Method and system for signal transmission using 5g antenna

Abstract

The application discloses a method and system for signal transmission by using 5G antenna, and relates to the field of signal transmission of 5G antenna, and comprises the following operation steps: S1: adaptive beamforming based on biological inspiration; S2: dynamic antenna topology; S3: dynamic spectrum sharing; S4: management and distribution based on holographic beam; S5: construction of hotspot area networking; S6: optimization of communication function based on current environment sensing. The method and system for signal transmission by using 5G antenna can integrate the communication behavior, equipment and use scene of users, can comprehensively describe the state of users based on this, can analyze the intention correlation and complementarity of multiple users in the same scene, can play the effect of overall allocation of beam resources and improvement of group network service experience, can avoid the conflict and waste of resources at the same time, can serve more users and provide higher quality service under the same resource condition.

Description

Technical Field

[0001] This invention relates to the field of signal transmission using 5G antennas, and particularly to a method and system for signal transmission using 5G antennas. Background Technology

[0002] 5G antennas are devices used to transmit and receive radio signals in fifth-generation mobile communication technology. They play a crucial role in 5G networks and have undergone significant technological upgrades and innovations compared to traditional 4G antennas. 5G antennas can adjust the phase and amplitude of each antenna element in the antenna array to form a high-gain beam in a specific direction, achieving directional signal transmission and improving signal strength and anti-interference capabilities. For example, in densely populated areas such as shopping malls and train stations, 5G antennas can precisely point the beam towards the user's location, enhancing signal coverage and transmission quality.

[0003] 5G antenna beamforming is mostly adjusted based on preset rules and simple environmental feedback. It lacks the ability to adjust the physical layout of 5G antennas according to the scenario, making it difficult to make more complex and precise decision-making. In complex scenarios such as cities, canyons, and indoors, it is easy for the signal to be weakened or interrupted due to obstacles. At the same time, its response speed to environmental changes is slow, making it difficult to adapt to dynamic environments in real time and make it difficult to make full use of spectrum resources, resulting in limited utilization and a lack of flexibility and precision in the allocation of spectrum resources.

[0004] Furthermore, traditional beam resource allocation is mostly static or semi-static. Once beam resources are allocated to users, they will not be easily changed for a period of time. Even if the network environment or user needs change, it is difficult to adjust in real time. When allocating resources, they can only be allocated based on simple service types, which cannot accurately match the actual needs of users, resulting in a decline in user experience and failing to provide stable and efficient communication services to users in different scenarios and needs.

[0005] Therefore, it is necessary to propose methods and systems for signal transmission using 5G antennas to solve the above problems. Summary of the Invention

[0006] The main objective of this invention is to provide a method and system for signal transmission using 5G antennas, which can effectively solve the problems in the background art.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0008] The method for signal transmission using 5G antennas includes the following steps:

[0009] S1: Based on bio-inspired adaptive beamforming, it draws on the perception and response mechanisms of organisms in nature. It analyzes the echo signals of environmental signals through 5G antennas to construct a signal map of the environment. Based on this signal map, it simulates the decision-making process of organisms to adjust the beam direction, width and intensity in real time.

[0010] S2: Dynamic antenna topology, which uses scalable and rotatable 5G antenna elements to achieve wide coverage, forming a fan-shaped topology structure to expand the signal coverage range;

[0011] S3: Dynamic spectrum sharing. Based on the determined spectrum range to be shared, the corresponding equipment is deployed, the signal quality of the spectrum is evaluated, and spectrum resources are allocated according to the evaluation. At the same time, during the sharing process, the spectrum usage is monitored in real time and it is determined whether the spectrum allocation needs to be adjusted.

[0012] S4: Based on holographic beams, management and allocation are carried out. Historical communication behavior of users is collected to learn and analyze user intentions. According to different user intentions and their corresponding business needs, the required beam resources are determined. At the same time, the mapping relationship between user intentions and beams is dynamically adjusted, and beam resources are allocated accordingly.

[0013] S5: The construction of hotspot area networking involves densely deploying small 5G base stations and 5G antennas that can cooperate with each other in urban hotspot areas to cover wide coverage beams including low-frequency bands and millimeter-wave beams in high-frequency bands.

[0014] S6: Optimize communication functions based on the perception of the current environment, including optimizing the allocation of spectrum resources in the current area and the modulation and coding methods of communication signals.

[0015] Preferably, step S1 specifically includes the following steps:

[0016] S101: Construct a 5G antenna array, receive the echo signal generated by the 5G antenna array, and extract its key features through signal processing algorithms. The key features include the amplitude, phase, time of arrival, and angle of arrival of the signal. Based on the extracted key features, combined with the known antenna position and parameters of the transmitted signal, construct an environmental signal feature set.

[0017] S102: Environmental signal map creation, which maps the environmental signal feature set to three-dimensional space to form an environmental signal map. The environmental signal map is represented by a grid, with each grid storing the signal feature information of the corresponding area. Different colors and markers are used to represent different signal features. Areas with high signal strength are represented by brighter colors, and areas with low signal strength are represented by darker colors. Areas where obstacles are located are marked with special markers to show the environmental conditions within the entire signal coverage area, including factors that affect signal propagation from facilities within the coverage area.

[0018] S103: Target user location and tracking. Based on the environmental signal map, locate the position of the target user equipment. By analyzing the signals fed back from the user equipment, the coordinates of the user equipment in three-dimensional space are determined by using the signal arrival time difference and arrival angle difference. For mobile user equipment, its movement trajectory is tracked by continuous signal monitoring. The Kalman filter algorithm is used to predict its future position based on the historical movement trajectory and speed of the user equipment.

