Control method and control device for thermal comfort system in passenger compartment
By using a trained thermal comfort control model and reinforcement learning optimization techniques, the problem of coordinated control of the passenger cabin thermal comfort system under different environments and driving conditions was solved, achieving efficient and personalized thermal comfort control, and improving user experience and energy efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NIO TECH ANHUI CO LTD
- Filing Date
- 2026-01-23
- Publication Date
- 2026-04-17
AI Technical Summary
The existing control schemes for passenger cabin thermal comfort systems cannot adapt to the differences in thermal comfort requirements under different ambient temperatures, humidity and driving conditions, and lack the coordinated operation of multiple thermal comfort control devices, resulting in poor thermal comfort experience and energy waste.
A trained thermal comfort control model is used to determine the collaborative control scheme of multiple thermal comfort control devices based on multimodal sensing inputs (thermal environment parameters, thermal comfort system state, and driving device state). The model is then optimized through reinforcement learning to adapt to individual preferences and environmental changes.
It improves the accuracy and efficiency of thermal comfort control, enhances the user experience, saves energy, and adapts to changes in the environment and individual preferences during long-term use.
Smart Images
Figure CN121879244A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of natural language processing, and more particularly to control methods and control devices, computing devices, and computer storage media for thermal comfort systems in passenger cabins. Background Technology
[0002] With the intelligent upgrading of automobiles, rail transit, and other transportation systems, passengers' demands for cabin thermal comfort are increasing. Existing control schemes for passenger cabin thermal comfort systems mostly employ control logic based on fixed rules, such as adjusting the air conditioning on / off based on preset temperature thresholds. However, these traditional control schemes have significant drawbacks: firstly, fixed rules can only cover limited scenarios and cannot adapt to the differences in thermal comfort requirements under different ambient temperatures, humidity levels, and driving states (e.g., high-speed driving versus idling); secondly, current control schemes rely solely on a few temperature sensors, lacking other sensory information, and the control parameters are singular, almost entirely focused on controlling the air conditioning system. This makes it difficult to coordinate the collaborative work of multiple thermal comfort control devices (e.g., air conditioning, heated and ventilated seats, air vent adjustments, etc.), leading to poor thermal comfort and energy waste.
[0003] Furthermore, current solutions typically employ controllers with limited computing power. Once the control logic is determined, it is difficult to optimize it based on actual usage data. This makes it impossible to adapt to changes in the environment and differences in individual occupant preferences during long-term use, resulting in low efficiency and accuracy of thermal comfort control, which fails to meet user needs. Summary of the Invention
[0004] In view of this, this disclosure provides a control method and control device, computing device and computer storage medium for a thermal comfort system in the occupant cabin, which is intended to overcome some or all of the above-mentioned defects and other possible defects.
[0005] According to a first aspect of this disclosure, a control method for a thermal comfort system within a passenger compartment is provided, comprising: acquiring thermal environment parameters of the passenger compartment, the current state of the thermal comfort system, and the state of the driving device in which the passenger compartment is located, wherein the thermal comfort system includes a plurality of thermal comfort control devices; using a trained thermal comfort control model, determining thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device, wherein the thermal comfort control parameters indicate a corresponding control scheme for each of the plurality of thermal comfort control devices; and controlling the corresponding thermal comfort control device based on the control scheme.
[0006] In some embodiments, the trained thermal comfort control model includes a pre-trained global thermal comfort control model, wherein the pre-trained global thermal comfort control model includes the initial version of the pre-trained global thermal comfort control model or an updated version of the global thermal comfort control model, and the updated version of the global thermal comfort control model is obtained by iteratively updating the initial version of the pre-trained global thermal comfort control model.
[0007] In some embodiments, the initial version of the pre-trained global thermal comfort control model is obtained by training a deep learning model based on a training dataset in a pre-designed database, the training dataset including data related to preset thermal comfort control rules.
[0008] In some embodiments, the method further includes: obtaining comfort feedback from users in the passenger cabin regarding the thermal comfort system in a first state, wherein the first state is the state in which the thermal comfort system is in after controlling the corresponding thermal comfort control device based on the control scheme; updating the model parameters of the pre-trained global thermal comfort control model based on the obtained comfort feedback to obtain a personalized thermal comfort control model; and updating the trained thermal comfort control model to the personalized thermal comfort control model.
[0009] In some embodiments, updating the model parameters of the pre-trained global thermal comfort control model based on the acquired comfort feedback includes: updating the model parameters of the pre-trained global thermal comfort control model based on the acquired comfort feedback in response to the number of acquired comfort feedbacks being greater than a feedback number threshold.
