Communication channel determination method and system of tire pressure sensor and storage medium

Abstract

The invention is suitable for the technical field of vehicle control, and provides a communication channel determination method and system of a tire pressure sensor and a storage medium, and the method comprises the steps: obtaining multi-dimensional data of a vehicle, including vehicle operation data, environment perception data of an environment where the vehicle is located, and radio frequency signal data; feature extraction is carried out on the environment sensing data and the radio frequency signal data, and radar features corresponding to the environment sensing data and radio frequency features corresponding to the radio frequency signal data are obtained. And inputting the radar features, the radio frequency features and the vehicle operation data into an interference prediction model, and predicting interference information in a future moment through the interference prediction model to obtain an interference prediction result. And determining a target communication channel of the tire pressure sensor in the vehicle according to the interference prediction result and a preset channel evaluation rule. According to the invention, the conversion from passive response to active prediction of the tire pressure sensor can be realized, and the conflict delay rate and retransmission times of data transmission are reduced, so that the stability and timeliness of data transmission are improved.

Description

Technical Field

[0001] This application belongs to the field of vehicle control technology, and in particular relates to a method, system and storage medium for determining the communication channel of a tire pressure sensor. Background Technology

[0002] Tire Pressure Monitoring System (TPMS), as an important component of modern automotive safety systems, provides drivers with tire status information by monitoring parameters such as tire pressure and temperature in real time. Current TPMS technology primarily relies on radio frequency communication to transmit data between tire pressure sensors and the vehicle's receiving system.

[0003] However, traditional tire pressure sensors generally use a fixed frequency design, with communication bands primarily divided into 315MHz, 433MHz, and 2.4GHz Bluetooth bands. When tire pressure sensors are adapted to vehicles, the communication channel is also essentially fixed. In such cases, when the tire pressure sensor is in a complex signal environment, it is easily interfered with by multiple other signal sources on the same channel, leading to decreased data transmission reliability and even data loss. This can easily result in loss of communication with the vehicle's electronic control unit (ECU). Furthermore, when encountering communication channel conflicts, the data transmission latency is high, making real-time monitoring of vehicle tire pressure data impossible, affecting the system's real-time performance, and consequently impacting the system's stability and reliability. Summary of the Invention

[0004] This application provides a method, system, and storage medium for determining the communication channel of a tire pressure sensor, which can solve the technical problem that traditional tire pressure sensors are easily affected by interference from co-frequency signals in complex signal environments, resulting in data transmission loss and delay.

[0005] In a first aspect, embodiments of this application provide a method for determining the communication channel of a tire pressure sensor, the method comprising: Acquire multi-dimensional data of the vehicle; wherein, the multi-dimensional data includes vehicle operation data, environmental perception data of the environment in which the vehicle is located, and radio frequency signal data; Feature extraction is performed on the environmental perception data and the radio frequency signal data respectively to obtain the radar features corresponding to the environmental perception data and the radio frequency features corresponding to the radio frequency signal data; The radar features, radio frequency features, and vehicle operation data are input into the interference prediction model. The interference prediction model is used to predict interference information in the future to obtain the interference prediction result. The interference prediction model is a prediction model pre-trained based on a convolutional neural network. Based on the interference prediction results and the preset channel evaluation rules, the target communication channel of the tire pressure sensor in the vehicle is determined; wherein, the preset channel evaluation rules are used to quantify the quality of the communication channel.

[0006] In one possible implementation of the first aspect, acquiring the multi-dimensional data of the vehicle includes: The environmental perception data is collected by a radar device installed inside the wheel arch of the vehicle and close to the tires. The radio frequency signal data is acquired by tire pressure sensors installed inside the tires of the vehicle.

[0007] In one possible implementation of the first aspect, the step of extracting features from the environmental perception data and the radio frequency signal data to obtain radar features corresponding to the environmental perception data and radio frequency features corresponding to the radio frequency signal data includes: Multiple target objects in the environmental perception data are identified using a clustering algorithm; The multiple target objects are continuously tracked by a target tracking algorithm, and each target object is assigned a unique identifier. The motion trajectory of each target object is calculated by a trajectory fitting algorithm. Based on the motion trajectory, the radar features are extracted, wherein the radar features include at least one of the following: surrounding vehicle density, distance and relative speed of the nearest vehicle, angular distribution of surrounding vehicles, and convergence / divergence trend based on trajectory prediction. The radio frequency signal data is scanned to obtain the spectrum diagrams corresponding to the multiple communication channels. The frequency and power information in multiple spectrum diagrams are quantized and the interference pulses in the spectrum diagrams are statistically analyzed to obtain the radio frequency characteristics; wherein the radio frequency characteristics include at least one of the following: channel average signal strength, channel signal-to-noise ratio, channel occupancy, and statistical characteristics of interference pulses.

[0008] In one possible implementation of the first aspect, the step of inputting the radar features, the radio frequency features, and the vehicle operation data into an interference prediction model, and using the interference prediction model to predict interference information in future time periods to obtain an interference prediction result, includes: The radar features, the radio frequency features, and the vehicle operation data are normalized to obtain the processed radar features, the processed radio frequency features, and the processed vehicle features. The processed radar features, the processed radio frequency features, and the processed vehicle features are fused to obtain multi-dimensional fused features; Based on the relationship between the multidimensional fusion features learned by the interference prediction model and the interference information, the interference information in the future time is predicted by the interference prediction model to obtain the interference prediction result, wherein the interference prediction result includes: the type of interference signal and the interference intensity of the interference signal.