[0019] S104: Beam parameter calculation. Based on the location of the user equipment and the environmental signal map, calculate the parameters required for beamforming, including beam direction, width, and gain. Using a ray tracing algorithm, simulate the signal propagation path from the antenna to the user equipment, find the optimal propagation path, and determine the beam direction. Based on the distance to the user equipment and signal attenuation, determine the beam gain to ensure sufficient signal strength. Based on the user equipment's moving speed and direction, adjust the beam width to ensure that the user equipment remains within the beam coverage area during movement.

[0020] S105: Beam adjustment and optimization. Based on the calculated beam parameters, the weights of each element in the 5G antenna array are adjusted, as well as the excitation amplitude and phase of the antenna elements, to generate the required beam. Beam performance is monitored in real time, and the beam is optimized based on signal quality feedback from user equipment. When a decline in signal quality is detected, the weights of the antenna elements are adjusted to achieve adaptive beam adjustment. The signal-to-noise ratio (SNR) Snr is used to evaluate signal quality. Let the signal power be P. s The noise power is P n The formula for calculating the signal-to-noise ratio is:

[0021]

[0022] Self-defined signal-to-noise ratio threshold Snr th When Snr < Snr th At that time, beam optimization and adjustment will be performed.

[0023] Preferably, step S3 specifically includes the following steps:

[0024] S301: Spectrum sensing. Based on usage requirements, determine the target frequency band range for spectrum sharing. Deploy spectrum sensing devices capable of receiving and analyzing signals within the target area. The sensing devices continuously monitor signal activity within the target frequency band, including signal strength, frequency, and modulation method. Analyze the monitored signals using signal processing algorithms to identify whether other systems or users are currently using the frequency band.

[0025] S302: Spectrum assessment, based on the sensed signal information, assesses the possible interference in different frequency bands, analyzes the degree of interference that existing signals may cause to new access systems and users, and the potential interference impact of new access behavior on existing systems;

[0026] S303: Resource allocation. Based on the service needs of different communication systems and users, determine their demand for spectrum resources in terms of quantity and quality. Based on spectrum assessment results and user needs, formulate a reasonable spectrum resource allocation strategy. The strategy includes priority-based allocation, fairness-based allocation, and auction-based allocation. Emergency communication services can be given higher priority and spectrum resources can be allocated to them first. According to the formulated allocation strategy, spectrum resources are allocated to various systems and users.

[0027] S304: Dynamic adjustment. During spectrum sharing, continuously monitor spectrum usage and communication performance of various systems and users in real time. By collecting feedback information, including signal quality indicators and data transmission rates, promptly understand the actual effect of spectrum sharing. Based on the monitoring data, determine whether spectrum allocation needs to be adjusted. When the interference level of a certain frequency band suddenly increases, leading to a decline in communication quality or a change in the service needs of a user, spectrum allocation adjustment is triggered. When it is determined that adjustment is necessary, a new resource allocation strategy is formulated and implemented based on the new spectrum perception and evaluation results.

[0028] Preferably, step S4 includes holographic beam pre-assignment based on intent understanding, specifically comprising the following steps:

[0029] S401: User intent learning, collecting users' historical communication behavior over a period of time, including the type of application used, timestamp of application use, duration of each use, and amount of data transmitted; obtaining relevant information about the user's device, including device type, operating system version, and hardware performance; and using sensor data from the user's device to obtain real-time scene information.

[0030] S402: Analyze users' historical communication behavior based on artificial intelligence and machine learning technologies; preprocess the collected historical communication behavior data to extract representative features, including calculating the frequency of use of various applications, average usage time, and data transmission volume trends in different time periods to reflect users' behavioral patterns in different time periods; combine scenario information with communication behavior features to understand users' intentions in different scenarios; and build a detailed user profile for each user based on the extracted features. The user profile includes the user's basic information, behavioral characteristics, and scenario preference information to describe the user's usage habits and potential needs and intentions.

[0031] S403: Model selection and training. For predicting the current user intent category, select decision tree, support vector machine, or Naive Bayes model. For regression problems that predict the user's possible future behavior and needs, use linear regression, decision tree regression, or neural network regression model. Divide the preprocessed and feature-extracted data into training and test sets, and use the training set to train and test the selected model.

[0032] S404: Model evaluation and optimization, evaluate the training results of the model, and further optimize the model based on the evaluation results;

[0033] S405: Beam pre-assignment, including intent and beam mapping: Establish the mapping relationship between user intent and holographic beam resources, and build a holographic beam map. Determine the required beam resource characteristics according to different user intents and corresponding business needs.

[0034] It also includes dynamic mapping adjustment: as user behavior and network environment change, the relationship between user intent and beam mapping is dynamically adjusted. When new application types appear in the network or user habits change, the demand for beam resources for different intents is reassessed and the markers in the holographic beam diagram are updated accordingly. At the same time, the dynamic changes of network resources are considered and the markers of beam resources are adjusted in real time to ensure the availability of pre-allocated beam resources in actual use.

[0035] S406: Pre-allocation implementation: Before the user actually makes a request, according to the user's intent and the beam mapping relationship, the corresponding beam resources are reserved in the holographic beam diagram for the predicted user intent, including setting relevant beam parameters such as center frequency, bandwidth, and transmit power, to ensure that they can be allocated to the user immediately when the user requests them.

[0036] Preferably, step S4 further includes holographic beam dynamic management, which performs more precise beam allocation and adjustment in the holographic beam diagram based on the user's business needs; collects application characteristic information based on 5G antennas, such as frame rate and resolution requirements for video applications and real-time requirements for game applications; and allocates the most suitable beam resources for different applications in the holographic beam diagram according to the characteristics. For high frame rate and high resolution video applications, beams with high bandwidth and low latency characteristics are allocated; for real-time games, beam stability and extremely low latency are ensured.

