A cloud-based in-cabin seat intelligent temperature adjustment system

Abstract

The application discloses a cloud-based in-cabin seat intelligent temperature adjustment system, and relates to the technical field of vehicle control.The system comprises a vehicle-mounted sensing and executing module, a cloud platform intelligent regulation and control module, and a user interaction module.The vehicle-mounted module collects in-cabin environment, seat operation, driver and passenger body feeling, and vehicle basic data, and transmits the data to the cloud platform after encryption, receives temperature adjustment parameters to drive seat temperature adjustment, supports weak network breakpoint continuation and local caching of core data.The cloud platform module performs distributed storage and preprocessing on the data, synchronously outputs aging grades and individual temperature adjustment requirements through a seat aging and temperature adjustment requirement double model, generates graded temperature adjustment parameters and continuously iteratively optimizes the parameters, and supports OTA remote upgrading.The user interaction module supports individual parameter setting, maintenance reminder receiving, state query, and remote temperature control.The system can improve the adaptability and operation stability of the seat temperature adjustment system, realize intelligent regulation and control of the seat throughout its life cycle, and optimize the use experience of drivers and passengers.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a cloud-based intelligent temperature control system for cabin seats. Background Technology

[0002] The seat temperature control system in the vehicle cabin is a core component for improving driving and riding comfort. Most existing seat temperature control systems adopt heating and cooling operation modes with fixed parameters. Although some solutions are connected to the cloud to achieve remote control, there are still many shortcomings.

[0003] Existing systems suffer from limited data collection dimensions, making it difficult to comprehensively cover seat operating status, aging levels, and occupant comfort information. Furthermore, communication stability is insufficient, leading to data loss and functional interruptions in weak network environments, thus compromising continuous and reliable temperature control. Simultaneously, existing cloud-based solutions often merely relay commands, failing to intelligently assess seat aging characteristics and personalized temperature control needs. This results in the inability to generate tiered, adaptable temperature parameters and a lack of continuous iterative optimization based on operational data, hindering adaptation to performance changes throughout the seat's lifecycle. Moreover, the system's interactive functions are limited, failing to meet diverse user needs for personalized parameter settings, maintenance reminders, and remote temperature control. Therefore, there is an urgent need for an intelligent in-cabin seat temperature control system with comprehensive perception, cloud-based intelligent control, and robust interactive capabilities to improve temperature adaptability, operational reliability, and overall user experience. Summary of the Invention

[0004] This application provides a cloud-based intelligent temperature control system for cabin seats. It addresses the problems of existing technologies, such as limited data collection dimensions, cloud-based systems only handling command forwarding and lacking intelligent evaluation capabilities, limited interactive functions, and insufficient reliability in weak network environments.

[0005] According to a first aspect of this application, a cloud-based intelligent temperature control system for cabin seats is provided, comprising: This includes an on-board perception and execution module, a cloud platform intelligent control module, and a user interaction module; The vehicle-mounted sensing and execution module is used to collect cabin environment data, seat operation data, driver and passenger body sensation data and vehicle basic data. After encryption processing, the data is transmitted to the cloud platform and receives temperature adjustment parameters from the cloud to drive seat temperature adjustment. It also supports weak network interruption resume and local caching of core data. The cloud platform intelligent control module is used for distributed storage and preprocessing of collected data. It outputs seat aging level and personalized temperature control requirements simultaneously through seat aging assessment model and temperature control requirement assessment model, generates graded temperature control parameters and continuously iterates and optimizes them, and supports OTA remote upgrades. The user interaction module enables two-way interaction between the user and the system, supporting personalized temperature control parameter settings, maintenance reminder reception, system status query, and remote control of seat temperature adjustment.

[0006] This application addresses the limitations of existing technologies. By incorporating an onboard sensing and execution module for multi-dimensional data acquisition, encrypted transmission, weak network interruption recovery, and local caching, coupled with a cloud-based intelligent control module that generates graded temperature control parameters through dual-model synchronous evaluation and supports continuous iterative optimization and OTA remote upgrades, and a user interaction module that enables personalized settings, maintenance reminders, status queries, and remote temperature control, this technology solves the problems of limited data acquisition dimensions, cloud-based systems that only forward commands and lack intelligent evaluation capabilities, limited interactive functions, and insufficient reliability in weak network environments. This results in improved adaptability and operational stability of the seat temperature control system, enabling intelligent control throughout the seat's lifecycle, while simultaneously optimizing the user experience for drivers and passengers.

[0007] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0008] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments 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.