[0009] In one possible implementation of the first aspect, determining the target communication channel of the tire pressure sensor in the vehicle based on the interference prediction result and a preset channel evaluation rule includes: Based on the interference prediction results and the preset channel evaluation rules, the quality of each communication channel is scored to obtain a quality score for each communication channel. The target communication channel is determined based on the quality score of each communication channel.

[0010] In one possible implementation of the first aspect, after determining the target communication channel of the tire pressure sensor in the vehicle, the method includes: Based on the quality score of the target communication channel and a preset score threshold, a channel switching command is generated and sent to the tire pressure sensor.

[0011] Secondly, embodiments of this application provide a communication channel determination system for a tire pressure sensor, the system comprising: a radar device, a tire pressure sensor, an artificial intelligence device, and a central controller; The radar device is located inside the wheel arch of the vehicle and close to the tires. It is used to collect environmental perception data of the vehicle's environment and send the environmental perception data to the artificial intelligence device. The tire pressure sensor is installed inside the tire of the vehicle and is used to collect radio frequency signal data of the environment in which the vehicle is located, and send the radio frequency signal data to the artificial intelligence device. The artificial intelligence device is installed in the tire pressure sensor and is used to receive vehicle operation data sent by the central controller, environmental perception data sent by the radar device, and radio frequency signal data sent by the tire pressure sensor; and to extract features from the environmental perception data and the radio frequency signal data respectively to obtain radar features corresponding to the environmental perception data and radio frequency features corresponding to the radio frequency signal data. The artificial intelligence device is further configured to input the radar features, the radio frequency features, and the vehicle operation data into an interference prediction model, and predict interference information in future time periods through the interference prediction model to obtain an interference prediction result; wherein, the interference prediction model is a prediction model pre-trained based on a convolutional neural network; and, based on the interference prediction result and a preset channel evaluation rule, determine the target communication channel of the tire pressure sensor in the vehicle, wherein the preset channel evaluation rule is used to quantify the quality of the communication channel; and send the target communication channel to the central controller.

[0012] In one possible implementation of the second aspect, The central controller is further configured to generate a channel switching command based on the quality score of the target communication channel and a preset score threshold, and send the channel switching command to the tire pressure sensor so that the tire pressure sensor switches to the target communication channel for communication according to the channel switching command.

[0013] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the communication channel determination method for the tire pressure sensor described in any of the above claims.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for determining the communication channel of a tire pressure sensor as described in any of the preceding claims.

[0015] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the tire pressure sensor communication channel determination method described in any of the first aspects above.

[0016] The beneficial effects of the embodiments in this application compared with the prior art are: This application provides a method for determining the communication channel of a tire pressure sensor. The method includes: acquiring multi-dimensional data of the vehicle, including vehicle operation data, environmental perception data of the vehicle's environment, and radio frequency (RF) signal data. Then, feature extraction is performed on the environmental perception data and RF signal data to obtain radar features corresponding to the environmental perception data and RF features corresponding to the RF signal data. The radar features, RF features, and vehicle operation data are input into an interference prediction model. The interference prediction model predicts interference information in future timeframes to obtain an interference prediction result. The interference prediction model is a prediction model pre-trained based on a convolutional neural network. Finally, the target communication channel of the tire pressure sensor in the vehicle is determined based on the interference prediction result and a preset channel evaluation rule, whereby the preset channel evaluation rule quantifies the quality of the communication channel. This method predicts interference information based on environmental perception data and RF signal data using an interference prediction model, and switches the tire pressure sensor's communication channel in advance based on the interference information. This enables the tire pressure sensor to shift from passive response to active prediction, reducing data transmission conflict latency and retransmission frequency, thereby improving the stability and timeliness of data transmission. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for determining the communication channel of a tire pressure sensor according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a communication channel determination system for a tire pressure sensor according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0021] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0023] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0025] The communication channel of a tire pressure sensor is a specific radio frequency band and corresponding communication parameter combination used for data transmission between the tire pressure sensor and the vehicle's electronic control unit (or other receiving device). In other words, the communication channel is the carrier of data transmission during the real-time transmission of tire pressure, temperature, and other data from the tire pressure sensor to the vehicle's electronic control unit.

[0026] Traditional tire pressure sensors typically use a fixed frequency design, primarily communicating in the 315MHz, 433MHz, and 2.4GHz Bluetooth bands. When these sensors are integrated into vehicles, the communication channel is also essentially fixed. In such cases, when the tire pressure sensor is in a complex signal environment, it is susceptible to interference from multiple signal sources, leading to data loss, data transmission delays, and potential communication breakdowns with the vehicle's electronic control unit (ECU). This prevents real-time monitoring of tire pressure data and poses certain safety hazards.

[0027] Therefore, in this embodiment, the tire pressure sensor, radar device, and artificial intelligence device can be combined to achieve dynamic channel selection for the tire pressure sensor. The tire pressure sensor is designed with multiple communication channels. The radar device observes various environments the vehicle passes through and collects environmental data. The tire pressure sensor receives and records interference signals appearing in the current environment. The environmental data and signal data are sent to the artificial intelligence device. The interference prediction model set in the artificial intelligence device uses the collected environmental data and signal data for learning and training. When the radar device senses that the vehicle has arrived in a certain environment, it predicts potential signal interference signals based on the interference prediction model. The tire pressure sensor can then dynamically select the best communication channel from multiple communication channels in advance, reducing interference from other signals and reducing the channel conflict delay rate, thereby improving the data communication efficiency and reliability between the tire pressure sensor and the vehicle.

