A temperature control device and method for a smart helmet

Abstract

This invention proposes a temperature control device and method for a smart helmet. It belongs to the interdisciplinary fields of smart wearable devices, thermal management, and human factors engineering. The method includes: dividing the wearing area of ​​the smart helmet into three physiological thermal sensing zones to generate physiological thermal response data for the forehead, temples, and occipital region; deploying a multimodal physiological sensor array based on the physiological thermal response data of the forehead, temples, and occipital region to construct a zoned monitoring network based on a human thermal comfort model. Through the three-zone physiological thermal sensing division and the construction of the multimodal physiological sensor array, it is possible to accurately capture individual differences among cyclists and dynamic riding conditions, greatly improving the accuracy of helmet temperature control and allowing each cyclist to enjoy a comfortable temperature tailored to their individual needs.

Description

Technical Field

[0001] This invention proposes a temperature control device and method for a smart helmet, belonging to the interdisciplinary fields of smart wearable devices, thermal management, and human factors engineering. Background Technology

[0002] In the field of smart cycling equipment, helmets, as key pieces of equipment for ensuring cyclists' safety and enhancing the cycling experience, are seeing their functions continuously expand. However, current smart helmets or cycling helmets with temperature control functions still have many problems that urgently need to be solved in terms of temperature regulation and control.

[0003] Traditional helmets have a very crude control strategy, often using a single temperature control switch or fixed settings. They cannot accurately adapt to individual differences among riders, such as heat tolerance and perspiration, as well as dynamic riding conditions, such as speed and ambient temperature, resulting in some users feeling too hot or too cold.

[0004] Optical anti-fog treatment is passive and inefficient, relying solely on hydrophobic coatings. In high humidity environments, the lenses still fog up frequently, severely affecting the clarity of AR displays and posing safety hazards to cyclists.

[0005] Interference between functional modules is a prominent issue. The electromagnetic noise generated by the cooling fan can interfere with the bone conduction microphone, reduce noise reduction performance, and affect the rider's communication with the outside world.

[0006] Furthermore, the excessive energy consumption of the full-area cooling mode significantly shortens battery life, forcing users to disable the temperature control function to extend battery life. Existing patents mostly focus on hardware stacking, failing to deeply integrate functions such as temperature control, purification, display, and noise reduction to build a cognitive-level microclimate operating system with "physiological perception, zoned regulation, optical protection, and multi-field collaboration," thus failing to achieve an intelligent temperature control paradigm that "understands the human body, protects optics, and saves energy." Summary of the Invention

[0007] This invention provides a helmet temperature control device and method for a smart helmet, to solve the problems mentioned in the background section: This invention proposes a method for temperature control and regulation of a smart helmet, the method comprising: S1. Divide the wearing area of ​​the smart helmet into three physiological thermal sensing zones to generate physiological thermal response data for the forehead, temples, and occipital region of the head; deploy a multimodal physiological sensor array based on the physiological thermal response data for the forehead, temples, and occipital region of the head to construct a zoned monitoring network based on the human thermal comfort model. S2. Based on the zoned monitoring network, perform dynamic heat load weight allocation and generate three-zone priority control commands; drive the microfluidic cooling channel and local heating unit to work together through the priority control commands to collect raw microclimate environment data; perform multi-physics field coupling analysis on the raw microclimate environment data to generate zoned heat flux density distribution data. S3. Based on the zoned heat flux density distribution data, perform optical anti-fogging priority assessment and generate a lens fogging risk index. When the lens fogging risk index exceeds the threshold, initiate the microfluidic guide layer directional defogging program and generate an anti-fogging control signal. Adjust the local airflow speed and humidity gradient through the anti-fogging control signal to generate optical clarity assurance data. S4. Collect power consumption data of display unit through AR display load feedback module and generate display thermal disturbance compensation command; fuse display thermal disturbance compensation command with zone heat flux density distribution data to generate multi-field coordinated control parameters; optimize power allocation of cooling / heating unit according to multi-field coordinated control parameters and generate energy efficiency optimization control data. S5. Based on the energy efficiency optimization control data, perform bone conduction microphone noise suppression processing to generate electromagnetic interference isolation commands; adjust the working phase of the cooling fan through the electromagnetic interference isolation commands to generate noise reduction control data; generate a comprehensive comfort index by combining optical clarity assurance data and noise reduction control data; trigger a dynamic warning when the comprehensive comfort index is lower than the preset value, and generate helmet temperature control adjustment warning data.