[0010] In some embodiments, the method further includes: obtaining a pre-trained updated version of the global thermal comfort control model as the trained thermal comfort control model, wherein the pre-trained updated version of the global thermal comfort control model is obtained by updating the previous updated version of the global thermal comfort control model in the iterative update using parameters of a preset number of personalized thermal comfort control models.
[0011] In some embodiments, the trained thermal comfort control model includes a multi-head attention encoder, a position encoder, and a decoder. The thermal comfort control model is used to determine thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device. This includes: extracting features from the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device to obtain a context vector; splitting the context vector into multiple attention heads using the multi-head attention encoder and determining the weight of each attention head relative to the thermal comfort level of the thermal comfort system; using the position encoder to position-encode the context vector according to its association priority with thermal comfort level to obtain a position-encoded vector; and using the decoder to determine the thermal comfort control parameters based on the position-encoded vector and the weights. The thermal comfort control parameters include a multi-step control parameter sequence with a temporal order, where each step control parameter includes control parameters for at least one of multiple thermal comfort control devices.
[0012] According to a second aspect of this disclosure, a control device for a thermal comfort system within a passenger compartment is provided, comprising: an acquisition module configured to acquire thermal environment parameters of the passenger compartment, the current state of the thermal comfort system, and the state of the driving device in which the passenger compartment is located, wherein the thermal comfort system includes a plurality of thermal comfort control devices; a determination module configured to determine thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device using a trained thermal comfort control model, wherein the thermal comfort control parameters indicate a corresponding control scheme for each of the plurality of thermal comfort control devices; and a control module configured to control the corresponding thermal comfort control device based on the control scheme.
[0013] According to a third aspect of this disclosure, a computing device is provided, including a processor; and a memory configured to store computer-executable instructions thereon, which, when executed by the processor, perform any of the methods described above.
[0014] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions that, when executed, perform any of the methods described above.
[0015] In the control method and control device for a thermal comfort system in the passenger compartment claimed in this disclosure, multimodal sensing inputs (thermal environment parameters of the passenger compartment, the current state of the thermal comfort system including multiple thermal comfort control devices, and the state of the driving device in which the passenger compartment is located) are used as inputs to a trained thermal comfort control model. Thermal comfort control parameters are output, indicating a corresponding control scheme for each of the multiple thermal comfort control devices, and the corresponding thermal comfort control device is controlled based on the control scheme. In this way, the technical solution of this disclosure can adapt to differences in thermal comfort requirements under different ambient temperatures, humidity, driving conditions, etc., and the control parameters are diverse, enabling multiple thermal comfort control devices (e.g., air conditioning, heated and ventilated seats, air vent adjustment, etc.) to work collaboratively, improving the accuracy and efficiency of thermal comfort control, enhancing the user's thermal comfort experience while saving energy. Moreover, the technical solution of the embodiments of this disclosure can optimize the thermal comfort control model according to the user's personal preferences and feedback, adapting to the needs of environmental changes and differences in individual passenger preferences during long-term use, further improving the efficiency and accuracy of thermal comfort control.
[0016] These and other advantages of this disclosure will become clear from the embodiments described below, and will be illustrated with reference to the embodiments described below. Attached Figure Description
[0017] Embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings, in which: Figure 1 The illustrations depict exemplary application scenarios in which the technical solutions according to embodiments of this disclosure can be implemented; Figure 2 The illustration shows a schematic flowchart of a control method for a thermal comfort system in a passenger compartment according to an embodiment of the present disclosure. Figure 3 An exemplary flowchart of training a deep learning model according to an embodiment of the present disclosure is shown; Figure 4 An exemplary embodiment of a thermal comfort control model performing personalized learning and global optimization according to an embodiment of the present disclosure is illustrated; Figure 5 The illustration shows an exemplary schematic diagram of determining thermal comfort control parameters using a trained thermal comfort control model according to an embodiment of the present disclosure; Figure 6 The figure shows an exemplary structural block diagram of a control device for a thermal comfort system in a passenger compartment according to an embodiment of the present disclosure; Figure 7 An example block diagram of a computing device according to some embodiments of the present disclosure is shown schematically. Detailed Implementation
[0018] The following description provides specific details of various embodiments of this disclosure to enable those skilled in the art to fully understand and implement the various embodiments of this disclosure. It should be understood that the technical solutions of this disclosure can be implemented without some of these details. In some cases, this disclosure does not show or describe in detail some well-known structures or functions to avoid such unnecessary descriptions that would obscure the description of the embodiments of this disclosure. The terminology used in this disclosure should be understood in its broadest and most reasonable manner, even when used in conjunction with specific embodiments of this disclosure.
