Intelligent cabin comfort degree adjusting method, device and equipment and readable storage medium

Abstract

The invention provides an intelligent cabin comfort degree adjusting method, device and equipment and a readable storage medium. The method comprises the steps that passenger physiological data and environment data are collected in real time; at the starting moment of each round of adjustment, the passengers and the environment serve as two game main bodies of dynamic game, a strategy combination with the optimal utility is generated according to passenger physiological data and environment data at the current moment, and the strategy combination is adopted to adjust the comfort degree of the intelligent cabin; and at each moment between the starting moments of two adjacent rounds of adjustment, performing fine adjustment on the strategy combination adopted at the previous moment according to the passenger physiological data and the environmental data at the current moment, and performing intelligent cabin comfort adjustment by adopting the strategy combination after fine adjustment. According to the method and the device, the strategy combination updated in real time is provided under the limited operation capability to adapt to the physiological state of the passenger and the dynamic change of the external environment, so that the overall comfort experience of the passenger is improved.

Description

Technical Field

[0001] This application relates to the technical field of intelligent cockpits, and particularly to a method, device, equipment and readable storage medium for adjusting the comfort of an intelligent cockpit. Background Art

[0002] With the continuous development of the automotive industry, intelligent cockpit technology has gradually become an important part of modern vehicles. The intelligent cockpit not only brings great convenience to drivers and passengers in terms of safety, convenience and entertainment, but also plays an important role in improving riding comfort.

[0003] In the prior art, the method for adjusting the comfort of an intelligent cockpit usually adopts a preset control strategy, and improves comfort by adjusting parameters such as the temperature, humidity, seat position and sound effect in the vehicle. This static control strategy cannot adapt to the physiological state of passengers and the dynamic changes of the external environment, resulting in poor comfort improvement effect. Summary of the Invention

[0004] This application provides a method, device, equipment and readable storage medium for adjusting the comfort of an intelligent cockpit, which can solve the technical problem of poor comfort improvement effect caused by the static control strategy in the prior art.

[0005] In a first aspect, an embodiment of this application provides a method for adjusting the comfort of an intelligent cockpit, and the method for adjusting the comfort of the intelligent cockpit includes:

[0006] Real-time collect passenger physiological data and environmental data;

[0007] At the starting moment of each round of adjustment, taking the passenger and the environment as two game players in a dynamic game, generate a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment, and use this strategy combination to adjust the comfort of the intelligent cockpit;

[0008] At each moment between the starting moments of two adjacent rounds of adjustment, fine-tune the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment, and use the fine-tuned strategy combination to adjust the comfort of the intelligent cockpit.

[0009] Further, in one embodiment, the step of generating a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment includes:

[0010] Construct a passenger strategy set and an environment strategy set according to the passenger physiological data and environmental data at the current moment;

[0011] Combine each strategy in the passenger strategy set with each strategy in the environment strategy set pairwise to form a plurality of alternative strategy combinations;

[0012] For each alternative strategy combination, predict the passenger physiological data and environmental data after adopting the corresponding strategy combination based on the passenger physiological data and environmental data at the current moment, and calculate the passenger utility value and environmental utility value based on the predicted passenger physiological data and environmental data;

[0013] Select the strategy combination with the optimal passenger utility value and environmental utility value from all alternative strategy combinations.

[0014] Further, in one embodiment, the step of predicting the passenger physiological data and environmental data after adopting the corresponding strategy combination based on the passenger physiological data and environmental data at the current moment includes:

[0015] Based on the deep Q-network algorithm, predict the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment. In the deep Q-network algorithm, the state is defined as the passenger physiological data and environmental data, the action is defined as the strategy combination, and the Q-network is trained in each round of adjustment. The target network adopted is copied from the Q-network trained in the previous round of adjustment.

[0016] Further, in one embodiment, the step of fine-tuning the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment includes:

[0017] Based on the adaptive algorithm, fine-tune the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment.

