AI-based LED display screen interactive display method

Abstract

The invention discloses an AI-based LED display screen interactive display method, and relates to the technical field of intelligent display, and the method comprises the following steps: a microwave radar sensor monitors electromagnetic spectrum information in a surrounding environment in real time through a built-in spectrum sensing module, and receives and analyzes electromagnetic wave signals emitted from different electronic devices in real time; collected electromagnetic wave signal data are preprocessed to construct a data set, and key features reflecting the risk of overlapping between the working frequency band of the microwave radar sensor and the frequency band of surrounding electronic equipment are extracted from the data set. Through real-time frequency spectrum monitoring, intelligent interference evaluation and dynamic frequency band switching, it is ensured that the radar system automatically avoids interference in a complex environment, misjudgment is reduced, and the target positioning precision, the response speed and the system stability are improved. According to the scheme, technical guarantee is provided for application of the microwave radar sensor in a high electromagnetic interference environment, and the reliability and the adaptive capacity of a system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent display, and particularly to an AI-based interactive display method for LED displays. Background Art

[0002] AI-based interactive display of LED displays refers to the real-time perception and interaction between the LED display and users by introducing artificial intelligence technologies such as computer vision, speech recognition, natural language processing, and behavior analysis, so that the display content is no longer static playback or preset information, but dynamically generated and adjusted according to the user's actions, voice commands, facial expressions, location behaviors, etc. For example, when a user approaches the display screen or makes a certain gesture, the AI system can recognize the behavior and instantly switch the corresponding content to achieve an intelligent and personalized interactive display experience, which is widely used in scenarios such as intelligent navigation, advertising display, and exhibition interaction.

[0003] AI-based interactive display of LED displays will use microwave radar sensors, especially when it is necessary to real-time sense the position, movement or gesture of users in a non-contact manner. The microwave radar sensor can accurately detect the distance, speed and direction of an object by transmitting microwave signals and receiving the echo signals reflected from the user or object. Its main role is to provide real-time user behavior data in the interactive display system, such as monitoring whether the user approaches the display screen, the user's gesture actions or moving speed, etc. When the radar sensor detects that the user approaches or makes a specific gesture, the AI algorithm can analyze these data in real time and trigger corresponding display content changes or interactive feedback, so as to provide a more intelligent and personalized user experience. For example, user gesture operations can be used to switch advertisements, adjust the screen brightness or select display content to ensure that the interaction between the user and the LED display is more natural and smooth.

[0004] The prior art has the following deficiencies: in a high electromagnetic environment, especially in areas with dense electromagnetic wave frequencies such as subways and airports, the working frequency band of the microwave radar sensor is prone to overlap with the frequencies of other surrounding electronic devices. Common interference sources include Wi-Fi, 5G communication, radar monitoring devices, and other wireless sensors, and these signal frequency bands are close to or overlap with the working frequency band of the radar system. Due to the frequency band overlap, when the radar sensor receives the echo signal, it may be affected by external interference sources, resulting in the generation of abnormal echoes. Specifically, the system erroneously receives the reflected waves from non-target objects, resulting in misjudgment or misidentification.

[0005] This interference phenomenon will seriously affect the positioning accuracy and target recognition ability of radar sensors. Especially in high-speed moving or multi-target scenarios, it may lead to problems such as incorrect triggering of interaction content, inaccurate distance measurement, and even system crashes, thus affecting the stability and user experience of the LED display interactive display system based on microwave radar sensors.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The object of the present invention is to provide an AI-based LED display interactive display method. Through real-time spectrum monitoring, intelligent interference evaluation, and dynamic frequency band switching, it ensures that the radar system automatically avoids interference in complex environments, reduces misjudgment, and improves target positioning accuracy, response speed, and system stability. This solution provides technical support for the application of microwave radar sensors in high electromagnetic interference environments, enhances the reliability and adaptability of the system, and solves the problems in the above background art.

[0008] To achieve the above object, the present invention provides the following technical solution: An AI-based LED display interactive display method, including the following steps:

[0009] The microwave radar sensor uses the built-in spectrum sensing module to continuously monitor the electromagnetic spectrum information in the surrounding environment, and receives and analyzes the electromagnetic wave signals emitted from different electronic devices in real time;

[0010] After preprocessing the collected electromagnetic wave signal data, a data set is constructed. Key features reflecting the risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices are extracted from the data set, and the extracted key features are comprehensively analyzed to quantify the risk of frequency band overlap.

[0011] The key features after comprehensive analysis are input into a pre-trained machine learning model, and through the model, an intelligent overlap risk assessment is performed to determine whether there is a risk of frequency band overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices;

[0012] When the assessment shows that there is a risk of frequency band overlap between the radar operating frequency band and surrounding electronic devices, the frequency hopping control mechanism is automatically triggered. According to the overlap risk assessment result, an available frequency band is selected from the preset standby frequency band pool, and the transmission and reception parameters of the radar are dynamically adjusted to complete the frequency band switching operation.