[0009] Figure 1 This is a schematic diagram of a cloud-based intelligent temperature control system for cabin seats provided in an embodiment of this application. Detailed Implementation

[0010] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0011] The cloud-based intelligent temperature control system for cabin seats according to embodiments of this application is described below with reference to the accompanying drawings.

[0012] Figure 1 This is a schematic diagram of a cloud-based intelligent temperature control system for cabin seats provided in an embodiment of this application.

[0013] like Figure 1 As shown, the system includes: Vehicle-mounted sensing and execution module 1; cloud platform intelligent control module 2; user interaction module 3; The vehicle-mounted sensing and execution module 1 is used to collect cabin environment data, seat operation data, driver and passenger body sensation data and vehicle basic data. After encryption processing, the data is transmitted to the cloud platform and receives temperature adjustment parameters from the cloud to drive seat temperature adjustment. It also supports weak network interruption resume and local caching of core data. The cloud platform intelligent control module 2 is used for distributed storage and preprocessing of collected data. It outputs seat aging level and personalized temperature control requirements simultaneously through seat aging assessment model and temperature control requirement assessment model, generates graded temperature control parameters and continuously iterates and optimizes them, and supports OTA remote upgrades. User interaction module 3 is used to realize two-way interaction between users and the system, and supports personalized temperature control parameter settings, maintenance reminder reception, system status query and remote control of seat temperature control.

[0014] In some embodiments, the cloud-based intelligent temperature control system for cabin seats in this embodiment is composed of an on-board sensing and execution module 1, a cloud platform intelligent control module 2, and a user interaction module 3, forming a complete operating system for data collection, intelligent decision-making, execution feedback, and user interaction.

[0015] The vehicle-mounted sensing and execution module 1 is deployed inside the vehicle compartment, responsible for front-end data acquisition and temperature control execution. This module can simultaneously collect environmental data inside the compartment, seat operation data, occupant sensation data, and basic vehicle data. All collected data is encrypted before being transmitted to the cloud platform. In the downlink control link, the module receives temperature control parameters from the cloud platform and drives the seat temperature control mechanism to complete the corresponding temperature adjustment action. For scenarios where the vehicle may experience weak network connectivity inside the compartment, the module supports a breakpoint resume mechanism and locally caches core operational data. Once the network is restored, interrupted data is automatically retransmitted, ensuring the integrity of data transmission and the continuity of system operation.

[0016] The cloud-based intelligent control module 2 is the core decision-making unit of the system, possessing end-to-end capabilities in data management, intelligent evaluation, parameter generation, and iterative upgrades. The module employs a distributed storage architecture to categorize and store data uploaded from the vehicle terminal and performs standardized preprocessing to ensure data quality. The module incorporates a seat aging assessment model and a temperature regulation requirement assessment model, enabling simultaneous dual-dimensional evaluation based on preprocessed data, outputting seat aging levels and personalized temperature regulation requirement parameters respectively. Combining the evaluation results, the module generates graded and adapted temperature regulation parameters and distributes them to the vehicle terminal for execution. During system operation, the module can iteratively optimize the evaluation model and temperature regulation rules based on continuously collected operational data, while also supporting over-the-air (OTA) upgrades, allowing for continuous system performance optimization without offline intervention.

[0017] User interaction module 3 provides a two-way interactive interface for drivers and passengers, enabling information exchange and function control between users and the system. Users can customize personalized temperature control parameters through this module, receive timely maintenance reminders from the system, view the real-time system operating status and seat temperature control status, and remotely activate seat temperature control in advance to meet usage needs in various scenarios.

[0018] This system achieves intelligent cloud-based control of seat temperature regulation through a three-module collaborative architecture. It can adapt to the performance changes of the seat throughout its entire life cycle and the personalized needs of users, while ensuring reliable operation in complex network environments. This effectively improves temperature regulation comfort and system lifespan, and optimizes the user experience.

