Method for setting up air conditioning system
By creating a comfort model based on overlay, using AI units to train basic models and sub-models from data of all users and vehicles, the problem of inability to automatically adapt to user preferences in the prior art is solved, and the personalized setting and model of air conditioning facilities are realized. Transferability improves user experience and development efficiency.
Patent Information
- Application Number
- CN202410835725.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-06-27
- Filing Date
- 2024-06-26
- Publication Date
- 2024-12-27
AI Technical Summary
The characteristic curve-based climate regulation of existing air conditioning facilities cannot automatically adapt to personalized user preferences, resulting in the need of manually resetting to the comfort temperature and the inability to transfer the comfort model to other users or vehicles.
By creating a comfort model based on overlay, using AI units to train an averaged basic model from the data of all users and vehicles, and through the overlay of the basic model and sub-model, predict and set the air conditioning facility parameters that adapt to specific users and vehicles, the model is realized. transfer and personalized adjustments.
Reduces the number of manual settings for users, reduces the cost of model transfer, and significantly reduces the development workload, and improves the personalized adaptability of air-conditioning facilities.
Smart Images
Figure CN119189597A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a method for adjusting the air conditioning system of a vehicle in a user-adapted manner by means of a control architecture according to the preamble of claim 1. The invention also relates to a control architecture for carrying out the method. Background Art
[0002] The user of the air conditioning system can set the air conditioning system according to his thermal sensation by changing a number of parameters. The climate control based on the characteristic curve can be set by the user and the operation of the air conditioning system is thus simplified. However, the thermal comfort of each user is very individual. Conventional climate control based on the characteristic curve is disadvantageously designed for "ordinary" people and cannot be automatically adapted to each user. If the user feels uncomfortable in the climate control based on the characteristic curve, he must laboriously reset the air conditioning system manually.
[0003] Another solution is provided by AI-supported comfort models (AI: Artificial Intelligence), which can be adapted to the individual preferences of the individual user. In this case, the settings of the air conditioning system carried out by the user are correlated with situational data, such as the outdoor temperature or the indoor temperature, and used to train the comfort model. The trained comfort model can predict the optimal settings of the air conditioning system for the individual user at a predetermined point in time based on the situational data. Disadvantageously, this solution does not allow the comfort model to be transferred to other users and other vehicles. Summary of the invention
[0004] It is therefore an object of the present invention to provide an improved or at least alternative embodiment of a method of the generic type, in which the described disadvantages are overcome. It is also an object of the present invention to provide a corresponding control architecture for carrying out the method.
[0005] This object is achieved according to the invention by the subject matter of the independent claim. Advantageous embodiments are the subject matter of the dependent claims.
[0006] The invention is based on the general idea of creating a comfort model by superposition, in order thereby to be able to transfer the comfort model to different vehicles and different users.
[0007] The method is used to set the air conditioning of a vehicle in a user-adapted manner for a user by means of a control architecture. In this case, data related to the setting of the air conditioning is collected for all users and / or all vehicles by means of the control architecture, and an averaged basic model is trained in an AI unit based on the collected data for all users and all vehicles. Subsequently, a comfort model is created from the basic model at least in the AI unit, and user-adapted settings for setting the air conditioning are predicted for a specific user based on the comfort model.
[0008] The comfort model therefore contains at least an averaged base model, which takes into account the collected data for all users and all vehicles. Thus, a trained base model can be used to predict user-adapted settings for all users in all vehicles or for any user in any vehicle. Thus, a comfort model based on the base model can be transferred to any vehicle and / or any user. As a result, on the one hand, the comfort model can reduce the number of entries to be manually performed by the user, and on the other hand, the comfort model can be transferred to any vehicle and / or any user with little effort. The base model and the comfort model can be data-based models, whereby the development effort is significantly reduced compared to conventional characteristic curve-based models. Alternatively, the base model can also be depicted by a characteristic curve model.
