or intermediate nodes. In the embodiment of the present application, the 5G signal can be processed in the case of device accessing 5G network.

[0058] 5G signal can refer to the radio signals used by the fifth generation mobile communication technology (5G). These signals are transmitted through radio waves between base stations and user devices to achieve high-speed, low-latency communication. In the embodiment of the present application, the state information of the 5G signal can be received.

[0059] 5G signal state message can refer to various messages and indications used to report and monitor the state of wireless signals in 5G networks. These messages can enable network operators and users to understand the current network connection quality, signal strength, data transmission status and other information. In the embodiment of the present application, the 5G signal state message can be received in the case of device accessing 5G network.

[0060] In the embodiment of the present application, the 5G signal state message can be received in the case of device accessing 5G network.

[0061] In a specific implementation, when the device first connects to the 5G network, it can first obtain the signal state information through a specific protocol. These information can be used to initialize the beam splitting parameters to ensure the best signal processing performance in a dynamic environment.

[0062] Among them, the specific protocol can be the RRC (Radio Resource Control, control plane) protocol, and the RRC protocol can obtain and report the signal state information by sending and receiving RRC messages.

[0063] The specific protocol can also be a NAS (Non-Access Stratum) protocol, which is located between the user equipment and the core network and is responsible for managing user sessions and mobility. Signal state information can be obtained and reported by sending and receiving NAS messages.

[0064] The specific protocol can also be other protocols that can be used to obtain 5G signal state messages, and the present application does not limit this.

[0065] Step 102, inputting the 5G signal state message into a preset neural network model to determine beamforming parameters output by the neural network model;

[0066] It should be noted that the beamforming parameters are parameters that need to be referred to in the case of dividing the received 5G signal into multiple sub-signals. The 5G signal state message can be input into a preset neural network model to determine the beamforming parameters output by the neural network model.

[0067] The beamforming parameters can include at least one of a beamforming direction, power allocation, and a spectrum division strategy.

[0068] In specific implementations, an adaptive beamforming algorithm can be used to dynamically adjust the beamforming parameters through deep learning and optimization algorithms. First, the signal receiving module collects 5G signal state messages and other data in real time and inputs them into the constructed neural network model. The neural network model can analyze historical data and current environmental characteristics to adjust the beamforming direction, power allocation, and spectrum division strategy in real time. In the embodiments of the present application, the neural network model can predict channel state information (CSI) through a gradient descent optimization algorithm and combine reinforcement learning techniques to quickly iterate the optimal beamforming scheme, thereby achieving adaptive adjustment of signal beamforming in a dynamic environment and improving transmission efficiency.

[0069] Gradient descent can be an optimization algorithm applied in the field of machine learning and deep learning, which can be used to minimize the loss function or cost function. The gradient descent algorithm can update the model parameters through iteration to gradually approach the optimal solution.

[0070] The application realizes adaptive beam splitting algorithm based on deep learning and intelligent optimization technology. By constructing a neural network model, real-time analysis is performed on the received signal characteristics. First, the deep learning model learns the characteristics of network environment changes based on historical transmission data, continuously optimizes model parameters, and improves the accuracy of signal beam splitting. During operation, the algorithm dynamically adjusts the direction, intensity and spectrum allocation strategy of signal beam splitting according to the real-time input signal characteristics to adapt to different transmission environments. This adaptability ensures stable transmission of signals in high-density or high-speed mobile scenarios, effectively improving the transmission efficiency and reliability of the system.

[0071] Step 103: Based on the beam splitting parameters, the 5G signal is divided into at least one frequency band sub-signal stream;

[0072] In the embodiment of the application, the 5G signal can be divided into at least one frequency band sub-signal stream based on the beam splitting parameters. In this way, the 5G signal can be segmented.

[0073] Wherein, the frequency band (Frequency Band) refers to the frequency range of radio waves such as 5G signals. Different frequency bands have different characteristics and application scenarios, and are suitable for various wireless communication and broadcast systems. In the embodiment of the application, the sub-signal stream can be in different frequency bands.

[0074] In the embodiment of the application, the beam splitting parameters can include parameters representing the sub-signal stream segmentation mode. By segmenting the 5G signal based on the beam splitting parameters, the beam splitting mode of the 5G signal can be more accurate, and the 5G signal as a whole can be more inclined to use the frequency band that has not been interfered for signal transmission, thereby improving the transmission efficiency of the 5G signal.

[0075] Step 104: Based on the beam splitting parameters, weights are assigned to the at least one frequency band.