[0018] Further, in one embodiment, the intelligent cockpit comfort adjustment method further includes:

[0019] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is less than the preset period, it is determined that the current moment is not the end moment of this round of adjustment;

[0020] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is greater than or equal to the preset period, it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0021] Further, in one embodiment, the intelligent cockpit comfort adjustment method further includes:

[0022] If the current moment is not the starting moment of this round of adjustment, and the difference between the passenger physiological data and environmental data at the current moment and the starting moment of this round of adjustment is within the preset range, it is determined that the current moment is not the end moment of this round of adjustment;

[0023] If the current moment is not the starting moment of the current round of adjustment, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are not within the preset range, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0024] Further, in one embodiment, the intelligent cockpit comfort adjustment method further includes:

[0025] If the current moment is not the starting moment of the current round of adjustment, the time interval between the current moment and the starting moment of the current round of adjustment is less than the preset period, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are within the preset range, then it is determined that the current moment is not the end moment of the current round of adjustment;

[0026] If the current moment is not the starting moment of the current round of adjustment, and the time interval between the current moment and the starting moment of the current round of adjustment is greater than or equal to the preset period, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment;

[0027] If the current moment is not the starting moment of the current round of adjustment, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are not within the preset range, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0028] In a second aspect, an embodiment of the present application further provides an intelligent cockpit comfort adjustment device, and the intelligent cockpit comfort adjustment device includes:

[0029] A data acquisition module, configured to collect passenger physiological data and environmental data in real time;

[0030] A strategy generation module, configured to, at the starting moment of each round of adjustment, take the passenger and the environment as the two game players in a dynamic game, generate a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment, and perform intelligent cockpit comfort adjustment by using the strategy combination;

[0031] A strategy fine-tuning module, configured to, at each moment between the starting moments of two adjacent rounds of adjustment, fine-tune the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment, and perform intelligent cockpit comfort adjustment by using the fine-tuned strategy combination.

[0032] In a third aspect, an embodiment of the present application further provides an intelligent cockpit comfort adjustment device, and the intelligent cockpit comfort adjustment device includes a processor, a memory, and an intelligent cockpit comfort adjustment program stored on the memory and executable by the processor. When the intelligent cockpit comfort adjustment program is executed by the processor, the steps of the above intelligent cockpit comfort adjustment method are implemented.

[0033] In a fourth aspect, an embodiment of the present application further provides a readable storage medium, on which an intelligent cockpit comfort adjustment program is stored. When the intelligent cockpit comfort adjustment program is executed by a processor, the steps of the above-mentioned intelligent cockpit comfort adjustment method are implemented.

[0034] In the present application, in each round of adjustment, first, the passenger and the environment are used as the two game players in a dynamic game, and an initial strategy combination is generated based on the initial passenger physiological data and environmental data to initially meet the personalized needs of the passenger and the overall adaptability of the environment. Next, the strategy combination is continuously fine-tuned according to the latest passenger physiological data and environmental data, reducing the computational complexity while ensuring the effectiveness of the strategy combination. Through the present application, a real-time updated strategy combination is provided under limited computing power to adapt to the dynamic changes of the passenger's physiological state and the external environment, thereby improving the overall comfort experience of the passenger. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a schematic flowchart of an intelligent cockpit comfort adjustment method in an embodiment of the present application;

[0036] Figure 2 is a schematic diagram of the principle of strategy generation and fine-tuning in an embodiment of the present application;

[0037] Figure 3 is a schematic diagram of the functional modules of an intelligent cockpit comfort adjustment device in an embodiment of the present application;

[0038] Figure 4 is a schematic diagram of the hardware structure of an intelligent cockpit comfort adjustment device involved in the embodiment solution of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0040] To make the purpose, technical solution and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0041] In a first aspect, an embodiment of the present application provides an intelligent cockpit comfort adjustment method.

[0042] Figure 1 shows a schematic flowchart of an intelligent cockpit comfort adjustment method in an embodiment of the present application.

[0043] Referring to Figure 1 , in one embodiment, the intelligent cockpit comfort adjustment method includes the following steps:

[0044] S1. Collect passenger physiological data and environmental data in real time.

[0045] In this embodiment, the passenger physiological data directly reflects the passenger's physiological state and comfort needs, and the environmental data provides the state of the current environment. The two jointly determine the generation of the strategy. The passenger physiological data affects the demand for comfort adjustment, and the environmental data affects the feasibility and effect of environmental adjustment. The combination of the two can help construct a more accurate and responsive strategy to dynamically adjust the cockpit control parameters to optimize the passenger's comfort.

[0046] Exemplarily, the passenger physiological data includes body temperature, heart rate, and posture, and the environmental data includes temperature, humidity, and noise level.