[0008] This invention proposes a helmet temperature control device for a smart helmet, the device comprising: One or more processors; Memory, used to store one or more programs; Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method described in any one of the above.

[0009] The beneficial effects of this invention are as follows: By dividing the body into three physiological thermal sensing zones and constructing a multimodal physiological sensor array, it can accurately capture individual differences among cyclists and dynamic riding conditions, greatly improving the accuracy of helmet temperature control and allowing each cyclist to enjoy a comfortable temperature tailored to their individual needs. The optical anti-fog priority and display load feedback mechanism effectively reduce the risk of lens fogging while ensuring AR display clarity, avoiding safety accidents caused by obstructed vision and enhancing riding safety. The generation of multi-physics field coupling analysis and multi-field collaborative control parameters reduces mutual interference between functional modules and reduces the impact of cooling fan electromagnetic noise on the bone conduction microphone, ensuring clear communication between the cyclist and the outside world. Energy efficiency optimization control and dynamic heat load weight allocation avoid the high energy consumption problem caused by full-area cooling, reduce battery life loss, and extend helmet usage time. Attached Figure Description

[0010] Figure 1 This is a diagram illustrating the steps of the method described in this invention. Detailed Implementation

[0011] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0012] One embodiment of the present invention, such as Figure 1 As shown, a method for temperature control adjustment of a smart helmet includes: S1. Divide the wearing area of ​​the smart helmet into three physiological thermal sensing zones to generate physiological thermal response data for the forehead, temples, and occipital region of the head; deploy a multimodal physiological sensor array based on the physiological thermal response data for the forehead, temples, and occipital region of the head to construct a zoned monitoring network based on the human thermal comfort model. S2. Based on the zoned monitoring network, perform dynamic heat load weight allocation and generate three-zone priority control commands; drive the microfluidic cooling channel and local heating unit to work together through the priority control commands to collect raw microclimate environment data; perform multi-physics field coupling analysis on the raw microclimate environment data to generate zoned heat flux density distribution data. S3. Based on the zoned heat flux density distribution data, perform optical anti-fogging priority assessment and generate a lens fogging risk index. When the lens fogging risk index exceeds the threshold, initiate the microfluidic guide layer directional defogging program and generate an anti-fogging control signal. Adjust the local airflow speed and humidity gradient through the anti-fogging control signal to generate optical clarity assurance data. S4. Collect power consumption data of display unit through AR display load feedback module and generate display thermal disturbance compensation command; fuse display thermal disturbance compensation command with zone heat flux density distribution data to generate multi-field coordinated control parameters; optimize power allocation of cooling / heating unit according to multi-field coordinated control parameters and generate energy efficiency optimization control data. S5. Based on the energy efficiency optimization control data, perform bone conduction microphone noise suppression processing to generate electromagnetic interference isolation commands; adjust the working phase of the cooling fan through the electromagnetic interference isolation commands to generate noise reduction control data; generate a comprehensive comfort index by combining optical clarity assurance data and noise reduction control data; trigger a dynamic warning when the comprehensive comfort index is lower than the preset value, and generate helmet temperature control adjustment warning data.

[0013] The working principle and effects of the above technical solution are as follows: By dividing the head into three physiological thermal sensing zones and deploying sensor arrays, the thermal response state of different zones can be accurately captured, improving the detail of temperature control monitoring and avoiding control deviations caused by single-zone sensing. Dynamic heat load weight allocation can improve temperature control response efficiency and enhance the thermal comfort balance of different parts of the head. Multi-physics field coupling analysis can accurately grasp the zoned heat flow state, reduce ineffective temperature control actions, and reduce energy waste. Optical anti-fog priority assessment and directional defogging procedures improve lens clarity and prevent fogging from affecting the user's vision. AR display thermal disturbance compensation optimizes power allocation and improves the overall system energy efficiency. Bone conduction noise suppression and fan phase adjustment reduce operating noise and electromagnetic interference. Real-time monitoring of the comprehensive comfort index ensures accurate and efficient temperature control adjustment and comprehensively improves the wearing experience, avoiding the decrease in comfort caused by the superposition of temperature, fog, and noise.