[0019] Figure 1 The illustration shows an exemplary application scenario 100 in which the technical solutions according to embodiments of this disclosure can be implemented. For example... Figure 1 As shown, the application scenario includes a terminal 110 and a server 120, with the terminal 110 communicatively coupled to the server 120 via a network 130. As an example, the terminal 110 can implement a control method for a thermal comfort system within the occupant cabin according to this disclosure, and the server 120 can pre-train a global thermal comfort control model and provide the pre-trained global thermal comfort control model to the terminal.
[0020] Terminal 110 can be a vehicle domain control device, in-vehicle host, smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, and big data and artificial intelligence platforms. Terminals and servers can be directly or indirectly connected via wired or wireless communication, which is not limited herein. The network 130 can be, for example, a wide area network (WAN), a local area network (LAN), a wireless network, a public telephone network, an intranet, and any other type of network well known to those skilled in the art.
[0021] The scenario described above is merely one example in which embodiments of this disclosure can be implemented and is not restrictive. It should be understood that although server 120 and terminal 110 are shown and described as separate structures herein, they can be different components of the same device. Optionally, some or all steps of the methods according to some embodiments of this disclosure can also be implemented on the server 120 side, or can be implemented collaboratively on the terminal 110 side and the server 120 side.
[0022] Figure 2 A schematic flowchart of a control method 200 for a thermal comfort system in an occupant cabin according to an embodiment of the present disclosure is shown. Figure 2 As shown, the method 200 includes the following steps.
[0023] In step 210, the thermal environment parameters of the passenger compartment, the current status of the thermal comfort system, and the status of the driving device in which the passenger compartment is located are acquired. The thermal comfort system includes multiple thermal comfort control devices. The multiple thermal comfort control devices may include multiple different types of thermal comfort control devices, such as air conditioners, electric air vents, ventilated and heated seats, sunshade systems, etc.
[0024] As an example, various suitable sensors can be used to acquire the thermal environment parameters of the occupant cabin. These parameters may include, for example, the cabin's internal heat flow field, external temperature and humidity information, internal humidity information, and the microclimate field of the human body surface within the cabin. As another example, an Occupant Monitoring System (OMS) camera can be used to collect OMS image information (e.g., the location of joints and bones in the human body, the area of light spots on the human body surface, and light intensity information), and then the thermal environment parameters of the occupant cabin can be identified from the OMS image information. The current state of the thermal comfort system may include the current set temperature, wind direction, airflow, vent location, and seat ventilation / heating level. The state of the vehicle on which the occupant cabin is located may include, for example, the vehicle's speed, heading angle, latitude and longitude, and absolute time. The vehicle may include a car, aircraft, or other mobile device.
[0025] In step 220, using a trained thermal comfort control model, thermal comfort control parameters are determined based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device. These thermal comfort control parameters indicate a corresponding control scheme for each of the plurality of thermal comfort control devices. The thermal comfort control parameters may include a multi-step sequence of control parameters with a temporal order, where each step contains control parameters for at least one of the plurality of thermal comfort control devices. For example, the control scheme indicated by the thermal comfort control parameters could be, for instance, adjusting the air conditioning temperature to 24°C, increasing the fan speed to level 3 while directing the air vents towards the passenger's shoulder area to avoid direct airflow onto the face, for 5 minutes; activating the front seat ventilation at level 2, for 8 minutes; and opening the sunshade system to reduce the proportion of sunlight entering the cabin, for 10 minutes.
[0026] In some embodiments, when determining thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device using a trained thermal comfort control model, the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device can be directly input into the trained thermal comfort control model to determine the thermal comfort control parameters; alternatively, features can be extracted from the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device first, and then the extracted features can be input into the trained thermal comfort control model to determine the thermal comfort control parameters. This is not a limitation.
[0027] In some embodiments, the trained thermal comfort control model may be a pre-trained global thermal comfort control model obtained from a server, wherein the pre-trained global thermal comfort control model includes the initial version of the pre-trained global thermal comfort control model or an updated version of the global thermal comfort control model, and the updated version of the global thermal comfort control model is obtained by iteratively updating the initial version of the pre-trained global thermal comfort control model. The initial version of the pre-trained global thermal comfort control model may be deployed on the driving device during initial deployment for use by new users of the driving device. The server may continuously iteratively update the global thermal comfort control model based on various common user preference parameters and deploy the updated version of the global thermal comfort control model to the driving device. Unless otherwise specified, "user" here refers to an occupant, especially an occupant in the driver's seat.