[0047] Optionally, for the passenger physiological data and environmental data directly collected by the sensor, first perform data cleaning to remove outliers and missing values, then perform denoising processing, use a noise filtering algorithm to filter out the noise in the data, and finally perform standardization processing to convert the data to the same scale. The subsequent steps use the processed passenger physiological data and environmental data.

[0048] S2. At the start of each round of adjustment, taking the passenger and the environment as the two game players in a dynamic game, generate a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment, and use this strategy combination to adjust the comfort of the intelligent cockpit.

[0049] In this embodiment, taking the passenger and the environment as the two game players in a dynamic game, the passenger's utility function pays more attention to how to maximize the passenger's comfort, for example, is more concerned about the stable state of body temperature and heart rate. The utility function of the environment focuses on the stability of environmental parameters and energy efficiency optimization, for example, is more concerned about the balance of temperature and humidity within an appropriate range. The strategy combination includes a passenger strategy and an environment strategy. The passenger strategy is mainly aimed at the physiological needs of individual passengers and aims to improve the passenger's subjective comfort by adjusting the cockpit control parameters. The environment strategy mainly focuses on the overall environmental conditions inside the cockpit to ensure that these conditions are within an appropriate range. The difference between the two is that the passenger strategy is more personalized and targeted, while the environment strategy pays more attention to the overall adaptability of the cockpit control parameters.

[0050] Exemplarily, for the case where the passenger has a high body temperature, the passenger strategy may be set to lower the cockpit temperature and increase the ventilation rate at the same time to help the passenger cool down, while the environment strategy may include adjusting the humidity or reducing the noise to meet the predetermined environmental standards. These strategies are evaluated and selected through a dynamic game model to achieve a balance between passenger comfort and environmental quality.

[0051] Exemplarily, the specific manifestation of using a policy combination for intelligent cockpit comfort adjustment is as follows: The policy combination is transmitted to the intelligent control system, and the intelligent control system performs parameter mapping according to the policy combination to generate specific cockpit adjustment instructions. For example, temperature adjustment instructions, humidity adjustment instructions, seat position adjustment instructions, and sound effect adjustment instructions. The intelligent control system adjusts the cockpit control parameters in the cockpit in real time according to the generated cockpit adjustment instructions.

[0052] It should be noted that in this embodiment, the comfort adjustment is carried out in rounds, and the computational amount of step S2 is relatively large, and it is only executed once at the start moment of each round of adjustment.

[0053] S3. At each moment between the start moments of two adjacent rounds of adjustment, fine-tune the policy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment, and use the fine-tuned policy combination for intelligent cockpit comfort adjustment.

[0054] In this embodiment, in the case of no obvious intervention, the passenger physiological data and environmental data at the subsequent moment can reflect the effect of the policy combination adopted at the previous moment, and be used as the basis for fine-tuning, so as to improve the effect of the policy combination with a relatively small computational amount.

[0055] Figure 2 Fig. shows a schematic diagram of the principle of policy generation and fine-tuning in an embodiment of the present application.

[0056] Exemplarily, referring to Figure 2 , assume that the time from moment 1 to n is a round of adjustment. At moment 1, collect passenger physiological data 1 and environmental data 1, generate policy combination 1 according to passenger physiological data 1 and environmental data 1, and use policy combination 1 for intelligent cockpit comfort adjustment. At moment 2, collect passenger physiological data 2 and environmental data 2, fine-tune policy combination 1 according to passenger physiological data 2 and environmental data 2 to obtain policy combination 2, and use policy combination 2 for intelligent cockpit comfort adjustment. At moment 3, collect passenger physiological data 3 and environmental data 3, fine-tune policy combination 2 according to passenger physiological data 3 and environmental data 3 to obtain policy combination 3, and use policy combination 3 for intelligent cockpit comfort adjustment,... At moment n, collect passenger physiological data n and environmental data n, fine-tune policy combination n - 1 according to passenger physiological data n and environmental data n to obtain policy combination n, and use policy combination n for intelligent cockpit comfort adjustment.

[0057] Thus, in this embodiment, in each round of adjustment, first, the passengers and the environment are taken as the two game players in the dynamic game. An initial strategy combination is generated based on the initial passenger physiological data and environmental data to preliminarily meet the personalized needs of the passengers and the overall adaptability of the environment. Next, the strategy combination is continuously fine-tuned according to the latest passenger physiological data and environmental data, while ensuring the effectiveness of the strategy combination and reducing the computational complexity. Through this embodiment, a real-time updated strategy combination is provided under limited computing power to adapt to the dynamic changes of the passengers' physiological states and the external environment, thereby enhancing the overall comfort experience of the passengers.