[0028] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for determining the communication channel of a tire pressure sensor according to an embodiment of this application. The method includes: S11. Acquire multi-dimensional data of the vehicle. This multi-dimensional data includes vehicle operation data, environmental perception data of the vehicle's surrounding environment, and radio frequency signal data.

[0029] S12. Extract features from the environmental perception data and radio frequency signal data respectively to obtain the radar features corresponding to the environmental perception data and the radio frequency features corresponding to the radio frequency signal data.

[0030] S13. Input radar characteristics, radio frequency characteristics, and vehicle operation data into the interference prediction model. Use the interference prediction model to predict interference information in future time periods to obtain the interference prediction result. The interference prediction model is a prediction model pre-trained based on a convolutional neural network.

[0031] S14. Based on the interference prediction results and the preset channel evaluation rules, determine the target communication channel of the tire pressure sensor in the vehicle; wherein, the preset channel evaluation rules are used to quantify the quality of the communication channel.

[0032] It should be noted that in this embodiment, the executing entity can be a terminal device such as a server, and there are no specific limitations on this.

[0033] Multi-dimensional data includes vehicle operation data, environmental perception data of the vehicle's surroundings, and radio frequency signal data. Vehicle operation data comprises various data generated during vehicle operation, such as vehicle speed, acceleration, steering angle, and GPS location (used to determine scenarios like cities, highways, and parking lots). This data reflects the vehicle's current operating status and driving behavior. Environmental perception data consists of information about the vehicle's surrounding environment acquired through sensors (such as radar), including the relative position, distance, speed, and trajectory of obstacles (such as surrounding vehicles), as well as road conditions. This data helps in understanding the vehicle's surroundings and provides a basis for driving decisions. Radio frequency signal data consists of radio frequency signals in the space surrounding the vehicle, including TPMS signals from other vehicles or equipment (such as same-channel signals and adjacent-channel interference). These signals may interfere with the communication of the tire pressure sensor.

[0034] Radar features are characteristic information related to the surrounding environment extracted from environmental perception data, such as the relative position, speed, density, and trajectory of surrounding vehicles. Radar features can help identify potential interference signals in the vehicle's surrounding environment. Radio frequency (RF) features are characteristic information related to the communication channel extracted from RF signal data, such as channel occupancy status, signal strength, and signal-to-noise ratio. RF features can help analyze the potential impact of RF signals on tire pressure sensor communication.

[0035] The interference prediction model is a prediction model based on pre-trained convolutional neural networks. It is used to predict signal interference information in the future based on input radar features, radio frequency features, and vehicle operation data. The interference prediction result is the interference information in the future output by the interference prediction model, which may include the type of interference signal, the interference intensity, etc.

[0036] The preset channel evaluation rules are pre-defined rules for quantifying channel quality. For example, if the interference intensity is below a preset intensity threshold, the channel is usable; if the interference frequency overlaps with the tire pressure sensor's operating frequency band, the channel is disabled. The target communication channel is the most suitable channel for communication with the tire pressure sensor, determined based on the predicted interference information and according to the preset channel evaluation rules. Selecting the target communication channel can reduce signal interference in the environment and improve the reliability and accuracy of communication.

[0037] Specifically, firstly, vehicle operation data, environmental perception data, and radio frequency (RF) signal data are acquired through sensors on the vehicle, providing a foundation for subsequent interference prediction and communication channel selection. Next, radar features are extracted from the environmental perception data, and radio frequency (RF) features are extracted from the RF signal data. These extracted radar features, RF features, and vehicle operation data are then used as inputs to predict interference information in the future using a pre-trained interference prediction model. Finally, based on the interference prediction results and pre-defined channel evaluation rules, the most suitable channel for communication with the tire pressure sensor is selected as the target communication channel. It should be understood that the interference prediction model can predict potential interference information in advance, providing time for the tire pressure sensor to select a suitable communication channel; and by selecting the optimal target communication channel, the risk of communication interruption and mistransmission can be reduced, the channel collision delay rate can be lowered, thereby improving the reliability and accuracy of system communication.

[0038] It is understood that this application provides a method for determining the communication channel of a tire pressure sensor. This method includes: acquiring multi-dimensional data of the vehicle; wherein the multi-dimensional data includes vehicle operation data, environmental perception data of the vehicle's environment, and radio frequency (RF) signal data. Then, feature extraction is performed on the environmental perception data and RF signal data respectively to obtain radar features corresponding to the environmental perception data and RF features corresponding to the RF signal data. The radar features, RF features, and vehicle operation data are input into an interference prediction model, which predicts interference information in future timeframes to obtain an interference prediction result; wherein the interference prediction model is a prediction model pre-trained based on a convolutional neural network. Finally, based on the interference prediction result and a preset channel evaluation rule, the target communication channel of the tire pressure sensor in the vehicle is determined, wherein the preset channel evaluation rule is used to quantify the quality of the communication channel. This method, by predicting interference information based on environmental perception data and RF signal data using an interference prediction model, and switching the tire pressure sensor's communication channel in advance based on the interference information, can realize the transformation of the tire pressure sensor from passive response to active prediction, reducing the data transmission conflict delay rate and retransmission count, thereby improving the stability and timeliness of data transmission.

