Methods and devices for intelligent health management of vehicle cabins

Abstract

This invention relates to the field of in-vehicle environment monitoring and control. The invention provides a method for intelligent health management of a vehicle's interior, comprising the following steps: S1: acquiring health level information related to the user's health status within the vehicle interior; S2: acquiring user operation preference data for at least one in-vehicle infotainment function; and S3: analyzing the correlation between the user's operation preference data for at least one in-vehicle infotainment function and the health level information within a defined time period, and presenting the analysis results to the user. This invention also relates to a device and a computer program product for intelligent health management of a vehicle's interior. The invention aims to integrate fragmented user operations within the vehicle interior and establish a correlation with the health of the in-vehicle environment, thereby enabling users to not only comprehensively understand the health level of the in-vehicle environment but also to be aware of the impact of their own driving habits on this health level.

Description

Technical Field

[0001] This invention relates to a method for intelligent health management of a vehicle's passenger compartment, a device for intelligent health management of a vehicle's passenger compartment, and a computer program product. Background Technology

[0002] As vehicles become increasingly intelligent, various human-machine interaction functions contribute to improved driver safety and comfort. However, with increasing environmental pollution and longer periods of time spent inside vehicles, the health and safety of the in-vehicle environment also deserves attention.

[0003] To address this issue, existing technologies propose real-time monitoring of in-vehicle air quality and providing voice prompts to guide users in taking relevant actions to improve in-vehicle air quality. A method for controlling the in-vehicle air environment is also known, in which a corresponding odor control strategy is invoked based on the vehicle's environment, and the in-vehicle air conditioning equipment is controlled according to the odor control strategy, thereby intelligently processing the in-vehicle air based on the scenario.

[0004] However, the solutions currently offered still have many shortcomings. In particular, these known monitoring solutions can only simply collect and report indoor environmental parameters, but cannot let users know which of their operating habits in the vehicle have what impact on the health of the in-vehicle environment. In addition, given the highly individualized user groups, uniformly formulated adjustment measures cannot accurately meet the preferences of different users.

[0005] Against this backdrop, there is a need to provide an improved intelligent health management solution for train carriages, which can conduct a comprehensive and integrated intelligent analysis of the environmental health within the carriages by taking into account the different operating habits of each user. Summary of the Invention

[0006] The purpose of this invention is to provide a method for intelligent health management of vehicle cabins, a device for intelligent health management of vehicle cabins, and a computer program product, so as to at least solve some of the problems in the prior art.

[0007] According to a first aspect of the present invention, a method for intelligent health management of a vehicle cabin is provided, the method comprising the following steps:

[0008] S1: Obtain health level information related to the health status of users in the carriage;

[0009] S2: Obtain user operation preference data for at least one in-vehicle infotainment function; and

[0010] S3: Analyze the correlation between user's operational preference data for at least one in-vehicle system function and health level information within a defined time period, and present the analysis results to the user.

[0011] This invention specifically includes the following technical concept: by integrating fragmented user operations within the vehicle and establishing a connection with the health of the in-vehicle environment, vehicle users can not only understand the health level of the in-vehicle environment but also better understand the impact of their own driving habits on this health level. This imbues the monitored health indicators with contextual meaning, transforming the vehicle from a point-to-point carrier into one that facilitates communication and interaction with the user.

[0012] Optionally, health level information can be obtained in the form of raw sensor signals and / or grading results of the raw sensor signals.

[0013] In particular, the following technical advantages are achieved: by recording raw sensor signals, monitoring of the interior environment of the carriage can be carried out in a simple manner, thus enabling the possibility of lower energy consumption or allocating resources to other functions. Through hierarchical processing of the raw sensor signals, the health status of the carriage and its fluctuations can be more clearly conveyed, which is beneficial for subsequent correlation analysis and data presentation.

[0014] Optionally, the health level information includes environmental level information and biological level information. The environmental level information particularly includes the temperature inside the carriage, the air quality inside the carriage, the pollen concentration inside the carriage, the ultraviolet index inside the carriage, the oxygen concentration inside the carriage, and the humidity inside the carriage. The biological level information particularly includes the user's infrared vital signs, concentration level, and visual fatigue level.

[0015] In particular, the following technological advantages are achieved: the health level of the train carriage is reflected not only in environmental factors, but also in the physical and mental state of the users. Therefore, by understanding these two aspects, the health level within the train carriage can be analyzed more comprehensively and effectively.

[0016] Optionally, the operation preference data includes: the number of times a user activates at least one vehicle system function, the duration of use, the frequency of use, the time period of use, the operating mode, the operating temperature, the operating angle, and the operating intensity under the corresponding external environmental conditions.

[0017] In particular, the following technical advantages are achieved: by extracting existing functional data from the vehicle, the original hardware and software in the vehicle become an active source of data reception and analysis, enabling users to fully understand their own operating habits and patterns of the vehicle's functions.

[0018] Optionally, step S3 includes:

[0019] Pre-assign a score to the impact of different operating states of each vehicle infotainment function on the health level information;

[0020] The cumulative impact score of each in-vehicle infotainment function based on user operation preference data is calculated; and

[0021] The correlation is determined based on the cumulative influence score.

[0022] In particular, the following technical advantages are achieved: This allows for the quantification of the correlation between different operating states of each vehicle system function and the health level, enabling more effective analysis of the impact of different factors on the health level using statistical results, thereby allowing for more targeted adjustment strategies.