[0058] Further, in one embodiment, the step of generating a strategy combination with optimal utility according to the passenger physiological data and environmental data at the current moment includes:

[0059] Construct a passenger strategy set and an environment strategy set according to the passenger physiological data and environmental data at the current moment;

[0060] Combine each strategy in the passenger strategy set with each strategy in the environment strategy set pairwise to form a plurality of alternative strategy combinations;

[0061] For each alternative strategy combination, predict the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment, and calculate the passenger utility value and the environment utility value according to the predicted passenger physiological data and environmental data;

[0062] Select the strategy combination with the optimal passenger utility value and environment utility value from all alternative strategy combinations.

[0063] Exemplarily, the passenger utility values and environment utility values corresponding to all alternative strategy combinations are expressed as:

[0064]

[0065] where σ pi represents the i-th strategy of the passenger, σ ej represents the j-th strategy of the environment, and U p (σ pi , σ ej ) and U e (σ pi , σ ej ) respectively represent the utility values of the passenger and the environment under the alternative strategy combination (σ pi , σ ej ).

[0066] Further, in one embodiment, the step of predicting the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment includes:

[0067] Based on the deep Q-network algorithm, the passenger physiological data and environmental data after adopting the corresponding strategy combination are predicted based on the current passenger physiological data and environmental data. In the deep Q-network algorithm, the state is defined as the passenger physiological data and environmental data, and the action is defined as the strategy combination. The Q-network is trained in each round of adjustment, and the target network used is copied from the Q-network trained in the previous round of adjustment.

[0068] For example, at the start of the first round of adjustment, the same target network and Q network are randomly initialized and generated. The target network predicts the passenger physiological data and environmental data after adopting different alternative strategy combinations, and selects the strategy combination with the best utility. At each moment in the first round of adjustment, the current action (i.e., the adopted strategy combination), the current state (i.e., the collected passenger physiological data and environmental data), and the state at the next moment are stored as empirical data in the playback buffer. A batch of empirical data is randomly extracted from the playback buffer and used to train the Q network. During the training process, the target network is used to calculate the target Q value, and the parameters of the Q network are updated by minimizing the difference between the predicted Q value and the target Q value (usually using a mean square error loss function, etc.). At the start of the second round of adjustment, the parameters of the Q network at the end of the first round of adjustment are copied to the target network.

[0069] In this embodiment, the changes in passenger physiological and environmental data after the adoption of the strategy combination involve the interactions and changes of multiple factors, resulting in a high-dimensional state space and a large amount of information. Deep Q-networks have powerful feature extraction and representation capabilities. Through an experience replay mechanism, they leverage past experience data for learning and training. This accumulated historical data contains information about changes under different strategy combinations. Deep Q-networks can then mine the potential relationships and patterns between strategy combinations and this information, thereby accurately predicting future external conditions after the adoption of these strategies.

[0070] Through this embodiment, instead of using a model solidified before leaving the factory for prediction, the prediction link in the dynamic game model is continuously optimized during the actual vehicle operation process, thereby ensuring the adaptability of the dynamic game model in different actual vehicle operation scenarios.

[0071] Furthermore, in one embodiment, the step of fine-tuning the strategy combination adopted at the previous moment based on the passenger physiological data and environmental data at the current moment includes:

[0072] Based on the adaptive algorithm, the strategy combination adopted at the previous moment is fine-tuned according to the passenger's physiological data and environmental data at the current moment.

[0073] The Adaptive Algorithm is a type of algorithm that can automatically adjust its own parameters or structure according to factors such as environmental changes, input data characteristics, or the system's own state, in order to optimize performance and achieve better operating effects. In this embodiment, the policy combination is fine-tuned through the adaptive algorithm to cope with environmental changes, make up for information limitations, and optimize long-term performance.

[0074] Further, in one embodiment, the intelligent cockpit comfort adjustment method further includes:

[0075] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is less than the preset period, then it is determined that the current moment is not the end moment of this round of adjustment;

[0076] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is greater than or equal to the preset period, then it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0077] In this embodiment, by restricting the duration of each round of adjustment, it is ensured that the policy combination generated in step S2 can maintain its effectiveness through continuous fine-tuning.