[0019] Compared with related technologies, in this embodiment, the vehicle-mounted sensing and execution module 1 is used to collect cabin environment data, seat operation data, occupant sensation data, and vehicle basic data. After encryption processing, the data is transmitted to the cloud platform, and the cloud platform receives temperature adjustment parameters to drive seat temperature adjustment. It also supports resuming interrupted transmission in weak network conditions and local caching of core data. The cloud platform intelligent control module 2 is used to perform distributed storage and preprocessing of the collected data. Through the seat aging assessment model and the temperature adjustment demand assessment model, it synchronously outputs the seat aging level and personalized temperature adjustment demand, generates graded temperature adjustment parameters, and continuously iterates and optimizes them, supporting OTA remote upgrades. The user interaction module 3 is used to realize two-way interaction between the user and the system, supporting personalized temperature adjustment parameter settings, maintenance reminder reception, system status query, and remote control of seat temperature adjustment. This can solve the problems of limited data collection dimensions, cloud platform only handling command forwarding and lacking intelligent assessment capabilities, single interaction functions, and insufficient reliability in weak network environments in existing technologies. It achieves the technical effect of improving the adaptability and operational stability of the seat temperature adjustment system, realizing intelligent control of the seat throughout its entire life cycle, and optimizing the user experience of occupants.

[0020] As a specific implementation of this application, based on the basic solution, the vehicle-mounted perception and execution module 1 is further defined to include a perception unit, an execution unit, and a communication unit; The sensing unit includes cabin temperature / humidity / light sensors, seat cushion / backrest temperature sensor array, pressure sensor, air duct differential pressure sensor, and sponge porosity ultrasonic sensor, with a sampling frequency of ≥2 times / second. The execution unit includes a seat temperature control ECU, a heating wire module, a semiconductor cooling module, and a ventilation fan module. It supports PWM precise power adjustment and fan speed control, with an execution delay of ≤5 seconds. The communication unit integrates a 4G / 5G / 5.8G vehicle networking module, supports local caching and weak network interruption resume transmission, data transmission latency ≤8 seconds, and adopts AES-256 + national cryptographic SM4 dual encryption transmission.

[0021] Specifically, in this embodiment, the vehicle-mounted sensing and execution module 1 consists of a sensing unit, an execution unit, and a communication unit. The three units work together to complete the functions of front-end data acquisition, temperature regulation action execution, and data interaction and transmission.

[0022] The sensing unit integrates multiple types of sensors, including cabin temperature sensors, humidity sensors, light sensors, as well as seat cushion temperature sensor arrays, backrest temperature sensor arrays, pressure sensors, air duct differential pressure sensors, and ultrasonic sensors for sponge porosity. These sensors cover multiple dimensions, including environmental conditions, seat structure conditions, and occupant contact conditions, enabling comprehensive data collection related to the cabin seats. The sensing unit collects data at a frequency of no less than twice per second, with a data collection accuracy of no less than 99.6%, and can stably output high-quality raw data, providing a reliable data foundation for subsequent intelligent control.

[0023] The actuator uses the seat temperature control electronic control unit (ECU) as its core, and is equipped with a heating wire module, a semiconductor cooling module, and a ventilation fan module. The actuator supports pulse width modulation (PWM) for precise power adjustment and fan speed control, and can finely adjust the heating power, cooling power, and ventilation volume based on received temperature control parameters. The unit's execution delay is no more than 5 seconds, and the parameter adjustment accuracy error is no more than 1.5%, enabling rapid response to control commands and ensuring the accuracy and stability of the temperature control process.

[0024] The communication unit integrates 4G, 5G, and 5.8G multi-standard vehicle-to-everything (V2X) communication modules, supporting local caching of core data and resume transmission from interrupted points in weak network environments. The unit employs a dual encryption mechanism of AES-256 and the national standard SM4 to encrypt transmitted data, ensuring data security and minimizing data transmission latency to no more than 8 seconds. In warehouse scenarios with unstable network signals, the communication unit can temporarily store critical data locally and resume transmission from the point of interruption once the network is restored, effectively preventing data loss and maintaining system continuity.

[0025] This implementation achieves high-precision and high-reliability design for the sensing, execution, and communication links through the three types of units configured in a layered manner. It can adapt to the complex operating environment inside the warehouse and provide stable front-end hardware support for the overall intelligent temperature control of the system.

[0026] As a specific implementation of this application, based on the basic scheme, the dual-model evaluation method of the cloud platform intelligent control module 2 is further defined, including the following steps: a. Seat aging assessment: Using the vehicle's years of use and the cumulative number of seat temperature adjustments as core input parameters, combined with the changes in heating wire current, cooling module power attenuation, airflow reduction rate in the air duct, and changes in sponge porosity, the aging assessment model trained by the XGBoost algorithm outputs three aging levels: mild, moderate, and severe. b. Temperature control requirement assessment: Based on the ambient temperature inside the cabin, the intensity of solar radiation, the skin temperature of drivers and passengers, and the data of their physical sensations, combined with the users' historical temperature control habits, a big data collaborative filtering algorithm is used to output the target temperature control range, temperature control priority, and temperature control speed requirements, and generate a personalized temperature control parameter template.