[0037] Preferably, in step S4, the data transmitted is encoded using the unique characteristics of the holographic beam, including the beam's phase, amplitude, and direction. A specific bit of the data is encoded as a specific beam phase offset. The receiving end recovers the data by parsing the beam's phase information. The holographic beam is used as a carrier of the encryption key, which is hidden in the beam's characteristics.

[0038] Preferably, in step S5, small 5G base stations and 5G antennas that can cooperate with each other are densely deployed in urban hotspot areas to form an ultra-dense network. Each small 5G base station and 5G antenna can use different frequency bands and beam patterns to cover wide coverage beams including low-frequency bands and millimeter-wave beams including high-frequency bands, in order to meet the needs of different users.

[0039] Preferably, in step S6, changes in the surrounding environment are sensed by analyzing the reflection, scattering, and diffraction characteristics of the signal, and spectrum resources are allocated to the current area based on the sensed changes.

[0040] Based on environmental awareness information, optimize the modulation and coding methods of communication signals.

[0041] A system for signal transmission using 5G antennas includes a data acquisition module, a data preprocessing and transmission module, an intent analysis module, and a beam management module. The data acquisition module is used to collect user communication behavior, device information, and scene perception data.

[0042] The data preprocessing and transmission module is used to perform preliminary cleaning and format unification on the collected data, and then transmit the data to the intent analysis module through an encrypted channel.

[0043] The intent analysis module integrates preprocessed communication behavior, device information, and scene awareness data, and extracts key features to discover potential user behavior patterns and intent change trends. Depending on the intent prediction task, it selects multiple machine learning and deep learning models for ensemble learning. For short-term intent prediction, it uses a long short-term memory network combined with an attention mechanism to capture long-term dependencies in time-series data and highlight key information. For long-term intent prediction, it combines a decision tree ensemble model, using large-scale historical data for training. The module continuously optimizes model parameters through cross-validation, establishes a real-time feedback mechanism, and updates the model online based on newly collected data. When the model's prediction accuracy decreases or user behavior patterns change significantly, it automatically triggers a model retraining and optimization process. The module categorizes the predicted results to determine the user's most likely intent category and calculates the probability of each intent category. Simultaneously, it prioritizes multiple possible intents based on self-defined intent urgency and resource requirements, prioritizing key needs when resources are limited.

[0044] The beam management module is used to build an updatable holographic beam database, and to formulate and implement user beam pre-allocation strategies based on the holographic beam database.

[0045] Preferably, the holographic beam database is used to store various characteristic information of different beams, including beam direction, bandwidth, delay, reliability, coverage, and interaction characteristics with different environments;

[0046] Based on user intent, and combined with beam features in the holographic beam database, a mapping relationship between intent and beam is established. For different types of user intent, beam resources with different bandwidth, latency, and stability requirements are matched respectively.

[0047] A beam pre-allocation strategy is formulated, which adopts a strategy that combines priority and fairness. For high-priority intentions, the best beam resources are allocated first, while ensuring that the basic needs of other users are also met. For multiple users with the same intention, beam resources are reasonably allocated according to the user's historical service quality and current network load, so as to avoid excessive concentration of resources in a few users. The beam resources pre-allocated to users are marked in the holographic beam database.

[0048] Compared with existing technologies, the present invention provides a method and system for signal transmission using a 5G antenna, which has the following beneficial effects:

[0049] 1. This method and system for signal transmission using 5G antennas utilizes bio-inspired adaptive beamforming, enabling the 5G antenna to adjust its beam according to environmental changes and user device movement. This achieves more efficient and stable signal transmission, simulating biological perception and decision-making mechanisms. The 5G antenna can construct a map by analyzing environmental signals, and based on this, it can adjust the beam direction, width, and intensity in real time and accurately, allowing it to more flexibly bypass obstacles and always precisely point to the target user device. Even in complex and changing environments, it can ensure stable signal transmission, greatly improving the effectiveness and accuracy of signal coverage.

[0050] 2. The method and system for signal transmission using 5G antennas can integrate user communication behavior, devices, and usage scenarios. Based on this, the user's state can be comprehensively characterized, enabling a more accurate understanding of the user's intent by combining the characteristics of 5G devices and scenario information. Therefore, it can provide more suitable beam resources, establish corresponding mapping relationships based on the precise needs of beam resource characteristics according to different intents, and allocate resources for different intents of the same service.

[0051] 3. The method and system for signal transmission using 5G antennas can analyze the intent relevance and complementarity of multiple users in the same scenario. It can coordinate the allocation of beam resources and improve the group network service experience, while avoiding resource conflicts and waste. It can serve more users and provide higher quality services under the same resource conditions.

[0052] 4. The method and system for signal transmission using 5G antennas can detect spectrum holes and allocate them to systems and users with demand, avoiding the waste of spectrum resources. It can flexibly allocate resources according to the dynamic changes in spectrum demand of different services, effectively alleviate the competition for spectrum resources among different systems, and achieve reasonable allocation of spectrum resources through sharing. At the same time, it can achieve more precise resource allocation based on service needs and spectrum conditions. For latency-sensitive services, it can allocate higher-quality spectrum resources to ensure service quality and improve overall network performance.