[0023] Optionally, step S3 includes:

[0024] For different in-vehicle infotainment functions, the positive and / or negative contributions of user operation preference data to health status information are presented.

[0025] In particular, this technology offers the following advantages: it allows users to understand which of their actions deteriorate the health of the vehicle compartment and which habits positively impact it and therefore should be retained. This guidance helps users adjust their behavior more effectively in future use of the vehicle.

[0026] Optionally, step S3 includes:

[0027] Present the correlation between user operation preference data for each vehicle system function and health level information separately; and / or

[0028] It collaboratively presents the correlation between user operation preference data for multiple vehicle system functions and health level information.

[0029] Here, the following technical advantages are particularly achieved: Individual presentation methods can more clearly reflect the impact of each operational behavior on specific health indicators, thus ensuring controllability of specific operational behaviors. Collaborative presentation methods also consider the logical and temporal relationships between different vehicle system functions or different operating states of vehicle system functions, thus reflecting the combined effect of multiple interactive functions in a fusion manner, facilitating more precise subsequent adjustments.

[0030] Optionally, step S3 includes: presenting the correlation in different time dimensions, particularly in the form of daily, weekly, monthly, quarterly, and / or yearly time dimensions.

[0031] In particular, this technology offers the following advantages: the recording and presentation methods across different time dimensions can reflect and visualize changes in user behavior and the overall health level within the carriage over time. This allows users to understand the short-term and long-term characteristics of their actions, enabling them to incorporate time factors into future behavioral planning.

[0032] Optionally, the method further includes the following steps:

[0033] Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and

[0034] Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

[0035] In particular, the following technological advantages are achieved: when formulating future adjustment strategies or generating rationalization suggestions, the aim is not only to stabilize the health level within the vehicle compartment within a reasonable range, but also to take into account users' usage habits and preferences for various in-vehicle infotainment functions. Therefore, a tailored health management solution is provided for users in the vehicle, improving user satisfaction.

[0036] Optionally, at least one vehicle infotainment function may be automatically adjusted according to the adjustment strategy only if the user confirms the adjustment strategy.

[0037] In particular, the following technical advantages are achieved: this leaves users with ample room for independent choice, thus improving the user experience.

[0038] Optionally, a user habit model for at least one vehicle infotainment function is trained using user operation preference data and health level information in the carriage. The trained user habit model is used to predict operation preference data that will enable the health level information in the carriage to meet preset conditions under corresponding external environmental conditions. An adjustment strategy for at least one vehicle infotainment function is generated based on the predicted operation preference data.

[0039] In particular, the following technical advantages are achieved: by establishing a self-learning model, the vehicle's infotainment system can simulate the perceptual mechanisms in the user's brain, thereby predicting the adjustment methods that meet health requirements and at the same time conform to the user's expectations as much as possible. This can reduce the manual operation of vehicle functions by vehicle users to a certain extent, allowing them to focus more on driving behavior.

[0040] Optionally, before training the usage habit model using user operation preference data and health level information in the carriage, the usage habit model has been pre-trained based on big data, especially crowdsourced operation preference data and corresponding crowdsourced health level information for user groups with defined geographical regions and / or seasons and / or genders and / or ages.

[0041] Here, the following technical advantages are particularly achieved: By pre-training the machine learning model with big data, an initial framework of the parametric model can be quickly established based on fully utilizing historically accumulated prior knowledge. This model can then be fine-tuned based on specific user habits and preferences, thereby accelerating the convergence process of the training algorithm. Since the overall framework of the parametric model has already been estimated, only fine-tuning is needed on the details, significantly reducing the time cost of the initial learning phase and improving user satisfaction. Furthermore, user groups from the same region, season, cultural background, gender, etc., may share common operating habits; clustering training methods can better match the output results to user habits.

[0042] Optionally, the adjustment strategy is generated in a first mode and / or a second mode. In the first mode, the user's usage habits are classified based on the user's operation preference data, and a predefined adjustment strategy is retrieved according to the classification result. In the second mode, it is checked whether there is a deviation between the predefined adjustment strategy and the user's usage habits, and the predefined adjustment strategy is modified in response to the deviation to reduce the deviation.

[0043] Here, the following technical advantages are particularly achieved: By pre-storing adjustment strategies and directly categorizing them according to user habits, suitable adjustment strategies can be quickly identified, saving time spent on repeated adjustments. This is especially beneficial for users with relatively stable operating habits. Through feedback-based learning, the adjustment process can be executed more specifically, allowing the adjustment strategy to continuously align with user expectations during the iteration process. This is particularly beneficial for users with more random operating habits.

[0044] Optionally, the existence of the deviation can be determined by recording user feedback events on the adjustment strategy, including: manual adjustments by the user to the operating status of at least one vehicle infotainment function.

[0045] In particular, the following technical advantages are achieved: the number and extent of user manual intervention can reflect their satisfaction with the currently applied automatic adjustment strategy, so such feedback events can be used as supplementary training data to update the internal parameters of the machine learning model, thereby continuously optimizing the final training results.

[0046] Optionally, the method further includes the following steps: storing the adjustment policy in the cloud and / or locally based on the user's identity, and retrieving the corresponding adjustment policy from the cloud and / or locally when the identity of the corresponding user is identified.

[0047] In particular, the following technical advantages are achieved: through this retrieval process, a matching automatic adjustment strategy can be applied directly to the user identity in the next usage cycle, or retraining can be performed directly based on the previous training results, without having to start the adaptive process from scratch, thus improving user satisfaction.