[0013] Preferably, the specific steps for the microwave radar sensor to continuously monitor the environmental electromagnetic spectrum through the built-in spectrum sensing module include:

[0014] First, the sensor turns on the high-sensitivity reception mode to continuously scan the electromagnetic waves in the surrounding space; secondly, the spectrum sensing module down-converts and samples the received broadband signal through the RF front end to convert it into a digital signal;

[0015] Next, perform spectrum analysis on the acquired signal to extract the power spectral density and signal intensity distribution parameters in each frequency band;

[0016] Subsequently, combined with the sliding window mechanism, identify whether there are abnormal enhancements or continuous signal activities in each frequency band, so as to determine whether there is an external interference source;

[0017] Finally, the spectrum data will be used as sensing input for interference risk assessment, feature extraction, or subsequent frequency hopping decision analysis to achieve real-time monitoring and response to the environmental electromagnetic situation.

[0018] Preferably, key features reflecting the overlapping risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices are extracted from the dataset. The extracted features include the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width and the number of power energy mutations occurring per unit time. The ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width and the number of power energy mutations occurring per unit time are comprehensively analyzed under the detection window to generate a frequency occupancy density reference value and an energy sudden increase reference value respectively, and the risk of frequency band overlap is quantified through the frequency occupancy density reference value and the energy sudden increase reference value.

[0019] Preferably, the specific steps for comprehensively analyzing the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width under the detection window to generate a frequency occupancy density reference value are as follows:

[0020] Divide the operating frequency band of the radar into multiple equally wide small frequency points, analyze the signal intensity of each frequency point, sum up the signal indication amounts of all small frequency points to obtain the total number of active signals detected in the operating frequency band per unit time, and the calculation expression is as follows:

[0021]

[0022] , where N sig is the total number of detected active signals, S i is the signal intensity indication amount detected at the i-th frequency point, and n is the number of small frequency points into which the radar operating frequency band is divided;

[0023] Based on the obtained total number of active signals N sig , further calculate the frequency occupancy density reference value. The frequency occupancy density reference value reflects the signal density of the radar operating frequency band, and the calculation expression is as follows:

[0024]

[0025] , where OD is the occupancy density reference value and B is the total frequency bandwidth of the operating frequency band of the microwave radar sensor.

[0026] Preferably, the specific steps for comprehensively analyzing the number of power energy mutations occurring within a unit time under a detection window to generate an energy sudden increase reference value are as follows:

[0027] Monitor and analyze the power energy mutations within a unit time, define a threshold recognition method, and identify whether it is a "sudden increase" based on the amount of power mutation. The calculation formula for the mutation is as follows:

[0028] E change = |P current - P previous |

[0029] , where E change is the power change amplitude, P current is the power value at the current sampling moment, and P previous is the power value at the previous sampling moment;

[0030] When the power change amplitude E change is greater than the set threshold, it is considered that a sudden increase in power energy occurs at this moment. The recognition criterion for the sudden increase event is defined as follows:

[0031]

[0032] , where I burst is the sudden increase event indication function, which is a binary function used to indicate whether a power sudden increase has occurred. If E change > T threshold , then I burst = 1, indicating that a sudden increase event has occurred; otherwise, I burst = 0;

[0033] After detecting a power energy sudden increase event, calculate the energy sudden increase reference value. The calculation expression is as follows:

[0034]

[0035] , where TES is the calculated energy sudden increase reference value, w j is the weight of the power sudden increase event occurring at each time point j, and M is the total number of time points.

[0036] Preferably, the occupancy frequency density reference value and the energy sudden increase reference value obtained through comprehensive analysis are input into a pre-trained machine learning model. The machine learning model generates a frequency band overlap risk coefficient, and based on the frequency band overlap risk coefficient, an intelligent assessment of the frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices is carried out to determine whether there is a frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices.

[0037] Preferably, the frequency band overlap risk coefficient is compared and analyzed with a pre-set reference threshold of the frequency band overlap risk coefficient to determine whether there is a frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices. The judgment logic is as follows:

[0038] If the frequency band overlap risk coefficient is greater than the pre-set reference threshold of the frequency band overlap risk coefficient, it is determined that there is a frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices;

[0039] If the frequency band overlap risk coefficient is less than or equal to the pre-set reference threshold of the frequency band overlap risk coefficient, it is determined that there is no frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices.

[0040] Preferably, when the assessment shows that there is a frequency band overlap risk between the radar operating frequency band and surrounding electronic devices, the frequency hopping control mechanism is automatically triggered. According to the overlap risk assessment result, an available frequency band is selected from a pre-set pool of alternative frequency bands, and the transmitting and receiving parameters of the radar are dynamically adjusted. The specific steps for completing the frequency band switching operation are as follows:

[0041] When it is evaluated that there is a frequency band overlap risk between the radar operating frequency band and the frequency bands of surrounding electronic devices, the frequency hopping control mechanism is automatically triggered, and a frequency band with low interference and high stability is selected from the pre-set pool of alternative frequency bands, and it is ensured that it can provide sufficient bandwidth and signal quality to maintain the normal operation of the radar. The formula is as follows;

[0042]

[0043] , where C k is the signal clarity score of the alternative frequency band k, F k is the bandwidth capacity of the alternative frequency band k, H is the total number of alternative frequency bands, F switch is the optimal frequency band selection value for the frequency band switching operation;

