Intelligent travel planning method for signal anti-disturbance transmission

Abstract

The application discloses an intelligent travel planning method for signal anti-interference transmission, and the steps comprise the following: obtaining the starting point and the ending point of user travel, and planning a travel path based on a high-precision map; collecting voltage signals and environmental auxiliary data on the travel path by a microbial electrochemical sensor as radio frequency interference data; inputting the radio frequency interference data into a pre-trained deep learning network after pretreatment, and outputting interference source data from the deep learning network; performing collaborative decision on the interference source data based on a reinforcement learning network model, and outputting anti-interference adjustment instructions; adjusting the parameters of a transparent electrochromic film outside the transmission channel and the antenna based on the anti-interference adjustment instructions; evaluating the signal transmission quality after anti-interference adjustment, and modifying the travel path based on the current position when the signal transmission quality does not meet the preset requirements, so that the whole-process closed-loop travel planning is realized in combination with an artificial intelligence middleware, the signal anti-interference effect can be greatly improved, and normal travel of the user is ensured.

Description

A Smart Mobility Planning Method for Signal Disturbance-Resistant Transmission Technical Field

[0001] This invention relates to the field of signal processing technology, and in particular to an intelligent travel planning method for signal anti-disturbance transmission. Background Technology

[0002] With the development of intelligent connected vehicles and vehicle-to-everything (V2X) technology, the demand for stable transmission of multimodal traffic data during driving trips is increasing. However, in actual driving scenarios, external interference sources are complex and diverse. These include radio frequency reflections from buildings in densely populated urban areas, signal blockages in tunnels, strong electromagnetic radiation from equipment in industrial areas, and high-frequency communication interference from neighboring vehicles. These interferences can easily lead to signal attenuation, bit errors, or even interruptions in the signals received by the vehicle terminal. Such interference can not only cause navigation deviations and delays in V2X data transmission, but may also affect the signal interaction of intelligent driving assistance systems equipped with AI-optimized operating systems, reducing travel safety and user experience. At the same time, vehicle terminals are limited by battery life and hardware size, making it difficult to resist interference by simply increasing power, further exacerbating the signal transmission difficulties in complex interference environments.

[0003] Existing methods for dealing with the aforementioned interference are mostly passive defense strategies, mainly including fixed-band filters, traditional frequency hopping technology, and single power control algorithms. Fixed-band filters can only shield interference in preset frequency bands and cannot adapt to the dynamically changing interference frequency bands during driving, resulting in extremely poor flexibility. Traditional frequency hopping technology requires detecting interference before switching channels, which has a response lag and can easily lead to brief signal interruptions. Single power control algorithms only adjust the transmission power to resist interference, ignoring the coupling effect of energy consumption constraints and other interference factors, which can easily lead to excessive terminal energy consumption or insufficient anti-interference effect. In addition, existing methods do not combine artificial intelligence middleware and computer vision and audiovisual software technologies to achieve the prediction of interference sources and multi-dimensional collaborative control, making it difficult to adapt to the complex characteristics of dynamic migration of interference sources and superposition of multiple interferences in driving scenarios, and failing to fundamentally guarantee the stability and adaptability of signal anti-disturbance transmission. Summary of the Invention

[0004] In view of this, the present invention proposes an intelligent travel planning method for signal anti-disturbance transmission, which can significantly improve the effectiveness of signal anti-disturbance, ensure travel safety, and improve the driving experience.

[0005] The technical solution of this invention is implemented as follows:

[0006] A method for intelligent travel planning with disturbance-resistant signal transmission includes the following steps:

[0007] Step S1: Obtain the user's origin and destination, and plan the travel route based on a high-precision map;

[0008] Step S2: Collect voltage signals and environmental auxiliary data along the travel path using a microbial electrochemical sensor as radio frequency interference data;

[0009] Step S3: After preprocessing the radio frequency interference data, it is input into the pre-trained deep learning network, and the deep learning network outputs the interference source data.