[0053] 5. The method and system for signal transmission using 5G antennas, through intent-based holographic beam pre-allocation, can, on the one hand, rapidly adjust the allocation of holographic beam resources according to real-time monitoring of changes in user intent to meet the usage needs under different intents; on the other hand, as the network environment changes in real time, such as signal interference or other users occupying the spectrum, it can be updated in real time and beam resources can be reallocated accordingly to ensure that users always obtain the best communication service. Attached Figure Description

[0054] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0055] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0056] Example 1:

[0057] like Figure 1 As shown, the method for signal transmission using a 5G antenna includes the following steps:

[0058] S1: Bio-inspired adaptive beamforming, drawing on the perception and response mechanisms of organisms in nature, analyzes the echo signals of environmental signals through a 5G antenna to construct a signal map of the environment. Based on this signal map, it simulates the decision-making process of organisms to adjust the beam direction, width, and intensity in real time. Specifically, it includes the following steps:

[0059] S101: Construct a 5G antenna array, receive the echo signal generated by the 5G antenna array, and extract its key features through signal processing algorithms. The key features include the amplitude, phase, time of arrival, and angle of arrival of the signal. Based on the extracted key features, combined with the known antenna position and parameters of the transmitted signal, construct an environmental signal feature set.

[0060] S102: Environmental signal map creation, which maps the environmental signal feature set to three-dimensional space to form an environmental signal map. The environmental signal map is represented by a grid, with each grid storing the signal feature information of the corresponding area. Different colors and markers are used to represent different signal features. Areas with high signal strength are represented by brighter colors, and areas with low signal strength are represented by darker colors. Areas where obstacles are located are marked with special markers to show the environmental conditions within the entire signal coverage area, including factors that affect signal propagation from facilities within the coverage area.

[0061] When new facilities emerge and atmospheric conditions change, the environmental signal map is updated by periodically transmitting detection signals and updating the feature set. The Kalman filter algorithm is used to determine the update frequency and range based on the frequency of environmental changes and their impact on signal propagation. For areas with frequent changes, the update frequency is increased; for relatively stable areas, the update frequency is decreased.

[0062] S103: Target user location and tracking. Based on the environmental signal map, locate the position of the target user equipment. By analyzing the signals fed back from the user equipment, the coordinates of the user equipment in three-dimensional space are determined by using the signal arrival time difference and arrival angle difference. For mobile user equipment, its movement trajectory is tracked by continuous signal monitoring. The Kalman filter algorithm is used to predict its future position based on the historical movement trajectory and speed of the user equipment.

[0063] S104: Beam parameter calculation. Based on the location of the user equipment and the environmental signal map, calculate the parameters required for beamforming, including beam direction, width, and gain. Using a ray tracing algorithm, simulate the signal propagation path from the antenna to the user equipment, find the optimal propagation path, and determine the beam direction. Based on the distance to the user equipment and signal attenuation, determine the beam gain to ensure sufficient signal strength. Based on the user equipment's moving speed and direction, adjust the beam width to ensure that the user equipment remains within the beam coverage area during movement.

[0064] S105: Beam adjustment and optimization. Based on the calculated beam parameters, the weights of each element in the 5G antenna array are adjusted, as well as the excitation amplitude and phase of the antenna elements, to generate the required beam. Beam performance is monitored in real time, and the beam is optimized based on signal quality feedback from user equipment. When a decline in signal quality is detected, the weights of the antenna elements are adjusted to achieve adaptive beam adjustment. The signal-to-noise ratio (SNR) Snr is used to evaluate signal quality. Let the signal power be P. s The noise power is P n The formula for calculating the signal-to-noise ratio is:

[0065]

[0066] Self-defined signal-to-noise ratio threshold Snr th When Snr < Snr th At that time, beam optimization and adjustment will be performed.

[0067] S2: Dynamic antenna topology, employing scalable and rotatable 5G antenna elements to achieve wide coverage, forming a fan-shaped topology structure to expand the signal coverage area. When an increase in user equipment density is detected in a specific area, such as during a rural market, the antenna elements are rearranged and combined through mechanical devices to form a denser array structure, enhancing the signal strength and data transmission capability of the area, thus significantly improving the signal transmission efficiency of 5G antennas in different scenarios.

[0068] S3: Dynamic spectrum sharing. Based on a defined spectrum range to be shared, corresponding equipment is deployed, the signal quality of the spectrum is assessed, and spectrum resources are allocated according to the assessment. Simultaneously, during the sharing process, spectrum usage is monitored in real time to determine whether adjustments to spectrum allocation are necessary. Specific operational steps include:

[0069] S301: Spectrum sensing. Based on usage requirements, determine the target frequency band range for spectrum sharing. Deploy spectrum sensing devices capable of receiving and analyzing signals within the target area. The sensing devices continuously monitor signal activity within the target frequency band, including signal strength, frequency, and modulation method. Analyze the monitored signals using signal processing algorithms to identify whether other systems or users are currently using the frequency band.

[0070] S302: Spectrum assessment. Based on the sensed signal information, assess the potential interference in different frequency bands, analyze the degree of interference that existing signals may cause to new access systems and users, and the potential interference impact of new access behavior on existing systems. For example, calculate the power spectral density of the interference signal to determine whether it exceeds a certain interference threshold, find underutilized or temporarily idle frequency bands in the spectrum, and statistically analyze the sensed spectrum occupancy to determine which frequency bands have a low occupancy rate within a certain time and space range and can be used by other systems and users. It is also necessary to assess the overall quality of the spectrum, such as the impact of signal transmission loss and multipath effects on spectrum transmission performance. The spectrum quality can be quantitatively assessed by calculating channel capacity and bit error rate.

[0071] S303: Resource allocation. Based on the service needs of different communication systems and users, determine their demand for spectrum resources in terms of quantity and quality. Based on spectrum assessment results and user needs, formulate a reasonable spectrum resource allocation strategy. The strategy includes priority-based allocation, fairness-based allocation, and auction-based allocation. Emergency communication services can be given higher priority and spectrum resources can be allocated to them first. According to the formulated allocation strategy, spectrum resources are allocated to various systems and users.