[0039] In one possible implementation, multi-dimensional data of the vehicle is acquired, including: Environmental perception data is collected by a radar device installed inside the wheel arch of the vehicle and close to the tires.

[0040] Radio frequency signal data is collected by tire pressure sensors installed inside the tires of the vehicle.

[0041] Radar devices are electronic devices that use electromagnetic waves to detect information such as the position and speed of targets. In vehicle operation, radar devices are often used for environmental perception, such as detecting obstacles and measuring distances. Tire pressure sensors are electronic devices that monitor tire pressure, temperature, and other parameters in real time, and can also collect radio frequency signals from the environment. Tire pressure sensors typically transmit the monitored radio frequency signal data wirelessly (such as via radio frequency signals) to a receiver within the tire pressure sensor.

[0042] The inner side of a vehicle's wheel arch is a recessed area within the body above the tires, typically covered with an inner liner to protect the body structure and reduce noise. Because the inner side of the wheel arch is close to the tires and less susceptible to obstruction from external objects, it is a preferred location for installing radar devices. This location ensures the radar device is close enough to the tires for accurate environmental sensing while preventing direct impact or obstruction from external objects. The radar device emits electromagnetic waves and receives reflected waves, processing the reflected wave signals to obtain information about the vehicle's surroundings, forming environmental perception data. Tire pressure sensors, installed inside the tires, collect radio frequency signals from the environment, forming environmental radio frequency signal data.

[0043] It should be understood that by collecting environmental perception data and radio frequency signal data, the quality and interference level of radio frequency signals in the environment can be analyzed, providing a reference for subsequent interference prediction and channel selection.

[0044] In one possible implementation, feature extraction is performed on the environmental sensing data and the radio frequency signal data respectively to obtain the radar features corresponding to the environmental sensing data and the radio frequency features corresponding to the radio frequency signal data, including: Multiple target objects in environmental perception data are identified using clustering algorithms.

[0045] Multiple target objects are continuously tracked using a target tracking algorithm, and each target object is assigned a unique identifier. The motion trajectory of each target object is calculated using a trajectory fitting algorithm.

[0046] Radar features are extracted based on the motion trajectory. These radar features include at least one of the following: surrounding vehicle density, distance and relative speed of the nearest vehicle, angular distribution of surrounding vehicles, and convergence / divergence trend based on trajectory prediction.

[0047] Multiple communication channels in the radio frequency signal data are scanned to obtain the spectrum diagrams corresponding to the multiple communication channels.

[0048] The frequency and power information in multiple spectrum plots are quantized, and the interference pulses in the spectrum plots are statistically analyzed to obtain radio frequency (RF) characteristics. These RF characteristics include at least one of the following: average channel signal strength, channel signal-to-noise ratio (SNR), channel occupancy, and statistical characteristics of interference pulses.

[0049] Clustering algorithms are unsupervised learning algorithms that identify patterns or structures in data by grouping data points into clusters with similar characteristics. In processing environmental perception data, clustering algorithms can identify multiple target objects (such as pedestrians, vehicles, and obstacles) in radar scans. Target tracking algorithms are dynamic system modeling methods that predict the future trajectory of a target object by continuously observing its position, velocity, and other state information. Trajectory fitting algorithms generate mathematical models of a target object's trajectory by fitting its historical position data, such as least squares methods and spline interpolation. In processing environmental perception data, target tracking algorithms continuously track identified target objects, assigning each object a unique identifier to distinguish them. Then, trajectory fitting algorithms calculate the trajectory of each target object, providing a foundation for subsequent feature extraction.

[0050] A spectrum diagram is a graphical representation of how signal frequency components change over time. In radio frequency (RF) signal data processing, spectrum diagrams are used to show the frequency occupancy of different communication channels. Quantization is the process of converting continuous signals or data into discrete values. In RF feature extraction, quantization can convert the frequency and power information in the spectrum diagram into numerical features, facilitating subsequent analysis and processing. Among these, the average channel signal strength is the average power level of the signal in the communication channel, reflecting the strength of the channel signal. The channel signal-to-noise ratio (SNR) is the ratio of signal power to noise power, reflecting the quality of the channel signal; a higher SNR indicates better signal quality and less interference. Channel occupancy is the proportion of time the communication channel is occupied by signals, reflecting the channel's busyness; a higher channel occupancy indicates a busier channel and greater potential interference. Interference pulse statistical characteristics are features obtained through statistical analysis of interference pulses in the RF signal, such as pulse count, pulse width, and pulse interval, used to distinguish different types of interference pulses.

[0051] Specifically, clustering algorithms are applied to group environmental perception data, grouping data points with similar characteristics into the same cluster, with each cluster representing a target object. Then, a target tracking algorithm is applied to continuously track each target object, updating its position, velocity, and other state information, and assigning a unique identifier to each target object to distinguish them from others. Simultaneously, a trajectory fitting algorithm is applied to calculate the motion trajectory of each target object. Finally, based on the motion trajectory, radar features are extracted, such as the number of surrounding vehicles per unit time or unit area (i.e., surrounding vehicle density, such as the number of vehicles within 0-50 meters of the current vehicle), the distance and relative speed between the current vehicle and the nearest vehicle (i.e., the distance and relative speed between the nearest vehicles), the angular distribution of surrounding vehicles relative to the current vehicle (i.e., the angular distribution of surrounding vehicles), and the prediction of the target object's future motion trend (i.e., based on the convergence / divergence trend of the trajectory prediction, predicting whether a vehicle is rapidly approaching and merging into the lane, representing an impending strong interference signal).