[0010] Step S4: Based on the reinforcement learning network model, make collaborative decisions on the interference source data and output anti-disturbance adjustment instructions;

[0011] Step S5: Adjust the parameters of the transparent electrochromic film around the transmission channel and antenna based on the anti-disturbance adjustment command;

[0012] Step S6: Evaluate the signal transmission quality after disturbance rejection adjustment, and modify the travel route based on the current location if the signal transmission quality does not meet the preset requirements.

[0013] Preferably, step S1 includes the following steps:

[0014] Step S1-1: Obtain the user's input of the origin, destination, and travel preferences;

[0015] Step S1-2: Call up a high-precision map and generate several initial routes based on the origin and destination of the trip;

[0016] Steps S1-3: Filter the initial routes based on the user's travel preferences and provide the filtered initial routes back to the user;

[0017] Steps S1-4: The user selects one of the initial routes as the travel route.

[0018] Preferably, step S2 includes the following specific steps:

[0019] Step S2-1: Activate the microbial electrochemical sensor integrated into the smart travel terminal and preheat the electrogenic bacterial membrane electrode assembly to a stable operating temperature range.

[0020] Step S2-2: During the movement along the travel path, drive the microbial electrochemical sensor to continuously collect microcurrent signals corresponding to radio frequency interference and environmental auxiliary data;

[0021] Step S2-3: Amplify the micro-current signal to obtain a voltage signal, and output the voltage signal and environmental auxiliary data as radio frequency interference data.

[0022] Preferably, step S3 includes the following specific steps:

[0023] Step S3-1: Perform adaptive normalization on the voltage signal and obtain the normalized signal. At the same time, calculate the temperature correction coefficient based on the environmental auxiliary data.

[0024] Step S3-2: Extract the time-domain and frequency-domain features of the normalized signal and construct a multi-dimensional feature vector;

[0025] Step S3-3: Calculate the interference source intensity based on the pre-trained CNN-LSTM deep learning network, combined with temperature correction coefficients and multi-dimensional feature vectors, and identify the type and frequency band of the interference source.

[0026] Step S3-4: Output the interference source strength, interference source type, and interference source frequency band as interference source data.

[0027] Preferably, the interference source strength in step S3-3 The calculation formula is:

[0028] ;

[0029] in , , For feature weights, and , For signal fluctuation frequency, The reference interference-free frequency is N, where N is the number of data points within the sliding window. for Normalized signal at time, The sampling time of the k-th data point within the window. The normalized signal mean within the window. This is the temperature correction factor.

[0030] Preferably, the specific steps of step S4 are as follows:

[0031] Step S4-1: Construct a deep Q-network reinforcement learning model and define the state space S={I,T,R,P}, where I is the intensity of the interference source, T is the current transmittance of the transparent electrochromic film, R is the transmission rate, and P is the terminal power consumption.

[0032] Step S4-2: Define the action space A={U,C,P_t} of the deep Q-network reinforcement learning model, where U is the voltage applied to the transparent electrochromic film, C is the channel number, and P_t is the transmission power.

[0033] Step S4-3: Construct a nonlinear multi-objective reward function that includes anti-interference reward, transmission quality reward, and energy consumption reward;

[0034] Step S4-4: Based on the interference source data and communication status, update the Q value table through model iteration and output the anti-disturbance adjustment command.

[0035] Preferably, the expression for the nonlinear multi-objective reward function is:

[0036] ;

[0037] in For the total reward, These are the weighting coefficients, and , For the target transmittance, R is the current transmittance, and R is the transmission rate. The maximum transmission rate is given by BER, which is the bit error rate. This is the terminal's maximum transmit power.

[0038] Preferably, step S5 includes the following specific steps:

[0039] Step S5-1: Extract the applied voltage of the transparent electrochromic film from the anti-disturbance adjustment command, and adjust the transmittance of the transparent electrochromic film.

[0040] Step S5-2: Parse the channel switching command and power adjustment command from the anti-disturbance adjustment command, switch to the target channel based on the signal switching command, and adjust the transmission power based on the power adjustment command.