[0072] S304: Dynamic adjustment. During spectrum sharing, continuously monitor spectrum usage and communication performance of various systems and users in real time. By collecting feedback information, including signal quality indicators and data transmission rates, promptly understand the actual effect of spectrum sharing. Based on the monitoring data, determine whether spectrum allocation needs to be adjusted. When the interference level of a certain frequency band suddenly increases, leading to a decline in communication quality or a change in the service needs of a user, spectrum allocation adjustment is triggered. When it is determined that adjustment is necessary, a new resource allocation strategy is formulated and implemented based on the new spectrum perception and evaluation results.

[0073] S4: Based on holographic beam management and allocation, historical user communication behavior is collected to learn and analyze user intent. Based on different user intents and their corresponding business needs, the required beam resources are determined, and the mapping relationship between user intents and beams is dynamically adjusted. Beam resources are then allocated based on this, including holographic beam pre-allocation based on intent understanding. Specifically, this includes the following steps:

[0074] S401: User intent learning collects the user's historical communication behavior over a period of time, including the type of application used, timestamps of application usage, duration of each use, and data transmission volume; obtains relevant information about the user's device, including device type, operating system version, and hardware performance; uses sensor data from the user's device to obtain real-time scene information, obtains the user's geographical location through GPS positioning, and combines map information to determine whether the user is indoors or outdoors; uses accelerometer and gyroscope data to determine whether the user is stationary, walking, cycling, or using transportation; and uses an ambient light sensor to perceive ambient light intensity to assist in determining the user's environmental scene.

[0075] S402: Based on artificial intelligence and machine learning technologies, analyze users' historical communication behavior, preprocess the collected historical communication behavior data, and extract representative features, including calculating the changing trends of users' usage frequency, average usage time, and data transmission volume of various applications in different time periods. This reflects users' behavioral patterns in different time periods. For example, if it is found that users use video applications more frequently and for a longer average time between 7-10 pm on weekdays, it suggests that users have a strong intention to engage in video entertainment during this period. Combine scenario information with communication behavior features to understand users' intentions in different scenarios. For example, analyze users' application usage in different scenarios and extract scenario-related features. If it is found that users tend to use fitness applications and music playback applications more often in outdoor sports scenarios, and the data transmission volume is relatively small, this provides an important basis for understanding users' intentions in different scenarios. Based on the extracted features, build a detailed user profile for each user. The user profile includes the user's basic information, behavioral characteristics, and scenario preference information to describe the user's usage habits and potential needs and intentions.

[0076] S403: Model selection and training. For predicting the current user intent category, select decision tree, support vector machine, or Naive Bayes model. For regression problems that predict the user's possible future behavior and needs, use linear regression, decision tree regression, or neural network regression model. Divide the preprocessed and feature-extracted data into training and test sets, and use the training set to train and test the selected model.

[0077] S404: Model evaluation and optimization, evaluate the training results of the model, and further optimize the model based on the evaluation results;

[0078] S405: Beam pre-allocation, including intent and beam mapping: Establish the mapping relationship between user intent and holographic beam resources, and build a holographic beam map. Based on different user intents and corresponding business needs, determine the required beam resource characteristics. For video viewing intents, high-bandwidth, low-latency beam resources are required to ensure smooth video playback. For real-time game intents, in addition to high bandwidth and low latency, high reliability of the beams is also required to ensure accurate transmission of game data. According to the requirements, mark the beam resources that meet the conditions in the holographic beam map.

[0079] It also includes dynamic mapping adjustment: as user behavior and network environment change, the relationship between user intent and beam mapping is dynamically adjusted. When new application types appear in the network or user habits change, the demand for beam resources for different intents is reassessed and the markers in the holographic beam diagram are updated accordingly. At the same time, the dynamic changes of network resources are considered and the markers of beam resources are adjusted in real time to ensure the availability of pre-allocated beam resources in actual use.

[0080] S406: Pre-allocation implementation. Before the user actually makes a request, based on the user's intent and beam mapping relationship, corresponding beam resources are reserved in the holographic beam diagram for the predicted user intent. This includes setting relevant beam parameters, such as center frequency, bandwidth, and transmit power, to ensure that the beam can be immediately allocated to the user upon request. For example, if it is predicted that the user may start watching high-definition video at 8 pm, around 7:50 pm, beam resources that meet the requirements for high-definition video playback are marked in the holographic beam diagram, and the corresponding bandwidth and power are reserved, awaiting the user's request. For group users, such as at large event venues or office spaces, through analysis... By analyzing the shared intentions and behavioral patterns of a group, more efficient beam pre-allocation can be achieved. For example, at a concert, by analyzing the behavior of a large number of audience members, it can be predicted that most audience members may use their mobile phones to take photos and videos and share them on social media platforms during the climax of the performance. Based on this group intention, a set of beam resources suitable for this type of data transmission can be pre-allocated to the audience in this area in the holographic beam map. Multicast and broadcast methods can be used to optimize resource utilization efficiency and ensure the communication needs of group users. At the same time, the pre-allocated beam resources can be fine-tuned according to the device characteristics and needs of different users in the group to meet the service quality requirements of individual users.

[0081] It also includes dynamic holographic beam management, which performs more precise beam allocation and adjustment in the holographic beammap based on user business needs. For applications with high reliability requirements, it selects beam resources with low interference and stable signals in the holographic beammap and dynamically adjusts beam parameters to ensure that the stringent requirements of industrial control applications are met. It collects application characteristic information based on 5G antennas, such as frame rate and resolution requirements for video applications and real-time requirements for game applications. Based on these characteristics, it allocates the most suitable beam resources for different applications in the holographic beammap. For high frame rate and high resolution video applications, it allocates beams with high bandwidth and low latency characteristics; for real-time games, it ensures beam stability and extremely low latency.

[0082] It also includes using the unique characteristics of holographic beams, including the phase, amplitude, and direction of the beam, to encode the transmitted data. A certain bit of the data is encoded as a specific beam phase offset. The receiving end recovers the data by parsing the phase information of the beam. The holographic beam is used as a carrier of the encryption key, and the encryption key is hidden in the characteristics of the beam.