[0048] According to a second aspect of the present invention, an apparatus for intelligent health management of a vehicle cabin is provided, the apparatus being used to perform the method according to a first aspect of the present invention, the apparatus comprising:

[0049] The first acquisition module is configured to acquire health level information related to the user's health status within the carriage.

[0050] The second acquisition module is configured to acquire user operation preference data for at least one in-vehicle infotainment function; and

[0051] The analysis module is configured to analyze the correlation between user operational preference data for at least one in-vehicle system function and health level information within a defined time period, and present the analysis results to the user.

[0052] According to a third aspect of the present invention, a computer program product is provided, wherein the computer program product includes a computer program configured to implement the method according to the first aspect of the present invention when executed by a computer. Attached Figure Description

[0053] The invention will now be described in more detail with reference to the accompanying drawings, which will provide a better understanding of its principles, features, and advantages. The drawings include:

[0054] Figure 1 A block diagram of an apparatus for intelligent health management of a vehicle cabin according to an exemplary embodiment of the present invention is shown.

[0055] Figure 2 A schematic diagram of the electronic and electrical architecture of a vehicle according to an exemplary embodiment of the present invention is shown;

[0056] Figure 3 A flowchart illustrating a method for intelligent health management of a vehicle cabin according to an exemplary embodiment of the present invention is shown.

[0057] Figure 4 It shows Figure 3 A flowchart illustrating an exemplary embodiment of a method step in the method described above;

[0058] Figure 5 It shows Figure 3 A flowchart illustrating an exemplary embodiment of a method step in the method described above;

[0059] Figure 6 It shows Figure 3 A flowchart illustrating an exemplary embodiment of a method step in the method described above;

[0060] Figure 7 An illustrative user interface for displaying the results of a carriage health analysis to a user, according to an exemplary embodiment, is shown; and

[0061] Figure 8 An illustrative user interface for presenting adjustment strategies to different users, according to an exemplary embodiment, is shown. Detailed Implementation

[0062] To make the technical problems to be solved, the technical solutions, and the beneficial technical effects of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and several exemplary embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of protection of this invention.

[0063] Figure 1 A block diagram of an apparatus for intelligent health management of a vehicle compartment according to an exemplary embodiment of the present invention is shown. The apparatus 1 includes a first acquisition module 10, a second acquisition module 20, and an analysis module 30.

[0064] The first acquisition module 10 is used to acquire health level information related to the user's health status within the vehicle compartment. Here, the first acquisition module 10 can be configured as a communication interface, and thus be able to receive raw sensor signals measured in real time from various sensors deployed on the vehicle. Furthermore, the first acquisition module 10 can also receive the grading results of the raw sensor signals and treat them as health level information. It is also conceivable that the first acquisition module 10 can be directly configured as a sensor and include related processing units, thus directly using it to detect various signals within the vehicle compartment and provide health level information. In the context of this invention, the raw sensor signal represents, for example, absolute sensor parameters that can be directly measured by the sensor, such as temperature, air quality index, humidity, and the content of certain gases in the air. The grading evaluation result represents, for example, the result after preprocessing the raw sensor signal using a threshold or other evaluation index. For example, after collecting the in-vehicle air quality index over a period of time, it can be classified using an air quality threshold to obtain the air quality status during that period.

[0065] The second acquisition module 20 is used to acquire user operation preference data for at least one vehicle infotainment function. Here, the second acquisition module 20 can also be configured as a communication interface, and thus be able to receive data from various software and hardware on the vehicle for use in analyzing user operation behavior.

[0066] The analysis module 30 is connected to the first acquisition module 10 and the second acquisition module 20 to receive user operation preference data and health level information within the vehicle compartment, respectively. For ease of functional division, the analysis module 30 further includes a report generation unit 31 and a strategy generation unit 32. The report generation unit 31, for example, can extract operation preference data and health level information within a defined time period and analyze the correlation between the two. The strategy generation unit 32, for example, can generate adjustment strategies or rationalization suggestions for at least one vehicle system function based on historical operation preference data and health level information. In this exemplary embodiment, the analysis module 30 is also connected to an external environment sensor 41 and a user identity input device 42, thereby enabling it to output appropriate adjustment strategies based on real-time changes in the external environment of the vehicle and allowing the corresponding adjustment strategies to be retrieved based on the user's identity. Furthermore, the analysis module 30 is also communicatively connected to the user's mobile terminal 260, thereby presenting the analysis results to the user in the form of a vehicle compartment intelligent analysis report. Additionally, the analysis module 30 is also communicatively connected to at least one actuator 50 of the vehicle, thereby controlling the operation of at least one actuator according to the generated adjustment strategy.

[0067] Figure 2 A schematic diagram of the electronic and electrical architecture of a vehicle according to an exemplary embodiment of the present invention is shown.

[0068] The electronic and electrical architecture 200 includes a vehicle bus 201 and multiple domain controllers 210, 220, and 230, which are communicatively coupled to the vehicle bus 201. The vehicle bus 201 may include, for example, a LIN bus, a CAN bus, an Ethernet bus, or a FlexRay bus.

[0069] The domain controller 210 for the vehicle body domain is connected to multiple interior and exterior vehicle body modules, such as window module 211, ambient lighting module 212, seat adjustment module 213, and air conditioning module 214. This domain controller 210 can collect operating parameters of various vehicle functions from sensors / actuators distributed throughout the vehicle body, thereby understanding the user's operational preferences during the use of these functions.