[0028] As an example, the initial version of the pre-trained global thermal comfort control model can be obtained by training a deep learning model on a training dataset from a pre-designed database. This training dataset includes data related to preset thermal comfort control rules. The pre-designed database can be constructed based on vehicle operation data from the market or on simulation data from a controlled object model. The data related to the preset thermal comfort control rules are, for example, the input and output data of the trained thermal comfort control model. For instance, when the ambient temperature is 18°C and the humidity is 50%, the thermal comfort control parameters are the parameters corresponding to the control scheme "air conditioning set to 22°C, fan speed at level 1, seat heating off". As an example, Figure 3 An exemplary flowchart illustrating the training of a deep learning model according to an embodiment of this disclosure is shown. Figure 3As shown, the thermal environment parameters, the state of the thermal comfort system, and the state of the driving device in the training dataset 301 can be used as input data to the deep learning model 302 for feature extraction. Steps such as loss calculation on the corresponding thermal comfort control parameters and the output of the deep learning model are performed to continuously adjust the parameters of the deep learning model, minimizing the loss and thus achieving pre-training of the deep learning model. Pre-training can be achieved through multi-task learning 303, simultaneously outputting 304 "comfort index" and "thermal comfort control parameters," and simultaneously optimizing both the "comfort index" and "thermal comfort control parameters" to ensure the model's comprehensive capabilities in its basic functions.
[0029] In step 230, the corresponding thermal comfort control device is controlled based on the control scheme described above. For example, the thermal comfort control device can be automatically adjusted according to the control scheme described above: "Adjust the air conditioning temperature to 24°C, increase the fan speed to level 3, and simultaneously direct the air vents towards the passenger's shoulder area to avoid direct airflow onto the face for 5 minutes; turn on the front seat ventilation at level 2 for 8 minutes; and open the sunshade system to reduce the proportion of sunlight entering the cabin for 10 minutes."
[0030] After adjusting the corresponding thermal comfort controls, the thermal comfort system will enter a new state. Users can provide comfort feedback on this new state, such as positive or negative feedback. Positive feedback could include positive evaluations like "comfortable" or "just right" via vehicle system ratings or voice feedback; no manual adjustments made (default current comfort setting); and so on. Negative feedback could include manually modifying control parameters (such as lowering the temperature, changing the fan speed, or turning off seat heating); negative evaluations like "too cold," "too hot," or "too strong" via vehicle system ratings or voice feedback.
[0031] In some embodiments, user feedback on the thermal comfort system in a first state can also be obtained, wherein the first state is the state in which the thermal comfort system is after the corresponding thermal comfort control device is controlled based on the control scheme; then, the model parameters of the pre-trained global thermal comfort control model are updated based on the obtained comfort feedback to obtain a personalized thermal comfort control model; finally, the trained thermal comfort control model is updated to the personalized thermal comfort control model.
[0032] As an example, reinforcement learning can be used to update the model parameters of the pre-trained global thermal comfort control model based on the comfort feedback, thereby obtaining a personalized thermal comfort control model. Figure 3As shown, positive and negative user feedback can be converted into feedback signals 305, encoded by a feedback encoder 306, and then input into a reinforcement learning module 307. The reinforcement learning module includes an actor-critic network. The actor network 308 continuously attempts to adjust the control scheme 310. The critic network 309 evaluates the merits of the adjusted control scheme and calculates the cumulative reward brought by the adjustment. The reward can be the sum of a basic reward and a differential reward (the basic reward distinguishes whether the user intervenes, and the differential reward quantifies the difference between the user's adjustment and the model's output). The network parameters are updated based on the reward, allowing the model to gradually learn and optimize the control scheme that "maximizes user comfort." Of course, reinforcement learning is not mandatory; any other method can be used to update the model parameters of the pre-trained global thermal comfort control model based on comfort feedback.
[0033] In some embodiments, when the number of acquired comfort feedbacks exceeds a threshold, the model parameters of the pre-trained global thermal comfort control model can be updated based on the acquired comfort feedbacks. This avoids updating the model parameters of the pre-trained global thermal comfort control model every time comfort feedback is acquired, thus saving system resources.