[0076] In specific implementation, weight allocation can be performed based on beam splitting parameters, and the 5G signal as a whole is more inclined to use the frequency band that has not been interfered for signal transmission. For frequency bands that may be interfered, signal transmission power can be increased, thereby improving the transmission efficiency of the 5G signal.

[0077] Step 105: Based on the weights of the frequency bands, the sub-signal streams of the at least one frequency band are integrated into a complete signal stream and sent to downstream devices.

[0078] It should be noted that the downstream device can be a device located downstream of the data transmission path in the communication network. These devices usually receive data from upstream devices (such as base stations, routers or servers) and perform processing or forwarding. Downstream devices can be various types of terminal devices, network devices or intermediate nodes.

[0079] In the embodiments of the present application, the sub-signal streams of at least one frequency band can be integrated into a complete signal stream based on the weight of the frequency band and sent to the downstream device. In this way, the 5G signal as a whole can be more inclined to use the frequency band that is not interfered for signal transmission, and the signal transmission power of the frequency band that may be interfered can be improved, thereby improving the transmission efficiency of the 5G signal.

[0080] In a specific implementation, in the decomposition process of the sub-signal stream, the sub-signal stream can be decomposed in the time domain and the frequency domain based on short-time Fourier transform or wavelet transform. In the case of continuing to send the sub-signal stream, the sub-signal can be re-integrated into a complete signal stream and transmitted to the downstream device through an optimized encoding mode. The system can use a signal quality monitoring module to analyze the bit error rate, power intensity and delay of the output signal in real time, and input the feedback data into the adaptive optimization module for dynamic adjustment. For example, by adjusting the beam splitting parameters or reallocating the spectrum weight in real time, the stability and high transmission rate of the signal can be maintained in a high interference environment, thereby forming a closed-loop optimization mechanism.

[0081] Through the 5G signal processing method provided in the embodiments of the present application, in the case of device accessing 5G network, the 5G signal state message is received; the beam splitting parameters output by the preset neural network model are determined by inputting the 5G signal state message into the neural network model; the 5G signal is divided into at least one frequency band sub-signal stream based on the beam splitting parameters; weights are allocated to at least one frequency band based on the beam splitting parameters; and the sub-signal streams of at least one frequency band are integrated into a complete signal stream based on the weight of the frequency band and sent to the downstream device. In this way, the 5G signal can be more accurately processed by beam splitting, and the efficiency of 5G signal transmission can be improved.

[0082] In an embodiment of the present application, the step of receiving the 5G signal state message in the case of device accessing 5G network comprises:

[0083] S11, in the case of device accessing 5G network, at least one of signal intensity, signal spectrum distribution, noise level and signal delay is received as 5G signal state message.

[0084] It should be noted that the received signal strength (RSRP) is one of the key indicators for measuring the strength of the 5G signal. It can represent the power level of the received reference signal in dBm. A higher RSRP value indicates a stronger signal, and a lower RSRP value indicates a weaker signal. The device can obtain the RSRP value through the reference signal receiving power measurement function of the physical layer (L1). In the embodiments of the present application, the RSRP value can be sent to the network operator or user equipment as part of the 5G signal state message.

[0085] The signal spectrum distribution can refer to the distribution of the signal in the frequency domain, including spectrum occupation and spectrum efficiency. The device can obtain the signal spectrum distribution information through the spectrum analysis function of the physical layer (L1). In an embodiment of the present application, the signal spectrum distribution information can be sent to the network operator or user equipment as part of the 5G signal status message.

[0086] The noise level can refer to the noise component in the received signal, in units of dBm. A higher noise level indicates poorer signal quality, and a lower noise level indicates better signal quality. The device can obtain the noise level information through the noise measurement function of the physical layer (L1). In an embodiment of the present application, the noise level information can be sent to the network operator or user equipment as part of the 5G signal status message.

[0087] The signal delay can refer to the transmission time of the signal from the sending end to the receiving end, in units of milliseconds (ms). A lower signal delay indicates faster signal transmission speed, and a higher signal delay indicates slower signal transmission speed. The device can obtain the signal delay information through the delay measurement function of the physical layer (L1) and the data link layer (L2). In an embodiment of the present application, the signal delay information can be sent to the network operator or user equipment as part of the 5G signal status message.

[0088] In an embodiment of the present application, at least one of the signal strength, signal spectrum distribution, noise level, and signal delay can be received as a 5G signal status message when the device accesses the 5G network.