[0044] After completing the frequency band switching, the radar needs to perform dynamic reconfiguration on the new operating frequency band to adapt to the new frequency band characteristics and ensure that the operating state of the radar is optimized on the new frequency band, and keep the positioning accuracy and target recognition ability unaffected. The configuration formula is as follows:

[0045] P adjust =α·Pmax +β·RSSI new +γ·ΔF

[0046] , where P adjust is the adjusted transmit power, P max is the maximum power limit, RSSI new is the received signal strength indication value of the new frequency band, ΔF is the frequency offset after frequency band switching, α is the transmit power adjustment coefficient, β is the received signal strength indication adjustment coefficient, and γ is the frequency offset adjustment coefficient.

[0047] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0048] Through technologies such as real-time spectrum monitoring, intelligent interference assessment, and dynamic frequency band switching, the present invention ensures that the radar system can automatically identify and avoid interference sources in a complex environment, reducing the risks of misjudgment and misidentification, thereby improving the target positioning accuracy, interaction response speed, and overall stability of the system, and ensuring that users can still enjoy a smooth and accurate interaction experience in scenarios with multiple targets and high-speed movement. This solution provides strong technical support for the application of microwave radar sensors in high electromagnetic interference environments, enhancing the reliability and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0050] Figure 1 is the method flow chart of the LED display interactive display method based on AI of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0051] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these examples are provided so that the present disclosure will be more comprehensive and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art.

[0052] The present invention provides an AI-based LED display interactive display method as Figure 1 shown, including the following steps:

[0053] The microwave radar sensor monitors the electromagnetic spectrum information in the surrounding environment in real time through the built-in spectrum sensing module, and receives and analyzes the electromagnetic wave signals emitted from different electronic devices (such as Wi-Fi, 5G base stations, radar monitoring devices, etc.) in real time;

[0054] The microwave radar sensor receives and analyzes the electromagnetic wave signals emitted from different electronic devices (such as Wi-Fi, 5G base stations, radar monitoring devices, etc.) in real time through the built-in spectrum sensing module. This module can capture the signal strength and frequency distribution in the environment, especially focusing on the frequency bands adjacent to or overlapping with the working frequency band of the radar sensor. The real-time nature of this process is crucial because it ensures that the system can dynamically respond and adapt to changes in the electromagnetic environment.

[0055] The core role of this module is to provide the system with the spectrum data in the current environment, including the interference source strength, frequency range, signal fluctuations, etc. These data form the basis for subsequent analysis.

[0056] The specific steps for the microwave radar sensor to monitor the environmental electromagnetic spectrum in real time through the built-in spectrum sensing module are as follows: First, the sensor turns on the high-sensitivity reception mode to continuously scan the electromagnetic waves in the surrounding space; Second, the spectrum sensing module down-converts and samples the received broadband signal through the RF front end to convert it into a digital signal; Then, perform spectrum analysis on the acquired signal (such as Fast Fourier Transform FFT) to extract the power spectral density and signal strength distribution parameters in each frequency band; Subsequently, combined with the sliding window mechanism, identify whether there is abnormal enhancement or continuous signal activity in each frequency band, so as to judge whether there is an external interference source; Finally, the spectrum data will be used as the sensing input for interference risk assessment, feature extraction or subsequent frequency hopping decision analysis to achieve real-time mastery and response to the environmental electromagnetic situation.

[0057] After preprocessing the collected electromagnetic wave signal data, construct a data set, extract the key features from the data set that reflect the risk of overlap between the working frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices, and comprehensively analyze the extracted key features to quantify the risk of frequency band overlap;

[0058] The preprocessing process processes the original spectrum signal through denoising algorithms and filters to remove the noise part in the electromagnetic interference and ensure the accuracy and reliability of the data. In addition, the system will also perform segmented analysis on the signal through time windows or sliding windows to identify the interference conditions in different time periods. The preprocessed data will be used for subsequent data analysis and feature extraction to more accurately evaluate the interference risk. The established data set contains historical environmental information, which provides rich samples for the training of machine learning models.

[0059] The function of establishing a data set is to convert the pre - processed spectrum sensing data into a structured information set, providing a reliable basis for subsequent analysis, feature extraction, interference assessment, and machine learning modeling. The data set can help the system store and organize the electromagnetic spectrum characteristics in different environments in a clear way, enabling the system to effectively identify interference patterns, quantify the risk of frequency band overlap, and provide high - quality training samples for machine learning models. Through the construction of the data set, the system can perform accurate feature analysis and pattern recognition in subsequent processing, providing a basis for automatic frequency band switching and interference control, and thus improving the adaptability and stability of the system in a dynamic and complex environment.

[0060] Extract the key features from the data set that reflect the risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices. The extracted features include the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width and the number of power energy mutations occurring per unit time. Conduct a comprehensive analysis of the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width and the number of power energy mutations occurring per unit time under the detection window, and generate a frequency occupancy density reference value and an energy sudden increase reference value respectively. Quantify the risk of frequency band overlap through the frequency occupancy density reference value and the energy sudden increase reference value.