[0052] Then, spectrum analysis techniques (such as Fast Fourier Transform) are applied to scan the radio frequency signal data to obtain spectrum diagrams corresponding to multiple channels. Next, the frequency and power information in the spectrum diagrams are quantified, such as calculating the channel average signal strength, channel signal-to-noise ratio, and channel occupancy. Statistical analysis is also performed on interference pulses in the spectrum diagrams to extract statistical characteristics of the interference pulses, thus obtaining the final radio frequency characteristics used to quantify the interference level of the current communication channel.

[0053] It should be understood that radar signatures can provide a comprehensive description of the surrounding environment, while radio frequency signatures can describe the quality and interference level of the current communication channel, providing a reliable basis for subsequent interference prediction and channel selection.

[0054] In one possible implementation, radar characteristics, radio frequency characteristics, and vehicle operation data are input into an interference prediction model. The interference prediction model then predicts interference information for future timeframes, yielding interference prediction results, including: The radar features, radio frequency features, and vehicle operation data are normalized to obtain the processed radar features, processed radio frequency features, and processed vehicle features.

[0055] The processed radar features, processed radio frequency features, and processed vehicle features are fused to obtain multi-dimensional fused features.

[0056] Based on the relationship between the multidimensional fusion features learned by the interference prediction model and the interference information, the interference information in future time periods is predicted using the interference prediction model, resulting in interference prediction results. These results include: the type of interference signal and the interference intensity.

[0057] Normalization is the process of mapping data of different dimensions or ranges to a unified range (such as [0,1] or [-1,1]) through mathematical transformations (e.g., linear transformation, Z-score standardization). Normalization can eliminate the dimensional differences between different data, improving model training efficiency and prediction accuracy. Multidimensional fusion features are a single feature vector that integrates features from different data sources (such as radar features, radio frequency features, and vehicle operation data) through concatenation, weighting, or deep learning fusion methods. This multidimensional fusion feature contains multidimensional information and can more comprehensively describe the system state. Interference prediction models can predict interference signals and their intensity at future moments by learning the relationship between multidimensional fusion features and interference information in historical data. Interference signals are signals that generate electromagnetic interference, which may be from other vehicles, electronic devices, etc. Interference intensity is the degree of impact of interference signals on the system (such as tire pressure sensors), usually quantified by indicators such as signal power, signal-to-noise ratio reduction, or bit error rate.

[0058] Specifically, firstly, radar features, radio frequency (RF) features, and vehicle operation data are normalized to obtain processed radar features, processed RF features, and processed vehicle features. Normalizing these features avoids model training bias caused by different features having different dimensions. Simultaneously, the normalized data distribution is more concentrated, improving the convergence speed of the interference prediction model and reducing dependence on specific data ranges, thus enhancing the generalization ability of the interference prediction model.

[0059] Then, the processed radar features, processed radio frequency features, and processed vehicle features are fused to obtain a multi-dimensional fused feature. For example, the processed radar features, processed radio frequency features, and processed vehicle features can be sequentially concatenated into a multi-dimensional fused feature; or a multi-dimensional fused feature can be obtained by weighting the processed radar features, processed radio frequency features, and processed vehicle features according to their feature importance and then summing them; alternatively, a multi-dimensional fused feature can be obtained by automatically learning the nonlinear relationships between features through a neural network. It should be understood that the fused feature combines environmental perception, radio frequency signals, and vehicle dynamic information, providing more comprehensive contextual information for interference prediction, reducing the limitations of single-feature prediction, and improving the accuracy of interference prediction.

[0060] Finally, the obtained multi-dimensional fused features are input into the trained interference prediction model. The model then predicts interference information for future timeframes, thus obtaining the future interference signal and its intensity. It should be understood that the prediction results allow for advance adjustments to communication channels to avoid interference and reduce security incidents caused by communication interruptions.

[0061] Interference prediction models can infer patterns by learning the correlation between multi-dimensional fused features and interference information. After the interference prediction model has been trained, it is fed with current and historical radar features, radio frequency features, and vehicle operation data. The model can infer the vehicle's location based on these features. For example, when a vehicle is traveling at 60 km / h (vehicle operation data), if it detects a vehicle traveling alongside it at a small relative speed (radar feature), and the RSSI of a certain communication channel is slowly increasing (radio frequency feature), the interference prediction model will internally increase its prediction of future interference intensity for that communication channel. Similarly, if it detects a high-density traffic flow on the right (radar feature), the model will infer that it will soon enter a complex electromagnetic environment, thus generally increasing the medium- to long-term interference risk for all channels. Through its memory capabilities, the model can learn that a rapidly approaching target will become a major interference signal within seconds, thus providing early warning.