[0014] In one embodiment of the present invention, S1 includes: S11. The system synchronously collects raw positioning signal data, inertial measurement data, and environmental perception data during the riding process through the multimodal sensor group built into the smart helmet. S12. The acquired raw positioning signal data is distinguished by signal type, and independent positioning signal units with different transmission modes are separated. S13. Perform abnormal data filtering and signal normalization on the independent positioning signal units to generate high-quality normalized positioning signal data; S14. Perform multi-source signal cross-fusion on the normalized positioning signal data to generate fused positioning basic data compatible with multiple types of signals; S15. Unify the signal format and integrate the features of the fused positioning basic data to generate standardized hybrid positioning source data.

[0015] The working principle and effects of the above technical solution are as follows: Simultaneous acquisition of multiple types of data by multimodal sensors ensures the comprehensiveness of positioning information, avoids data gaps caused by single-sensor acquisition, and improves the integrity of raw data. Differentiating and independently splitting signals by type reduces mutual interference caused by signal mixing, improving the clarity of subsequent processing. Abnormal data filtering and signal normalization reduce the proportion of invalid data and improve signal quality. Cross-fusion of multi-source signals enhances the complementarity of different positioning methods and reduces the impact of environmental changes on positioning. Unifying signal formats and integrating features improves data compatibility and standardization, avoiding format conflicts that affect subsequent calculations. This not only makes the basic positioning data more stable and reliable but also provides solid support for subsequent precise positioning, improving the smoothness and accuracy of the overall positioning process.

[0016] In one embodiment of the present invention, step S14 includes: Signal dimension analysis is performed on the normalized positioning signal data to extract the transmission characteristics and spatial response information of different signals and generate a multi-source signal basic feature set; Perform cross-signal association matching on the basic feature set of multi-source signals, establish feature correspondence between different positioning signals, and generate a signal association dataset; Perform multi-dimensional cross-fusion operations on the signal association dataset to fuse the advantageous features of different signals and generate intermediate fused positioning data. Signal conflict detection and smoothing are performed on intermediate fused positioning data to eliminate numerical differences between different signals and generate consistent fused data. Signal compatibility adjustments are made to the consistent fusion data to adapt to subsequent data processing procedures and generate fusion positioning base data compatible with multiple types of signals.

[0017] The working principle and effects of the above technical solution are as follows: By performing multi-dimensional analysis and feature extraction on the normalized positioning signal, the core attributes of various signals can be fully preserved, improving signal utilization efficiency and avoiding positioning deviations caused by the loss of key features. Cross-signal association matching establishes the correspondence between different data sources, enhancing data synergy and reducing signal disconnection issues. Multi-dimensional cross-fusion fully leverages the advantages of various signals, improving the stability and reliability of overall positioning data. Signal conflict detection and smoothing eliminate numerical differences, reduce data fluctuations, and avoid logical contradictions during fusion. Compatibility adjustments allow the output data to better adapt to subsequent processes, improving overall processing smoothness. This ensures efficient collaboration of multi-source signals and provides high-quality basic data for subsequent accurate positioning, enhancing the adaptability of the entire positioning system.

[0018] In one embodiment of the present invention, S2 includes: S21. Based on the adaptive positioning source allocation results, perform quality grading and evaluation of multi-source positioning signals and divide the signal quality distribution range. S22. Redundant signal completion and distorted signal correction are performed on the low-quality signal areas identified in the assessment to generate repaired positioning signal data. S23. Extract the temporal and spatial information of the repaired positioning signal data and inertial measurement data to complete the time dimension synchronization of the two data sources; S24. Perform spatial coordinate benchmark calibration on the time-synchronized data to eliminate spatial offset between data and generate spatiotemporally unified data. S25. Introduce the trained cycling dynamics model, correct the motion state of the spatiotemporal unified data, and generate compensated positioning signal data.