[0061] An increase in the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width does indicate a risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices. An increase in the frequency occupancy density means that more active signals appear in the radar operating frequency band per unit time. This is usually because surrounding electronic devices (such as Wi - Fi, 5G communication, radar monitoring devices, etc.) frequently use this frequency band or adjacent frequency bands, resulting in a high degree of sharing of spectrum resources. When this ratio increases, it represents that there is more spectrum occupancy in the radar operating frequency band. Especially if these signals come from devices adjacent to or overlapping with the radar frequency band, it will cause frequency band interference. This interference can manifest as cross - frequency band leakage of external signals, that is, non - target signals are misreceived as radar echoes, affecting the accuracy and stability of the radar. Specifically, when device frequency bands are overly concentrated or shared, their signals may cause frequency spillover, power superposition effects, and signal interference, resulting in the radar receiving incorrect reflected echoes, and thus affecting the target positioning and recognition ability. Therefore, an increase in the frequency occupancy density is one of the important indicators for evaluating the risk of frequency band overlap and can provide an effective basis for subsequent frequency band switching or interference management.

[0062] The specific steps for comprehensively analyzing the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width under the detection window to generate a frequency occupancy density reference value are as follows:

[0063] Divide the operating frequency band of the radar into multiple small frequency points with equal bandwidths, and analyze the signal strength of each frequency point. If the signal strength of a certain frequency point exceeds the preset threshold, indicating that there is an active signal at this frequency point, it is recorded as 1; if the signal strength is lower than the threshold, it is recorded as 0. Sum up the signal indication amounts of all small frequency points to obtain the total number of active signals detected within the operating frequency band per unit time. The calculation formula is as follows:

[0064]

[0065] , where N sig is the total number of detected active signals, S i is the signal strength indication amount detected at the i-th frequency point (frequency band partition) (if the signal strength exceeds the threshold, it is recorded as 1, otherwise it is recorded as 0), n is the number of small frequency points into which the operating frequency band of the radar is divided. For the convenience of analysis, the operating frequency band of the radar is usually divided into multiple small frequency bands (frequency points) with equal bandwidths, and each frequency point corresponds to a certain frequency range;

[0066] Divide the operating frequency band of the radar into multiple small frequency points, and detect the signal strength of each frequency point to determine the number of active signals present in this frequency band per unit time. This step helps to quantify the occupancy degree of the operating frequency band of the radar, provides important information about signal density, and provides a data basis for subsequent evaluation of the risk of frequency band overlap.

[0067] Based on the obtained total number of active signals N sig , further calculate the frequency occupancy density reference value. The frequency occupancy density reference value reflects the signal density of the operating frequency band of the radar. The calculation formula is as follows:

[0068]

[0069] , where OD is the frequency occupancy density reference value, and B is the total frequency bandwidth of the operating frequency band of the microwave radar sensor.

[0070] Based on the total number of active signals, combined with the frequency band width and the number of frequency band partitions, calculate the frequency occupancy density reference value to quantify the signal density of the operating frequency band of the radar. It can effectively reflect the occupancy degree of signals within the frequency band, help to evaluate the risk of frequency band overlap and the possibility of interference, and thus guide frequency band switching or interference management decisions.

[0071] The larger the occupation frequency density reference value generated after comprehensively analyzing the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width under the detection window, the more active signals appear in the radar operating frequency band under the monitoring window, and these signals occupy a larger spectrum resource. Usually, it indicates that the use of this frequency band is very intensive, which may be due to the overlap of the frequency bands of surrounding electronic devices. At this time, there is a greater risk of overlap in the operating frequency band where the radar sensor is located, which will cause the radar to receive interference signals from other devices and affect its accuracy and stability. On the contrary, when the occupation frequency density reference value is small, it indicates that there are fewer active signals in this frequency band, the use of the frequency band is relatively scattered, and the risk of overlap between the radar operating frequency band and the frequency bands of other devices is low.

[0072] An increase in the number of power energy mutations occurring per unit time usually indicates a risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices. The reason is that when the operating frequency band of the radar sensor overlaps with the frequency bands of surrounding electronic devices, external interference signals (such as those from Wi-Fi, 5G base stations, or other wireless devices) may irregularly enter the receiving range of the radar. These external signals usually exhibit short-term power mutations. Due to the interweaving or proximity of the frequency bands of the radar sensor and external devices, the interference signals will cause a sharp increase in the instantaneous power within the operating frequency band of the radar. Especially when high-power devices (such as large base stations or radar systems) switch frequencies or transmit pulse signals, the intensity of the interference signals will produce obvious mutations during the radar reception process. Such mutations may cause the radar system to misreceive reflected signals from the interference source, thereby disturbing the normal analysis of the echo signals and increasing the risk of misidentification. Therefore, the increase in power energy mutations is an obvious signal of frequency band overlap, indicating that the frequency components of external interference invade the operating range of the radar and affect its normal operation. This increase in mutations not only affects the accuracy of the radar but may also lead to system instability, especially in multi-target detection or dynamic scenarios.