[0062] It should be noted that the collected environmental data and corresponding interference signals are input into the model. This data is used to train the model, specifically learning the correlation between the inputs (environmental perception data, radio frequency signal data, and vehicle operation data) and the output (interference prediction results). This allows the model to predict which channels will be affected by interference in advance, enabling the vehicle to predict potential interference signals in different environments. The tire pressure sensor then switches to the optimal channel in advance. The specific process of training the interference prediction model is as follows: (1) Obtain the training dataset. Select multi-dimensional data of vehicles related to various typical display scenarios and interference prediction, namely environmental perception data, radio frequency signal data, and vehicle operation data. Clean the environmental perception data, radio frequency signal data, and vehicle operation data, and extract the features related to interference prediction, namely radar features, radio frequency features, and vehicle features. Through the above operations, generate at least 10,000 to 100,000 multi-dimensional data of vehicles covering different scenarios. Divide the multi-dimensional data into training set and validation set according to an 8:2 or 7:3 ratio, and store them in the data server for subsequent model training.

[0063] (2) Constructing an interference prediction model. Based on multi-dimensional data and prediction requirements, select an appropriate model type, construct the basic architecture of the interference prediction model, and determine the model's activation function, loss function, and optimizer, among other hyperparameters. For example, in this embodiment, the interference prediction model can employ a convolutional neural network based on an attention mechanism.

[0064] (3) Training the interference prediction model. Environmental perception data, radio frequency signal data, and vehicle operation data from the training set are used as inputs. After feature extraction and fusion, radar features, radio frequency features, and vehicle features are obtained. The multi-dimensional fused features obtained by splicing and fusing the radar features, radio frequency features, and vehicle features are then input into the interference predictor, which outputs the corresponding interference prediction results. Using the real interference information matched by this set of data as labels, the difference between the interference prediction results and the labels (i.e., real interference information) is calculated using a loss function (such as the mean squared error function). The weight parameters of each layer of the interference prediction model (such as convolution kernel parameters and attention weights) are adjusted based on the backpropagation algorithm. During training, the performance of the interference prediction model (such as the goodness of fit between the prediction parameters and the labels) is evaluated using a validation set after a certain number of iterations (such as 1000). When the validation set error no longer decreases after multiple consecutive iterations (such as 10), the interference prediction model is considered converged and training is stopped. Finally, the trained interference prediction model is obtained. This interference prediction model can receive new environmental perception data, radio frequency signal data, and vehicle operation data, and output interference prediction results that meet the interference prediction requirements.

[0065] It should be understood that the training dataset constructed through the above process and the trained interference prediction model can ensure the accuracy of the interference prediction results.

[0066] In one possible implementation, the target communication channel of the tire pressure sensor in the vehicle is determined based on interference prediction results and preset channel evaluation rules, including: Based on the interference prediction results and the preset channel evaluation rules, the quality of each communication channel is scored to obtain a quality score for each communication channel.

[0067] The target communication channel is determined based on the quality score of each communication channel.

[0068] The interference prediction result is the interference information for future moments output by the interference prediction model, which may include the type of interference signal (such as radar signals from other vehicles, signals from industrial equipment, etc.) and the interference intensity (such as signal power, signal-to-noise ratio reduction, etc.). The preset channel evaluation rules are pre-defined rules for quantifying channel quality. For example, if the interference intensity is below a preset intensity threshold, the channel quality score is increased; if the interference frequency overlaps with the tire pressure sensor's operating frequency band, the channel quality score is decreased, etc. The interference prediction result is converted into a quantifiable channel quality score. The communication channel quality score is a comprehensive score calculated for each candidate communication channel according to the preset channel evaluation rules, reflecting the applicability of the communication channel. A higher communication channel quality score indicates better channel quality.

[0069] The target communication channel is the optimal channel for communication with the tire pressure sensor, determined based on the predicted interference information and the channel's quality score. The selection of the target communication channel must meet the conditions of low interference, high reliability, and low latency to ensure accurate and real-time transmission of tire pressure data.

[0070] Specifically, firstly, based on the interference prediction results and preset channel evaluation rules, the quality of each communication channel is scored, giving each communication channel a comprehensive quality score, and these comprehensive quality scores are then ranked. Then, the channel with the highest quality score is selected as the target communication channel.

[0071] For example, in application scenarios involving congested urban roads, dense surrounding traffic, and strong interference from radar and WiFi signals, the interference prediction model's prediction results are as follows: Communication Channel A: Interference intensity -60dBm (high), SNR 8dB (low), occupancy rate 40%. Communication Channel B: Interference intensity -85dBm (low), SNR 15dB (high), occupancy rate 10%. Assume the preset channel evaluation rules are: 20 points deducted for interference intensity above -70dBm; 15 points deducted for SNR below 10dB; 10 points deducted for occupancy rate above 30%; and 5 points deducted for occupancy rate above 10% but below 30%, etc. Therefore, the quality scores for the two communication channels are: for Communication Channel A: 100-20-15-10=55 points; for Communication Channel B: 100-0-0-5=95 points. Therefore, Communication Channel B is selected as the target communication channel to ensure stable transmission of tire pressure data.

[0072] It should be understood that choosing the communication channel with the least interference can reduce the risk of tire pressure data being lost or erroneous during transmission.

[0073] In one possible implementation, after determining the target communication channel for the tire pressure sensor in the vehicle, the method includes: Based on the quality score of the target communication channel and the preset score threshold, a channel switching command is generated and sent to the tire pressure sensor.