[0019] The working principle and effects of the above technical solution are as follows: Quality grading and evaluation of multi-source positioning signals enables rapid screening of effective signals, improving data filtering efficiency and preventing inferior signals from directly affecting positioning accuracy. Completion and correction are performed on low-quality signals to improve data integrity and reduce positioning fluctuations caused by signal loss or distortion. Dual data source time synchronization enhances data matching accuracy and avoids trajectory breaks caused by time misalignment. Spatial coordinate benchmark calibration eliminates data offset and improves the consistency of positioning output. Introducing a cycling dynamics model completes motion state correction, making the trajectory more closely resemble real cycling conditions and reducing positioning errors in complex cycling scenarios. This ensures continuous and stable positioning data while ensuring the output results closely match actual cycling behavior, avoiding positioning distortion caused by data mismatch and further improving the reliability of smart helmet positioning.

[0020] In one embodiment of the present invention, step S23 includes: Extract the timestamp, spatial coordinates, and signal sampling frequency information of each frame of the repaired positioning signal data to generate temporal spatial detail data of the positioning signal. Extract the timestamp, acceleration, angular velocity, and attitude angle information of each frame of inertial measurement data to generate detailed data of inertial measurement timing parameters; The time-series spatial detail data of positioning signals and the time-series parameter detail data of inertial measurement are initially screened by timestamps to remove invalid time-series data and generate a time-series filtered dataset. Based on the timestamps of the spatial details of the positioning signal time series, the time series filtering dataset is calibrated at the millisecond level to eliminate the time deviation between the two data sources and generate a time series calibration dataset. Perform time-series consistency verification on the time-series calibration dataset, filter out data that still have time deviations after calibration, complete the time dimension synchronization of the two data sources, and generate a time-series synchronized dataset.

[0021] The working principle and effects of the above technical solution are as follows: By fully extracting the temporal, spatial, and attitude information of positioning signals and inertial measurement data, core data details can be preserved, avoiding calculation deviations caused by the loss of key information. Initial screening and invalid value removal of temporal data reduces interference data and improves subsequent calibration efficiency. Millisecond-level temporal calibration is performed based on the positioning signal, significantly improving the matching accuracy of dual data sources and avoiding data disorder caused by temporal misalignment. Temporal consistency verification further filters abnormal data, enhancing data collaboration stability. The entire processing flow reduces the probability of multi-source data conflicts, avoiding trajectory breaks or positioning jumps due to time asynchrony. It enables efficient collaboration between positioning signals and inertial measurement data, provides standardized and reliable data support for subsequent motion compensation, and improves the coherence and output accuracy of the overall positioning process.

[0022] In one embodiment of the present invention, S3 includes: S31. Perform continuous temporal decomposition and frame-by-frame feature extraction on the compensated positioning signal data to generate a complete single-frame positioning feature set. S32. Perform behavioral semantic analysis on the single-frame localization feature set to extract cycling direction, turning angle and speed changes, and generate cycling semantic data. S33. Extract the core features of cycling behavior and semantic map rule features, and establish a frame-by-frame matching relationship between cycling behavior and map information; S34. Perform correlation verification and deviation correction on the preliminary matching results to generate regional data that accurately matches cycling behavior with map rules; S35. Perform behavioral compliance verification and constraint optimization on the matched trajectory to generate behavior-enhanced matched trajectory data that conforms to road rules.

[0023] The working principle and effects of the above technical solution are as follows: Temporal decomposition and frame-by-frame extraction of the compensated positioning signal completely preserves positioning details, improves the comprehensiveness of feature collection, and avoids trajectory deviation caused by information omissions. Behavioral semantic parsing transforms coordinate data into realistic cycling states, enhancing the data's fit with the actual scene and reducing the unrealistic problems caused by simple numerical calculations. Frame-by-frame matching of cycling features and map rules improves the fit between the trajectory and the road environment, reducing computational losses caused by invalid matching. Association verification and deviation correction improve matching accuracy and prevent erroneous associations from affecting trajectory output. Compliance verification and constraint optimization ensure the trajectory conforms to road traffic rules, improving navigation usability. This approach ensures both accurate and consistent positioning trajectories and output results that closely match real-world cycling scenarios, avoiding usage risks caused by deviations from roads or illegal trajectories.