[0073] The specific steps for comprehensively analyzing the number of power energy mutations occurring per unit time to generate an energy surge reference value under the detection window are as follows:

[0074] Monitor and analyze the power energy mutations per unit time. The power energy mutation refers to a drastic fluctuation or sudden increase in power change within the time window. Define a threshold identification method to identify whether it is a "sudden increase" based on the amount of power mutation. The calculation formula for the mutation is as follows:

[0075] E change =|P current -P previous |

[0076] where, E changeis the power change amplitude, which represents the power change amplitude between two consecutive time points, that is, the difference between the current sampling value and the previous sampling value, and is the basis for measuring the sudden increase in power. It can reflect the drastic fluctuations or sudden increases in the signal, P current is the power value at the current sampling moment, P previous is the power value at the previous sampling moment;

[0077] When the power change amplitude E change is greater than the set threshold, it is considered that a sudden increase in power energy occurs at this moment. The recognition criteria for the sudden increase event are defined as follows:

[0078]

[0079] , where I burst is the sudden increase event indicator function, which is a binary function used to indicate whether a power sudden increase has occurred. If E change >T threshold , then I burst =1, indicating that a sudden increase event has occurred. Otherwise, I burst =0;

[0080] This detection step ensures that the detection of energy sudden increase is more accurate and can capture the mutations caused by external interference sources (such as spectrum overlap of other devices).

[0081] After detecting the power energy sudden increase event, calculate the energy sudden increase reference value. The energy sudden increase reference value reflects the number of power mutations occurring per unit time and is proportional to the sudden increase frequency within the time window, reflecting the intensity of frequency band overlap. The calculation expression is as follows:

[0082]

[0083] , where TES is the calculated energy sudden increase reference value, w j is the weight of the power sudden increase event occurring at each time point j, and M is the total number of time points.

[0084] By performing weighted accumulation on the detected power sudden increase events, the energy sudden increase reference value is generated. The energy sudden increase reference value quantifies the frequency and intensity of interference signals per unit time. By introducing an adaptive weight function, the contribution of the interference signal to the reference value can be adjusted according to the intensity and persistence of the interference signal, so as to more accurately reflect the interference risk brought by frequency band overlap.

[0085] The larger the energy surge reference value generated after comprehensively analyzing the number of power energy mutations occurring within a unit time under the detection window, the higher the risk that the operating frequency band of the microwave radar sensor overlaps with the frequency bands of surrounding electronic devices. The energy surge reference value reflects the frequency and amplitude of power energy mutations within a unit time. If, within the monitoring window, the external signals received by the radar exhibit frequent and intense power mutations, it indicates that there may be other electronic devices (such as Wi-Fi, 5G base stations, etc.) transmitting strongly within adjacent or overlapping frequency bands. These surges suggest that the external signals interfere with or cross the operating frequency band of the radar, resulting in the radar being unable to stably receive clear echo signals and affecting normal target recognition and positioning. Conversely, if the energy surge reference value is low, it indicates less external interference, a clearer operating frequency band for the radar, and no significant risk of frequency band overlap as it is not affected by surrounding devices.

[0086] Input the key features obtained through comprehensive analysis into a pre-trained machine learning model, and use the model to conduct intelligent overlap risk assessment to determine whether there is a risk of frequency band overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices;

[0087] Input the occupancy frequency density reference value and energy surge reference value obtained through comprehensive analysis into a pre-trained machine learning model, generate a frequency band overlap risk coefficient through the machine learning model, and conduct intelligent assessment of the frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices based on the frequency band overlap risk coefficient to determine whether there is a risk of frequency band overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices.

[0088] The pre-trained machine learning model refers to the machine learning model obtained by training with a large amount of historical data during the initial construction of the system. These historical data include spectrum information in different environments, the intensity of interference sources, the characteristics of frequency band overlap, etc. The purpose of model training is to enable the system to learn from these data how to identify the patterns of frequency band overlap, so as to automatically detect and predict interference risks in newly acquired real-time signal data. This training process usually involves using a labeled dataset (i.e., knowing which frequency bands overlap and which do not), and through supervised learning methods, the model learns how to predict the target variable (i.e., the probability or intensity of frequency band overlap occurrence) based on input features (such as occupancy frequency density value, energy surge value, etc.). The trained model adjusts internal parameters (such as weights and biases) to minimize the prediction error as much as possible, so as to accurately predict new data in subsequent practical applications.

[0089] The role of a pre-trained model in practical applications is crucial. It can quickly process input data and make intelligent judgments based on patterns learned previously. Specifically, when new spectrum sensing data is input into the model, the trained model will calculate a frequency band overlap risk coefficient according to the feature relationships learned during the historical training process. This coefficient represents the overlap risk between the current radar frequency band and the frequency bands of surrounding electronic devices. The higher the value, the greater the interference risk. In this way, the machine learning model can achieve automated evaluation of complex electromagnetic environments without manual intervention, helping the system make timely response decisions, such as initiating frequency band switching or optimizing interference control strategies. In addition, the machine learning model has adaptability. As environmental data accumulates continuously and the model is retrained, the prediction ability of the system will become stronger and stronger, thus improving the stability and robustness of the radar sensor in a dynamic environment.