[0089] In an embodiment of the present application, the step of inputting the 5G signal status message into a preset neural network model to determine the beam splitting parameters output by the neural network model includes:

[0090] S21, input at least one of the signal strength, the signal spectrum distribution, the noise level, and the signal delay into a preset neural network model, and obtain the beam splitting parameters output by the neural network model.

[0091] In an embodiment of the present application, at least one of the signal strength, signal spectrum distribution, noise level, and signal delay can be input into a preset neural network model to obtain the beam splitting parameters output by the neural network model.

[0092] In an embodiment of the present application, the beam splitting parameters include a spectrum division strategy.

[0093] It should be noted that the spectrum division strategy can be a division method of the 5G signal to optimize spectrum utilization efficiency and improve system performance. In an embodiment of the present application, the 5G signal can be decomposed according to the spectrum division strategy.

[0094] The step of dividing the 5G signal into at least one frequency band sub-signal stream based on the beam splitting parameter includes:

[0095] S31, based on the frequency spectrum division strategy, the 5G signal is decomposed from the time domain and the frequency domain to obtain at least one frequency band sub-signal stream.

[0096] It should be noted that the time domain can refer to the representation of the signal on the time axis. In the time domain, the characteristics of the signal (such as amplitude, phase, waveform, etc.) change with time. Time domain analysis mainly focuses on the changes and fluctuations of the signal in time. In the embodiments of the present application, the 5G signal can be decomposed from the time domain.

[0097] The frequency domain refers to the representation of the signal on the frequency axis. In the frequency domain, the characteristics of the signal (such as frequency components, amplitude spectrum, phase spectrum, etc.) change with frequency. Frequency domain analysis mainly focuses on the frequency components and spectral characteristics of the signal. In the embodiments of the present application, the 5G signal can also be decomposed from the frequency domain.

[0098] In the embodiments of the present application, the 5G signal can be decomposed from the time domain and the frequency domain based on the frequency spectrum division strategy to obtain at least one frequency band sub-signal stream.

[0099] In specific implementation, advanced signal processing techniques such as short-time Fourier transform (STFT) and wavelet transform can be used to simultaneously decompose the received 5G signal from the time domain and the frequency domain. Specifically, the signal is first divided into multiple time windows by a window function to form sub-signal streams within the time windows. Then, the wavelet transform can be used to analyze the local frequency characteristics and time domain trends of the signal.

[0100] Among them, the short-time Fourier transform is a method of decomposing the signal into time and frequency components, which can be realized by sliding the window in time and performing Fourier transform on the signal in each window to obtain the distribution of the signal in time and frequency.

[0101] Wavelet transform is a method of decomposing a signal into wavelet components of different scales and positions, which can be realized by sliding a wavelet function in time and scale to analyze the signal in multiple resolutions.

[0102] The application can analyze and decompose the 5G signal from time domain and frequency domain at the same time through advanced signal processing methods such as short-time Fourier transform (STFT) and wavelet transform. In the time-frequency analysis process, the signal can be decomposed into multiple sub-signal streams of different frequency bands, and each sub-signal stream is processed independently within a specific frequency and time window. The instantaneous change characteristics of the signal can be effectively captured, and the potential interference source and noise distribution can be identified. The fine processing of time-frequency analysis can improve the accuracy of signal beam splitting, make the spectrum resource more efficiently utilized, and ensure that the data transmission rate and signal stability in different application scenarios are optimized.

[0103] In an embodiment of the application, the step of assigning weights to the at least one frequency band based on the beam splitting parameters comprises:

[0104] S41, extracting the frequency characteristics and time domain change trend in the sub-signal stream of the at least one frequency band;

[0105] It should be noted that the frequency characteristics refer to the distribution and characteristics of the signal on the frequency axis, including the frequency components, amplitude spectrum, phase spectrum, etc. of the signal. Frequency characteristic analysis mainly focuses on the frequency components and spectrum characteristics of the signal. In specific implementation, the frequency characteristics in the sub-signal stream of the at least one frequency band can be obtained.

[0106] The time domain change trend refers to the change and fluctuation of the signal on the time axis, including the waveform, amplitude, period, frequency, phase, etc. of the signal. Time domain analysis mainly focuses on the change and fluctuation of the signal in time. In the embodiment of the application, the time domain change trend in the sub-signal stream of the at least one frequency band can be obtained.

[0107] In the embodiment of the application, the frequency characteristics and time domain change trend in the sub-signal stream of the at least one frequency band can be extracted;

[0108] S42, assigning weights to the at least one frequency band based on the beam splitting parameters, the frequency characteristics and time domain change trend in the sub-signal stream of the at least one frequency band.