[0024] In one embodiment of the present invention, step S4 includes: S41. Perform multi-dimensional quality detection on behavior-enhanced matching trajectory data, statistically analyze positioning error and signal stability, and generate trajectory credibility index. S42. Normalize the trajectory credibility index and convert it into an intuitive quantitative value to generate a visual credibility index. S43. Extract core trajectory data and credibility information, complete the temporal alignment of the two types of data and the one-to-one correspondence of nodes; embed the credibility identifier into the corresponding trajectory node, update the data structure, and generate node-enhanced trajectory data. S44. Integrate the node-enhanced trajectory data and transmit it to the AR display module to generate real-time navigation trajectory data with credibility overlay.

[0025] The working principle and effects of the above technical solution are as follows: Multi-dimensional quality inspection of the behavior-enhanced matching trajectory comprehensively reflects the true state of the trajectory, improves the comprehensiveness of the evaluation, and avoids judgment bias caused by single-dimensional detection. It transforms credibility indicators into intuitive quantitative values, reducing the cost of understanding and minimizing user misjudgments of positioning accuracy. Temporal alignment and node binding ensure precise correspondence between the trajectory and credibility information, enhancing data correlation and avoiding display confusion caused by information gaps. Embedding credibility identifiers to update the data structure improves the completeness of navigation information. AR module overlay presentation enhances intuitive perception, allowing users to easily grasp the reliability of positioning in real time. This ensures stable output of navigation trajectories while allowing users to clearly identify the credibility of the data, avoiding riding risks caused by information opacity and improving overall safety and user experience.

[0026] In one embodiment of the present invention, S43 includes: S431. Read the behavior enhancement matching trajectory data, extract trajectory coordinates, driving time sequence, path nodes and attitude information, and generate the core trajectory dataset. S432. Read the visualized credibility index, extract the numerical quantification results, change trends and level classification information, and generate a credibility feature dataset. S433. Using the time-series nodes of the trajectory core dataset as a benchmark, perform time-series alignment on the credibility feature dataset to generate a time-series matching dataset. S434. Perform node correspondence verification on the time-series matching dataset, establish a one-to-one correspondence between trajectory nodes and credibility information, and generate associated benchmark data. S435. Embed credibility information into the core trajectory data structure node by node, update data attributes, and generate node-enhanced trajectory data.

[0027] The working principle and effects of the above technical solution are as follows: Extracting complete feature information of trajectory and credibility preserves core data attributes, improves the accuracy of subsequent processing, and avoids display deviations caused by the loss of key information. Alignment is achieved based on trajectory time sequence, enhancing the synergy between the two types of data and reducing information confusion caused by time sequence misalignment. Node correspondence verification establishes precise binding relationships, reducing the probability of erroneous associations and avoiding data correspondence disorder. Credibility information is embedded node by node and the structure is updated, improving the information integrity of trajectory data and making navigation content more comprehensive. The entire process strengthens data association and structural rationality, ensuring a high degree of matching between trajectory and credibility information and providing a stable data foundation for subsequent AR overlay display, preventing information gaps from affecting the user's judgment of the positioning status.

[0028] In one embodiment of the present invention, S433 includes: Traverse the time-series nodes of the core trajectory dataset, extract the time-series baseline sequence, and generate unified time-series reference data; Match the corresponding moments of the credibility feature dataset with the time series baseline sequence, filter out the valid time series segments, and generate credibility data to be aligned; Interpolation correction is performed on the reliability feature data of time series deviation to ensure that the time is consistent with the trajectory nodes, and the corrected reliability data is generated. The corrected credibility data is combined with the core trajectory dataset segment by segment according to time sequence nodes to generate a time sequence matching dataset.

