Operation parameter adjusting method of functional module and vehicle

Abstract

The invention provides an operation parameter adjusting method of a function module and a vehicle, the method is applied to the vehicle, a cabin of the vehicle is associated with the function module which is installed on the vehicle and used for achieving a preset cabin function, and the method comprises the steps that environment data and module related information of the function module are obtained, the module related information comprises current operation parameters set by a target passenger in the cabin for the functional module; inputting the environment data and the module related information into a personalized parameter prediction model corresponding to the target passenger to obtain target operation parameters of the functional module output by the personalized parameter prediction model; and controlling the function module to operate according to the target operation parameter.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method for adjusting operating parameters of a functional module and a vehicle. Background Art

[0002] With the continuous development of the automobile industry and the increasing demand of passengers for driving experience, modern cars have evolved from simple means of transportation to a mobile living space that integrates comfort, entertainment and personalization.

[0003] In the related art, in order to improve the driving experience of passengers, vehicles are usually equipped with some basic preset modes, such as air conditioning temperature settings, audio styles, etc. Although these preset modes simplify the operation process to a certain extent, they often fail to meet the unique needs of passengers for preset functions. In addition, although passengers can also control the environment in the car by manual adjustment, this manual adjustment method is more cumbersome and complicated, thus reducing the passenger's car experience. Summary of the invention

[0004] In view of this, the present application provides a method for adjusting the operating parameters of a functional module and a vehicle to solve the defects existing in the related art. The technical solution of the present application is as follows:

[0005] According to an embodiment of the first aspect of the present application, there is provided a method for adjusting operating parameters of a functional module, which is applied to a vehicle, wherein a cockpit of the vehicle is associated with a functional module installed in the vehicle for realizing a preset cockpit function, and the method comprises:

[0006] Acquiring environmental data and module-related information of the functional module, wherein the module-related information includes current operating parameters set by the target occupant in the cabin for the functional module;

[0007] Inputting the module-related information and the environmental data into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model;

[0008] Control the functional modules to operate according to the target operating parameters.

[0009] Optionally, the personalized parameter prediction model is obtained by incrementally learning a basic parameter prediction model based on historical operating parameters set by the target occupant for the functional module and their corresponding historical environmental data.

[0010] Optionally, the historical operating parameters include: operating parameters of the functional module within a preset historical period, and / or label parameters obtained by processing the operating parameters of the functional module within a preset historical period.

[0011] Optionally, when there are multiple candidate occupants in the cabin, the candidate occupant with the highest priority in a preset occupant priority sequence is determined as the target occupant.

[0012] Optionally, the method further includes:

[0013] Acquiring personal status data of the target occupant and / or location data of the vehicle;

[0014] The module-related information, the environmental data, the personal status data and / or the position data are input into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model.

[0015] Optionally, inputting the environmental data and the module-related information into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model includes:

[0016] In the case where the personalized parameter prediction model is deployed on a cloud server, a target parameter acquisition request including the module-related information is initiated to the cloud server, and the target operating parameter output by the model is returned after the cloud server inputs the environment data and the module-related information into the personalized parameter prediction model; or,

[0017] In the case where the personalized parameter prediction model is deployed locally in the vehicle, the environmental data and the module-related information are input into the personalized parameter prediction model, and the target operating parameters output by the model are obtained.

[0018] Optionally, the functional module is an air conditioning module, and the method further includes:

[0019] Obtaining an in-vehicle air quality index of the vehicle;

[0020] When the in-vehicle air quality index reaches a preset adjustment threshold, the air conditioning module is controlled to operate according to the operating parameters of the fresh air mode.

[0021] Optionally, the method further includes:

[0022] Determining whether the target operating parameter is within a safe range;

[0023] The controlling the functional module to operate according to the target operating parameters includes:

[0024] When the target operating parameter is within a safe range, the functional module is controlled to operate according to the target operating parameter.

[0025] According to an embodiment of the second aspect of the present application, a vehicle is provided, wherein the vehicle is used to implement the steps of the method described in the first aspect.

[0026] According to an embodiment of the third aspect of the present application, there is provided an electronic device, comprising a processor; and a memory for storing processor-executable instructions; wherein the processor implements the method as described in the first aspect by running the executable instructions.

[0027] According to an embodiment of the fourth aspect of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0028] In the technical solution provided by the present application, the cockpit of the vehicle is associated with a functional module installed in the vehicle for realizing a preset cockpit function, and the module-related information and environmental data including the current operating parameters set by the target occupant for the functional module can be input into the personalized prediction model corresponding to the target occupant, so that the personalized prediction model can infer and output the target operating parameters of the functional module that match the personal preferences of the target occupant, so that the corresponding functional module can operate according to the target operating parameters. By applying the technical solution of the present application, since the personalized prediction model and the occupant are in a one-to-one correspondence, the target operating parameters output by the personalized prediction model can accurately match the personal preferences of the occupant, and the occupant does not need to manually adjust the operating parameters of each functional module in the cockpit, which reduces the operating burden of the occupant and significantly improves the occupant's car experience.