[0090] The machine learning model is not limited here. Any machine learning model that can comprehensively analyze the occupancy density reference value OD and the energy sudden increase reference value TES to generate the frequency band overlap risk coefficient FOR can be used. To implement the technical solution of the present invention, the present invention provides a specific implementation method:

[0091] The formula for generating the frequency band overlap risk coefficient FOR is as follows: FOR = z1·OD + z2·TES, where z1 and z2 are respectively the preset proportionality coefficients of the occupancy density reference value OD and the energy sudden increase reference value TES, and both z1 and z2 are greater than 0.

[0092] The preset proportionality coefficient refers to the weight coefficient used for the two parameters of the occupancy density reference value OD and the energy sudden increase reference value TES when generating the frequency band overlap risk coefficient FOR. When calculating the frequency band overlap risk, the contributions of these two parameters need to be weighted by the proportionality coefficient to reflect their importance in different situations.

[0093] Specifically, z1 and z2 are respectively the proportionality coefficients corresponding to the occupancy density reference value OD and the energy sudden increase reference value TES, used to balance the influence of the two on the final risk coefficient FOR. By setting these two coefficients, the weight of each parameter in the risk assessment can be adjusted according to actual application requirements. The selection of the preset proportionality coefficient is usually determined through experiments or experience to ensure that the calculated risk coefficient can accurately reflect the overlap risk between the radar operating frequency band and the frequency bands of surrounding electronic devices.

[0094] The adjustment of these proportionality coefficients is crucial for ensuring the accuracy and flexibility of the model because they determine the contribution degree of each parameter to the risk prediction in different environments. In practical applications, the values of z1 and z2 may be optimized according to the actual environment and data, so as to improve the prediction accuracy and reliability.

[0095] From the frequency band overlap risk coefficient, it can be seen that the larger the occupation frequency density reference value generated after comprehensively analyzing the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width under the detection window, and the larger the energy sudden increase reference value generated after comprehensively analyzing the number of power energy mutations occurring per unit time under the detection window, the larger the frequency band overlap risk coefficient generated when the intelligent evaluation of the overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices is carried out through a pre-trained machine learning model, indicating that the risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices is greater. On the contrary, it indicates that the risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices is smaller.

[0096] Compare and analyze the frequency band overlap risk coefficient with a pre-set reference threshold of the frequency band overlap risk coefficient to determine whether there is a frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices. The judgment logic is as follows:

[0097] If the frequency band overlap risk coefficient is greater than the pre-set reference threshold of the frequency band overlap risk coefficient, it is determined that there is a frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices;

[0098] If the frequency band overlap risk coefficient is less than or equal to the pre-set reference threshold of the frequency band overlap risk coefficient, it is determined that there is no frequency band overlap risk between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices.

[0099] When the evaluation shows that there is a frequency band overlap risk between the radar operating frequency band and surrounding electronic devices, automatically trigger the frequency hopping control mechanism. According to the overlap risk assessment result, select an available frequency band from the pre-set pool of alternative frequency bands, and dynamically adjust the transmission and reception parameters of the radar to complete the frequency band switching operation;

[0100] By continuously detecting and intelligently evaluating the frequency band overlap risk between the radar operating frequency band and surrounding electronic devices, automatically trigger the frequency hopping control mechanism, so as to ensure that the radar sensor can maintain its accurate working performance in an interference environment. Since the radar frequency band may overlap with surrounding wireless devices (such as Wi-Fi, 5G base stations, radar monitoring systems, etc.), resulting in interference signals affecting the accuracy of radar echoes, thereby affecting target recognition, distance measurement, and positioning accuracy, and even possibly causing the system to fail or crash. Through the automated frequency band switching mechanism, the system can intelligently identify whether the current operating frequency band is interfered, and based on the evaluation results of the interference intensity and overlap risk, select an available frequency band from the pool of alternative frequency bands in real time for switching.

[0101] This process not only helps the system avoid frequency band interference, but also enables dynamic adjustment of the radar's transmission and reception parameters, such as adjusting the transmission power, optimizing the reception sensitivity, adjusting the frequency tuning, etc., to ensure that the radar can still operate stably and maintain high-precision performance in the new frequency band. Through this adaptive adjustment, the system can continuously provide accurate real-time data in a complex electromagnetic environment, while avoiding performance degradation and failure risks caused by frequency band overlap.

[0102] Therefore, the core role of this step is to enhance the robustness and intelligent response ability of the system, enabling it to maintain efficient and stable operation in a dynamically changing electromagnetic environment, avoiding the negative impact of external interference on the radar's operating frequency band and performance, and thus ensuring the reliability of the system and the user experience.