[0083] S5: The construction of hotspot area networking involves densely deploying small 5G base stations and 5G antennas that can cooperate with each other in urban hotspot areas to cover wide coverage beams including low-frequency bands and millimeter-wave beams in high-frequency bands.

[0084] In 5G antennas, a dedicated beam for the millimeter wave band is used for applications with extremely high bandwidth requirements. Targeting the characteristics of millimeter waves, adaptive beam adjustment and signal enhancement technologies are employed. When a user moves indoors with a millimeter wave-enabled device, the 5G antenna dynamically changes the direction and power of the millimeter wave beam based on the user's location and signal attenuation through adaptive beam adjustment. At the same time, signal enhancement technology is used to enhance the signal coverage and signal strength of the millimeter wave, solving the problem of weak penetration capability of millimeter waves.

[0085] In urban hotspots, small 5G base stations and 5G antennas that can cooperate with each other are densely deployed to form an ultra-dense network. Each small 5G base station and 5G antenna can use different frequency bands and beam patterns to cover wide coverage beams including low-frequency bands and millimeter-wave beams in high-frequency bands, in order to meet the needs of different users.

[0086] In ultra-dense networks, 5G antennas are used to achieve distributed beamforming. Through information exchange between different base stations and antennas, joint beamforming is achieved, further optimizing signal coverage and interference control. 5G antennas from different base stations can coordinate to adjust beams, avoiding mutual interference, while improving the overall network capacity and performance.

[0087] S6: Optimize communication functions based on the perception of the current environment, including optimizing the allocation of spectrum resources in the current area and the modulation and coding methods of communication signals;

[0088] By analyzing the reflection, scattering, and diffraction characteristics of signals, changes in the surrounding environment can be perceived. Based on the perceived changes, spectrum resources can be allocated to the current area. When the movement of devices, the flow and speed of vehicles are detected, in transportation hubs, 5G antennas can provide data support for traffic by sensing the position and speed of surrounding vehicles. At the same time, the perceived information can be used to adjust signal transmission strategies, such as providing a more stable beam for moving vehicles. Environmental perception information can be used to assist in beam adjustment and spectrum allocation. When a large number of people are perceived to be gathered in a certain area, the coverage and intensity of the beam can be adjusted according to the density and distribution of the crowd. At the same time, spectrum resources can be allocated in advance according to the movement trend of the crowd to ensure stable signal transmission for users during their movement.

[0089] Based on environmental awareness, the modulation and coding of communication signals are optimized. When a user is detected to be in a complex electromagnetic environment, a more robust modulation and coding scheme is adopted to improve the signal's anti-interference capability. When an obstacle is detected between the user and the antenna, the frequency and beam of the signal are automatically adjusted to adapt to signal attenuation and scattering. In underground parking lot scenarios, after sensing the distribution of vehicles in different parking spaces and the signal attenuation, the 5G antenna can adopt different modulation and coding methods for vehicles in different parking spaces to ensure stable communication between the vehicle and the network.

[0090] Example 2:

[0091] The system that uses 5G antennas for signal transmission includes a data acquisition module, a data preprocessing and transmission module, an intent analysis module, and a beam management module. The data acquisition module is used to collect user communication behavior, device information, and scene perception data.

[0092] The data preprocessing and transmission module is used to perform preliminary cleaning and format standardization on the collected data, and then transmits the data to the intent analysis module through an encrypted channel.

[0093] The intent analysis module integrates preprocessed communication behavior, device information, and scene-aware data, and extracts key features to discover potential user behavior patterns and intent change trends. Depending on the intent prediction task, it selects multiple machine learning and deep learning models for ensemble learning. For short-term intent prediction, it uses a long short-term memory network combined with an attention mechanism to capture long-term dependencies in time-series data and highlight key information. For long-term intent prediction, it combines a decision tree ensemble model, using large-scale historical data for training. Model parameters are continuously optimized through cross-validation, and a real-time feedback mechanism is established to update the model online based on newly collected data. When the model's prediction accuracy decreases or user behavior patterns change significantly, the model retraining and optimization process is automatically triggered. The results obtained from the model prediction are classified to determine the user's most likely intent category and calculate the probability of each intent category. Simultaneously, multiple possible intents are prioritized based on self-defined intent urgency and resource requirements to prioritize key needs when resources are limited.

[0094] The beam management module is used to build an updatable holographic beam database, and to formulate and implement user beam pre-allocation strategies based on the holographic beam database;

[0095] Holographic beam databases are used to store various characteristic information of different beams, including beam direction, bandwidth, delay, reliability, coverage, and interaction characteristics with different environments.

[0096] Based on user intent, and combined with beam features in the holographic beam database, a mapping relationship between intent and beam is established. For different types of user intent, beam resources with different bandwidth, latency, and stability requirements are matched respectively.

[0097] A beam pre-allocation strategy is formulated, which adopts a strategy that combines priority and fairness. For high-priority intentions, the best beam resources are allocated first, while ensuring that the basic needs of other users are also met. For multiple users with the same intention, beam resources are reasonably allocated according to the user's historical service quality and current network load, so as to avoid excessive concentration of resources in a few users. The beam resources pre-allocated to users are marked in the holographic beam database.

[0098] It should be noted that this invention relates to a method and system for signal transmission using a 5G antenna, and is used in accordance with this invention.