[0041] Preferably, step S6 includes the following specific steps:

[0042] Step S6-1: Collect the bit error rate, transmission rate, and delay after disturbance rejection adjustment as signal parameters;

[0043] Step S6-2: Calculate the signal transmission quality based on the signal parameters and compare it with the preset quality threshold;

[0044] Step S6-3: If the signal transmission quality is greater than the preset quality threshold, continue driving along the travel route;

[0045] Step S6-4: If the signal transmission quality is less than the preset quality threshold, a new travel route is generated by calling a high-precision map based on the current location and the user's destination.

[0046] Preferably, the formula for calculating the signal transmission quality is:

[0047] ;

[0048] Where K represents the signal transmission quality. R is the bit error rate, and R is the transmission rate. The maximum transmission rate is represented by `delay`, and the delay is the latency.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] This invention discloses an intelligent travel planning method for signal anti-disturbance transmission. After planning a travel route based on the user's starting point and destination, the user can travel according to the planned route. The installed microbial electrochemical sensor can collect radio frequency interference data on the travel route in real time. When radio frequency interference exists, it is identified and processed by a pre-trained deep learning network to determine the interference source data. Then, a reinforcement learning network is introduced, which can make collaborative decisions based on the interference source data and output anti-disturbance adjustment commands including adjusting the transmittance of the transparent electrochromic film around the antenna, channel switching, and output power adjustment. Based on three dimensions, anti-disturbance adjustment can significantly improve the anti-disturbance effect and ensure the stability of signal transmission.

[0051] A closed-loop feedback mechanism was also added to evaluate the signal transmission quality after the anti-disturbance adjustment was performed and compare it with a preset quality threshold. If the quality quality is greater than the preset quality threshold, it indicates that the signal anti-disturbance strategy is effective and can maintain the driving on the travel route. If the quality quality is less than the preset quality threshold, it indicates that the signal anti-disturbance strategy has not played a significant role. In this case, the travel route can be modified based on the current location to avoid the signal failure caused by continuous driving on the route, which would affect normal driving. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only preferred embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 is a schematic diagram of the structure of an intelligent travel planning method for signal anti-disturbance transmission according to the present invention;

[0054] Figure 2 is a structural schematic diagram of step S1 of the intelligent travel planning method for signal anti-disturbance transmission according to the present invention;

[0055] Figure 3 is a structural schematic diagram of step S2 of the intelligent travel planning method for signal anti-disturbance transmission according to the present invention;

[0056] Figure 4 is a structural schematic diagram of step S3 of the intelligent travel planning method for signal anti-disturbance transmission according to the present invention;

[0057] Figure 5 is a structural schematic diagram of step S4 of the intelligent travel planning method for signal anti-disturbance transmission according to the present invention;

[0058] Figure 6 is a structural schematic diagram of step S5 of the intelligent travel planning method for signal anti-disturbance transmission according to the present invention;

[0059] Figure 7 is a structural schematic diagram of step S6 of the intelligent travel planning method for signal anti-disturbance transmission according to the present invention. Detailed Implementation

[0060] To better understand the technical content of this invention, a specific embodiment is provided below, and the invention will be further described in conjunction with the accompanying drawings.

[0061] Referring to Figures 1-7, the present invention provides an intelligent travel planning method for signal disturbance-resistant transmission, comprising the following steps:

[0062] Step S1: Obtain the user's origin and destination, and plan the travel route based on a high-precision map;

[0063] Step S2: Collect voltage signals and environmental auxiliary data along the travel path using a microbial electrochemical sensor as radio frequency interference data;

[0064] Step S3: After preprocessing the radio frequency interference data, it is input into the pre-trained deep learning network, and the deep learning network outputs the interference source data.

[0065] Step S4: Based on the reinforcement learning network model, make collaborative decisions on the interference source data and output anti-disturbance adjustment instructions;

[0066] Step S5: Adjust the parameters of the transparent electrochromic film around the transmission channel and antenna based on the anti-disturbance adjustment command;

[0067] Step S6: Evaluate the signal transmission quality after disturbance rejection adjustment, and modify the travel route based on the current location if the signal transmission quality does not meet the preset requirements.