[0029] The working principle and effects of the above technical solution are as follows: By extracting the time-series reference sequence, a unified reference standard can be provided for multi-source data, improving the standardization of time-series processing and avoiding matching deviations caused by reference confusion. Valid time-series segments are filtered, invalid data is removed, reducing subsequent computational load and improving overall processing efficiency. Interpolation correction is performed on time-series deviation data to ensure that the credibility information strictly corresponds to the trajectory time, reducing information distortion caused by time-series misalignment. Segment-by-segment combination forms a time-series matching dataset, strengthening the synergy between the two types of data and avoiding display anomalies caused by information disconnect. The entire process makes data alignment more accurate and stable, ensuring a high degree of synchronization between the trajectory and credibility information, and providing a reliable foundation for subsequent node binding and AR display, improving the accuracy and readability of navigation information.

[0030] In one embodiment of the present invention, step S5 includes: S51. Perform continuous curve fitting and signal jitter removal based on real-time navigation trajectory data to complete trajectory smoothing optimization. S52. Perform multi-dimensional accuracy verification on the optimized trajectory, filter out deviation data, and generate the final high-precision cycling trajectory data; compare the high-precision cycling trajectory data with the safety threshold item by item, and identify abnormal cycling states such as deviation and wrong-way riding in real time. S53. Based on the abnormal state identification results, generate cycling safety warning data such as yaw warning, collision risk and wrong-way riding warning; S54. Simultaneously outputs high-precision cycling trajectory data and cycling safety warning data, completing the entire process of trajectory generation and safety prompts.

[0031] The working principle and effects of the above technical solution are as follows: Curve fitting and jitter removal of the real-time navigation trajectory improves trajectory smoothness, reduces trajectory distortion caused by signal fluctuations, and enhances the stability of navigation display. Multi-dimensional accuracy verification further filters deviation data, strengthens trajectory accuracy, and avoids the accumulation of errors affecting the user experience. Comparing the trajectory with safety thresholds item by item can promptly identify abnormal states such as deviation and wrong-way riding, enhancing the ability to perceive riding risks. Based on the identification results, multiple types of safety warning information are generated to provide early warning of potential dangers and reduce the probability of accidents. Synchronous output of trajectory and warning data ensures coordinated response between navigation and safety prompts, avoiding safety hazards caused by information lag. This ensures both continuous and reliable riding trajectory and comprehensive protection of riding safety, improving the overall user experience of the smart helmet.

[0032] In one embodiment of the present invention, S51 includes: Read real-time navigation trajectory data, extract continuous trajectory nodes and temporal change information, and generate a trajectory dataset to be optimized; Fluctuation detection is performed on the trajectory optimization dataset to identify abnormal jitter nodes and generate trajectory jitter labeled data. Curve fitting is performed on continuous trajectory nodes to reconstruct a smooth path and generate preliminary optimized trajectory data; jittery nodes and abrupt changes in value are removed from the preliminary optimized trajectory data to generate intermediate trajectory smoothing data. The continuity of intermediate data for trajectory smoothing is verified, the node distribution is adjusted, and the trajectory smoothing optimization process is completed.

[0033] The working principle and effects of the above technical solution are as follows: Extracting trajectory nodes and temporal information to generate a dataset for optimization fully preserves the original trajectory features, avoiding the loss of key information that could affect optimization results. Fluctuation detection and jitter node marking accurately locate abnormal data, improving the targeted nature of subsequent processing. Curve fitting reconstructs the path, improving the overall smoothness of the trajectory and reducing visual interference caused by irregular fluctuations. Eliminating jitter and abrupt changes reduces the probability of data distortion, preventing outliers from affecting navigation judgment. Continuity verification and node adjustment ensure natural trajectory transitions and enhance output stability. This entire process makes the trajectory more closely resemble real driving conditions, improving the aesthetics and readability of the navigation display, providing a reliable foundation for subsequent accuracy verification and safety warnings, and enhancing the overall practicality of the positioning system.