[0009] Advantageously, the collected data of all users and all vehicles can be transmitted to the cloud, and the average base model can be trained in the AI unit of the cloud using the collected data. Therefore, a comfort model can also be created in the cloud at least from the average base model. Therefore, the average base model and / or the submodels described in detail below can be trained centrally using the collected data of all users and all vehicles. Subsequently, the trained comfort model can be transmitted from the cloud to a specific vehicle with the air conditioning facility to be set, and the user-adapted settings of the air conditioning facility to be set for a specific user can be obtained directly in the vehicle. Alternatively, the user-adapted settings of the air conditioning facility to be set for a specific user for a specific vehicle can be obtained in the cloud and transmitted to the vehicle. Here, the cloud is a network that provides computer resources such as servers and / or data storage devices and / or applications.
[0010] In the context of the present invention, vehicles are all vehicles with air conditioning, regardless of their characteristics. Vehicles can be divided into a plurality of mutually different vehicle types, wherein a vehicle type includes a plurality of vehicles with the same characteristics. In this case, a specific vehicle can only be assigned to a vehicle type. Vehicles of a vehicle type are, for example, vehicles of a specific manufacturer or vehicles of a specific model of a specific manufacturer.
[0011] The data related to the setting of the air conditioning facility may include the scenario data of the vehicle, such as the indoor temperature and / or the outdoor temperature and / or the air humidity and / or the sun position and / or the light intensity and / or the air pressure and / or the vehicle type. The data related to the setting of the air conditioning facility may include the setting data input by the user, such as the desired temperature and / or the fan gear level to be set and / or the seat heating to be set and / or the heating surface to be set and / or the heating intensity to be set. The data related to the setting of the air conditioning facility may include the user data with the physiological user information of the user, such as the user identity and / or the seat position and / or the skin temperature and / or the pulse and / or the breathing rate and / or the age and / or the sex and / or the clothing state and / or the emotional state and / or the biometric input and / or the physiological input. The data related to the setting of the air conditioning facility may include the optimization data of the user inputted by the user, such as the feeling that varies from user to user, such as "the head is too cold", "the right leg is too hot", "the air flow is uncomfortable".
[0012] In an advantageous embodiment of the method, at least one sub-model can additionally be trained or created in the AI unit. Subsequently, a comfort model can be created by superposition of a base model and at least one sub-model. The respective sub-models can be trained based on the total data collected for all users and all vehicles or based on a subset of the data collected for all users and / or all vehicles. Thus, the respective sub-models can correct or adapt the average base model and thereby personalize specific aspects or specific parameters of the comfort model. In particular, the respective sub-models can adapt or personalize the comfort model for a specific user and / or for a specific vehicle and / or for a specific user of a specific vehicle based on the average base model.
[0013] Advantageously, multiple sub-models can be trained or created in the AI unit, each of which reflects different aspects or different parameters of the comfort model. For this purpose, when training one sub-model, individual data related to the settings of the air conditioning facility can be excluded, and when training another sub-model, they can be taken into account. Thus, when training the sub-models, for example, user data and / or situational data and / or setting data and / or optimization data can be partially or completely excluded. Thus, in one of the sub-models, for example, user data or situational data can be partially or completely excluded, and the sub-model can be trained independently of the user or independently of the vehicle. As already explained above, the respective sub-models can then be based on an averaged basic model, adapted to a specific user and / or to a specific vehicle and / or to a specific user of a specific vehicle or a personalized comfort model.
[0014] For example, the respective submodels can be created in the form of deviations from a basic model. In other words, the respective submodels can indicate the extent to which the comfort model deviates from the average basic model when aspects taken into account by the submodels or parameters taken into account by the submodels are adapted or personalized in the comfort model. The respective submodels can be described, for example, by a characteristic curve model.
[0015] The user-adapted settings of the air conditioning system may include values to be set in the air conditioning system for setting parameters of the air conditioning system in a user-adapted manner, such as a target temperature to be set and / or a fan level to be set. The basic model may output or contain at least one absolute value of at least one assigned parameter to be set of the air conditioning system (e.g., the target temperature is equal to 23.3°C). The respective sub-model may output or contain at least one difference value of at least one assigned parameter to be set of the air conditioning system (e.g., the difference from the target temperature is equal to -0.5°C).
[0016] Advantageously, the sub-model can be trained in the form of a vehicle model by means of the control architecture. In this case, the vehicle model can be a model based on the collected data of all users of a specific vehicle type for all vehicles. The collected data of all users of the specific vehicle type are therefore taken into account in the vehicle model and the characteristics of the specific vehicle type are thus taken into account independently of the users. The vehicle model can then be used to predict user-adapted settings for all users in the specific vehicle type.