[0027] Specifically, based on the basic solution, this implementation further defines the dual-model evaluation method of the intelligent control module 2 on the cloud platform. The evaluation process includes two parallel steps: seat aging evaluation and temperature control demand evaluation. The two types of evaluations are calculated and output synchronously, providing a two-dimensional decision-making basis for the subsequent generation of temperature control parameters.

[0028] Seat aging assessment uses vehicle age and cumulative seat temperature adjustments as core input parameters, both of which directly reflect the overall usage intensity and service life of the seat. The assessment process also incorporates four operational parameters: heating wire current change, cooling module power attenuation, duct airflow reduction rate, and sponge porosity change. These four parameters directly characterize the actual degree of degradation of the seat's temperature control hardware and sponge structure. The assessment uses an aging assessment model trained with the XGBoost algorithm to fuse and classify multi-dimensional input features, ultimately outputting three aging levels: mild, moderate, and severe. Mild aging corresponds to a service life of no more than 2 years, cumulative temperature adjustments of no more than 5000 times, and a performance parameter degradation of no more than 10%. Moderate aging corresponds to a service life of more than 2 years but no more than 5 years, cumulative temperature adjustments of more than 5000 times but no more than 15000 times, and a performance parameter degradation between 10% and 30%. Severe aging corresponds to a service life of more than 5 years, cumulative temperature adjustments of more than 15000 times, and a performance parameter degradation exceeding 30%.

[0029] Temperature control needs assessment is based on four types of real-time data collected: cabin ambient temperature, solar radiation intensity, passenger skin temperature, and body temperature feedback. This comprehensively captures the current cabin environmental conditions and the immediate body temperature sensations of passengers. The assessment also incorporates users' historical temperature control habits, using a big data collaborative filtering algorithm to match preferences and quantify needs. This results in the output of the target temperature range, temperature control priority, and required temperature control speed, ultimately generating a personalized temperature control parameter template tailored to the user. The big data collaborative filtering algorithm can match scenario parameters similar to the current user's body temperature preferences based on massive amounts of historical temperature control behavior data, making the output temperature control solution more aligned with individual comfort needs.

[0030] This implementation uses a dual-model parallel evaluation mechanism to simultaneously quantify the aging status of the seat hardware and identify the personalized temperature adjustment needs of users. The evaluation dimensions cover both hardware performance and human comfort, and the evaluation results are accurate and comprehensive, providing reliable decision support for the reasonable generation of subsequent temperature adjustment parameters.

[0031] As a specific implementation of this application, based on the basic scheme, the graded temperature control parameters are further customized with differentiated parameters for three aging levels: mild, moderate, and severe. Specifically, these include: Mild aging: Fine-tune heating power ±5%, cooling power ±5%, ventilation volume ±5%, dynamically adjust temperature control priority based on sunlight radiation intensity, and fine-tune temperature control range according to the skin temperature of drivers and passengers; Moderate aging: Increase heating power by 10%-15%, increase cooling power by 15%-20%, reduce initial ventilation volume by 5%-10%, adjust airflow distribution in the duct, and add constant temperature buffer parameters; Severe aging: Heating power increased by 25%-30%, cooling power increased by 30%-35%, temperature adjustment rate slowed by 15%-20%, ventilation volume increased by 20%-25%, maintenance reminders pushed, and energy-saving mode switching supported.

[0032] Specifically, this implementation, based on the basic solution, customizes differentiated graded temperature control parameters for three aging levels: mild, moderate, and severe. It matches the corresponding power, airflow, and operating strategy according to the different aging degrees of the seats, ensuring the temperature control effect while taking into account system losses and energy consumption control.

[0033] In the mild aging stage, the seat temperature control hardware and structure show minimal degradation. The system maintains basic temperature control parameters, making minor adjustments to heating power, cooling power, and ventilation volume within ±5%. During operation, the system dynamically adjusts temperature control priority based on real-time solar radiation intensity, prioritizing cooling in high-radiation environments and heating in low-temperature environments. Simultaneously, it fine-tunes the temperature adjustment based on the skin temperature of passengers to avoid over-adjustment and ensure a smooth and comfortable temperature control process.