[0068] This invention discloses an intelligent travel planning method for signal anti-disturbance transmission, which is used to monitor in real time along a preset travel route to determine whether interference exists. When interference exists, after identifying parameters such as the intensity and type of interference, a reinforcement learning network is used to make collaborative decisions on the interference source and obtain corresponding anti-disturbance adjustment instructions. The anti-disturbance adjustment instructions transmit the signal in an anti-disturbance manner from three dimensions, thereby improving the accuracy of signal transmission during travel, reducing false alarms and delays, and ensuring that automated decisions such as autonomous driving and assisted driving can be executed accurately and safely, thereby improving the user's driving experience.

[0069] Specifically, the first step is to determine the user's travel itinerary. This can be achieved by recommending the origin and destination based on the user's manually input or pre-defined travel habits. Then, a travel route from the origin to the destination can be planned using mature high-precision maps. The user can then choose between manual driving or driverless assistance based on this route. The user's vehicle's intelligent travel terminal integrates a microbial electrochemical sensor, which can collect environmental data in real time along the travel route, including the presence of radio frequency interference (RF interference). RF interference can cause signal transmission problems, including false alarms and delays, thus affecting the intelligent vehicle's real-time decision-making. This not only impacts the user's riding and driving experience but also increases the risk of safety accidents. Therefore, if RF interference is present, its intensity needs to be identified, and corresponding anti-interference strategies need to be implemented. For this purpose, this invention pre-trains a deep learning system... The learning network can identify relevant interference sources based on radio frequency interference data collected by microbial electrochemical sensors. Then, a reinforcement learning network model is introduced, which can dynamically fuse interference source data, the state of the transparent electrochromic film, and signal transmission parameters to achieve an optimal balance among multiple objectives: anti-interference effect, transmission stability, and terminal power consumption. It also generates corresponding anti-disturbance adjustment commands. The main components of the anti-disturbance adjustment commands include the transparent electrochromic film and the transmission channel. The transparent electrochromic film is located on the periphery of the antenna. By adjusting its transmittance, it can dynamically shield electromagnetic waves of different frequency bands and simultaneously adjust the transmitted signal, greatly improving the signal's anti-disturbance capability and ensuring the accuracy and stability of signal transmission. It can accurately adapt to the dynamic changes in interference in driving scenarios and overcome the shortcomings of traditional single control methods, such as poor flexibility and slow response.

[0070] Furthermore, this invention incorporates a closed-loop feedback mechanism. After anti-disturbance adjustment, the transmitted signal parameters are collected, and the signal transmission quality is evaluated. The signal transmission quality is compared with preset requirements. If the preset requirements are met, it indicates that the anti-disturbance adjustment strategy is effective, and the user can continue traveling along the route. If the preset requirements are not met, it indicates that the anti-interference strategy is ineffective. To ensure the user's travel safety, the route can be replanned based on the user's current location, and the user can then travel along the new route, avoiding the impact of uncontrollable interference in the original route on normal travel. Through the entire process of real-time acquisition, interference identification, collaborative decision-making, and closed-loop feedback, the signal anti-disturbance effect can be significantly improved, ensuring the user's normal travel.

[0071] Preferably, step S1 includes the following steps:

[0072] Step S1-1: Obtain the user's input of the origin, destination, and travel preferences;

[0073] Step S1-2: Call up a high-precision map and generate several initial routes based on the origin and destination of the trip;

[0074] Steps S1-3: Filter the initial routes based on the user's travel preferences and provide the filtered initial routes back to the user;

[0075] Steps S1-4: The user selects one of the initial routes as the travel route.