[0034] In some embodiments, a pre-trained updated version of the global thermal comfort control model can be obtained as the trained thermal comfort control model. This pre-trained updated version of the global thermal comfort control model is obtained by updating the previous updated version of the global thermal comfort control model in iterative updates using parameters from a preset number of personalized thermal comfort control models. The update of the global thermal comfort control model can be triggered when the parameters of the preset number of personalized thermal comfort control models are obtained.
[0035] As an example, Figure 4 An exemplary embodiment of a thermal comfort control model according to one embodiment of the present disclosure, involving personalized learning and global optimization, is illustrated. Figure 4As shown, the thermal comfort control model 401 can output instructions for a corresponding control scheme 402 for each of the plurality of thermal comfort control devices, and can control the corresponding thermal comfort control device 403 based on the control scheme. Users can provide comfort feedback 404 regarding the comfort of the thermal comfort system after control is executed. Data from each comfort feedback session can be aggregated into a single feedback data entry 405 (which may include a timestamp, user name, environmental status, current control, and user comfort feedback). When a specified number of feedback entries is accumulated (such as a feedback quantity threshold), personalized learning 406 is triggered. Personalized learning, based on the feedback data, performs gradient calculations, model parameter updates 407, etc., with the main purpose of making the model's subsequent output more closely match the user's personal habits. The server can collect parameters from multiple models (e.g., models corresponding to multiple driving devices or multiple occupants). Upon obtaining a preset number of parameters 408 for personalized thermal comfort control models, it can use a federated averaging algorithm 408 to aggregate the parameters of these personalized models. This aggregated parameters is then used to update the global thermal comfort control model from the previous iteration. The updated global thermal comfort control model is then distributed 409 to each driving device for local model updates 410. In this way, each driving device updates its local model based on the global model, achieving global optimization through "sharing the advantages of multi-model data and retaining private data locally."
[0036] As described above, features can first be extracted from the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device. Then, the extracted features are input into a trained thermal comfort control model to determine the thermal comfort control parameters. In some embodiments, the trained thermal comfort control model includes a multi-head attention encoder, a position encoder, and a decoder. In this case, determining the thermal comfort control parameters using the trained thermal comfort control model based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device may include: extracting features from the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device to obtain a context vector; splitting the context vector into multiple attention heads using a multi-head attention encoder and determining the weight of each attention head relative to the thermal comfort level of the thermal comfort system; using a position encoder to position-encode the context vector according to its association priority with thermal comfort level to obtain a position-encoded vector; and using a decoder to determine the thermal comfort control parameters based on the position-encoded vector and the weights. The thermal comfort control parameters include a multi-step control parameter sequence with a time order, each step of the control parameter sequence containing control parameters for at least one of multiple thermal comfort control devices. It should be noted that the multiple attention heads here can include control parameters, user thermal comfort values, and head temperatures of passengers inside the vehicle. In addition to control parameters, multiple output heads of system states can be added, which can be measured by multiple sensors, thereby increasing the accuracy of the model.
[0037] As an example, Figure 5 The illustration shows an exemplary schematic diagram of determining thermal comfort control parameters using a trained thermal comfort control model according to an embodiment of the present disclosure. Figure 5 As shown, firstly, features are extracted from the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device to obtain a context vector 501. A multi-head attention encoder 502 encodes the context vector to determine the weight of each attention head relative to the thermal comfort level of the thermal comfort system. A position encoder 503 performs position encoding on the context vector according to its association priority with thermal comfort to obtain a position encoded vector. A decoder 504 can determine the thermal comfort control parameters based on the position encoded vector and the weights. The thermal comfort control parameters include a multi-step control parameter sequence with a time order, such as... Figure 5 Steps 505, 506, and 507 are shown in the diagram. Each step's control parameters include control parameters for at least one of a plurality of thermal comfort control devices. As an example, the control parameters may include set temperature, target air temperature, air speed, seat ventilation / heating level, expected time, confidence level, etc., and the sequence may end with a "stop signal".
[0038] In the control method for a thermal comfort system within a passenger compartment claimed in this disclosure, multimodal sensing inputs (thermal environment parameters of the passenger compartment, the current state of the thermal comfort system including multiple thermal comfort control devices, and the state of the driving device in which the passenger compartment is located) are used as inputs to a trained thermal comfort control model. The model outputs thermal comfort control parameters, which indicate a corresponding control scheme for each of the multiple thermal comfort control devices. The corresponding thermal comfort control device is then controlled based on the control scheme. In this way, the control method of this disclosure can adapt to differences in thermal comfort requirements under different ambient temperatures, humidity levels, and driving conditions. Furthermore, the diverse control parameters enable multiple thermal comfort control devices (e.g., air conditioning, heated and ventilated seats, air vent adjustment, etc.) to work collaboratively, improving the accuracy and efficiency of thermal comfort control, enhancing the user's thermal comfort experience while saving energy. Moreover, the technical solutions of the embodiments of this disclosure can optimize the thermal comfort control model based on the user's personal preferences and feedback, adapting to the needs of environmental changes and individual passenger preferences during long-term use, further improving the efficiency and accuracy of thermal comfort control.