[0034] During the moderate aging stage, the seat's temperature regulation efficiency decreases to some extent. The system employs a power compensation strategy to offset the performance degradation caused by aging, with heating power increased by 10% to 15% and cooling power increased by 15% to 20%. To address the issue of wind noise caused by aging air ducts, the system initially reduces the ventilation airflow by 5% to 10%, gradually increasing the airflow during operation to ensure effective heat dissipation. Simultaneously, the airflow distribution within the air ducts is adjusted according to the seat's structural condition to optimize the uniformity of heat conduction and dissipation. The system also incorporates a constant temperature buffer parameter; when the seat temperature approaches the target value, the output power is reduced to 30% to 40% of the baseline parameter, minimizing unnecessary energy consumption and temperature fluctuations.

[0035] During the severe aging stage, the seat hardware and structure show significant degradation. The system implements high-power compensation temperature regulation, increasing heating power by 25% to 30% and cooling power by 30% to 35% to ensure basic temperature regulation efficiency. To avoid further damage to the aging structure due to rapid high-power temperature regulation, the system slows down the heating and cooling rates by 15% to 20%, while increasing ventilation volume by 20% to 25% to alleviate heat dissipation lag caused by airflow blockage. During this stage, the system simultaneously generates maintenance reminder parameters and pushes them to the user interface to prompt the inspection or replacement of aging parts and the cleaning of airflow ducts. Users can also manually switch to energy-saving mode to extend the remaining lifespan of the system by reducing power output.

[0036] This embodiment, through graded and differentiated temperature control parameter settings, can adapt to the operating characteristics of different aging stages throughout the entire life cycle of the seat. It not only ensures the temperature control effect and human comfort at each stage, but also reasonably controls hardware losses and energy consumption levels, effectively extending the overall service life of the seat temperature control system.

[0037] As a specific implementation of this application, based on the basic solution, the cloud platform intelligent control module 2 is further defined as being used for: When the vehicle-mounted terminal executes the temperature adjustment parameters, it collects the seat temperature, cabin ambient temperature, and operating parameters in real time and transmits them back to the cloud platform. The cloud platform combines the transmitted data to optimize the aging assessment model, the temperature adjustment requirement assessment model, and the graded temperature adjustment rules.

[0038] Specifically, this implementation further defines the data closed-loop optimization mechanism of the cloud platform intelligent control module 2 on the basis of the basic solution. Through the feedback of real-time operating data from the vehicle terminal and the iterative update in the cloud, the system control capability is continuously optimized.

[0039] During the execution of temperature control parameters on the vehicle-mounted system, built-in sensors collect real-time data on seat temperature, cabin ambient temperature, and operating parameters of the temperature control system, continuously transmitting this data back to the cloud platform. This transmitted data provides a clear picture of the actual temperature control effect under the current temperature control parameters, environmental change trends, and hardware operating status, offering valuable feedback for model iteration and rule optimization.

[0040] After receiving the returned data, the cloud platform compares and analyzes the actual operating results with the model predictions and preset temperature control rules, extracting deviation characteristics and optimization directions. It then specifically optimizes the seat aging assessment model, temperature control demand assessment model, and graded temperature control rules. For the aging assessment model, the weighting of each aging characteristic can be adjusted based on long-term operating data to improve the accuracy of aging level determination. For the temperature control demand assessment model, the demand matching logic can be optimized based on actual user feedback data, making the output temperature control solution more aligned with comfort needs. For the graded temperature control rules, thresholds for parameters such as power compensation and airflow configuration can be adjusted according to actual temperature control efficiency to ensure a balance between temperature control effect and energy consumption at each aging level.

[0041] This implementation constructs a complete data closed-loop iteration mechanism, enabling the system to continuously optimize itself based on real operating data, and continuously improve the accuracy of regulation and scenario adaptability as the usage time increases.

[0042] As a specific implementation of this application, based on the basic solution, the user interaction module 3 is further defined to include an in-vehicle central control screen and a mobile APP. The in-vehicle central control screen supports temperature control mode switching, status query, and maintenance reminder viewing, while the mobile APP supports remote temperature control, personalized parameter modification, system upgrade notification reception, and maintenance reminder viewing.

[0043] Specifically, the user interaction module 3 includes two types of interaction entry points: the in-vehicle central control screen and the mobile APP, which respectively cover two usage scenarios: local operation inside the vehicle and remote control outside the vehicle, realizing two-way interaction between users and the system in all scenarios.

[0044] The in-vehicle central control screen is deployed in the central control area within the vehicle's cabin, serving as a local interactive platform for drivers and passengers during vehicle use. It supports temperature control mode switching, allowing users to select different modes according to their needs; it supports system status queries, displaying real-time information such as the current seat temperature and temperature control operation status; and it supports maintenance reminders, with system-generated maintenance prompts directly pushed to the central control screen interface for timely notifications during driving.