[0078] Further, in one embodiment, the intelligent cockpit comfort adjustment method further includes:

[0079] If the current moment is not the starting moment of this round of adjustment, and the difference between the passenger physiological data and environmental data at the current moment and the starting moment of this round of adjustment is within the preset range, then it is determined that the current moment is not the end moment of this round of adjustment;

[0080] If the current moment is not the starting moment of this round of adjustment, and the difference between the passenger physiological data and environmental data at the current moment and the starting moment of this round of adjustment is not within the preset range, then it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0081] In this embodiment, by restricting the change range of the passenger physiological data and environmental data in each round of adjustment, it is ensured that the policy combination generated in step S2 can maintain its effectiveness through continuous fine-tuning.

[0082] Further, in one embodiment, the intelligent cockpit comfort adjustment method further includes:

[0083] If the current moment is not the starting moment of this round of adjustment, the time interval between the current moment and the starting moment of this round of adjustment is less than the preset period, and the difference between the passenger physiological data and environmental data at the current moment and the starting moment of this round of adjustment is within the preset range, then it is determined that the current moment is not the end moment of this round of adjustment;

[0084] If the current moment is not the starting moment of the current round of adjustment, and the time interval between the current moment and the starting moment of the current round of adjustment is greater than or equal to the preset period, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment;

[0085] If the current moment is not the starting moment of the current round of adjustment, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are not within the preset range, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0086] In this embodiment, by restricting the duration of each round of adjustment and the change range of the passenger physiological data and environmental data, it is ensured that the policy combination generated in step S2 can maintain effectiveness through continuous fine-tuning.

[0087] In a second aspect, an embodiment of the present application further provides an intelligent cockpit comfort adjustment device.

[0088] Figure 3 The functional module schematic diagram of the intelligent cockpit comfort adjustment device in an embodiment of the present application is shown.

[0089] Referring to Figure 3 , in one embodiment, the intelligent cockpit comfort adjustment device includes:

[0090] A data acquisition module 10 for real-time acquisition of passenger physiological data and environmental data;

[0091] A policy generation module 20 for, at the starting moment of each round of adjustment, taking the passenger and the environment as the two game players in a dynamic game, generating a policy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment, and using this policy combination to adjust the comfort of the intelligent cockpit;

[0092] A policy fine-tuning module 30 for, at each moment between the starting moments of two adjacent rounds of adjustment, fine-tuning the policy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment, and using the fine-tuned policy combination to adjust the comfort of the intelligent cockpit.

[0093] Furthermore, in one embodiment, the policy generation module 20 is used for:

[0094] Constructing a passenger policy set and an environment policy set according to the passenger physiological data and environmental data at the current moment;

[0095] Pairwise combining each policy in the passenger policy set and each policy in the environment policy set to form a plurality of alternative policy combinations;

[0096] For each alternative strategy combination, predict the passenger physiological data and environmental data after adopting the corresponding strategy combination based on the passenger physiological data and environmental data at the current moment, and calculate the passenger utility value and environmental utility value based on the predicted passenger physiological data and environmental data;

[0097] Select the strategy combination with the optimal passenger utility value and environmental utility value from all alternative strategy combinations.

[0098] Further, in one embodiment, the strategy generation module 20 is configured to:

[0099] Based on the deep Q-network algorithm, predict the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment. In the deep Q-network algorithm, the state is defined as the passenger physiological data and environmental data, the action is defined as the strategy combination, and the Q-network is trained in each round of adjustment. The target network adopted is copied from the Q-network trained in the previous round of adjustment.

[0100] Further, in one embodiment, the strategy fine-tuning module 30 is configured to:

[0101] Based on the adaptive algorithm, fine-tune the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment.

[0102] Further, in one embodiment, the intelligent cockpit comfort adjustment device further includes a round update module, which is used for:

[0103] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is less than the preset period, it is determined that the current moment is not the end moment of this round of adjustment;

[0104] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is greater than or equal to the preset period, it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0105] Further, in one embodiment, the intelligent cockpit comfort adjustment device further includes a round update module, which is used for:

[0106] If the current moment is not the starting moment of this round of adjustment, and the difference between the passenger physiological data and environmental data at the current moment and the starting moment of this round of adjustment is within the preset range, it is determined that the current moment is not the end moment of this round of adjustment;