[0039] Figure 6 The illustration shows an exemplary structural block diagram of a control device 600 for a thermal comfort system in an occupant cabin according to an embodiment of the present disclosure. Figure 6 As shown, the control device for the thermal comfort system in the occupant cabin includes an acquisition module 610, a determination module 620, and a control module 630.
[0040] The acquisition module 610 is configured to acquire thermal environment parameters of the passenger compartment, the current state of the thermal comfort system, and the state of the vehicle on which the passenger compartment is located. The thermal comfort system includes multiple thermal comfort control devices. These multiple thermal comfort control devices may include various types of thermal comfort control devices, such as air conditioners, electric air vents, ventilated and heated seats, sunshade systems, etc. As an example, various suitable sensors can be used to acquire the thermal environment parameters of the passenger compartment. These parameters may include, for example, the heat flow field inside the passenger compartment, the temperature and humidity information of the outside environment, the humidity information inside the passenger compartment, and the microclimate field of the human body surface inside the passenger compartment. The current state of the thermal comfort system may include the current set temperature, wind direction, airflow, air vent position, and seat ventilation / heating level. The state of the vehicle on which the passenger compartment is located may include, for example, the speed, heading angle, latitude and longitude position, and absolute time of the vehicle. The vehicle may include a car, an aircraft, or other mobile device.
[0041] The determining module 620 is configured to utilize a trained thermal comfort control model to determine thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device. These thermal comfort control parameters indicate a corresponding control scheme for each of the plurality of thermal comfort control devices. The thermal comfort control parameters may include a multi-step sequence of control parameters in a time order, with each step containing control parameters for at least one of the plurality of thermal comfort control devices.
[0042] The control module 630 is configured to control the corresponding thermal comfort control device based on the control scheme. In some embodiments, it can also acquire the comfort feedback of users in the passenger cabin on the thermal comfort system in a first state, wherein the first state is the state of the thermal comfort system after controlling the corresponding thermal comfort control device based on the control scheme; then, the model parameters of the pre-trained global thermal comfort control model are updated based on the acquired comfort feedback to obtain a personalized thermal comfort control model; finally, the trained thermal comfort control model is updated to the personalized thermal comfort control model.
[0043] In the control device for a thermal comfort system within the passenger compartment claimed in this disclosure, multimodal sensing inputs (thermal environmental parameters of the passenger compartment, the current state of the thermal comfort system including multiple thermal comfort control devices, and the state of the driving device in which the passenger compartment is located) are used as inputs to a trained thermal comfort control model. The model outputs thermal comfort control parameters, which indicate a corresponding control scheme for each of the multiple thermal comfort control devices. The corresponding thermal comfort control device is then controlled based on the control scheme. In this way, the control device of this disclosure can adapt to differences in thermal comfort requirements under different ambient temperatures, humidity levels, and driving conditions. Furthermore, the diverse control parameters enable multiple thermal comfort control devices (e.g., air conditioning, heated and ventilated seats, air vent adjustment, etc.) to work collaboratively, improving the accuracy and efficiency of thermal comfort control, enhancing the user's thermal comfort experience while saving energy. Moreover, the technical solution of the embodiments of this disclosure can optimize the thermal comfort control model based on the user's personal preferences and feedback, adapting to the needs of environmental changes and individual passenger preferences during long-term use, further improving the efficiency and accuracy of thermal comfort control.
[0044] Figure 7An example block diagram of a computing device 700 according to some embodiments of the present disclosure is schematically shown. The computing device 700 may represent a device for implementing the various means or modules described herein and / or performing the various methods described herein. The computing device 700 may be, for example, a server, desktop computer, laptop computer, tablet, smartphone, smartwatch, wearable device, or any other suitable computing device or computing system, which may include various levels of devices ranging from full-resource devices with large storage and processing resources to low-resource devices with limited storage and / or processing resources. In some embodiments, the above regarding... Figure 6 The control device for the thermal comfort system in the occupant cabin described herein can be implemented in one or more computing devices.