[0109] In specific implementation, the beam splitting parameters can include beam splitting direction, beam splitting strength, and spectrum allocation information. At the same time, the sub-signal stream can be analyzed to extract the frequency characteristics and time domain change trend therein.

[0110] Thereafter, the weight can be assigned to the at least one frequency band in consideration of the beam splitting parameter, the frequency characteristics in the sub-signal stream of the at least one frequency band, and the time domain variation trend. Thus, a higher weight can be assigned to a frequency band with higher beam splitting intensity, better frequency response, wider bandwidth, higher signal-to-noise ratio, stable amplitude variation, smaller phase variation, and shorter time delay, so that the 5G signal can be overall inclined to use the better frequency band for signal transmission, thereby improving the transmission efficiency. A higher weight can also be assigned to a frequency band with lower beam splitting intensity, lower frequency response, lower bandwidth, lower signal-to-noise ratio, unstable amplitude variation, larger phase variation, and longer time delay, so that the 5G signal can be better transmitted on the frequency band subject to interference, thereby improving the stability of transmission.

[0111] In a specific implementation, the decomposed frequency bands can be dynamically assigned weights to avoid resource waste of high-interference frequency bands, thereby realizing accurate decomposition of signals and maximizing spectrum utilization.

[0112] In an embodiment of the present application, the step of extracting the frequency characteristics and the time domain variation trend in the sub-signal stream of the at least one frequency band comprises:

[0113] S51, the frequency characteristics and the time domain variation trend in the sub-signal stream of the at least one frequency band are extracted by using at least one computing thread.

[0114] It should be noted that a thread is a basic unit for executing program code in an operating system. A process can contain multiple threads, and these threads share the resources (such as memory, file handles, etc.) of the process, but each thread has its own execution path and stack space. The concept and use of threads are very important in multitasking, concurrent programming, and performance optimization. In the embodiment of the present application, the extraction of the frequency characteristics and the time domain variation trend in the sub-signal stream can be realized by using multiple threads.

[0115] In an embodiment of the present application, the frequency characteristics and the time domain variation trend in the sub-signal stream of the at least one frequency band can be extracted by using at least one computing thread.

[0116] In a specific implementation, a high-efficiency parallel processing architecture can be constructed based on multi-threading and distributed computing technology. The received sub-signal streams are allocated to independent threads in a multi-core processor according to priority, and the signal processing tasks are run in parallel. A task scheduling algorithm, such as dynamic load balancing, can be used to reasonably allocate computing resources and prevent performance bottlenecks caused by overloading of some threads. In addition, through a distributed computing architecture, high-bandwidth signals can be processed in parallel across multiple nodes, significantly improving overall processing efficiency while ensuring low latency and high throughput.

[0117] Among them, the multi-core processor (Multi-Core Processor) can refer to a processor that integrates multiple processing cores (Core) on one chip. Each core can independently execute instructions, enabling parallel processing and improving computing power and system performance. Multi-core processors can overcome the performance bottleneck of single-core processors and improve overall processing capacity through parallel computing.

[0118] Task scheduling algorithm (Task Scheduling Algorithm) can refer to an algorithm used in the operating system to manage and allocate processor time to different tasks. Task scheduling algorithms can optimize system performance, improve resource utilization, ensure fairness and response time. Here are some task scheduling algorithms and their detailed explanations:

[0119] First-come, first-served (First-Come, First-Served, FCFS) can schedule tasks in the order of their arrival, with the first arriving task being executed first. It is simple to implement and has high fairness.

[0120] Shortest job first (Shortest Job First, SJF) can select the task with the shortest execution time to execute first. The average waiting time is the shortest, and the response time is relatively short.

[0121] Priority scheduling (Priority Scheduling) can assign a priority to each task, with higher priority tasks being executed first. It can be scheduled according to the importance and urgency of the task.

[0122] Round robin (Round Robin, RR) can allocate a fixed length of time slice to each task in order, and switch to the next task when the time slice is used up. It has high fairness, short response time, and is suitable for interactive systems.

[0123] Multi-level feedback queue (Multi-Level Feedback Queue, MLFQ) can arrange multiple queues according to priority, and move tasks between different queues, adjusting the priority according to the execution of the task. It combines the advantages of priority scheduling and round robin, and has strong adaptability.

[0124] Shortest remaining time first (Shortest Remaining Time First, SRTF) can select the task with the shortest remaining execution time to execute first, suitable for preemptive scheduling. The average waiting time is the shortest, and the response time is relatively short.