[0076] The vehicle's intelligent terminal can automatically locate the vehicle's current position to determine the starting point of the trip. Then, the user can input the destination through manual or voice interaction, and call existing mature high-precision map software to generate a route. Depending on the city's road network, there will be multiple accessible initial routes, so it is necessary to filter the initial routes. For this purpose, user travel preferences can be collected, such as preference for short travel time, preference for less congestion, preference for beautiful scenery, etc. Based on different travel preferences, the initial routes can be filtered to obtain 2-3 initial routes. The final filtered initial routes will be fed back to the visualization terminal for the user to select. The initial route selected by the user will be the final travel route. Then, the user can drive the vehicle along the travel route manually or using unmanned assisted intelligent driving functions.

[0077] Preferably, step S2 includes the following specific steps:

[0078] Step S2-1: Activate the microbial electrochemical sensor integrated into the smart travel terminal and preheat the electrogenic bacterial membrane electrode assembly to a stable operating temperature range.

[0079] Step S2-2: During the movement along the travel path, drive the microbial electrochemical sensor to continuously collect microcurrent signals corresponding to radio frequency interference and environmental auxiliary data;

[0080] Step S2-3: Amplify the micro-current signal to obtain a voltage signal, and output the voltage signal and environmental auxiliary data as radio frequency interference data.

[0081] Microbial electrochemical sensors are a novel type of sensor that combines microbial metabolic activity with electrochemical conversion technology. The core of the sensor consists of a bioanode, cathode, signal amplification, and acquisition module. It can achieve real-time response to target stimuli without additional power. Integrated into intelligent mobility terminals in vehicles, the microbial electrochemical sensor preheats the electrogenic bacterial membrane electrode assembly to a stable operating temperature range as the vehicle travels along its path. During movement, the electrogenic bacteria on the anode surface generate electrons through metabolic activity by oxidizing the substrate. These electrons are transferred to the cathode via an external circuit, forming a stable microcurrent. When radio frequency interference exists in the external environment, the metabolic activity of the electrogenic bacteria is affected, altering electron transfer efficiency and causing fluctuations in the output electrical signal. The anode captures these fluctuations to obtain the corresponding microcurrent signal, which is then amplified by a signal amplification circuit, increasing the nA-level current signal to a V-level voltage signal. Simultaneously, the microbial electrochemical sensor integrates a temperature and humidity sensor, allowing for the synchronous acquisition of temperature and humidity data as environmental auxiliary data. Finally, the voltage signal and environmental auxiliary data are output as radio frequency interference data, which can then be used as input to a deep learning network to identify interference sources.

[0082] Preferably, step S3 includes the following specific steps:

[0083] Step S3-1: Perform adaptive normalization on the voltage signal and obtain the normalized signal. At the same time, calculate the temperature correction coefficient based on the environmental auxiliary data.

[0084] Step S3-2: Extract the time-domain features (fluctuation frequency, peak interval) and frequency-domain features (dominant frequency component, harmonic amplitude) of the normalized signal, and construct a multi-dimensional feature vector;

[0085] Step S3-3: Calculate the interference source intensity based on a pre-trained CNN-LSTM deep learning network combined with temperature correction coefficients and multi-dimensional feature vectors, and identify the interference source type and frequency band. The calculation formula is:

[0086] ;

[0087] in , , For feature weights, and , For signal fluctuation frequency, The reference interference-free frequency is N, where N is the number of data points within the sliding window. for Normalized signal at time, The sampling time of the k-th data point within the window. The normalized signal mean within the window. This is a temperature correction factor, ranging from 0.8 to 1.2.

[0088] Step S3-4: Output the interference source strength, interference source type, and interference source frequency band as interference source data.

[0089] The deep learning network of this invention is a CNN-LSTM deep learning network, trained on a large amount of historical data. Before identifying and processing radio frequency interference data, the radio frequency interference data needs to be preprocessed. Voltage signals and environmental auxiliary data require different processing methods. The voltage signal undergoes adaptive normalization with noise suppression using a normalization formula, which is: ,in for Normalized signal at time, Let be the mean of the signal within the sliding window at time t. Let be the standard deviation of the signal within the sliding window at time t. To minimize the value, we avoid the denominator being zero, which could lead to calculation errors. Finally, by multiplying by 1 / 2 and adding 0.5, we can normalize the signal to the [0,1] interval, eliminating time-varying noise and dimensional effects. The environmental auxiliary data can then be used to calculate the temperature correction coefficient, which is used for subsequent calculations of interference source intensity.