[0074] The preset score threshold is a pre-defined minimum quality score standard used to determine whether the target communication channel meets the communication requirements. The channel switching command instructs the tire pressure sensor to switch from the current communication channel to the target communication channel. If the quality score of the target communication channel is higher than the preset score threshold, a channel switch can be initiated, generating a corresponding channel switching command, which is then sent to the tire pressure sensor to switch communication channels. If the quality score of the target communication channel is lower than the preset score threshold, the tire pressure sensor continues to use the current communication channel to avoid frequent switching due to minor fluctuations.

[0075] It should be noted that this method can also perform predictive switching. If the interference prediction model predicts that the quality score of the current best channel will drop sharply in the next few seconds due to the approach of a vehicle, while the quality score of another communication channel is stable and rising slowly, the model may switch to the other communication channel in advance to achieve a seamless transition.

[0076] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0077] A method for determining the communication channel of a tire pressure sensor corresponding to the above embodiment, Figure 2 A schematic diagram of a communication channel determination system for a tire pressure sensor according to an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0078] Reference Figure 2 The tire pressure sensor communication channel determination system 100 of this embodiment includes: a radar device 10, a tire pressure sensor 20, an artificial intelligence device 30, and a central controller 40.

[0079] The radar device 10 is located inside the wheel arch of the vehicle and close to the tires. It is used to collect environmental perception data of the vehicle's surroundings and send the environmental perception data to the artificial intelligence device 30.

[0080] Tire pressure sensor 20 is installed inside the vehicle's tires to collect radio frequency signal data of the vehicle's environment and send the radio frequency signal data to artificial intelligence device 30.

[0081] An artificial intelligence device 30, installed in the tire pressure sensor 20, receives vehicle operation data from the central controller 40, environmental perception data from the radar device 10, and radio frequency signal data from the tire pressure sensor 20. It extracts features from the environmental perception data and radio frequency signal data to obtain radar features corresponding to the environmental perception data and radio frequency features corresponding to the radio frequency signal data. The artificial intelligence device 30 also inputs the radar features, radio frequency features, and vehicle operation data into an interference prediction model. The interference prediction model predicts interference information in the future, obtaining an interference prediction result. This interference prediction model is a prediction model pre-trained based on a convolutional neural network. Furthermore, based on the interference prediction result and preset channel evaluation rules, it determines the target communication channel of the tire pressure sensor 20 in the vehicle, where the preset channel evaluation rules are used to quantify the quality of the communication channel. Finally, it sends the target communication channel to the central controller 40.

[0082] It is understood that the tire pressure sensor communication channel determination system 100 in this embodiment inputs the environmental perception data collected by the radar device 10, the radio frequency signal data collected by the tire pressure sensor 20, and the vehicle operation data sent by the central controller 40 into the interference prediction model. The interference prediction model predicts interference information based on the environmental perception data, radio frequency signal data, and vehicle operation data, obtains the interference prediction result, and switches the communication channel of the tire pressure sensor in advance based on the interference prediction result. This can realize the transformation of the tire pressure sensor from passive response to active prediction, reduce the data transmission conflict delay rate and retransmission number, thereby improving the stability and timeliness of data transmission. In one possible implementation, the central controller 40 is further configured to generate a channel switching command based on the quality score of the target communication channel and a preset score threshold, and send the channel switching command to the tire pressure sensor 20 so that the tire pressure sensor 20 switches to the target communication channel for communication according to the channel switching command.

[0083] If the quality score of the target communication channel is higher than the preset score threshold, the central controller 40 can generate a corresponding channel switching command and send it to the tire pressure sensor 20. Upon receiving the command, the tire pressure sensor 20 switches its communication channel, allowing tire pressure data to be transmitted on the target communication channel. It should be understood that by comparing the quality score with the preset score threshold, low-quality communication channels can be actively avoided, and the communication channel for tire pressure sensor data transmission can be switched promptly, thereby reducing the risk of tire pressure data transmission interruption and ensuring the reliability of tire pressure data transmission.

[0084] It is understood that the tire pressure sensor communication channel determination system provided in this application embodiment can intelligently predict interference signals by using radar to perceive the environment and interference prediction models, so that the tire pressure sensor can switch communication channels in advance, thereby realizing the transformation from "passive response" to "active prediction". At the same time, the selection of dynamic communication channels can reduce data conflicts and retransmissions, and improve the stability and timeliness of critical safety data.

[0085] It should be noted that the information interaction and execution process between the modules in the above-mentioned tire pressure sensor communication channel determination system 100 are based on the same concept as the method embodiment of this application. For details on their specific functions and technical effects, please refer to the method embodiment section, and they will not be repeated here.

[0086] This application also provides a terminal device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. (Refer to...) Figure 3The terminal device 3 in this embodiment includes a memory 31, a processor 32, and a computer program stored in the memory 31 and executable on the processor 32. When the processor 32 executes the computer program, it implements the steps in the embodiment of the tire pressure sensor communication channel determination method described above.

[0087] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the various method embodiments above.