[0017] Advantageously, the submodel can be trained in the form of a user model by means of the control architecture. In this case, the user model can be a model based on user-specific data collected for a plurality of vehicles. Thus, the user-specific data collected for a plurality of vehicles and thus the preferences of the user-specific are taken into account in the trained user model, regardless of the vehicle or vehicle type. Thus, the user model can be used to predict user-adapted settings for a particular user in all vehicles.
[0018] Advantageously, a sub-model can be trained in the form of a user vehicle model by means of the control architecture. The user vehicle model can be a model based on the collected data of a specific user of a specific vehicle type for all vehicles. Thus, in the trained user vehicle model, the collected data of a specific user in a specific vehicle type are taken into account, and thus the preferences of the specific user and the characteristics of the specific vehicle type are taken into account. The user vehicle model can be used to predict user-adapted settings for a specific user in a specific vehicle type.
[0019] The vehicle model and / or the user model and / or the user vehicle model can be different from one another. In this case, the individual submodels take into account different subsets of the collected data and therefore have different accuracy and different availability. In particular, the submodels can be associated with a specific user and / or a specific vehicle type.
[0020] The comfort model can be created by superimposing the base model with the vehicle model and / or with the user model and / or with the user vehicle model. Based on the superimposed comfort model, user-adapted settings for setting the air conditioning system for a specific user can then be predicted with high accuracy.
[0021] The present invention also relates to a control architecture for implementing the above-mentioned method. Here, the control architecture is designed to: collect data related to the settings of air-conditioning facilities for all users and all vehicles; train an average basic model in the AI unit based on the collected data of all users and all vehicles; create a comfort model in the AI unit at least from the basic model; predict user-adaptive settings for setting air-conditioning facilities for a specific user based on the comfort model. It is to be understood that the control architecture may include the hardware required for implementing the method and the software required for implementing the method. Here, the hardware required for implementing the method and the software required for implementing the method may be part of the cloud and / or part of the vehicle. In order to avoid repetition, reference is made to the above-mentioned embodiments at this point.
[0022] Further important features and advantages of the invention emerge from the dependent claims, the drawings and the associated description of the figures with the aid of the drawings.
[0023] It goes without saying that the features mentioned above and those yet to be explained below can be used not only in the respectively stated combination but also in other combinations or alone, without departing from the scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Preferred exemplary embodiments of the invention are illustrated in the drawings and are explained in more detail in the following description, wherein identical reference numerals refer to identical or similar or functionally identical components.
[0025] Among them, schematically,
[0026] Figure 1 shows the data structure in the method according to the present invention;
[0027] Figure 2 A flow chart of a method according to the invention is shown. DETAILED DESCRIPTION
[0028] Figure 1The data structure in the method 1 according to the present invention is shown. In the method 1, data 2 related to the settings of the air conditioning system are collected for all users 3 and all vehicles 4. Based on the collected data 2, the basic model BM and the sub-model 5 are trained in the AI unit. In this embodiment, the trained sub-model 5 is a vehicle model FM, a user model NM and a user vehicle model NFM. Here, the comfort model KM can be created from the basic model BM, if necessary superimposed with the vehicle model FM and / or the user model NM and / or the user vehicle model NFM.
[0029] Here, the base model BM is an average model trained or created using the collected data 2 of all users 3 and all vehicles 4. Here, the base model BM reflects user-adapted settings for all users 3 and all vehicles 4. If the comfort model KM is created only by the base model BM, the comfort model KM can predict user-adapted settings for any or all users 3 and for any or all vehicles 4.
[0030] The vehicle model FM is a deviation from a base model BM that is trained or created using the collected data 2 of all users 3 of a specific vehicle type of vehicle 4. The vehicle model FM therefore describes how much the user-adapted settings for a specific vehicle type differ from the user-adapted settings for all other vehicle types. If a comfort model KM is created by superimposing the base model BM with the vehicle model FM, the comfort model KM can predict the user-adapted settings for all users 3 of a specific vehicle type.