[0045] The mobile app serves as a remote interaction portal, unrestricted by the vehicle's location. It supports remote temperature control, allowing users to pre-activate seat heating or cooling before entering the vehicle for a comfortable temperature upon arrival. It also supports personalized parameter modification, enabling users to adjust temperature-related parameters according to their preferences and customize a personalized temperature control solution. Furthermore, it supports receiving system upgrade notifications; when OTA (Over-The-Air) upgrade information is released in the cloud, the app can simultaneously push notifications to users. Finally, it supports viewing maintenance reminders, keeping them synchronized with maintenance information on the in-vehicle central control screen, ensuring users can stay informed about system maintenance needs even when outside the vehicle.

[0046] This implementation, through a dual-end interactive architecture, comprehensively covers both in-vehicle and remote usage scenarios. Its functional configuration is tailored to users' actual needs, effectively improving the ease of system operation and user experience.

[0047] As a specific implementation of this application, based on the basic solution, the cloud platform is further limited to support a vehicle-material-specific parameter adjustment library, which allows for customized temperature adjustment parameters for different vehicle models such as sedans, SUVs, and commercial vehicles, as well as different seat materials such as leather, fabric, and imitation leather.

[0048] Specifically, the parameter tuning covers three mainstream vehicle types: sedans, SUVs, and commercial vehicles. Different vehicle models have significant differences in interior space dimensions, seat layout, and air conditioning airflow paths, resulting in varying heat exchange environments and temperature change rates around the seats. A dedicated parameter tuning library pre-sets matching initial power, airflow, and temperature adjustment rate parameters for the interior environment characteristics of each vehicle type, avoiding deviations where the temperature adjustment rate is too fast or too slow when using uniform parameters across different models.

[0049] The parameter tuning covers three common seat materials: leather, fabric, and imitation leather. These materials differ significantly in thermal conductivity, heat storage capacity, and breathability, resulting in noticeable differences in surface temperature changes and perceived comfort under the same power output. The parameter tuning library customizes corresponding power compensation coefficients, constant temperature buffer thresholds, and ventilation airflow ratios based on the thermophysical properties of different materials, ensuring a stable and consistent comfortable temperature regulation effect for seats made of various materials.

[0050] When generating temperature control parameters on the cloud platform, the corresponding vehicle model and seat material are identified by combining the vehicle's basic data. The benchmark parameters in the dedicated parameter adjustment library are directly called, and dynamic adjustments are made by combining the aging assessment and demand assessment results, which improves the computing efficiency while ensuring parameter adaptability.

[0051] This implementation, through the configuration of a vehicle-material-specific parameter adjustment library, can achieve precise adaptation to different vehicles and seat types, effectively improving the system's versatility and temperature control comfort, and reducing parameter debugging costs when deploying on different vehicle models.

[0052] As a specific implementation of this application, based on the basic solution, the system is further limited to support OTA remote upgrades, and the cloud platform can remotely upgrade the vehicle-mounted ECU and the cloud algorithm model.

[0053] Specifically, OTA remote upgrades are coordinated by the cloud platform, which can remotely update both the vehicle-mounted ECU and the cloud-based algorithm model. This allows for continuous optimization of system performance and functional iteration without disassembling the vehicle or conducting offline maintenance.

[0054] For the vehicle-mounted ECU, the cloud platform can generate a compatible firmware upgrade package, which is encrypted and then sent to the vehicle terminal via the vehicle network link. The upgrade process supports breakpoint resumption and version verification to ensure the integrity and accuracy of the upgrade package. A version rollback mechanism is also configured so that if an upgrade anomaly occurs, it can automatically revert to the original stable version, ensuring system reliability. After the upgrade is completed, the vehicle-mounted ECU automatically restarts and takes effect, optimizing temperature control logic, fixing operational defects, adding compatible functions, and continuously improving the control accuracy and operational stability of the front-end actuator.

[0055] For cloud-based algorithm models, the cloud platform can iterate algorithms based on continuously collected operational data, updating model parameters and computational logic related to seat aging assessment and temperature regulation requirement assessment online, and simultaneously optimizing graded temperature regulation rules. Cloud-based algorithm upgrades do not require changes to the vehicle-mounted hardware configuration and take effect immediately after the update, quickly adapting to new vehicle models and seat materials, and continuously improving the system's assessment accuracy and temperature regulation adaptability.