[0034] According to one embodiment of the present invention, a helmet temperature control device for a smart helmet, the device comprising: One or more processors; Memory, used to store one or more programs; Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method described in any one of the above.

[0035] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for temperature control and regulation of a smart helmet, characterized in that, The method includes: S1. Divide the wearing area of ​​the smart helmet into three physiological thermal sensing zones to generate physiological thermal response data for the forehead, temples, and occipital region of the head; deploy a multimodal physiological sensor array based on the physiological thermal response data for the forehead, temples, and occipital region of the head to construct a zoned monitoring network based on the human thermal comfort model. S2. Based on the zoned monitoring network, dynamic heat load weight allocation is performed to generate priority control commands for the three zones; the priority control commands drive the microfluidic cooling channels and local heating units to work together to collect raw microclimate environment data; multi-physics field coupling analysis is performed on the raw microclimate environment data to generate zoned heat flux density distribution data. S3. Based on the zoned heat flux density distribution data, perform optical anti-fogging priority assessment and generate a lens fogging risk index. When the lens fogging risk index exceeds the threshold, initiate the microfluidic guide layer directional defogging program and generate an anti-fogging control signal. Adjust the local airflow speed and humidity gradient through the anti-fogging control signal to generate optical clarity assurance data. S4. Collect power consumption data of display unit through AR display load feedback module and generate display thermal disturbance compensation command; fuse display thermal disturbance compensation command with zone heat flux density distribution data to generate multi-field coordinated control parameters; optimize power allocation of cooling / heating unit according to multi-field coordinated control parameters and generate energy efficiency optimization control data. S5. Based on the energy efficiency optimization control data, perform bone conduction microphone noise suppression processing to generate electromagnetic interference isolation commands; adjust the working phase of the cooling fan through the electromagnetic interference isolation commands to generate noise reduction control data; generate a comprehensive comfort index by combining optical clarity assurance data and noise reduction control data; trigger a dynamic warning when the comprehensive comfort index is lower than the preset value, and generate helmet temperature control adjustment warning data.

2. The helmet temperature control method for a smart helmet according to claim 1, characterized in that, S1 includes: S11. The system synchronously collects raw positioning signal data, inertial measurement data, and environmental perception data during the riding process through the multimodal sensor group built into the smart helmet. S12. The acquired raw positioning signal data is distinguished by signal type, and independent positioning signal units with different transmission modes are separated. S13. Perform abnormal data filtering and signal normalization on the independent positioning signal units to generate high-quality normalized positioning signal data; S14. Perform multi-source signal cross-fusion on the normalized positioning signal data to generate fused positioning basic data compatible with multiple types of signals; S15. Unify the signal format and integrate the features of the fused positioning basic data to generate standardized hybrid positioning source data.

3. The helmet temperature control method for a smart helmet according to claim 1, characterized in that, The S2 includes: S21. Based on the adaptive positioning source allocation results, perform quality grading and evaluation of multi-source positioning signals and divide the signal quality distribution range. S22. Redundant signal completion and distorted signal correction are performed on the low-quality signal areas identified in the assessment to generate repaired positioning signal data. S23. Extract the temporal and spatial information of the repaired positioning signal data and inertial measurement data to complete the time dimension synchronization of the two data sources; S24. Perform spatial coordinate benchmark calibration on the time-synchronized data to eliminate spatial offset between data and generate spatiotemporally unified data. S25. Introduce the trained cycling dynamics model, correct the motion state of the spatiotemporal unified data, and generate compensated positioning signal data.

4. The helmet temperature control method for the smart helmet according to claim 3, characterized in that, S23 includes: Extract the timestamp, spatial coordinates, and signal sampling frequency information of each frame of the repaired positioning signal data to generate temporal spatial detail data of the positioning signal. Extract the timestamp, acceleration, angular velocity, and attitude angle information of each frame of inertial measurement data to generate detailed data of inertial measurement timing parameters; The time-series spatial detail data of positioning signals and the time-series parameter detail data of inertial measurement are initially screened by timestamps to remove invalid time-series data and generate a time-series filtered dataset. Based on the timestamps of the spatial details of the positioning signal time series, the time series filtering dataset is calibrated at the millisecond level to eliminate the time deviation between the two data sources and generate a time series calibration dataset. Perform time-series consistency verification on the time-series calibration dataset, filter out data that still have time deviations after calibration, complete the time dimension synchronization of the two data sources, and generate a time-series synchronized dataset.