[0031] The user model NM is a deviation from a base model BM that is trained or created using the collected data 2 of a specific user 3 of all vehicles 4. The user model NM describes how much the user-adapted settings for a specific user 3 differ from the user-adapted settings for all other users 3. If a comfort model KM is created by superimposing the base model BM with the user model NM, the comfort model KM can predict the user-adapted settings for a specific user 3 of all or any vehicles 4.
[0032] The user vehicle model NFM is a deviation from a base model BM that is trained or created using data 2 collected for a specific user 3 of a specific vehicle type. The user vehicle model NFM describes how much the user-adapted settings for a specific user 3 in a specific vehicle type differ from the user-adapted settings for all other users in all other vehicle types. If a comfort model KM is created by superimposing the base model BM and the user vehicle model NFM, the comfort model KM can predict the user-adapted settings for a specific user 3 of a specific vehicle type.
[0033] The comfort model KM can be created in particular by superimposing the basic model BM with all the mentioned partial models 5 .
[0034] Figure 2 The flowchart of the method 1 according to the present invention is partially shown. In the method 1, as already explained above, data 2 related to the setting of the air conditioning system are collected for all users 3 and all vehicles 4. Based on the data 2, a basic model BM and a sub-model 5, a vehicle model FM, a user model NM, and a user vehicle model NFM are trained or created. Subsequently, the basic model BM and the sub-model 5 are superimposed to form a comfort model KM. Subsequently, the user-adapted settings 6 for setting the air conditioning system of a specific user 3 in a specific vehicle 4 are predicted with the help of the comfort model KM.
Claims
1. A method (1) for setting up a climate control system of a vehicle (4) for a user (3) in a manner adapted to the user, wherein: With the control architecture: - Collecting data related to the settings of the air conditioning system for all users (3) and / or all vehicles (4); - In the AI unit, an average base model (BM) is trained based on the collected data (2) of all users (3) and all vehicles (4), - creating a comfort model (KM) in the AI unit at least from the base model (BM), - predicting user-adapted settings (6) for setting the air conditioning system for a specific user (3) based on the comfort model (KM).
2. The method according to claim 1, characterized in that: The averaged basic model (BM) is depicted by a characteristic curve model.
3. The method according to claim 1 or 2, characterized in that: In the AI unit, at least one sub-model (5) is additionally trained, and the comfort model (KM) is created by superimposing the base model (BM) and the at least one sub-model (5).
4. The method according to claim 3, characterized in that The respective sub-models (5) are created in the form of deviations from the base model (BM).
5. The method according to any one of claims 3 to 4, characterized in that The sub-model (5) is trained in the form of a vehicle model (FM) by means of the control architecture, wherein the vehicle model (FM) is a model based on data (2) collected from all users (3) of a specific vehicle type for all vehicles (4).
6. The method according to any one of claims 3 to 5, characterized in that The sub-model (5) is trained in the form of a user model (NM) by means of the control architecture, wherein the user model (NM) is a model based on collected data (2) of specific vehicle users (3) of a plurality of vehicles (4).
7. The method according to any one of claims 3 to 6, characterized in that The sub-model (5) is trained in the form of a user vehicle model (NFM) by means of the control architecture, wherein the user vehicle model (NFM) is a model based on data (2) collected for a specific user (3) of a specific vehicle type for all vehicles (4).
8. The method according to any one of claims 5 to 7, characterized in that The vehicle model (FM) and / or the user model (NM) and / or the user-vehicle model (NFM) are different from each other.
9. The method according to any one of claims 5 to 7, characterized in that The comfort model (KM) is created by superimposing the basic model (BM) with the vehicle model (FM) and / or with the user model (NM) and / or with the user vehicle model (NFM).
10. A control architecture for implementing the method (1) according to any one of the preceding claims, wherein: The control architecture is designed to: - Collecting data (2) related to the settings of the air conditioning facilities for all users (3) and all vehicles (4); - In the AI unit, an average base model (BM) is trained based on the collected data (2) of all users (3) and all vehicles (4), - creating a comfort model (KM) in the AI unit at least from the base model (BM), - predicting user-adapted settings (6) for setting the air conditioning system for a specific user (3) based on the comfort model (KM).