[0070] Domain controller 220 for the chassis domain is connected, for example, to the vehicle chassis and suspension module to collect operational preference data related to the vehicle's driving behavior and charging status.

[0071] In addition, multiple indoor sensors 202, 203, and 204 are connected to the vehicle bus 201. These indoor sensors 202, 203, and 204 are used to collect health level information inside the vehicle and feed it back to the vehicle bus. For example, the PM2.5 concentration inside the vehicle can be detected by the PM2.5 sensor 202, the air humidity inside the vehicle can be detected by the air humidity sensor 203, and the user's vital signs can be detected by the infrared sensor 204.

[0072] The integrated domain controller 230 is used, for example, to centrally process and integrate data from other domain controllers 210, 220 and indoor sensors. According to one embodiment, the device 1 for intelligent health management of a vehicle compartment according to the invention can be arranged inside the vehicle and thus within the integrated domain controller 230, thereby enabling the analysis and determination of the correlation between operational preference data and health level information over a period of time, and also enabling the generation of adjustment strategies for at least one vehicle infotainment function.

[0073] A smart antenna module 240 is also connected to the vehicle bus 201, allowing sensor data integrated by the integrated domain controller 230 to be sent to the cloud 250 for analysis and processing. According to one embodiment, the device 1' for intelligent health management of the passenger compartment according to the invention can also be located outside the vehicle and therefore in the cloud 250, thus eliminating the need to perform health intelligence analysis locally in the vehicle and saving on software / hardware overhead. After such analysis is completed in the cloud 250, the results can be output from the cloud to the user's mobile terminal 260, thereby presenting them to the user, for example, through a human-machine interface.

[0074] However, if device 1 is directly installed in the vehicle, the analyzed cabin smart health report can be output to the user's mobile terminal 260 with the help of the smart antenna module 240. This makes it easier for the user to understand the relationship between their usage habits and the cabin health, and also makes it easier for the user to remotely turn on or off the corresponding vehicle functions.

[0075] Figure 3 A flowchart illustrating a method for intelligent health management of a vehicle cabin according to an exemplary embodiment of the present invention is shown.

[0076] In step S1, health level information related to the user's health status within the vehicle compartment is acquired. Here, health level information includes, for example, environmental level information and biological level information. Environmental level information is understood as at least one indoor environmental parameter that potentially affects the health status of the user within the vehicle compartment, which in particular includes the temperature, air quality, pollen concentration, UV index, oxygen concentration, UV intensity, and humidity within the vehicle compartment. Biological level information is understood as biological parameters reflecting the user's health status during their stay within the vehicle compartment, which in particular includes the user's infrared vital signs, attention span, and visual fatigue. As an example, health level information can be acquired in the form of raw sensor signals and / or grading results of the raw sensor signals.

[0077] In step S2, user operation preference data for at least one vehicle infotainment function is acquired. In the context of this invention, operation preference data can be understood, for example, as the different operating states generated by various hardware and software components already installed in the vehicle under different user operating behaviors. This operation preference data includes, for example, the number of times a user activates at least one vehicle infotainment function (e.g., pre-ventilation, pre-air conditioning, internal / external air circulation, A / C, windows, doors, sunroof, seats, ambient lighting, etc.), usage duration, usage frequency, usage time period, operating mode, operating temperature, operating angle, and operating intensity under defined external environmental conditions.

[0078] In step S3, the correlation between user's operational preference data for at least one vehicle system function and health level information within a defined time period is analyzed, and the analysis results are presented to the user.

[0079] As an example, correlations can be analyzed individually for different areas within the carriage (e.g., the driver's cab, the passenger compartment, and the rear passenger compartment). Alternatively, correlations can be analyzed holistically for the entire carriage area.

[0080] As an example, the system can present the positive and / or negative contributions of user operation preference data to health level information for different in-vehicle infotainment functions. This data can be sorted according to the magnitude of positive or negative contribution, allowing users to clearly see which of their operating habits have the most significant impact on the health level within the vehicle. A positive contribution, for example, indicates that the operating state or pattern of a specific in-vehicle infotainment function under the operation preference data can cause health level information to change in a direction that meets preset conditions or reaches acceptable standards. For instance, closing the windows and turning on the vehicle's internal air circulation in inclement weather makes a positive contribution to improving the air quality inside the vehicle. A negative contribution indicates that the operating state or pattern of a specific in-vehicle infotainment function under the operation preference data can cause health level information to change in a direction that deviates from preset conditions or violates acceptable standards. For instance, opening the windows and frequently turning on the vehicle's external air circulation in inclement weather makes a negative contribution to improving the air quality inside the vehicle.

[0081] As an example, the correlation between user's operational preferences for each vehicle infotainment function and health status information can be presented separately. This means, for example, that when using the oxygen concentration inside the vehicle as a health indicator, the impact of the user's "number of times and duration of opening the car windows" and "number of times and duration of opening the external air circulation" on the oxygen concentration inside the vehicle can be presented to the user.

[0082] As another example, the correlation between user operational preferences for multiple in-vehicle infotainment functions and health status information can also be presented synergistically. This means, for example, that when using oxygen concentration in the vehicle compartment as a health indicator, the combined effect of the user's "number of times and duration of opening the windows" and "number of times and duration of opening the external air circulation" on oxygen concentration can be presented to the user. When performing this fusion analysis, it is also advantageous to consider the mutual cancellation or mutual promotion effects between the operating states of different in-vehicle infotainment functions.