[0099] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for signal transmission using a 5G antenna, characterized in that: The following steps are included: S1: Based on bio-inspired adaptive beamforming, it draws on the perception and response mechanisms of organisms in nature. It analyzes the echo signals of environmental signals through 5G antennas to construct a signal map of the environment. Based on this signal map, it simulates the decision-making process of organisms to adjust the beam direction, width and intensity in real time. S2: Dynamic antenna topology, which uses scalable and rotatable 5G antenna elements to achieve wide coverage, forming a fan-shaped topology structure to expand the signal coverage range; S3: Dynamic spectrum sharing. Based on the determined spectrum range to be shared, the corresponding equipment is deployed, the signal quality of the spectrum is evaluated, and spectrum resources are allocated according to the evaluation. At the same time, during the sharing process, the spectrum usage is monitored in real time and it is determined whether the spectrum allocation needs to be adjusted. S4: Based on holographic beam management and allocation, historical user communication behavior is collected to learn and analyze user intent. Based on different user intents and their corresponding business needs, the required beam resources are determined, and the mapping relationship between user intents and beams is dynamically adjusted. Beam resources are then allocated based on this, including holographic beam pre-allocation based on intent understanding. Specifically, this includes the following steps: S401: User intent learning, collecting users' historical communication behavior over a period of time, including the type of application used, timestamp of application use, duration of each use, and amount of data transmitted; obtaining relevant information about the user's device, including device type, operating system version, and hardware performance; and using sensor data from the user's device to obtain real-time scene information. S402: Analyze users' historical communication behavior based on artificial intelligence and machine learning technologies; preprocess the collected historical communication behavior data to extract representative features, including calculating the frequency of use of various applications, average usage time, and data transmission volume trends in different time periods to reflect users' behavioral patterns in different time periods; combine scenario information with communication behavior features to understand users' intentions in different scenarios; and build a detailed user profile for each user based on the extracted features. The user profile includes the user's basic information, behavioral characteristics, and scenario preference information to describe the user's usage habits and potential needs and intentions. S403: Model selection and training. For predicting the current user intent category, select decision tree, support vector machine, or Naive Bayes model. For regression problems that predict the user's possible future behavior and needs, use linear regression, decision tree regression, or neural network regression model. Divide the preprocessed and feature-extracted data into training and test sets, and use the training set to train and test the selected model. S404: Model evaluation and optimization, evaluate the training results of the model, and further optimize the model based on the evaluation results; S405: Beam pre-assignment, including intent and beam mapping: Establish the mapping relationship between user intent and holographic beam resources, and build a holographic beam map. Determine the required beam resource characteristics according to different user intents and corresponding business needs. It also includes dynamic mapping adjustment: as user behavior and network environment change, the relationship between user intent and beam mapping is dynamically adjusted. When new application types appear in the network or user habits change, the demand for beam resources for different intents is reassessed and the markers in the holographic beam diagram are updated accordingly. At the same time, the dynamic changes of network resources are considered and the markers of beam resources are adjusted in real time to ensure the availability of pre-allocated beam resources in actual use. S406: Pre-allocation implementation: Before the user actually makes a request, according to the user's intent and the beam mapping relationship, the corresponding beam resources are reserved in the holographic beam diagram for the predicted user intent, including setting relevant beam parameters such as center frequency, bandwidth and transmit power, to ensure that they can be allocated to the user immediately when the user makes a request. S4 also includes dynamic holographic beam management, which performs more precise beam allocation and adjustment in the holographic beammap based on user business needs; it collects application characteristic information based on 5G antennas, such as frame rate and resolution requirements for video applications and real-time requirements for game applications, and allocates the most suitable beam resources for different applications in the holographic beammap according to the characteristics. For high frame rate and high resolution video applications, it allocates beams with high bandwidth and low latency characteristics; for real-time games, it ensures beam stability and extremely low latency. S4 also includes using the unique characteristics of the holographic beam, including the beam's phase, amplitude, and direction, to encode the transmitted data. A specific bit of the data is encoded as a specific beam phase offset. The receiving end recovers the data by parsing the beam's phase information. The holographic beam is used as the carrier of the encryption key, which is hidden in the beam's characteristics. S5: The construction of hotspot area networking involves densely deploying small 5G base stations and 5G antennas that can cooperate with each other in urban hotspot areas to cover wide coverage beams including low-frequency bands and millimeter-wave beams in high-frequency bands. S6: Optimize communication functions based on the perception of the current environment, including optimizing the allocation of spectrum resources in the current area and the modulation and coding methods of communication signals.

2. The method for signal transmission using a 5G antenna according to claim 1, characterized in that: S1 specifically includes the following steps: S101: Construct a 5G antenna array, receive the echo signal generated by the 5G antenna array, and extract its key features through signal processing algorithms. The key features include the amplitude, phase, time of arrival, and angle of arrival of the signal. Based on the extracted key features, combined with the known antenna position and parameters of the transmitted signal, construct an environmental signal feature set. S102: Environmental signal map creation, which maps the environmental signal feature set to three-dimensional space to form an environmental signal map. The environmental signal map is represented by a grid, with each grid storing the signal feature information of the corresponding area. Different colors and markers are used to represent different signal features. Areas with high signal strength are represented by brighter colors, and areas with low signal strength are represented by darker colors. Areas where obstacles are located are marked with special markers to show the environmental conditions within the entire signal coverage area, including factors that affect signal propagation from facilities within the coverage area. S103: Target user location and tracking. Based on the environmental signal map, locate the position of the target user equipment. By analyzing the signals fed back from the user equipment, the coordinates of the user equipment in three-dimensional space are determined by using the signal arrival time difference and arrival angle difference. For mobile user equipment, its movement trajectory is tracked by continuous signal monitoring. The Kalman filter algorithm is used to predict its future position based on the historical movement trajectory and speed of the user equipment. S104: Beam parameter calculation. Based on the location of the user equipment and the environmental signal map, calculate the parameters required for beamforming, including beam direction, width, and gain. Using a ray tracing algorithm, simulate the signal propagation path from the antenna to the user equipment, find the optimal propagation path, and determine the beam direction. Based on the distance to the user equipment and signal attenuation, determine the beam gain to ensure sufficient signal strength. Based on the user equipment's moving speed and direction, adjust the beam width to ensure that the user equipment remains within the beam coverage area during movement. S105: Beam adjustment and optimization. Based on the calculated beam parameters, the weights of each element in the 5G antenna array are adjusted, as well as the excitation amplitude and phase of the antenna elements, to generate the required beam. Beam performance is monitored in real time, and the beam is optimized based on signal quality feedback from user equipment. When a decline in signal quality is detected, the weights of the antenna elements are adjusted to achieve adaptive beam adjustment, using signal-to-noise ratio (SNR). To evaluate signal quality, let the signal power be... The noise power is The formula for calculating the signal-to-noise ratio is: ； Custom signal-to-noise ratio threshold ,when At that time, beam optimization and adjustment will be performed.