5. The helmet temperature control method for a smart helmet according to claim 1, characterized in that, The S3 includes: S31. Perform continuous temporal decomposition and frame-by-frame feature extraction on the compensated positioning signal data to generate a complete single-frame positioning feature set. S32. Perform behavioral semantic analysis on the single-frame localization feature set to extract cycling direction, turning angle and speed changes, and generate cycling semantic data. S33. Extract the core features of cycling behavior and semantic map rule features, and establish a frame-by-frame matching relationship between cycling behavior and map information; S34. Perform correlation verification and deviation correction on the preliminary matching results to generate regional data that accurately matches cycling behavior with map rules; S35. Perform behavioral compliance verification and constraint optimization on the matched trajectory to generate behavior-enhanced matched trajectory data that conforms to road rules.

6. The helmet temperature control method for a smart helmet according to claim 1, characterized in that, The S4 includes: S41. Perform multi-dimensional quality detection on behavior-enhanced matching trajectory data, statistically analyze positioning error and signal stability, and generate trajectory credibility index. S42. Normalize the trajectory credibility index and convert it into an intuitive quantitative value to generate a visual credibility index. S43. Extract core trajectory data and credibility information, complete the temporal alignment of the two types of data and the one-to-one correspondence of nodes; embed the credibility identifier into the corresponding trajectory node, update the data structure, and generate node-enhanced trajectory data. S44. Integrate the node-enhanced trajectory data and transmit it to the AR display module to generate real-time navigation trajectory data with credibility overlay.

7. The helmet temperature control method for a smart helmet according to claim 6, characterized in that, S43 includes: S431. Read the behavior enhancement matching trajectory data, extract trajectory coordinates, driving time sequence, path nodes and attitude information, and generate the core trajectory dataset. S432. Read the visualized credibility index, extract the numerical quantification results, change trends and level classification information, and generate a credibility feature dataset. S433. Using the time-series nodes of the trajectory core dataset as a benchmark, perform time-series alignment on the credibility feature dataset to generate a time-series matching dataset. S434. Perform node correspondence verification on the time-series matching dataset, establish a one-to-one correspondence between trajectory nodes and credibility information, and generate associated benchmark data. S435. Embed credibility information into the core trajectory data structure node by node, update data attributes, and generate node-enhanced trajectory data.

8. The helmet temperature control method for a smart helmet according to claim 7, characterized in that, S433 includes: Traverse the time-series nodes of the core trajectory dataset, extract the time-series baseline sequence, and generate unified time-series reference data; Match the corresponding moments of the credibility feature dataset with the time series baseline sequence, filter out the valid time series segments, and generate credibility data to be aligned; Interpolation correction is performed on the reliability feature data of time series deviation to ensure that the time is consistent with the trajectory nodes, and the corrected reliability data is generated. The corrected credibility data is combined with the core trajectory dataset segment by segment according to time sequence nodes to generate a time sequence matching dataset.

9. The helmet temperature control method for a smart helmet according to claim 1, characterized in that, The S5 includes: S51. Perform continuous curve fitting and signal jitter removal based on real-time navigation trajectory data to complete trajectory smoothing optimization. S52. Perform multi-dimensional accuracy verification on the optimized trajectory, filter out deviation data, and generate the final high-precision cycling trajectory data; compare the high-precision cycling trajectory data with the safety threshold item by item, and identify abnormal cycling states in real time. S53. Based on the abnormal state identification results, generate cycling safety warning data; S54. Simultaneously outputs high-precision cycling trajectory data and cycling safety warning data, completing the entire process of trajectory generation and safety prompts.

10. A helmet temperature control device for a smart helmet, characterized in that, The device includes: One or more processors; Memory, used to store one or more programs; Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 9.

Images