[0083] As another example, the correlation between each vehicle infotainment function and a health level information can be presented individually, or the correlation between each vehicle infotainment function and multiple health level information can be presented simultaneously.

[0084] As another example, the correlation can be presented in different time dimensions. For example, the correlation can be presented in the form of hours, days, weeks, months, quarters, and / or years.

[0085] In step S4, an adjustment strategy for at least one vehicle system function can be generated based on operation preference data and health level information within a defined time period, and the user is requested to confirm the adjustment strategy.

[0086] As an example, reasonable suggestions for user behavior can be given directly based on the correlation derived from historical data. For instance, if a user previously had a habit of rarely turning on the air conditioning or the internal / external air circulation function during long drives, resulting in a persistently low oxygen concentration in the cabin, this habit could negatively impact driving attention. Therefore, based on this analysis, it could be suggested that the user appropriately roll down the windows or turn on the internal / external air circulation during future long drives.

[0087] As another example, an automatic adjustment strategy for at least one vehicle infotainment function can be generated by combining current or future information about the vehicle's external environment (such as weather, temperature, UV intensity, pollen dispersal, and air quality).

[0088] In the next step S5, it can be determined whether the user has confirmed the adjustment strategy.

[0089] If user confirmation is received, the adjustment strategy can be applied in step S6 to achieve automatic adjustment of at least one vehicle infotainment function.

[0090] If no user confirmation is received within a defined time period or if a message indicating user rejection is received, the recommended adjustment strategy can be disregarded in step S7, and manual adjustment mode can continue.

[0091] Figure 4 It shows Figure 3 A flowchart illustrating an exemplary embodiment of method step S3 of the method. Method step S3 exemplaryly includes steps S30-S32.

[0092] In step S30, a score is pre-assigned to each vehicle infotainment system function based on its different operating states, impacting the health level information. This can be accomplished, for example, through a manual annotation process, or it can be based on a specific mathematical model. For example, in winter, for the health level information "suitable indoor temperature," a score of "-1" can be assigned to the sunroof function's state "single sunroof opening," and a score of "-1" can be assigned to the state "sunroof open for 1 minute." Similarly, a score of "+1" can be assigned to the air conditioning function's state "single air conditioning heating on," and a score of "+1" can be assigned to the state "air conditioning heating on for 1 minute." The score of "+1" can also be assigned to the seat heating function's state "single seat heating on," and so on.

[0093] In step S31, the cumulative impact score of each vehicle system function is calculated based on the user's operation preference data. For example, over a month, if the user turns on the air conditioning for heating ten times with an average duration of 30 minutes, the cumulative score for the "air conditioning function" would be "40".

[0094] In step S32, the correlation between operational preference data and health level information is determined based on the cumulative impact score. As an example, the correlation can be directly displayed as a cumulative score; the higher the score, the stronger the correlation. Alternatively, different grading thresholds can be set, and the obtained cumulative impact score can be compared with each threshold to qualitatively determine the correlation between operational preference data and health level information. It is worth noting that the above embodiment only describes the correlation between operational preference data and one type of health level information (or one health indicator). However, it is also possible to comprehensively analyze the correlation between operational preference data and multiple types of health level information. For example, for the first health level information "suitable indoor temperature," the user's cumulative score for operational preference data regarding the air conditioning function is "40," while for the second health indicator "excellent indoor air quality," the user's cumulative score for operational preference data regarding the air conditioning function is only "5." Therefore, it is meaningful to average or weight the cumulative scores corresponding to the vehicle's functions for all types of health level information, thereby obtaining the correlation between the user's operational preference data and the overall health level within the vehicle.

[0095] Figure 5 It shows Figure 3 A flowchart illustrating an exemplary embodiment of method step S4 of the method. Method step S4 exemplaryly includes steps S40-S43.

[0096] In step S40, for example, crowdsourcing can be used to collect data on crowdsourcing operation preferences and corresponding crowdsourcing health status information for vehicle user groups defined by geographical region and / or season and / or gender and / or age. This can be achieved, in particular, by leveraging a shared cloud platform based on big data. For instance, Beijing and Shanghai have significant climate differences due to their geographical locations, so users in these two regions will also have different habits regarding the use of in-vehicle functions such as air conditioning, ventilation, and seat heating. In this case, it is meaningful to collect relevant data separately for users in Beijing and Shanghai for subsequent analysis.

[0097] In step S41, a usage habit model for at least one in-vehicle infotainment function can be established and pre-trained using the collected data. For example, operational preference data and health level information based on big data can be used as training data to establish an input-output mapping for the machine learning model. The purpose of this is to enable the machine learning model to simulate the human brain's perception of various environmental factors and to form logical connections between these perceptions and health levels. Thus, for example, when given external environmental information (such as vehicle exterior temperature, humidity, air quality, etc.) is input into the model, it can automatically output an adjustment strategy for at least one in-vehicle infotainment function. This output considers both the expected operational behavior of the user group in response to these environmental factors or physical conditions (such as adjusting the air conditioning to a preset temperature or opening the windows) and the impact of the user's operational behavior on the health level inside the vehicle. Therefore, through continuous iterative training, the model can seek a balance between user comfort and the health level inside the vehicle, obtaining the final adjustment strategy while taking both into account as much as possible. As an example, different usage habit models can be built and pre-trained for user groups of different geographical regions, seasons, genders and / or ages, and these usage habit models can be pre-stored on the cloud platform so that they can be invoked in different scenarios.