[0125] Highest Response Ratio Next (HRRN), which can choose the task with the highest response ratio to execute first, the response ratio = (waiting time + execution time) / execution time. Balances waiting time and execution time.

[0126] Fair Share Scheduling, which can allocate a certain processor time to each user or group, ensuring that each user or group obtains a fair share of resources. High fairness, suitable for multi-user environment.

[0127] Real-Time Scheduling, which can ensure that tasks are completed within the deadline, suitable for real-time systems. Meet real-time requirements, suitable for real-time applications.

[0128] Load Balancing Scheduling, which can evenly distribute tasks to multiple processors or computing nodes, optimizing system performance and resource utilization. Can improve system performance and resource utilization, suitable for distributed systems.

[0129] Distributed Computing Architecture can refer to distributing computing tasks to multiple independent computing nodes, communicating and cooperating through the network, and jointly completing complex computing tasks. Distributed computing architecture can improve the scalability, fault tolerance and performance of the system.

[0130] The present application sets up a parallel processing architecture based on multi-threaded computing and distributed computing technology, which can efficiently process multiple sub-signal streams. In 5G communication, each sub-signal stream needs to be processed in a very short time to ensure low latency and high efficiency. Through multi-threaded technology, each sub-signal stream can run in parallel in different processing units or cores, greatly improving the signal processing speed. At the same time, the distributed computing architecture can coordinate the processing tasks on multiple computing nodes, optimize the system resource utilization, and avoid the bottleneck problem of single computing unit. The parallel processing architecture not only shortens the signal processing time, but also ensures the real-time response performance of the entire system, meeting the strict requirements of 5G network for low latency and high throughput.

[0131] In an embodiment of the present application, the method further comprises:

[0132] S61, detecting at least one of the signal strength, signal spectrum distribution, noise level, and signal delay of the output complete signal stream, adjusting the model parameters in the neural network model.

[0133] It should be noted that the model parameters in the neural network model can refer to the parameters that need to be learned and optimized during the training process, which determine the structure and function of the neural network. The optimization of model parameters is the core task of neural network training, and through the optimization of model parameters, the neural network can learn the mapping relationship between input data and output labels. In the embodiments of the present application, the optimization of the neural network model can be realized by adjusting the model parameters. The model parameters can be one or more of the following parameters:

[0134] Weights, which are parameters connecting neurons in the neural network, can be used to calculate the weighted sum of input signals. The weights determine the degree of influence of input signals on neuron output.

[0135] Biases, which are additional parameters of each neuron in the neural network, can be used to adjust the activation threshold of the neuron. The bias determines the activation state of the neuron when there is no input signal.

[0136] Activation Function, which is a nonlinear transformation function of each neuron in the neural network, can be used to introduce nonlinear characteristics and enhance the expression ability of the neural network. Common activation functions include Sigmoid, Tanh, ReLU, Leaky ReLU, etc.

[0137] Loss Function, which is a function used to measure the difference between the output of the neural network and the true label, can be used to guide the optimization of model parameters. Common loss functions include Mean Squared Error (MSE), Cross-Entropy Loss, etc.

[0138] Optimizer, which is an algorithm used to update model parameters, can optimize model parameters by minimizing the loss function. Optimizers can include Gradient Descent, Stochastic Gradient Descent (SGD), Adam, RMSprop, etc.

[0139] In the embodiments of the present application, at least one of the signal strength, signal spectrum distribution, noise level, and signal delay of the output complete signal stream can be detected, and the model parameters in the neural network model can be adjusted.

[0140] In specific implementations, during signal transmission, the environment and network state can be continuously monitored, including channel quality, user mobility, and interference level, etc. By introducing intelligent optimization algorithms, such as multi-objective optimization models based on genetic algorithms, the system can dynamically optimize beam splitting parameters and resource allocation strategies under various constraints. At the same time, adaptive models can be trained using historical transmission data to continuously improve the prediction ability and response speed for complex channel environments, thereby achieving long-term stability and performance improvement of signal transmission.

[0141] Channel Quality can refer to the degree of interference and attenuation that signals experience during transmission. The quality of the channel directly affects the transmission effect and reception quality of signals. Channel quality can be evaluated by measuring signal-to-noise ratio (SNR), bit error rate (BER), received signal strength indicator (RSSI), and other indicators.

[0142] User Mobility can refer to the change in the location of user equipment in the network. User mobility affects the transmission path and channel quality of signals. The user's location changes and moving speed can be monitored in real time through positioning technology (such as GPS, base station positioning) and mobility prediction algorithms.