[0107] If the current moment is not the starting moment of this round of adjustment, and the difference between the passenger physiological data and environmental data at the current moment and the starting moment of this round of adjustment is not within the preset range, it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0108] Further, in one embodiment, the intelligent cockpit comfort adjustment device further includes a round update module, which is used for:

[0109] If the current moment is not the starting moment of this round of adjustment, the time interval between the current moment and the starting moment of this round of adjustment is less than the preset period, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of this round of adjustment are within the preset range, then it is determined that the current moment is not the end moment of this round of adjustment;

[0110] If the current moment is not the starting moment of this round of adjustment, and the time interval between the current moment and the starting moment of this round of adjustment is greater than or equal to the preset period, then it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment;

[0111] If the current moment is not the starting moment of this round of adjustment, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of this round of adjustment are not within the preset range, then it is determined that the current moment is the end moment of this round of adjustment, and the next moment is the starting moment of the next round of adjustment.

[0112] Among them, the function implementation of each module in the above intelligent cockpit comfort adjustment device corresponds to each step in the above embodiment of the intelligent cockpit comfort adjustment method, and its function and implementation process will not be elaborated here one by one.

[0113] In a third aspect, an embodiment of the present application provides an intelligent cockpit comfort adjustment device, and the intelligent cockpit comfort adjustment device may be a device with data processing functions such as a personal computer (PC), a laptop computer, a server, etc.

[0114] Figure 4 The hardware structure diagram of the intelligent cockpit comfort adjustment device involved in the embodiment of the present application is shown.

[0115] Refer to Figure 4 In the embodiment of the present application, the intelligent cockpit comfort adjustment device may include a processor, a memory, a communication interface, and a communication bus.

[0116] Among them, the communication bus can be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0117] The communication interface includes interfaces such as input / output (I / O) interfaces, physical interfaces, and logical interfaces for implementing the interconnection of components inside the intelligent cockpit comfort adjustment device, as well as interfaces for implementing the interconnection between the intelligent cockpit comfort adjustment device and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0118] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical memory, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0119] The processor can be a general-purpose processor, which can call the intelligent cockpit comfort adjustment program stored in the memory and execute the intelligent cockpit comfort adjustment method provided in the embodiments of the present application. For example, the general-purpose processor can be a central processing unit (CPU). Among them, the method executed when the intelligent cockpit comfort adjustment program is called can refer to the various embodiments of the intelligent cockpit comfort adjustment method of the present application, which will not be elaborated here.

[0120] Those skilled in the art can understand that Figure 4 the hardware structure shown in

[0121] does not constitute a limitation to the present application, and may include more or fewer components than shown in the figure, or combine certain components, or arrange different components.

[0122] The intelligent cockpit comfort adjustment program is stored on the readable storage medium of the present application. When the intelligent cockpit comfort adjustment program is executed by the processor, the steps of the intelligent cockpit comfort adjustment method as described above are implemented.

[0123] Among them, the method implemented when the intelligent cockpit comfort adjustment program is executed can refer to the various embodiments of the intelligent cockpit comfort adjustment method of the present application, which will not be elaborated here.

[0124] It should be noted that the serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0125] The terms "including" and "having" and any variations thereof in the description of the specification, claims and drawings of the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices. The descriptions of terms such as "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit that "first", "second" and "third" are different types.

[0126] In the description of the embodiments of the present application, terms such as "exemplary", "for example" or "for instance" are used to mean for example, illustration or explanation. Any embodiment or design solution described as "exemplary", "for example" or "for instance" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary", "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0127] In the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B can mean A or B; "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality of" means two or more than two.

[0128] In some processes described in the embodiments of the present application, there are a plurality of operations or steps that appear in a specific order. However, it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or may be executed in parallel. The serial numbers of the operations are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in order or in parallel, and these operations or steps may be combined.

[0129] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device to execute the methods described in various embodiments of the present application.

[0130] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. An intelligent cockpit comfort adjustment method, characterized in that, The intelligent cockpit comfort adjustment method includes: Collecting passenger physiological data and environmental data in real time; At the start of each round of adjustment, taking the passenger and the environment as the two game players in a dynamic game, generating a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment, and using this strategy combination to adjust the comfort of the intelligent cockpit; At each moment between the start times of two adjacent rounds of adjustment, fine-tuning the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment, and using the fine-tuned strategy combination to adjust the comfort of the intelligent cockpit.