[0098] In step S42, the preliminary usage habit model established in step S41 is retrained using specific user operation preference data and health level information. To make the pre-trained model more accurately match individual user habits, the kernel function or internal parameters of the model can be fine-tuned using data from a single user. As an example, a usage habit model is pre-trained based on big data analysis of specific regions and seasons to adapt to the "common behaviors" of users from the same region and season. For example, air conditioners are pre-programmed to automatically adjust to 24 degrees Celsius in spring and when the outdoor temperature reaches above 30 degrees Celsius, and this 24 degrees Celsius is generated based on the air conditioner adjustment operations of 100,000 users during this period. Then, the behavioral differences of individual users are used to specifically adjust this "common behavior." For example, if a specific user feels that 24 degrees Celsius is too hot and manually adjusts it to 22 degrees Celsius, then after 2-3 manual adjustments, the "artificial brain" will relearn and remember 22 degrees Celsius instead of 24 degrees Celsius.

[0099] In S43, a trained usage habit model is used to predict operational preference data and thereby generate adjustment strategies. For example, determined external environmental information and / or current cabin health level information are input into the usage habit model. The model can then output predicted operational preference data, taking into account the logical relationships between various constraints, specifically ensuring that the cabin health level meets preset conditions.

[0100] Figure 6 It shows Figure 3 A flowchart illustrating an exemplary embodiment of method step S4 of the method. Method step S4 exemplaryly includes steps S401-S409.

[0101] In step S401, user identity information is entered. This can be achieved, for example, by using a specific user information collection module (e.g., a face recognition module, a voice recognition module, an identity information input module, an identity identification module, and / or an iris recognition module).

[0102] In step S402, users are initially categorized according to their identity. For example, the user's purchased vehicle model or historical maintenance records can be retrieved based on their identity to estimate their purchasing power. As another example, the user's age and gender can be identified to estimate their approximate physical condition. As yet another example, the user's payment history or purchased versions for specific vehicle functions can be retrieved based on their identity to understand their usage rights to additional vehicle features.

[0103] In step S403, the user is determined to belong to group A or group B based on the preliminary classification results. Here, group A, for example, represents users who purchased the "basic" version of the carriage health management function, while group B, for example, represents users who purchased the "advanced" version. Compared to the "basic" version, the "advanced" version offers features such as better adaptation of automatic adjustment strategies to user operating habits, providing automated solutions that better suit individual operating styles or preferences, and including more types of health parameter records.

[0104] If the user is determined to belong to group A, then an adjustment strategy can be generated, for example, using the first mode. Therefore, in step S404, operation preference data over a period of time can be recorded, and the user's usage habits can be categorized based on this data.

[0105] Next, in step S405, adjustment strategies pre-stored for the determined usage habit category can be retrieved from the cloud platform or locally based on the classification results. For example, if it is determined that the user's air conditioning usage habit is "prefers warmth", an adjustment strategy for the air conditioning function can be retrieved from that group; conversely, another adjustment strategy for the air conditioning function can be retrieved from the "prefers cold" database.

[0106] If the vehicle is determined to belong to Group B, an adjustment strategy can be generated, for example, in the second mode. Therefore, in step S406, a preset adjustment strategy can be retrieved from a cloud database or the system backend. This adjustment strategy can, for example, be established and stored by default for this vehicle model during the R&D phase.

[0107] Then, in step S407, it is possible to check in real time whether there is a deviation between the preset adjustment strategy and the user's usage habits. To identify such deviations, user feedback events on the adjustment strategy can be recorded. These feedback events include manual adjustments made by the user to the operating status of at least one vehicle infotainment function. It is understood that if the user is satisfied with the current adjustment strategy, or believes that the current adjustment strategy conforms to their personal operating habits, the user generally will not manually intervene in the automatic adjustment process. Conversely, if the user is dissatisfied with the current automatic adjustment strategy, they will intervene in the automatic adjustment process through manual adjustment (e.g., over-the-horizon control). By recording the number and frequency of such feedback events, the deviation between the adjustment strategy and the user's usage habits can be determined. It is also possible to determine the correction trend direction of the adjustment strategy for at least one vehicle infotainment function based on the feedback events.

[0108] If a deviation is detected, the current preset adjustment strategy can be corrected in step S408 to reduce the deviation. For example, if the user manually changes the current air outlet direction, this air outlet direction can be stored as new operation preference data, and a new adjustment strategy can be generated based on this.

[0109] If it is determined that there is no deviation, the preset adjustment strategy can be determined and stored as the final adjustment strategy in step S409 so that the adjustment strategy can be directly invoked when the user uses the vehicle next time.

[0110] It should be noted that although the generation processes of the first and second regulation are carried out independently in this example, it is conceivable that the first mode, as the basic regulation mode, precedes the second mode. Furthermore, other combinations of the two modes are also possible.

[0111] Figure 7 An illustrative user interface for displaying the results of a vehicle compartment health analysis to a user, according to an exemplary embodiment, is shown. The user interface shown herein may, for example, be part of a user's mobile terminal, which can receive data and analysis reports from the vehicle compartment's intelligent health management device, and can also transmit user input commands to the device or to various software / hardware actuators on the vehicle.

[0112] like Figure 7 As shown on the left, this user interface illustrates the correlation between exemplary health level information and various operational preference data. In the example, the user is presented with the in-vehicle air quality over the past month (e.g., February), and this health level information is displayed, for example, as a graph. Below this graph, the user's operational preference data for different in-vehicle functions and the correlation between this operational preference data and the health level information are shown.