[0090] After the radio frequency interference data is processed, it can be input into a pre-trained CNN-LSTM deep learning network to calculate the interference source strength and achieve accurate quantification of the interference source. The interference source strength I is in the range of 0-10, and the larger the value, the stronger the interference. In addition to quantifying the interference source strength, the CNN-LSTM deep learning network will also identify the interference source type, interference source frequency band, and diffusion speed, and output the data as interference source data. The interference source data is then used as the input of the reinforcement learning network model.

[0091] Preferably, the specific steps of step S4 are as follows:

[0092] Step S4-1: Construct a deep Q-network reinforcement learning model and define the state space S={I,T,R,P}, where I is the intensity of the interference source, T is the current transmittance of the transparent electrochromic film, R is the transmission rate, and P is the terminal power consumption.

[0093] Step S4-2: Define the action space A={U,C,P_t} of the deep Q-network reinforcement learning model, where U is the voltage applied to the transparent electrochromic film, C is the channel number, and P_t is the transmission power.

[0094] Step S4-3: Construct a nonlinear multi-objective reward function that includes anti-interference reward, transmission quality reward, and energy consumption reward. The expression of the nonlinear multi-objective reward function is as follows:

[0095] ;

[0096] in For the total reward, These are the weighting coefficients, and It can dynamically adapt to intelligent travel scenarios. For the target transmittance, R is the current transmittance, and R is the transmission rate. The maximum transmission rate is given by BER, which is the bit error rate. Let be the maximum transmit power of the terminal. In the expression of the nonlinear multi-objective reward function, To mitigate interference, an exponential function is used to enhance transmittance control accuracy; the smaller the deviation, the closer the reward value is to the target value. , Rewards for transmission quality are directly related to communication stability. As an energy consumption reward, priority is given to low energy consumption adjustment strategies, which are in line with the battery life requirements of smart mobility terminals. By setting a nonlinear multi-objective reward function, anti-interference effect, transmission stability and energy consumption optimization can be balanced to improve decision robustness.

[0097] Step S4-4: Based on the interference source data and communication status, update the Q value table through model iteration and output the anti-disturbance adjustment command.

[0098] The reinforcement learning network employs a Deep Q-Network reinforcement learning model (DQN). Before outputting anti-disturbance adjustment commands, its state space, action space, and reward function need to be predefined. The state space corresponds to the multimodal parameters collected during the driving process, including the intensity of the interference source, the current transmittance of the transparent electrochromic film, the signal transmission rate, and the terminal power consumption. Essentially, it is the set of all real-time scene data that the DQN reinforcement learning model can acquire. Its function is to allow the model to accurately grasp the current interference situation, equipment status, and communication quality, providing a basis for decision-making and ensuring that the commands fit the real-time scenario. The action space corresponds to the final operation, namely, adjusting the transparent electrochromic film and the transmission signal. It represents all output anti-disturbance adjustment actions and serves to limit the decision boundary, ensuring that the model's output commands are within the hardware capabilities and avoiding invalid operations. The core function of the reward function is to transform the abstract anti-disturbance goal into a quantifiable one. This guides the model to iteratively optimize by rewarding high-quality decisions with high rewards and low-quality decisions with low rewards, allowing the model to gradually learn the optimal adjustment strategy to adapt to different interference scenarios.

[0099] Once the state space, action space, and reward function are defined, data from the state space can be collected in real time and substituted into the algorithm. In the calculation formula, the Q-value table is iteratively updated to filter out values ​​that are suitable for the current state. The maximum combination of actions is used to generate corresponding disturbance rejection control commands, including the applied voltage of the transparent electrochromic film, the target channel to be switched, and the transmission power.

[0100] Preferably, step S5 includes the following specific steps:

[0101] Step S5-1: Extract the applied voltage of the transparent electrochromic film from the anti-disturbance adjustment command, and adjust the transmittance of the transparent electrochromic film.