[0143] Interference Level can refer to the degree of interference that signals experience from other signals during transmission. The level of interference directly affects the transmission effect and reception quality of signals. Interference level can be evaluated by measuring interference-to-noise ratio (INR), interference power, and other indicators.

[0144] Intelligent Optimization Algorithm can refer to an algorithm that simulates the optimization process in nature (such as genetic algorithm, particle swarm optimization, ant colony algorithm, etc.) to find the optimal solution. Intelligent optimization algorithms can be applied to complex multi-objective optimization problems. In the process of signal transmission, intelligent optimization algorithms can be used to dynamically optimize beam splitting parameters and resource allocation strategies to improve signal transmission performance and stability.

[0145] Genetic Algorithm (GA) can be an optimization algorithm that simulates natural selection and genetic mechanisms. Through operations such as selection, crossover, and mutation, genetic algorithms can find optimal solutions in complex multi-objective optimization problems. In the process of signal transmission, genetic algorithms can be used to optimize beam splitting parameters and resource allocation strategies to improve signal transmission performance and stability.

[0146] Multi-Objective Optimization Model can refer to an optimization model that considers multiple objective functions and constraints simultaneously during the optimization process. Multi-Objective Optimization Model can find a balanced solution between multiple objectives. In the process of signal transmission, Multi-Objective Optimization Model can be used to optimize multiple objectives such as channel quality, user mobility, and interference level, to improve signal transmission performance and stability.

[0147] Adaptive Model can refer to a model that dynamically adjusts model parameters according to environmental changes and historical data. Adaptive Model can improve the adaptability of the model to complex environments and prediction accuracy. In the process of signal transmission, Adaptive Model can be used to dynamically adjust beam splitting parameters and resource allocation strategies to improve signal transmission performance and stability.

[0148] Historical Transmission Data can refer to historical data recorded during the process of signal transmission, including channel quality, user mobility, interference level, etc. Historical Transmission Data can be used to train Adaptive Model and optimization algorithms. In the process of signal transmission, Historical Transmission Data can be used to train Adaptive Model to improve the prediction ability and response speed of the model to complex channel environments.

[0149] Complex Channel Environment can refer to an environment affected by multiple interference and attenuation factors during the process of signal transmission. Complex Channel Environment will affect the transmission effect and reception quality of signals. Intelligent optimization algorithms and Adaptive Model can be used to dynamically optimize beam splitting parameters and resource allocation strategies to improve signal transmission performance and stability.

[0150] Through the above steps, the application can effectively improve the beam splitting processing capability of 5G signals, reduce delay, and improve spectrum utilization. The application not only optimizes the performance of 5G networks, but also provides users with more efficient and stable communication experience.

[0151] It should be noted that for the method embodiment, in order to simply describe, it is expressed as a series of action combinations, but those skilled in the art should know that the embodiments of the application are not limited by the order of the described actions, because according to the embodiments of the application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily necessary for the embodiments of the application.

[0152] Reference Figure 2, shows a structural block diagram of a 5G signal processing device provided in an embodiment of the present application, and can specifically include the following modules:

[0153] The state receiving module 201 is configured to receive a 5G signal state message in the case that the device accesses a 5G network.

[0154] The beam splitting parameter determining module 202 is configured to input the 5G signal state message into a preset neural network model, and determine a beam splitting parameter output by the neural network model.

[0155] The signal dividing module 203 is configured to divide the 5G signal into at least one frequency band sub-signal stream based on the beam splitting parameter.

[0156] The weight assigning module 204 is configured to assign a weight to the at least one frequency band based on the beam splitting parameter.

[0157] The signal sending module 205 is configured to integrate the at least one frequency band sub-signal stream into a complete signal stream based on the weight of the frequency band, and send the complete signal stream to a downstream device.

[0158] Optionally, the state receiving module includes:

[0159] The state message obtaining sub-module is configured to receive at least one of a signal strength, a signal spectrum distribution, a noise level, and a signal delay as the 5G signal state message in the case that the device accesses the 5G network.

[0160] Optionally, the beam splitting parameter determining module includes:

[0161] The beam splitting parameter obtaining sub-module is configured to input at least one of the signal strength, the signal spectrum distribution, the noise level, and the signal delay into a preset neural network model, and obtain a beam splitting parameter output by the neural network model.

[0162] Optionally, the beam splitting parameter includes a spectrum division strategy.