[0113] For example, regarding the vehicle's pre-ventilation function, it was shown that the driver drove 20 times in the past month and used the pre-ventilation function 5 times during that period. The contribution of this operational preference data to the aforementioned health level information was calculated to be +10.

[0114] For the car window function, operation preference data is presented across different analytical dimensions. For example, this shows the number of times the car windows were opened and the total duration (or average duration per opening) over the past month, as well as the overall contribution of this in-vehicle infotainment function to health status information.

[0115] In addition, the system also displays user preference data and corresponding contribution rates for the past month for both the recirculation and A / C air conditioning functions.

[0116] exist Figure 7 The right side shows reasonable suggestions generated based on the analysis results. For example, based on the analysis of historical data, it was found that the user frequently opened the windows and sunroof on several days, resulting in poor overall air quality inside the car. Therefore, it could be suggested to the user: The air quality was poor last month, and it was found that your frequent use of the windows and sunroof caused poor indoor air quality, which has an adverse effect on health.

[0117] As an alternative to opening windows and sunroofs, it is also advisable to reduce the frequency of opening windows and sunroofs, and to use the pre-ventilation and recirculation functions more often. This can also block polluted air and ensure clean indoor air during long drives.

[0118] Figure 8 An illustrative user interface for presenting adjustment strategies to different users, according to an exemplary embodiment, is shown.

[0119] Here, for example, adjustment strategies generated according to the method of the present invention are shown for two users, A and B. Health analysis results indicate that these two users have different perceptions of the environment, leading to differences in their usage habits and operational preferences for the vehicle's infotainment system. For example, regarding the same external environmental factors—"outdoor air temperature 34 degrees Celsius, summer, midday air pollution, low pollen concentration, and strong ultraviolet radiation"—user A prefers an indoor temperature of "22 degrees Celsius" and likes to open the sunroof and windows, while user B prefers an indoor temperature of "25 degrees Celsius," internal air circulation, and requires sun protection.

[0120] exist Figure 8The left side shows the adjustment strategy for User A: Today's air quality is poor and UV intensity is high. The target temperature inside the car is set at your preferred 22 degrees Celsius. The sunroof shade is retracted, and the windows and sunroof are closed. It can be seen that although historical user preference data indicates that User A frequently prefers to open the windows and sunroof, the resulting adjustment strategy, while taking into account user preferences, still partially contradicts the user's original habits to ensure an overall good level of cabin health, because the trained usage model also considers the overall health of the cabin.

[0121] exist Figure 8 The right side shows the adjustment strategy for User B: Today the air quality is poor and the UV intensity is high. The target temperature inside the car is set at your preferred 25 degrees Celsius. The windows and sunroof are closed, and the sunshade is opened. It can be seen that, facing the same external environmental conditions, the adjustment strategies developed for User A and User B differ due to their different individual operating habits.

[0122] At the same time, Figure 8 The user interface also displays a confirmation request to the user, thus ensuring that the auto-adjustment mode is activated only when user confirmation is received.

[0123] Although specific embodiments of the invention have been described in detail herein, they are given for illustrative purposes only and should not be construed as limiting the scope of the invention. Various substitutions, alterations, and modifications can be conceived without departing from the spirit and scope of the invention.

Claims

1. A method for intelligent health management of a vehicle's passenger compartment, the method comprising the following steps: S1: Obtain health level information inside the carriage, the health level information including environmental level information related to the environmental health inside the carriage, the environmental level information including at least one of the following indoor environmental parameters: temperature inside the carriage, air quality inside the carriage, pollen concentration inside the carriage, ultraviolet index inside the carriage, oxygen concentration inside the carriage, and humidity inside the carriage. S2: Obtain user operation preference data for at least one vehicle infotainment function, the operation preference data including user operation habits for at least one vehicle infotainment function within a certain time period; as well as S3: In the carriage health analysis, analyze the correlation between the user's operational preference data for at least one vehicle system function within a defined time period and the health level information, and present the results of the carriage health analysis to the user in the form of a carriage intelligent analysis report. The carriage intelligent analysis report includes which user operating habits have what impact on the environmental health level in the carriage.

2. The method according to claim 1, wherein, Health level information is obtained in the form of raw sensor signals and / or grading results of raw sensor signals.

3. The method according to claim 1 or 2, wherein, The health level information also includes biological level information.

4. The method according to claim 1 or 2, wherein, The operation preference data includes: the number of times a user activates at least one vehicle system function, the duration of use, the frequency of use, the time period of use, the operating mode, the operating temperature, the operating angle, and the operating intensity under the corresponding external environmental conditions.

5. The method according to claim 3, wherein, The operation preference data includes: the number of times a user activates at least one vehicle system function, the duration of use, the frequency of use, the time period of use, the operating mode, the operating temperature, the operating angle, and the operating intensity under the corresponding external environmental conditions.

6. The method according to claim 1, 2, or 5, wherein, Step S3 includes: Pre-assign a score to the impact of different operating states of each vehicle infotainment function on the health level information; The cumulative impact score of each in-vehicle infotainment function based on user operation preference data is calculated; and The correlation is determined based on the cumulative influence score.

7. The method according to claim 3, wherein, Step S3 includes: Pre-assign a score to the impact of different operating states of each vehicle infotainment function on the health level information; The cumulative impact score of each in-vehicle infotainment function based on user operation preference data is calculated; and The correlation is determined based on the cumulative influence score.