[0102] Step S5-2: Parse the channel switching command and power adjustment command from the anti-disturbance adjustment command, switch to the target channel based on the signal switching command, and adjust the transmission power based on the power adjustment command.

[0103] After receiving the anti-disturbance adjustment command, the anti-disturbance strategy can be executed. The specific targets of the execution include the transparent electrochromic film and the transmission signal. The applied voltage can be parsed from the anti-disturbance adjustment command, and then the voltage transmitted to the transparent electrochromic film can be changed based on the applied voltage, thereby changing the transmittance of the target interference frequency band. The adjustment of the transmission channel includes switching to the target channel and adjusting the transmission power. By switching the channel and adjusting the transmission power, the current interference intensity can be adapted. After the anti-disturbance adjustment command is executed, the transmittance of the transparent electrochromic film and the channel parameters can be collected in real time for feedback acquisition to confirm that the adjustment command has been executed in place.

[0104] Preferably, step S6 includes the following specific steps:

[0105] Step S6-1: Collect the bit error rate, transmission rate, and delay after disturbance rejection adjustment as signal parameters;

[0106] Step S6-2: Calculate the signal transmission quality based on the signal parameters and compare it with a preset quality threshold. The formula for calculating the signal transmission quality is:

[0107] ;

[0108] Where K represents the signal transmission quality. R is the bit error rate, and R is the transmission rate. The maximum transmission rate is represented by `delay`, and the delay is the latency.

[0109] Step S6-3: If the signal transmission quality is greater than the preset quality threshold, continue driving along the travel route;

[0110] Step S6-4: If the signal transmission quality is less than the preset quality threshold, a new travel route is generated by calling a high-precision map based on the current location and the user's destination.

[0111] To ensure travel safety, this invention introduces a closed-loop feedback process after the anti-disturbance adjustment command is executed. This process collects signal parameters after the command's execution and calculates the signal transmission quality using a signal transmission quality calculation formula. The signal transmission quality is then compared to a preset quality threshold, which is between 0.7 and 0.8. If the signal transmission quality is greater than the preset threshold, it indicates effective signal anti-interference, allowing the user to continue driving on the original route. If the signal transmission quality is less than the preset threshold, it indicates the anti-interference strategy is ineffective, and the external interference source is too strong to be effectively controlled by altering the transmittance of the transparent electrochromic film and signal parameters. In this case, the user's real-time location is obtained, and a new travel route is planned based on the user's preset destination. This new route differs from the original route, preventing excessive interference from the original route from affecting the driving process and ensuring user safety.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart travel planning method for signal anti-disturbance transmission, characterized in that, Includes the following steps: Step S1: Obtain the user's origin and destination, and plan the travel route based on a high-precision map; Step S2: Collect voltage signals and environmental auxiliary data along the travel path using a microbial electrochemical sensor as radio frequency interference data; Step S3: After preprocessing the radio frequency interference data, input it into a pre-trained deep learning network, which outputs interference source data; Step S4: Perform collaborative decision-making on the interference source data based on a reinforcement learning network model and output anti-disturbance adjustment commands; Step S5: Adjust the parameters of the transmission channel and the transparent electrochromic film around the antenna based on the anti-disturbance adjustment commands; Step S6: Evaluate the signal transmission quality after anti-disturbance adjustment, and modify the travel path based on the current location if the signal transmission quality does not meet the preset requirements; The specific steps of step S4 are as follows: Step S4-1: Construct a deep Q-network reinforcement learning model, defining the state space S={I,T,R,P}, where I is the interference source strength, T is the current transmittance of the transparent electrochromic film, R is the transmission rate, and P is the terminal power consumption; Step S4-2: Define the action space A={U,C,P_t} of the deep Q-network reinforcement learning model, where U is the voltage applied to the transparent electrochromic film, C is the channel number, and P_t is the transmit power; Step S4-3: Construct a nonlinear multi-objective reward function that includes anti-interference reward, transmission quality reward, and power consumption reward; Step S4-4: Based on the interference source data and communication status, update the Q-value table through model iteration and output the anti-interference adjustment command.