3. The method for signal transmission using a 5G antenna according to claim 1, characterized in that: S3 specifically includes the following operation steps: S301: Spectrum sensing. Based on usage requirements, determine the target frequency band range for spectrum sharing. Deploy spectrum sensing devices capable of receiving and analyzing signals within the target area. The sensing devices continuously monitor signal activity within the target frequency band, including signal strength, frequency, and modulation method. Analyze the monitored signals using signal processing algorithms to identify whether other systems or users are currently using the frequency band. S302: Spectrum assessment. Based on the sensed signal information, assess the possible interference in different frequency bands, analyze the degree of interference that existing signals may cause to new access systems and users, and the potential interference impact of new access behavior on existing systems. S303: Resource allocation. Based on the service needs of different communication systems and users, determine their demand for spectrum resources in terms of quantity and quality. Based on spectrum assessment results and user needs, formulate a reasonable spectrum resource allocation strategy. The strategy includes priority-based allocation, fairness-based allocation, and auction-based allocation. Emergency communication services can be given higher priority and spectrum resources can be allocated to them first. According to the formulated allocation strategy, spectrum resources are allocated to various systems and users. S304: Dynamic adjustment. During spectrum sharing, continuously monitor spectrum usage and communication performance of various systems and users in real time. By collecting feedback information, including signal quality indicators and data transmission rates, promptly understand the actual effect of spectrum sharing. Based on the monitoring data, determine whether spectrum allocation needs to be adjusted. When the interference level of a certain frequency band suddenly increases, leading to a decline in communication quality or a change in the service needs of a user, spectrum allocation adjustment is triggered. When it is determined that adjustment is necessary, a new resource allocation strategy is formulated and implemented based on the new spectrum perception and evaluation results.

4. The method for signal transmission using a 5G antenna according to claim 1, characterized in that: In S5, small 5G base stations and 5G antennas that can cooperate with each other are densely deployed in urban hotspot areas to form an ultra-dense network. Each small 5G base station and 5G antenna can use different frequency bands and beam patterns to cover wide coverage beams including low-frequency bands and millimeter-wave beams including high-frequency bands, in order to meet the needs of different users.

5. The method for signal transmission using a 5G antenna according to claim 1, characterized in that: In step S6, by analyzing the reflection, scattering, and diffraction characteristics of the signal, changes in the surrounding environment are perceived, and spectrum resources are allocated to the current area based on the perceived changes. Based on environmental awareness information, optimize the modulation and coding methods of communication signals.

6. A system for signal transmission using a 5G antenna, employing the method for signal transmission using a 5G antenna as described in any one of claims 1-5, comprising a data acquisition module, a data preprocessing and transmission module, an intent analysis module, and a beam management module, characterized in that: The data acquisition module is used to collect user communication behavior, device information, and scene perception data; The data preprocessing and transmission module is used to perform preliminary cleaning and format unification on the collected data, and then transmit the data to the intent analysis module through an encrypted channel. The intent analysis module integrates preprocessed communication behavior, device information, and scene awareness data, and extracts key features to discover potential user behavior patterns and intent change trends. Depending on the intent prediction task, it selects multiple machine learning and deep learning models for ensemble learning. For short-term intent prediction, it uses a long short-term memory network combined with an attention mechanism to capture long-term dependencies in time-series data and highlight key information. For long-term intent prediction, it combines a decision tree ensemble model, using large-scale historical data for training. The module continuously optimizes model parameters through cross-validation, establishes a real-time feedback mechanism, and updates the model online based on newly collected data. When the model's prediction accuracy decreases or user behavior patterns change significantly, it automatically triggers a model retraining and optimization process. The module categorizes the predicted results to determine the user's most likely intent category and calculates the probability of each intent category. Simultaneously, it prioritizes multiple possible intents based on self-defined intent urgency and resource requirements, prioritizing key needs when resources are limited. The beam management module is used to build an updatable holographic beam database, and to formulate and implement user beam pre-allocation strategies based on the holographic beam database.

7. The system for signal transmission using a 5G antenna according to claim 6, characterized in that: The holographic beam database is used to store various characteristic information of different beams, including beam direction, bandwidth, delay, reliability, coverage, and interaction characteristics with different environments; Based on user intent, and combined with beam features in the holographic beam database, a mapping relationship between intent and beam is established. For different types of user intent, beam resources with different bandwidth, latency, and stability requirements are matched respectively. A beam pre-allocation strategy is formulated, which adopts a strategy that combines priority and fairness. For high-priority intentions, the best beam resources are allocated first, while ensuring that the basic needs of other users are also met. For multiple users with the same intention, beam resources are reasonably allocated according to the user's historical service quality and current network load, so as to avoid excessive concentration of resources in a few users. The beam resources pre-allocated to users are marked in the holographic beam database.

Images