[0029] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and do not limit the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0031] Figure 1 is a schematic diagram of a vehicle networking architecture shown in an exemplary embodiment of the present application;

[0032] Figure 2 is a flow chart of a method for adjusting operating parameters of a functional module shown in an exemplary embodiment of the present application;

[0033] Figure 3 It is a schematic diagram of a construction method of a personalized parameter prediction model shown in an exemplary embodiment of the present application;

[0034] Figure 4 is a schematic diagram of an electronic device shown in an exemplary embodiment of the present application;

[0035] Figure 5 It is a schematic diagram of an operating parameter adjustment device of a functional module shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0036] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present application. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of the present application as detailed in the appended claims.

[0037] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this application. In some other embodiments, the steps included in the method may be more or less than those described in this application. In addition, a single step described in this application may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this application may also be combined into a single step for description in other embodiments.

[0038] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0039] With the continuous development of the automotive industry and the increasing demand of passengers for driving experience, modern cars have evolved from simple means of transportation to mobile living spaces that integrate comfort, entertainment and personalization. At the same time, with the advancement of intelligent network technology, people have higher requirements for the control of the in-car environment.

[0040] In the related technologies, in order to enhance the driving experience of passengers, vehicles are usually equipped with some basic preset modes, such as air conditioning temperature settings, audio styles, etc. Although these preset modes simplify the operation process to a certain extent, it is often difficult to accurately match the personal preferences of passengers. At the same time, although passengers can also issue adjustment commands to related functional modules through manual changes or related technologies such as voice recognition to control the environment in the car to achieve an ideal state that meets personal preferences, this method still requires passengers to perform certain adjustment operations, which is more cumbersome and complicated, reducing the passengers' car experience.

[0041] In order to solve the above problems, the present application proposes a method for adjusting the operating parameters of a functional module implemented by a vehicle. The cockpit of the vehicle described in the present application is associated with a functional module installed in the vehicle for realizing a preset cockpit function, and the module-related information and environmental data containing the current operating parameters set by the target occupant for the functional module can be input into the personalized prediction model corresponding to the target occupant, so that the personalized prediction model can infer and output the target operating parameters of the functional module that match the personal preferences of the target occupant, so that the corresponding functional module operates according to the target operating parameters. Applying the technical solution of the present application, since the personalized prediction model and the occupant are in a one-to-one correspondence, the target operating parameters output by the personalized prediction model can accurately match the personal preferences of the occupant, and the occupant does not need to manually adjust the operating parameters of each functional module in the cockpit, which reduces the operating burden of the occupant and significantly improves the occupant's car experience. Next, the embodiments of the present application are described in detail.

[0042] Figure 1 1 is a schematic diagram of a vehicle networking architecture according to an exemplary embodiment of the present application. As shown in FIG1 , the system may include a network 10 , a vehicle 11 , a mobile phone 12 and a cloud server 13 .

[0043] The vehicle 11 is any type of automobile, and the vehicle can achieve seamless connection with the Internet through the built-in 4G / 5G LTE (Long-Term Evolution) or other communication technology units in the system, and support real-time data transmission, real-time communication, online navigation and other functions. Specifically, the vehicle can achieve the above-mentioned multiple functions through its own operating system, and can also achieve related functions of a certain application by running the client-side program of the application.

[0044] The mobile phone 12 is only a part of the electronic devices that can be used by the passengers, and can be located in the cabin of the vehicle 11, such as a mobile phone used by the passengers. In fact, the passengers can obviously also use electronic devices such as tablet devices, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc., and one or more embodiments of the present application do not limit this. During operation, the electronic device can run a client-side program of a certain application to implement the relevant functions of the application.

[0045] Among them, when an electronic device such as a vehicle 11 or a mobile phone 12 runs a related application (that is, an application that can adjust the operating parameters of a functional module), it can be implemented as a client of the application. Among them, the client program of the above application can be started and run on an electronic device such as a vehicle 11 or a mobile phone 12. The program on the client side can be a native application installed on an electronic device, or the program on the client side can be a small program, a quick application or other similar forms. Of course, when using web page technologies such as HTML5 or similar, the relevant functions can be implemented through a page displayed by a browser. The browser here can be an independent browser application or a browser module embedded in certain applications. When the occupant opens the application, the operating parameters of the functional module can be adjusted automatically according to the method described in the present application scheme, or the operating parameters of the functional module can be adjusted according to the method described in the present application scheme in response to the occupant's confirmation operation or startup operation.