[0056] This implementation, through a full-link OTA remote upgrade architecture, enables synchronous iteration between the vehicle-mounted execution end and the cloud-based decision-making end, continuously improving system performance and adaptability, effectively reducing offline maintenance costs, and extending the overall service life of the system.

[0057] As a specific implementation of this application, based on the basic solution, the system is further limited to have fault warning and proactive maintenance functions. The system predicts the remaining service life of the seat temperature control system through the LSTM algorithm, pushes maintenance reminders 7-15 days in advance, and immediately stops the temperature control operation and feeds back fault information when a fault is detected.

[0058] Specifically, the system employs a Long Short-Term Memory (LSTM) algorithm to construct a predictive model for the remaining service life of the seat temperature control system. Based on time-series performance data and aging trends accumulated over long-term operation of the seat, it performs sequence modeling and trend extrapolation to accurately predict the system's remaining service life. When the system is predicted to be nearing a maintenance deadline, a maintenance reminder is sent 7 to 15 days in advance, allowing users to plan maintenance schedules ahead of time, avoiding disruptions to normal use due to sudden component failures, and preventing minor wear and tear from escalating into structural damage.

[0059] The system also possesses real-time fault detection and protection capabilities. During operation, it continuously monitors various operating parameters and hardware status of the temperature control system. Once a fault or abnormality is detected, it immediately stops temperature control operation and cuts off the power output of the relevant modules to prevent continued operation under fault conditions from exacerbating hardware damage. Simultaneously, the system provides fault information upon fault triggering, offering a clear basis for subsequent troubleshooting and repair.

[0060] This implementation achieves proactive maintenance through LSTM lifetime prediction, combined with real-time fault downtime protection, which can effectively reduce the risk of sudden system failures, reduce unplanned downtime, lower maintenance costs, and improve the overall reliability and service life of the system.

[0061] As a specific implementation of this application, based on the basic scheme, the energy consumption optimization method of the system is further defined to include constant temperature buffer control, dynamic power adjustment, and adaptive adjustment of airflow in the duct.

[0062] Specifically, this implementation further defines the energy consumption optimization method of the system based on the basic solution. It includes three mechanisms: constant temperature buffer control, dynamic power adjustment, and adaptive airflow adjustment. Through multi-dimensional coordinated regulation, it reduces operating energy consumption while ensuring temperature comfort, and achieves significant energy-saving effect in the case of seat aging.

[0063] The constant temperature buffer control operates at the end of the temperature adjustment process. As the seat temperature gradually approaches the target temperature range, the system gradually reduces the output power of the heating or cooling modules to avoid temperature overshoot and energy waste caused by continuous full-power operation. This keeps the seat temperature stable within the comfort range and reduces the additional energy consumption caused by frequent power start-stop.

[0064] Dynamic power adjustment provides on-demand energy supply based on real-time operating status. The system combines real-time collected data on cabin ambient temperature, seat aging level, and passenger comfort to dynamically match the output power of the heating and cooling modules. It does not need to maintain high power operation throughout the entire process. It adaptively adjusts the power output level according to the actual temperature control needs, accurately matching the current temperature control load.

[0065] The adaptive airflow adjustment system enables refined management of the ventilation system. Based on the degree of blockage in the seat's air duct, the porosity of the sponge, and the current temperature control priority, the system automatically adjusts the speed and airflow output of the ventilation fan. While ensuring heat dissipation or heat conduction, it avoids the ineffective energy consumption caused by long-term high-speed operation of the fan, and at the same time reduces operating noise.

[0066] Under moderate and severe aging operating modes, through the synergistic effect of three types of energy consumption optimization mechanisms, the overall energy consumption of the system is reduced by 15% to 25% compared to traditional fixed-parameter seat temperature control systems. Even in scenarios where the seat structure ages and the temperature control efficiency declines, it can still balance the temperature control effect and energy utilization efficiency.

[0067] This implementation, through a multi-dimensional collaborative energy consumption optimization mechanism, can effectively reduce system operating energy consumption without sacrificing temperature regulation comfort. It is especially suitable for operating scenarios after seat aging, achieving a balance between energy saving and comfort experience, and improving the overall operating efficiency of the system.