[0163] The signal dividing module includes:

[0164] The sub-signal stream obtaining sub-module is configured to decompose and process the 5G signal in a time domain and a frequency domain based on the spectrum division strategy, and obtain at least one frequency band sub-signal stream.

[0165] Optionally, the weight assigning module includes:

[0166] The information extracting sub-module is configured to extract a frequency characteristic and a time domain variation trend in the at least one frequency band sub-signal stream.

[0167] The frequency band weight distribution submodule is configured to distribute weights to the at least one frequency band based on the beam splitting parameter, the frequency characteristics and the time domain variation trend in the sub-signal stream of the at least one frequency band.

[0168] Optionally, the information extraction submodule comprises:

[0169] The thread extraction unit is configured to extract the frequency characteristics and the time domain variation trend in the sub-signal stream of the at least one frequency band by using at least one computing thread.

[0170] Optionally, the apparatus further comprises:

[0171] The model parameter adjustment module is configured to detect at least one of the signal intensity, the signal spectrum distribution, the noise level and the signal delay of the output complete signal stream, and adjust the model parameters in the neural network model.

[0172] The processing apparatus for 5G signals provided by the embodiment of the present application can, in the case that a device accesses a 5G network, receive a 5G signal state message, input the 5G signal state message into a preset neural network model, determine a beam splitting parameter output by the neural network model, divide a 5G signal into sub-signal streams of at least one frequency band based on the beam splitting parameter, distribute weights to the at least one frequency band based on the beam splitting parameter, integrate the sub-signal streams of the at least one frequency band into a complete signal stream based on the weights of the frequency bands, and send the complete signal stream to a downstream device. Thus, the 5G signal can be more accurately processed by beam splitting, and the efficiency of 5G signal transmission can be improved.

[0173] For the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts refer to the part of the method embodiment.

[0174] In addition, the embodiment of the present application also provides an electronic device, as shown in the figure, Figure 3 The processor 301, the communication interface 302 and the memory 303 can communicate with each other through the communication bus 304,

[0175] The memory 303 is configured to store a computer program.

[0176] The processor 301 is configured to execute the program stored in the memory 303 to implement the following steps:

[0177] In the case that a device accesses a 5G network, a 5G signal state message is received.

[0178] The 5G signal state message is input into a preset neural network model to determine a beam splitting parameter output by the neural network model.

[0179] splitting the 5G signal into at least one sub-signal stream of frequency band based on the splitting parameter;

[0180] assigning a weight to the at least one frequency band based on the splitting parameter;

[0181] integrating the at least one sub-signal stream of frequency band into a complete signal stream based on the weight of the frequency band and sending the complete signal stream to a downstream device.

[0182] Optionally, the step of receiving the 5G signal state message in the case that the device accesses the 5G network comprises:

[0183] receiving at least one of signal strength, signal spectrum distribution, noise level, signal delay as the 5G signal state message in the case that the device accesses the 5G network.

[0184] Optionally, the step of inputting the 5G signal state message into a preset neural network model to determine the splitting parameter output by the neural network model comprises:

[0185] inputting at least one of the signal strength, the signal spectrum distribution, the noise level, and the signal delay into a preset neural network model to obtain the splitting parameter output by the neural network model.

[0186] Optionally, the splitting parameter comprises a spectrum division strategy.

[0187] The step of splitting the 5G signal into at least one sub-signal stream of frequency band based on the splitting parameter comprises:

[0188] based on the spectrum division strategy, performing decomposition processing on the 5G signal in time domain and frequency domain to obtain at least one sub-signal stream of frequency band.

[0189] Optionally, the step of assigning a weight to the at least one frequency band based on the splitting parameter comprises:

[0190] extracting frequency characteristics and time domain variation trends in the at least one sub-signal stream of frequency band;

[0191] assigning a weight to the at least one frequency band based on the splitting parameter, the frequency characteristics and the time domain variation trends in the at least one sub-signal stream of frequency band.

[0192] Optionally, the step of extracting frequency characteristics and time domain variation trends in the at least one sub-signal stream of frequency band comprises:

[0193] extracting frequency characteristics and time domain variation trends in the at least one sub-signal stream of frequency band using at least one computing thread.

[0194] Optionally, the method further comprises:

[0195] detecting at least one of signal strength, signal spectrum distribution, noise level, signal delay of the output complete signal stream, and adjusting the model parameters in the neural network model.