[0046] The cloud server 13 may be a physical server including an independent host, or the server 13 may be a virtual server carried by a host cluster. During operation, the cloud server 13 may run a server-side program corresponding to the vehicle, or a server-side program of an application in the vehicle or mobile phone to implement the relevant functions of the application.

[0047] As for the network 10 for interaction between the vehicle 11, the mobile phone 12 and the cloud server 13, the communication can be realized by wired or wireless network based on the communication mode supported by the vehicle system of the corresponding vehicle, and the present application does not limit this. For example, a vehicle can support both wired and wireless communication, so a wired or wireless network can be used to realize communication as needed, while another vehicle usually only supports wireless communication, so a wireless network can be used to realize communication. Among them, the vehicle 11 can establish a connection with the mobile phone 12 through the network 10, and can also establish a connection with the cloud server 13 through the network 10, and the mobile phone 12 can also establish a connection with the cloud server 13 through the network 10.

[0048] Among them, after the vehicle 11 and the mobile phone 12 establish a connection through the network 10, the owner can view the vehicle status in real time through the dedicated application on the mobile phone (such as checking the remaining fuel, battery power, tire pressure, mileage and other key parameters), and can also remotely control some functions of the vehicle (such as locking the vehicle, starting the air conditioner, adjusting the air conditioning audio parameters, etc.). The connection between the vehicle 11 and the cloud server 13 enables the vehicle data to be uploaded to the cloud server for in-depth analysis. At the same time, the vehicle 11 can also update the software through the cloud server 13. The connection between the mobile phone 12 and the cloud server 13 allows the owner to access and manage vehicle information across devices. For example, the owner can synchronize information such as journey records and energy consumption data to the cloud server for future viewing or sharing; personal preference settings stored in the cloud server can be synchronized to the vehicle at any time to obtain a better personalized experience.

[0049] Figure 2 FIG. 1 is a flow chart of a method for adjusting operating parameters of a functional module shown in an exemplary embodiment of the present application. Figure 2 As shown, the method can be applied to a vehicle (for example, it can be deployed in Figure 1 The vehicle 11 is shown in the figure, the cockpit of the vehicle is associated with a functional module installed in the vehicle for realizing a preset cockpit function, and the method may include the following steps:

[0050] Step 202 , obtaining environmental data and module-related information of the functional module, wherein the module-related information includes current operating parameters set by the target occupant in the cockpit for the functional module.

[0051] In one embodiment, the environmental data is used to characterize various data information of the current environment, such as weather data (temperature outside or inside the vehicle, air humidity, precipitation, etc.), time data (current time, date, season, etc.), air quality data, lighting data, etc. The technicians can set the current operating parameters of the functional module and the data range covered by the environmental data according to actual needs, and this application does not limit this.

[0052] In one embodiment, the functional module is installed in the cockpit domain of the vehicle, and is usually coordinated by software components and hardware components to realize a certain function in the cockpit. Specifically, the functional module includes at least multiple functional modules such as air conditioning module, audio module, lighting module, display module, massage module, fragrance module, navigation module, application recommendation module, etc., and this application does not limit this. Taking the air conditioning module as an example, its hardware components may include a compressor, an evaporator, a condenser, a fan, etc., and the software components include a temperature control system for controlling operating parameters such as temperature, humidity, and wind speed, so that the air conditioning module as a whole can realize the function of adjusting the temperature and humidity in the car and improve the comfort of the occupants; taking the audio module as an example, its hardware components may include a speaker, an audio processor, etc., and the software components include an audio processing system for controlling the audio input and output modes, so that the audio module as a whole can provide the occupants with a high-quality audio experience; taking the application recommendation module as an example, its hardware components may include a display, a touch screen controller, etc., and the software components may include a car software system or an application installed in the car software system, so that the application recommendation module can recommend corresponding applications and / or services to the occupants according to the habits and preferences of the occupants. The lighting module, display module, massage module, fragrance module, navigation module, etc. also have corresponding hardware components and software components, which are used to adjust the lighting conditions in the car cabin, the media content played, the seat massage mode, the smell conditions and the navigation parameters, which will not be repeated here.

[0053] In one embodiment, any functional module has corresponding module-related information, including the current operating parameters of the functional module. Specifically, the current operating parameters are used to characterize the specific settings and states of the functional module at a certain moment. For example, for the air-conditioning module, the current operating parameters may include temperature parameters, wind speed parameters, humidity settings, and outlet directions, etc.; for the audio module, the current operating parameters may include the running music application, volume, playback mode (such as theater mode, pop mode), etc.; for the application recommendation module, the current operating parameters may include the application or service currently running in the foreground, the application or service running in the background, etc.