8. The method according to claim 4, wherein, Step S3 includes: Pre-assign a score to the impact of different operating states of each vehicle infotainment function on the health level information; The cumulative impact score of each in-vehicle infotainment function based on user operation preference data is calculated; and The correlation is determined based on the cumulative influence score.

9. The method according to any one of claims 1, 2, 5, 7, and 8, wherein, Step S3 includes: For different in-vehicle infotainment functions, the positive and / or negative contributions of user operation preference data to health status information are presented.

10. The method according to claim 3, wherein, Step S3 includes: For different in-vehicle infotainment functions, the positive and / or negative contributions of user operation preference data to health status information are presented.

11. The method according to claim 4, wherein, Step S3 includes: For different in-vehicle infotainment functions, the positive and / or negative contributions of user operation preference data to health status information are presented.

12. The method according to claim 6, wherein, Step S3 includes: For different in-vehicle infotainment functions, the positive and / or negative contributions of user operation preference data to health status information are presented.

13. The method according to any one of claims 1, 2, 5, 7, 8, 10, 11, and 12, wherein, Step S3 includes: Present the correlation between user operation preference data for each vehicle system function and health level information separately; and / or It collaboratively presents the correlation between user operation preference data for multiple vehicle system functions and health level information.

14. The method according to claim 3, wherein, Step S3 includes: Present the correlation between user operation preference data for each vehicle system function and health level information separately; and / or It collaboratively presents the correlation between user operation preference data for multiple vehicle system functions and health level information.

15. The method according to claim 4, wherein, Step S3 includes: Present the correlation between user operation preference data for each vehicle system function and health level information separately; and / or It collaboratively presents the correlation between user operation preference data for multiple vehicle system functions and health level information.

16. The method according to claim 6, wherein, Step S3 includes: Present the correlation between user operation preference data for each vehicle system function and health level information separately; and / or It collaboratively presents the correlation between user operation preference data for multiple vehicle system functions and health level information.

17. The method according to claim 9, wherein, Step S3 includes: Present the correlation between user operation preference data for each vehicle system function and health level information separately; and / or It collaboratively presents the correlation between user operation preference data for multiple vehicle system functions and health level information.

18. The method according to any one of claims 1, 2, 5, 7, 8, 10, 11, 12, 14-17, wherein, Step S3 includes: The correlation is presented in different time dimensions.

19. The method according to any one of claims 1, 2, 5, 7, 8, 10, 11, 12, 14-17, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

20. The method according to claim 3, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

21. The method according to claim 4, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

22. The method according to claim 6, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

23. The method according to claim 9, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

24. The method according to claim 13, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

25. The method according to claim 18, wherein, The method further includes the following steps: Generate an adjustment strategy for at least one in-vehicle infotainment function based on user preference data and health status information within a defined time period; and Present the adjustment strategy to the user and / or automatically adjust at least one vehicle infotainment function using the adjustment strategy.

26. The method according to claim 19, wherein, At least one vehicle infotainment function will be automatically adjusted according to the adjustment strategy only upon receiving confirmation from the user.

27. The method according to claim 19, wherein, By using user operation preference data and health level information in the carriage, a user habit model for at least one vehicle infotainment function is trained. The trained habit model is then used to predict operation preference data that will enable the health level information in the carriage to meet preset conditions under corresponding external environmental conditions. Based on the predicted operation preference data, an adjustment strategy for at least one vehicle infotainment function is generated.

28. The method according to claim 27, wherein, Before training the usage habit model using user operation preference data and health information in the carriage, the usage habit model had already been pre-trained based on big data.

29. The method according to claim 19, wherein, The adjustment strategy is generated in a first mode and / or a second mode. In the first mode, the user's usage habits are classified based on the user's operation preference data, and a predefined adjustment strategy is retrieved according to the classification result. In the second mode, it is checked whether there is a deviation between the predefined adjustment strategy and the user's usage habits, and the predefined adjustment strategy is modified in response to the deviation to reduce the deviation.

30. The method according to claim 29, wherein, The existence of the deviation is determined by recording user feedback events on the adjustment strategy, including: manual adjustments by the user to the operating status of at least one vehicle infotainment function.

31. The method according to claim 19, wherein, The method further includes the following steps: The adjustment strategy is stored in the cloud and / or locally based on the user's identity. When the identity of the corresponding user is identified, the corresponding adjustment strategy is retrieved from the cloud and / or locally.

32. The method according to claim 3, wherein, The biometric information includes the user's infrared vital signs, concentration level, and visual fatigue level.

33. The method according to claim 18, wherein, Step S3 includes presenting the correlation in the form of a time dimension in the form of days, weeks, months, quarters, and / or years.

34. The method according to claim 28, wherein, Before training the usage habit model using user operation preference data and health level information in the carriage, the usage habit model has been pre-trained using crowdsourced operation preference data and corresponding crowdsourced health level information of user groups that have determined geographical area and / or season and / or gender and / or age.

35. A device (1) for intelligent health management of a vehicle compartment, the device (1) being used to perform the method according to any one of claims 1 to 34, the device (1) comprising: The first acquisition module (10) is configured to acquire health level information related to the user's health status in the carriage. The second acquisition module (20) is configured to acquire user operation preference data for at least one vehicle system function; as well as The analysis module (30) is configured to analyze the correlation between user operation preference data for at least one vehicle system function and health level information within a certain time period, and present the analysis results to the user in the form of a smart analysis report for the vehicle compartment.

36. A computer program product, wherein, The computer program product includes a computer program that, when executed by a computer, performs the method according to any one of claims 1 to 34.

Images