[0045] like Figure 7 As shown, the example computing device 700 includes a processing system 701 communicatively coupled to each other, one or more computer-readable media 702, and one or more I / O interfaces 703. Although not shown, the computing device 700 may also include a system bus or other data and command transmission system that couples the various components to each other. The system bus may include any or a combination of different bus architectures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and / or a processor or local bus utilizing any of the various bus architectures. Alternatively, it may also include control and data lines.
[0046] Processing system 701 represents the functionality of performing one or more operations using hardware. Therefore, processing system 701 is illustrated as including hardware elements 704 that can be configured as processors, function blocks, etc. This may include other logic devices implemented in hardware as application-specific integrated circuits (ASICs) or formed using one or more semiconductors. Hardware element 704 is not limited by the materials in which it is formed or the processing mechanism employed therein. For example, a processor may consist of semiconductors and / or transistors (e.g., integrated circuits (ICs)). In such a context, processor-executable instructions may be electronically executable instructions.
[0047] Computer-readable medium 702 is illustrated as including memory / storage device 705. Memory / storage device 705 represents a memory / storage device associated with one or more computer-readable media. Memory / storage device 705 may include volatile media (such as random access memory (RAM)) and / or non-volatile media (such as read-only memory (ROM), flash memory, optical disk, magnetic disk, etc.). Memory / storage device 705 may include fixed media (e.g., RAM, ROM, fixed hard disk drive, etc.) and removable media (e.g., flash memory, removable hard disk drive, optical disk, etc.). Exemplarily, memory / storage device 705 may be used to store first audio of a first category of users mentioned in the above embodiments, a queue list of requests, etc. Computer-readable medium 702 may be configured in various other ways as further described below.
[0048] One or more I / O (input / output) interfaces 703 represent the functionality that allows a user to type commands and information into a computing device 700 and also allows information to be displayed to the user and / or sent to other components or devices using various input / output devices. Examples of input devices include keyboards, cursor control devices (e.g., mice), microphones (e.g., for voice input), scanners, touch functionality (e.g., capacitive or other sensors configured to detect physical touch), cameras (e.g., capable of detecting non-touch-related movements as gestures using visible or invisible wavelengths (such as infrared frequencies), network interface cards (NICs), receivers, and so on). Examples of output devices include display devices (e.g., monitors or projectors), speakers, printers, haptic-responsive devices, network interface cards (NICs), transmitters, and so on. Exemplarily, in the embodiments described above, both a first-category user and a second-category user can input through the input interfaces on their respective terminal devices to initiate requests and record audio and / or video, and can view various notifications and watch videos or listen to audio, etc., through the output interfaces.
[0049] The computing device 700 includes a control application 706 for the thermal comfort system within the occupant cabin. The control application 706 for the thermal comfort system within the occupant cabin can be stored as computing program instructions in a memory / storage device 705, or it can be hardware or firmware. The occupant positioning strategy 706 within the cabin can be implemented together with the processing system 701, etc., regarding... Figure 2 The method described is for controlling the thermal comfort system within the passenger cabin.
[0050] This disclosure provides a computer-readable storage medium having computer-readable instructions stored thereon, which, when executed, implement any of the methods described above.
[0051] This disclosure provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computing device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computing device to perform any of the methods provided in the various alternative implementations described above.
[0052] The user personal information involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, and based on the reasonable purpose of the business scenario. This processing involves personal information actively provided by users during the use of the product / service, information generated as a result of using the product / service, or information obtained with user authorization. The user personal information processed in this application may vary depending on the specific product / service scenario and should be based on the specific scenario in which the user uses the product / service. This may involve user account information, device information, driving information, vehicle information, or other related information. The applicant will treat user personal information and its processing with a high degree of diligence. This application attaches great importance to the security of user personal information and has adopted industry-standard and reasonable security protection measures to protect user information and prevent unauthorized access, public disclosure, use, modification, damage, or loss.
[0053] It should be understood that, for clarity, embodiments of this disclosure have been described with reference to different functional units. However, it will be apparent that, without departing from this disclosure, the functionality of each functional unit may be implemented in a single unit, in multiple units, or as part of other functional units. For example, functionality described as being performed by a single unit may be performed by multiple different units. Therefore, references to a particular functional unit are considered merely as references to the appropriate unit used to provide the described functionality, and not as indicating a strict logical or physical structure or organization. Thus, this disclosure may be implemented in a single unit, or may be physically and functionally distributed among different units and circuits.
[0054] It will be understood that although the terms first, second, third, etc., may be used herein to describe various devices, elements, components, or parts, these devices, elements, components, or parts should not be limited by these terms. These terms are used only to distinguish one device, element, component, or part from another device, element, component, or part.