[0103] When the assessment shows that there is a risk of frequency band overlap between the radar's operating frequency band and surrounding electronic devices, the frequency hopping control mechanism is automatically triggered. According to the results of the overlap risk assessment, an available frequency band is selected from the preset pool of backup frequency bands, and the radar's transmission and reception parameters are dynamically adjusted. The specific steps for completing the frequency band switching operation are as follows:

[0104] When it is assessed that there is a risk of frequency band overlap between the radar's operating frequency band and that of surrounding electronic devices, the frequency hopping control mechanism is automatically triggered. A frequency band with low interference and high stability is selected from the preset pool of backup frequency bands, and it is ensured that it can provide sufficient bandwidth and signal quality to maintain the normal operation of the radar. The selection process should consider the current load of the backup frequency band, the external signal strength, and the applicability of the frequency band. The formula is as follows;

[0105]

[0106] , where C k is the signal clarity score of the backup frequency band k, F k is the bandwidth capacity of the backup frequency band k, H is the total number of backup frequency bands, and F switch is the optimal frequency band selection value for the frequency band switching operation, that is, the optimal backup frequency band selected by the system based on the spectrum sensing results, the frequency band overlap risk assessment, and the attributes of the backup frequency band pool;

[0107] Through this step, the optimal frequency band is selected from the backup frequency band pool and switched according to the principle of minimum interference.

[0108] After completing the frequency band switching, the radar needs to perform dynamic reconfiguration on the new operating frequency band, including adjusting parameters such as transmission power, reception sensitivity, and frequency tuning, to adapt to the characteristics of the new frequency band and ensure that the radar's operating state is optimized on the new frequency band, maintaining the positioning accuracy and target recognition ability without being affected. Through this dynamic adjustment, the radar can better adapt to the electromagnetic environment after the frequency band switching and maintain efficient signal processing. The configuration formula is as follows:

[0109] P adjust = α·P max + β·RSSI new + γ·ΔF

[0110] , where P adjust is the adjusted transmit power, P max is the maximum power limit, RSSI new is the received signal strength indication value of the new frequency band, ΔF is the frequency offset after frequency band switching, α is the transmit power adjustment coefficient, which determines the proportion of the maximum power limit in the transmit power adjustment, β is the received signal strength indication adjustment coefficient, which is used to adjust the transmit power of the radar according to the signal strength received on the new frequency band, and γ is the frequency offset adjustment coefficient, which is used to adjust the frequency offset after frequency band switching.

[0111] Through this step, it is possible to ensure that the transmit power, receive sensitivity, and frequency tuning of the radar under the new operating frequency band are optimized, enabling the radar to maintain a normal and stable operating state in a frequency band with less interference.

[0112] Through technologies such as real-time spectrum monitoring, intelligent interference assessment, and dynamic frequency band switching, the present invention ensures that the radar system can automatically identify and avoid interference sources in a complex environment, reducing the risks of misjudgment and misidentification, thereby improving the target positioning accuracy, interaction response speed, and overall stability of the system, and ensuring that users can still enjoy a smooth and accurate interaction experience in scenarios with multiple targets and high-speed movement. This solution provides strong technical support for the application of microwave radar sensors in high electromagnetic interference environments, enhancing the reliability and adaptability of the system.

[0113] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0114] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0115] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0116] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0117] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0118] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0121] As described above, this is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0122] Only some exemplary embodiments of the present invention have been described by way of illustration above. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. AI-based interactive display method for LED displays, characterized in that, Including the following steps: The microwave radar sensor monitors the electromagnetic spectrum information in the surrounding environment in real time through the built-in spectrum sensing module, and receives and analyzes the electromagnetic wave signals emitted from different electronic devices in real time; After preprocessing the collected electromagnetic wave signal data, a data set is constructed, and key features reflecting the risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices are extracted from the data set. The extracted key features are comprehensively analyzed to quantify the risk of frequency band overlap; The key features obtained through comprehensive analysis are input into a pre-trained machine learning model, and the model is used for intelligent overlap risk assessment to determine whether there is a risk of frequency band overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices; When the assessment shows that there is a risk of frequency band overlap between the radar operating frequency band and surrounding electronic devices, the frequency hopping control mechanism is automatically triggered. Based on the overlap risk assessment results, an available frequency band is selected from the preset pool of standby frequency bands, and the transmission and reception parameters of the radar are dynamically adjusted to complete the frequency band switching operation.

2. The AI-based LED display interactive display method according to claim 1, wherein, The specific steps for the microwave radar sensor to monitor the environmental electromagnetic spectrum in real time through the built-in spectrum sensing module include: First, the sensor turns on the high-sensitivity reception mode to continuously scan the electromagnetic waves in the surrounding space; second, the spectrum sensing module down-converts and samples the received broadband signal through the RF front end to convert it into a digital signal; Next, spectrum analysis is performed on the acquired signal to extract the power spectral density and signal intensity distribution parameters within each frequency band; Subsequently, combined with the sliding window mechanism, it is identified whether there is abnormal enhancement or continuous signal activity in each frequency band, so as to determine whether there is an external interference source; Finally, the spectrum data will be used as the sensing input for interference risk assessment, feature extraction, or subsequent frequency hopping decision analysis to achieve real-time monitoring and response to the environmental electromagnetic situation.

3. The AI-based LED display interactive display method according to claim 1, wherein Key features reflecting the risk of overlap between the operating frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices are extracted from the data set. The extracted features include the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width and the number of power energy mutations occurring per unit time. The ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width and the number of power energy mutations occurring per unit time are comprehensively analyzed under the detection window to generate a frequency occupancy density reference value and an energy sudden increase reference value respectively, and the risk of frequency band overlap is quantified through the frequency occupancy density reference value and the energy sudden increase reference value.