2. The intelligent cockpit comfort adjustment method according to claim 1, wherein, The steps of generating a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment include: Constructing a passenger strategy set and an environment strategy set according to the passenger physiological data and environmental data at the current moment; Combining each strategy in the passenger strategy set with each strategy in the environment strategy set pairwise to form multiple alternative strategy combinations; For each alternative strategy combination, predicting the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment, and calculating the passenger utility value and the environment utility value according to the predicted passenger physiological data and environmental data; Selecting the strategy combination with the optimal passenger utility value and environment utility value from all alternative strategy combinations.

3. The intelligent cockpit comfort adjustment method according to claim 2, wherein, The steps of predicting the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment include: Based on the deep Q-network algorithm, predicting the passenger physiological data and environmental data after adopting the corresponding strategy combination according to the passenger physiological data and environmental data at the current moment. In the deep Q-network algorithm, the state is defined as the passenger physiological data and environmental data, the action is defined as the strategy combination, and the Q-network is trained during each round of adjustment. The target network adopted is copied from the Q-network trained in the previous round of adjustment.

4. The intelligent cockpit comfort adjustment method according to claim 1, characterized in that, The steps of fine-tuning the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment include: Based on the adaptive algorithm, fine-tuning the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment.

5. The intelligent cockpit comfort adjustment method according to any one of claims 1 to 4, characterized in that The intelligent cockpit comfort adjustment method further includes: If the current moment is not the start time of this round of adjustment, and the time interval between the current moment and the start time of this round of adjustment is less than the preset period, it is determined that the current moment is not the end time of this round of adjustment; If the current moment is not the start time of this round of adjustment, and the time interval between the current moment and the start time of this round of adjustment is greater than or equal to the preset period, it is determined that the current moment is the end time of this round of adjustment, and the next moment is the start time of the next round of adjustment.

6. The intelligent cockpit comfort adjustment method according to any one of claims 1 to 4, characterized in that The intelligent cockpit comfort adjustment method further includes: If the current moment is not the start time of this round of adjustment, and the difference between the passenger physiological data and environmental data at the current moment and the start time of this round of adjustment is within the preset range, it is determined that the current moment is not the end time of this round of adjustment; If the current moment is not the starting moment of the current round of adjustment, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are not within the preset range, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment.

7. The intelligent cockpit comfort adjustment method according to any one of claims 1 to 4, characterized in that The intelligent cockpit comfort adjustment method further includes: If the current moment is not the starting moment of the current round of adjustment, the time interval between the current moment and the starting moment of the current round of adjustment is less than the preset period, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are within the preset range, then it is determined that the current moment is not the end moment of the current round of adjustment; If the current moment is not the starting moment of the current round of adjustment, and the time interval between the current moment and the starting moment of the current round of adjustment is greater than or equal to the preset period, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment; If the current moment is not the starting moment of the current round of adjustment, and the differences in the passenger physiological data and environmental data between the current moment and the starting moment of the current round of adjustment are not within the preset range, then it is determined that the current moment is the end moment of the current round of adjustment, and the next moment is the starting moment of the next round of adjustment.

8. An intelligent cockpit comfort adjustment device, characterized in that, The intelligent cockpit comfort adjustment device includes: A data acquisition module for real-time acquisition of passenger physiological data and environmental data; A strategy generation module for, at the starting moment of each round of adjustment, taking the passenger and the environment as the two game players in a dynamic game, generating a strategy combination with the optimal utility according to the passenger physiological data and environmental data at the current moment, and using this strategy combination for intelligent cockpit comfort adjustment; A strategy fine-tuning module for, at each moment between the starting moments of two adjacent rounds of adjustment, fine-tuning the strategy combination adopted at the previous moment according to the passenger physiological data and environmental data at the current moment, and using the fine-tuned strategy combination for intelligent cockpit comfort adjustment.

9. An intelligent cockpit comfort adjustment device, characterized in that, The intelligent cockpit comfort adjustment device includes a processor, a memory, and an intelligent cockpit comfort adjustment program stored on the memory and executable by the processor. When the intelligent cockpit comfort adjustment program is executed by the processor, the steps of the intelligent cockpit comfort adjustment method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that, An intelligent cockpit comfort adjustment program is stored on the readable storage medium. When the intelligent cockpit comfort adjustment program is executed by the processor, the steps of the intelligent cockpit comfort adjustment method according to any one of claims 1 to 7 are implemented.

Images