[0055] Although this disclosure has been described in conjunction with some embodiments, it is not intended to be limited to the specific forms set forth herein. Rather, the scope of this disclosure is limited only by the appended claims. Additionally, although individual features may be included in different claims, these may be advantageously combined, and inclusion in different claims does not imply that such a combination of features is not feasible and / or advantageous. The order of features in the claims does not imply that the features must be in any particular order of their operation. Furthermore, in the claims, the word "comprising" does not exclude other elements, and the terms "a" or "an" do not exclude a plurality. Reference numerals in the claims are provided only by way of explicit example and should not be construed as limiting the scope of the claims in any way.
Claims
1. A control method for a thermal comfort system within a passenger cabin, comprising: Acquire thermal environment parameters of the passenger compartment, the current status of the thermal comfort system, and the status of the driving device in which the passenger compartment is located, wherein the thermal comfort system includes multiple thermal comfort control devices. Using a trained thermal comfort control model, thermal comfort control parameters are determined based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device. These thermal comfort control parameters indicate the corresponding control scheme for each of the plurality of thermal comfort control devices. The corresponding thermal comfort control device is controlled based on the control scheme.
2. The method according to claim 1, wherein, The trained thermal comfort control model includes a pre-trained global thermal comfort control model, wherein the pre-trained global thermal comfort control model includes the initial version of the pre-trained global thermal comfort control model or an updated version of the global thermal comfort control model, and the updated version of the global thermal comfort control model is obtained by iteratively updating the initial version of the pre-trained global thermal comfort control model.
3. The method according to claim 2, wherein, The initial version of the pre-trained global thermal comfort control model is obtained by training a deep learning model based on a training dataset in a pre-designed database, which includes data related to preset thermal comfort control rules.
4. The method according to claim 2, further comprising: Obtain comfort feedback from users in the passenger cabin regarding the thermal comfort system in a first state, wherein the first state is the state in which the thermal comfort system is after controlling the corresponding thermal comfort control device based on the control scheme; The model parameters of the pre-trained global thermal comfort control model are updated based on the obtained comfort feedback to obtain a personalized thermal comfort control model. The trained thermal comfort control model is updated to the personalized thermal comfort control model.
5. The method according to claim 4, wherein, The model parameters of the pre-trained global thermal comfort control model are updated based on the acquired comfort feedback, including: If the number of acquired comfort feedbacks exceeds a threshold, the model parameters of the pre-trained global thermal comfort control model are updated based on the acquired comfort feedbacks.
6. The method according to claim 4, further comprising: A pre-trained updated version of the global thermal comfort control model is obtained as the trained thermal comfort control model, wherein the pre-trained updated version of the global thermal comfort control model is obtained by updating the previous updated version of the global thermal comfort control model in the iterative update using parameters of a preset number of personalized thermal comfort control models.
7. The method according to claim 1, wherein, The trained thermal comfort control model includes a multi-head attention encoder, a position encoder, and a decoder. It utilizes this model to determine thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device. These parameters include: The thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device are used to extract features to obtain a context vector; The context vector is split into multiple attention heads using a multi-head attention encoder, and the weight of each attention head relative to the thermal comfort of the thermal comfort system is determined. The position encoder is used to position-encode the context vector according to its association priority with thermal comfort to obtain the position-encoded vector; The thermal comfort control parameters are determined using a decoder based on the location encoding vector and weights. The thermal comfort control parameters include a multi-step sequence of control parameters with a time order, and each step of the control parameters includes control parameters for at least one of a plurality of thermal comfort control devices.
8. A control device for a thermal comfort system within a passenger compartment, comprising: The acquisition module is configured to acquire thermal environment parameters of the passenger compartment, the current status of the thermal comfort system, and the status of the driving device in which the passenger compartment is located, wherein the thermal comfort system includes multiple thermal comfort control devices. The determination module is configured to: use a trained thermal comfort control model to determine thermal comfort control parameters based on the thermal environment parameters, the current state of the thermal comfort system, and the state of the driving device, wherein the thermal comfort control parameters indicate a corresponding control scheme for each of the plurality of thermal comfort control devices; The control module is configured to control the corresponding thermal comfort control device based on the control scheme.
9. A computing device, comprising Memory, which is configured to store computer-executable instructions; A processor configured to perform the method as described in any one of claims 1-7 when the computer-executable instructions are executed by the processor.
10. A computer-readable storage medium storing computer-executable instructions that, when executed, perform the method as described in any one of claims 1-7.