[0088] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0089] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographic device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0090] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0091] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0092] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining the communication channel of a tire pressure sensor, characterized in that, include: Acquire multi-dimensional data of the vehicle; wherein, the multi-dimensional data includes vehicle operation data, environmental perception data of the environment in which the vehicle is located, and radio frequency signal data; Feature extraction is performed on the environmental perception data and the radio frequency signal data respectively to obtain the radar features corresponding to the environmental perception data and the radio frequency features corresponding to the radio frequency signal data; The radar features, radio frequency features, and vehicle operation data are input into the interference prediction model. The interference prediction model is used to predict interference information in the future to obtain the interference prediction result. The interference prediction model is a prediction model pre-trained based on a convolutional neural network. Based on the interference prediction results and the preset channel evaluation rules, the target communication channel of the tire pressure sensor in the vehicle is determined; wherein, the preset channel evaluation rules are used to quantify the quality of the communication channel.

2. The method for determining the communication channel of a tire pressure sensor as described in claim 1, characterized in that, The acquisition of multi-dimensional vehicle data includes: The environmental perception data is collected by a radar device installed inside the wheel arch of the vehicle and close to the tires. The radio frequency signal data is acquired by tire pressure sensors installed inside the tires of the vehicle.

3. The method for determining the communication channel of a tire pressure sensor as described in claim 2, characterized in that, The step of extracting features from the environmental perception data and the radio frequency signal data to obtain radar features corresponding to the environmental perception data and radio frequency features corresponding to the radio frequency signal data includes: Multiple target objects in the environmental perception data are identified using a clustering algorithm; The multiple target objects are continuously tracked by a target tracking algorithm, and each target object is assigned a unique identifier. The motion trajectory of each target object is calculated by a trajectory fitting algorithm. Based on the motion trajectory, the radar features are extracted, wherein the radar features include at least one of the following: surrounding vehicle density, distance and relative speed of the nearest vehicle, angular distribution of surrounding vehicles, and convergence / divergence trend based on trajectory prediction. The radio frequency signal data is scanned to obtain the spectrum diagrams corresponding to the multiple communication channels. The frequency and power information in multiple spectrum diagrams are quantized and the interference pulses in the spectrum diagrams are statistically analyzed to obtain the radio frequency characteristics; wherein the radio frequency characteristics include at least one of the following: channel average signal strength, channel signal-to-noise ratio, channel occupancy, and statistical characteristics of interference pulses.

4. The method for determining the communication channel of a tire pressure sensor as described in claim 3, characterized in that, The step involves inputting the radar characteristics, radio frequency characteristics, and vehicle operation data into an interference prediction model, and using the interference prediction model to predict interference information in future timeframes to obtain interference prediction results, including: The radar features, the radio frequency features, and the vehicle operation data are normalized to obtain the processed radar features, the processed radio frequency features, and the processed vehicle features. The processed radar features, the processed radio frequency features, and the processed vehicle features are fused to obtain multi-dimensional fused features; Based on the relationship between the multidimensional fusion features learned by the interference prediction model and the interference information, the interference information in the future time is predicted by the interference prediction model to obtain the interference prediction result, wherein the interference prediction result includes: the type of interference signal and the interference intensity of the interference signal.

5. The method for determining the communication channel of a tire pressure sensor as described in claim 4, characterized in that, The step of determining the target communication channel of the tire pressure sensor in the vehicle based on the interference prediction results and preset channel evaluation rules includes: Based on the interference prediction results and the preset channel evaluation rules, the quality of each communication channel is scored to obtain a quality score for each communication channel. The target communication channel is determined based on the quality score of each communication channel.

6. The method for determining the communication channel of a tire pressure sensor as described in claim 1, characterized in that, After determining the target communication channel for the tire pressure sensor in the vehicle, the method includes: Based on the quality score of the target communication channel and a preset score threshold, a channel switching command is generated and sent to the tire pressure sensor.

7. A communication channel determination system for a tire pressure sensor, characterized in that, include: Radar unit, tire pressure sensor, artificial intelligence device, and central controller; The radar device is located inside the wheel arch of the vehicle and close to the tires. It is used to collect environmental perception data of the vehicle's environment and send the environmental perception data to the artificial intelligence device. The tire pressure sensor is installed inside the tire of the vehicle and is used to collect radio frequency signal data of the environment in which the vehicle is located, and send the radio frequency signal data to the artificial intelligence device. The artificial intelligence device is installed in the tire pressure sensor and is used to receive vehicle operation data sent by the central controller, environmental perception data sent by the radar device, and radio frequency signal data sent by the tire pressure sensor; and to extract features from the environmental perception data and the radio frequency signal data respectively to obtain radar features corresponding to the environmental perception data and radio frequency features corresponding to the radio frequency signal data. The artificial intelligence device is further configured to input the radar features, the radio frequency features, and the vehicle operation data into an interference prediction model, and predict interference information in future time periods through the interference prediction model to obtain an interference prediction result; wherein, the interference prediction model is a prediction model pre-trained based on a convolutional neural network; and, based on the interference prediction result and a preset channel evaluation rule, determine the target communication channel of the tire pressure sensor in the vehicle, wherein the preset channel evaluation rule is used to quantify the quality of the communication channel; and send the target communication channel to the central controller.

8. The tire pressure sensor communication channel determination system as described in claim 7, characterized in that, The central controller is further configured to generate a channel switching command based on the quality score of the target communication channel and a preset score threshold, and send the channel switching command to the tire pressure sensor so that the tire pressure sensor switches to the target communication channel for communication according to the channel switching command.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program, which, when run, causes the method as described in any one of claims 1 to 6 to be performed.

Images