[0068] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0069] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A cloud-based intelligent temperature control system for cabin seats, characterized in that, This includes an on-board perception and execution module, a cloud platform intelligent control module, and a user interaction module; The vehicle-mounted sensing and execution module is used to collect cabin environment data, seat operation data, driver and passenger body sensation data and vehicle basic data, and transmit them to the cloud platform after encryption. It also receives temperature adjustment parameters from the cloud to drive seat temperature adjustment, and supports weak network interruption resume and core data local caching. The cloud platform intelligent control module is used for distributed storage and preprocessing of collected data. It outputs seat aging level and personalized temperature control requirements simultaneously through seat aging assessment model and temperature control requirement assessment model, generates graded temperature control parameters and continuously iterates and optimizes them, and supports OTA remote upgrades. The user interaction module is used to enable two-way interaction between the user and the system, supporting personalized temperature control parameter settings, maintenance reminder reception, system status query, and remote control of seat temperature adjustment.

2. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The vehicle-mounted sensing and execution module includes a sensing unit, an execution unit, and a communication unit; The sensing unit includes a cabin temperature / humidity / light sensor, a seat cushion / backrest temperature sensor array, a pressure sensor, an air duct differential pressure sensor, and a sponge porosity ultrasonic sensor, with a sampling frequency of ≥2 times / second. The execution unit includes a seat temperature control ECU, a heating wire module, a semiconductor cooling module, and a ventilation fan module, supporting PWM precise power adjustment and fan speed control, with an execution delay of ≤5 seconds; The communication unit integrates a 4G / 5G / 5.8G vehicle networking module, supports local caching and weak network interruption resume transmission, data transmission latency is ≤8 seconds, and adopts AES-256 + national cryptographic SM4 dual encryption transmission.

3. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The dual-model evaluation method of the cloud platform intelligent control module includes the following steps: a. Seat aging assessment: Using the vehicle's years of use and the cumulative number of seat temperature adjustments as core input parameters, combined with the changes in heating wire current, cooling module power attenuation, airflow reduction rate in the air duct, and changes in sponge porosity, the aging assessment model trained by the XGBoost algorithm outputs three aging levels: mild, moderate, and severe. b. Temperature control requirement assessment: Based on the ambient temperature inside the cabin, the intensity of solar radiation, the skin temperature of drivers and passengers, and the data of their physical sensations, combined with the users' historical temperature control habits, a big data collaborative filtering algorithm is used to output the target temperature control range, temperature control priority, and temperature control speed requirements, and generate a personalized temperature control parameter template.

4. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The graded temperature control parameters are customized for three aging levels: mild, moderate, and severe. Specifically, they include: Mild aging: Fine-tune heating power ±5%, cooling power ±5%, ventilation volume ±5%, dynamically adjust temperature control priority based on sunlight radiation intensity, and fine-tune temperature control range according to the skin temperature of drivers and passengers; Moderate aging: Increase heating power by 10%-15%, increase cooling power by 15%-20%, reduce initial ventilation volume by 5%-10%, adjust airflow distribution in the duct, and add constant temperature buffer parameters; Severe aging: Heating power increased by 25%-30%, cooling power increased by 30%-35%, temperature adjustment rate slowed by 15%-20%, ventilation volume increased by 20%-25%, maintenance reminders pushed, and energy-saving mode switching supported.

5. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The cloud platform intelligent control module is also used for: When the vehicle-mounted terminal executes the temperature adjustment parameters, it collects the seat temperature, cabin ambient temperature, and operating parameters in real time and transmits them back to the cloud platform. The cloud platform combines the transmitted data to optimize the aging assessment model, the temperature adjustment requirement assessment model, and the graded temperature adjustment rules.

6. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The user interaction module includes an in-vehicle central control screen and a mobile APP. The in-vehicle central control screen supports temperature control mode switching, status query, and maintenance reminder viewing. The mobile APP supports remote temperature control, personalized parameter modification, system upgrade notification reception, and maintenance reminder viewing.

7. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The cloud platform supports a vehicle-material-specific parameter adjustment library, allowing for customized temperature control parameters for different vehicle models such as sedans, SUVs, and commercial vehicles, as well as different seat materials such as leather, fabric, and imitation leather.

8. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The system supports OTA remote upgrades, and the cloud platform can remotely upgrade the vehicle-mounted ECU and the cloud-based algorithm model.

9. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The system has fault warning and proactive maintenance functions. It uses the LSTM algorithm to predict the remaining service life of the seat temperature control system and pushes maintenance reminders 7-15 days in advance. When a fault is detected, it immediately stops the temperature control operation and reports the fault information.

10. The cloud-based intelligent temperature control system for cabin seats according to claim 1, characterized in that, The energy consumption optimization methods of the system include constant temperature buffer control, dynamic power adjustment, and adaptive adjustment of airflow in the duct.

Images