2. The intelligent travel planning method for signal anti-disturbance transmission according to claim 1, characterized in that, The specific steps of step S1 include: step S1-1, obtaining the user's input of the starting point, destination, and travel preferences; step S1-2, calling a high-precision map to generate several initial routes based on the starting point and destination; step S1-3, filtering the initial routes based on the user's travel preferences and providing the filtered initial routes back to the user; step S1-4, allowing the user to select one of the initial routes as their travel route.

3. The intelligent travel planning method for signal anti-disturbance transmission according to claim 1, characterized in that, The specific steps of step S2 include: step S2-1, starting the microbial electrochemical sensor integrated in the smart travel terminal and preheating the electrogenic bacterial membrane electrode assembly to a stable operating temperature range; step S2-2, driving the microbial electrochemical sensor to continuously collect microcurrent signals corresponding to radio frequency interference and environmental auxiliary data during the movement along the travel path; step S2-3, amplifying the microcurrent signal to obtain a voltage signal, and outputting the voltage signal and environmental auxiliary data as radio frequency interference data.

4. The intelligent travel planning method for signal anti-disturbance transmission according to claim 1, characterized in that, The specific steps of step S3 include: Step S3-1, adaptively normalizing the voltage signal to obtain a normalized signal, and calculating the temperature correction coefficient based on environmental auxiliary data; Step S3-2, extracting the time-domain and frequency-domain features of the normalized signal and constructing a multi-dimensional feature vector; Step S3-3, calculating the interference source strength based on a pre-trained CNN-LSTM deep learning network combined with the temperature correction coefficient and the multi-dimensional feature vector, and identifying the interference source type and frequency band; Step S3-4, outputting the interference source strength, interference source type, and interference source frequency band as interference source data.

5. The intelligent travel planning method for signal anti-disturbance transmission according to claim 4, characterized in that, The interference source strength in step S3-3 The calculation formula is: ;in 、 、 For feature weights, and ， For signal fluctuation frequency, The reference interference-free frequency is N, where N is the number of data points within the sliding window. for Normalized signal at time, The sampling time of the k-th data point within the window. The normalized signal mean within the window. This is the temperature correction factor.

6. The intelligent travel planning method for signal anti-disturbance transmission according to claim 1, characterized in that, The expression for the nonlinear multi-objective reward function is: ;in For the total reward, These are the weighting coefficients, and ， For the target transmittance, R is the current transmittance, and R is the transmission rate. The maximum transmission rate is given by BER, which is the bit error rate. This is the terminal's maximum transmit power.

7. The intelligent travel planning method for signal anti-disturbance transmission according to claim 1, characterized in that, The specific steps of step S5 include: step S5-1, parsing the applied voltage of the transparent electrochromic film from the anti-disturbance adjustment command, and adjusting the transmittance of the transparent electrochromic film; step S5-2, parsing the channel switching command and power adjustment command from the anti-disturbance adjustment command, switching to the target channel based on the signal switching command, and adjusting the transmission power based on the power adjustment command.

8. The intelligent travel planning method for signal anti-disturbance transmission according to claim 1, characterized in that, The specific steps of step S6 include: Step S6-1, collecting the bit error rate, transmission rate, and delay after disturbance rejection adjustment as signal parameters; Step S6-2, calculating the signal transmission quality based on the signal parameters and comparing it with a preset quality threshold; Step S6-3, if the signal transmission quality is greater than the preset quality threshold, maintaining the travel path; Step S6-4, if the signal transmission quality is less than the preset quality threshold, generating a new travel path based on the current location and the user's travel destination using a high-precision map.

9. The intelligent travel planning method for signal anti-disturbance transmission according to claim 8, characterized in that, The formula for calculating the signal transmission quality is as follows: Where K represents the signal transmission quality. R is the bit error rate, and R is the transmission rate. The maximum transmission rate is represented by `delay`, which represents the time delay.

Images