[0196] The electronic device provided by the embodiment of the present application, in the case of device access to a 5G network, receives a 5G signal state message; inputs the 5G signal state message into a preset neural network model to determine the splitting parameters output by the neural network model; based on the splitting parameters, divides the 5G signal into at least one frequency band sub-signal stream; based on the splitting parameters, assigns weights to the at least one frequency band; and based on the weights of the frequency bands, integrates the at least one frequency band sub-signal stream into a complete signal stream and sends it to a downstream device. Thus, the 5G signal can be more accurately split and processed, and the efficiency of 5G signal transmission can be improved.

[0197] The communication bus mentioned above 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. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0198] The communication interface is used for communication between the terminal and other devices.

[0199] The memory can include a Random Access Memory (RAM) and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0200] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0201] As shown in the above embodiments, in another embodiment provided by the present application, a computer readable storage medium 401 is also provided, and the computer readable storage medium 401 stores instructions, and the instructions, when executed on a computer, cause the computer to perform the method for processing 5G signals described in the above embodiments. Figure 4

[0202] In another embodiment provided by the present application, a computer program product including instructions is also provided, and the instructions, when executed on a computer, cause the computer to perform the method for processing 5G signals described in the above embodiments.

[0203] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented 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, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can 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 can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk (SSD)) and the like. ​

[0204] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0205] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0206] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method for processing 5G signals, characterized in that, The method comprises the following steps: In the case of device access to a 5G network, a 5G signal state message is received; the 5G signal state message comprises at least one of signal strength, signal spectrum distribution, noise level, and signal delay; The 5G signal state message is input into a preset neural network model to determine beam splitting parameters output by the neural network model; the beam splitting parameters comprise a spectrum division strategy; Based on the beam splitting parameters, the 5G signal is divided into at least one frequency band sub-signal stream; Based on the beam splitting parameters, weights are assigned to the at least one frequency band; Based on the weights of the frequency bands, the at least one frequency band sub-signal stream is integrated into a complete signal stream and sent to a downstream device; The step of dividing the 5G signal into at least one frequency band sub-signal stream based on the beam splitting parameters comprises: Based on the spectrum division strategy, the 5G signal is decomposed and processed from the time domain and the frequency domain to obtain at least one frequency band sub-signal stream; The step of assigning weights to the at least one frequency band based on the beam splitting parameters comprises: Extracting frequency characteristics and time domain variation trends in the at least one frequency band sub-signal stream; Based on the beam splitting parameters, the frequency characteristics and time domain variation trends in the at least one frequency band sub-signal stream, weights are assigned to the at least one frequency band.

2. The method of claim 1, wherein, The step of extracting frequency characteristics and time domain variation trends in the at least one frequency band sub-signal stream comprises: At least one computing thread is used to extract frequency characteristics and time domain variation trends in the at least one frequency band sub-signal stream.

3. The method of claim 1, wherein, The method further comprises: Detecting at least one of signal strength, signal spectrum distribution, noise level, and signal delay of the output complete signal stream, and adjusting model parameters in the neural network model.

4. A processing device of a 5G signal, characterized by, The method comprises the following steps: A state receiving module is configured to receive a 5G signal state message in the case of device access to a 5G network; The 5G signal state message comprises at least one of signal strength, signal spectrum distribution, noise level, and signal delay; A beam splitting parameter determination module is configured to input the 5G signal state message into a preset neural network model to determine beam splitting parameters output by the neural network model; the beam splitting parameters comprise a spectrum division strategy; A signal division module is configured to divide a 5G signal into at least one frequency band sub-signal stream based on the beam splitting parameters; A weight assignment module is configured to assign weights to the at least one frequency band based on the beam splitting parameters; A signal sending module is configured to integrate the at least one frequency band sub-signal stream into a complete signal stream and send it to a downstream device based on the weights of the frequency bands; The signal division module comprises: A sub-signal stream acquisition sub-module is configured to decompose and process the 5G signal from the time domain and the frequency domain based on the spectrum division strategy to obtain at least one frequency band sub-signal stream; The weight assignment module comprises: An information extraction sub-module is configured to extract frequency characteristics and time domain variation trends in the at least one frequency band sub-signal stream; The frequency band weight distribution sub-module is configured to distribute weights to the at least one frequency band based on the beam splitting parameter, frequency characteristics in the sub-signal stream of the at least one frequency band, and time domain variation trend.

5. An electronic device, comprising: The device comprises 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; The memory is configured to store a computer program; The processor is configured to execute the program stored in the memory, and implement the method in any one of claims 1-3. 6.A computer readable medium having stored thereon instructions that, when executed by one or more processors, cause the processors to perform the method in any one of claims 1-3.

Images