4. The AI-based LED display interactive display method according to claim 3, characterized in that The specific steps for comprehensively analyzing the ratio of the number of active signals detected in the radar operating frequency band per unit time to the frequency band width under the detection window to generate a frequency occupancy density reference value are as follows: The operating frequency band of the radar is divided into multiple equally wide small frequency points, and the signal intensity of each frequency point is analyzed. The signal indication quantities of all small frequency points are summed up to obtain the total number of active signals detected in the operating frequency band per unit time. The calculation formula is as follows: ， where N sig is the total number of detected active signals, S i is the signal strength indication quantity detected at the i-th frequency point, and n is the number of small frequency points into which the radar operating frequency band is divided; Based on the total number of active signals N obtained sig , the frequency occupancy density reference value is further calculated. The frequency occupancy density reference value reflects the signal density in the radar operating frequency band, and the calculation expression is as follows: ， In the formula, OD is the frequency occupancy density reference value, and B is the total frequency bandwidth of the operating frequency band of the microwave radar sensor.

5. The AI-based LED display interactive display method according to claim 3, wherein, The specific steps for comprehensively analyzing the number of sudden changes in power energy occurring within a unit time under a detection window to generate a reference value for sudden energy increase are as follows: Monitor and analyze the sudden changes in power energy within a unit time, define a threshold identification method, and identify whether it is a "sudden increase" based on the sudden change amount of power. The calculation formula for the sudden change is as follows: E change = |P current - P previous |, where, E change is the power change amplitude, P current is the power value at the current sampling moment, and P previous is the power value at the previous sampling moment; When the power change amplitude E change is greater than the set threshold, it is considered that there is a sudden increase in power energy at this moment. The recognition criteria for the sudden increase event are defined as follows: ， Among them, I burst is a sudden increase event indicator function, which is a binary function used to indicate whether a power sudden increase has occurred. If E change >T threshold , then I burst = 1, indicating that a sudden increase event has occurred; otherwise, I burst = 0; After detecting a sudden power energy increase event, calculate the reference value for sudden energy increase. The calculation expression is as follows: ， Where TES is the reference value of sudden energy increase, w j is the weight of the power sudden increase event occurring at each time point j, and M is the total number of time points.

6. The AI-based LED display interactive display method according to claim 3, wherein, Input the reference value for frequency occupation density and the reference value for sudden energy increase obtained through comprehensive analysis into a pre-trained machine learning model. Generate a frequency band overlap risk coefficient through the machine learning model, and based on the frequency band overlap risk coefficient, conduct an intelligent assessment of the risk of frequency band overlap between the working frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices, and determine whether there is a risk of frequency band overlap between the working frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices.

7. The AI-based LED display interactive display method according to claim 6, wherein Compare and analyze the frequency band overlap risk coefficient with a pre-set reference threshold for the frequency band overlap risk coefficient to determine whether there is a risk of frequency band overlap between the working frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices. The judgment logic is as follows: If the frequency band overlap risk coefficient is greater than the pre-set reference threshold for the frequency band overlap risk coefficient, it is determined that there is a risk of frequency band overlap between the working frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices; If the frequency band overlap risk coefficient is less than or equal to the pre-set reference threshold for the frequency band overlap risk coefficient, it is determined that there is no risk of frequency band overlap between the working frequency band of the microwave radar sensor and the frequency bands of surrounding electronic devices.

8. The AI-based LED display interactive display method according to claim 7, wherein When the assessment shows that there is a risk of frequency band overlap between the radar working frequency band and surrounding electronic devices, automatically trigger the frequency hopping control mechanism. According to the overlap risk assessment result, select an available frequency band from the pre-set standby frequency band pool, and dynamically adjust the transmission and reception parameters of the radar. The specific steps for completing the frequency band switching operation are as follows: When it is evaluated that there is a risk of frequency band overlap between the radar working frequency band and the frequency bands of surrounding electronic devices, automatically trigger the frequency hopping control mechanism, select a frequency band with low interference and high stability from the pre-set standby frequency band pool, and ensure that it can provide sufficient bandwidth and signal quality to maintain the normal operation of the radar. The formula is as follows; ， Where C k is the signal clarity score of the backup frequency band k, F k is the bandwidth capacity of the backup frequency band k, H is the total number of backup frequency bands, F switch is the optimal frequency band selection value for the frequency band switching operation; After completing the frequency band switching, the radar needs to perform dynamic reconfiguration on the new working frequency band to adapt to the new frequency band characteristics and ensure that the working state of the radar is optimized on the new frequency band, and keep the positioning accuracy and target recognition ability unaffected. The configuration formula is as follows: P adjust = α·P max + β·RSSI new + γ·ΔF, Where P adjust is the adjusted transmit power, P max is the maximum power limit, RSSI new is the received signal strength indication value of the new frequency band, ΔF is the frequency offset after frequency band switching, α is the transmit power adjustment coefficient, β is the received signal strength indication adjustment coefficient, and γ is the frequency offset adjustment coefficient.

Images