[0054] In one embodiment, the module-related information may include current operating parameters set by the target occupant in the cabin for any functional module.

[0055] Here, different natural persons can be determined as different passengers, and the current passengers can also be determined based on the user account logged in to the vehicle. When dividing passengers based on natural persons, the passengers can include all natural persons in the cabin, such as the main driver, the co-driver, the rear passengers, etc., and the target passenger can be any of these natural persons; when dividing passengers based on user accounts, even if the natural person using the vehicle has changed, if the user account has not changed, the passenger is still considered to have not changed, that is, the target passenger is the user account, and the data information corresponding to the target passenger may include data corresponding to multiple natural persons. In the case of determining different natural persons as different passengers, the passenger's information can be collected through the sensors equipped on the vehicle to identify the passenger's identity, such as collecting the passenger's facial information through a camera for face recognition, and collecting the passenger's fingerprint information through a fingerprint sensor for fingerprint recognition. Of course, when the identity of the occupant is identified, the user account logged in to the vehicle can also be automatically switched to the account corresponding to the occupant, thereby ensuring that the data of different natural persons can be maintained in independent user accounts, that is, different natural persons are different occupants, and each natural person has an independent user account and correspondingly has an independent personalized parameter prediction model. It can be understood that compared to dividing occupants according to user accounts (and one user account may include data of multiple different natural persons), in this case, it can be ensured that the personalized parameter prediction model can be learned according to the data of each natural person, so that the target operating parameters output in the subsequent steps are more in line with the personal preferences of each natural person occupant.

[0056] In one embodiment, when the passengers are divided according to natural persons, there may be multiple passengers in the vehicle cabin at the same time, such as a driver and a co-pilot at the same time, so these multiple members can be used as candidate passengers respectively. The preset passenger priority sequence records the priority information of each candidate passenger, so in this case, the candidate passenger with the highest priority in the sequence can be determined as the target passenger. The passenger priority sequence here can be set by the technician as the default passenger priority sequence, and at the same time, the passenger using the vehicle is allowed to adjust it according to the needs and set a personalized passenger priority sequence. For example, if a passenger sets the passenger priority sequence from high to low to: co-pilot, driver, rear left passenger, rear right passenger. Then, when there are two candidate passengers, the driver and the co-pilot, in the cabin at the same time, the co-pilot is determined as the target passenger, and the personalized parameter prediction model corresponding to the co-pilot will be used to output the target operating parameters of the functional module in the future.

[0057] In one embodiment, in addition to obtaining environmental data and module-related information, the personal status data of the target occupant or the location data of the vehicle can also be obtained, or the personal status data of the target occupant and the location data of the vehicle can be obtained at the same time, and used as the input of the personalized parameter prediction model. It is understandable that the target occupant may show different personal preferences in different personal states, such as tending to use a more intense audio playback mode when the mood is high, and tending to use a softer audio playback mode when the mood is low; similarly, the target occupant may also show different personal preferences when the vehicle is in different locations, such as adjusting the temperature higher near the company to rest in the car, etc.

[0058] Specifically, the personal status data of the target occupant refers to data reflecting the current physical condition of the target occupant. These data can be collected by the data acquisition device equipped by the vehicle. The data acquisition device can include at least one sensor that can collect the personal status of the target occupant. In the case of multiple sensors, these multiple sensors can be sensors of the same type (such as multiple image acquisition sensors) or sensors of different types (such as at least one image acquisition sensor and at least one infrared sensor, etc.). Different sensors can collect the personal status data of the target occupant in the same or different dimensions. For example, the facial status of the occupant can be collected by a camera, including but not limited to changes in pupil size and facial blood flow velocity, and the clothing information of the target occupant can also be collected; the blood oxygen saturation of the target occupant can be collected by an infrared sensor; the body temperature of the target occupant can be measured by a temperature sensor; the sitting posture of the target occupant can also be detected by a pressure sensor located on the seat, etc. These personal status data can characterize the health status level, emotional status level or other related characteristics of the target occupant. The location data of the vehicle's location refers to the current geographical location information of the vehicle and its related context data. These data can be obtained through navigation systems such as GPS (Global Positioning System) and Beidou Navigation System, or through map services or other geographic information systems with corresponding functions. In this embodiment, the module-related information includes more data, and these additional data can provide more comprehensive information for the personalized parameter calculation model, so that it can learn the personal preferences of the target occupants in more specific scenarios, and more accurately predict the target operating parameters of the functional modules, so as to better match the needs and preferences of the target occupants.

[0059] Step 204 , inputting the environmental data and the module-related information into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model.

[0060] The following will be combined Figure 3 , the construction process of the personalized parameter prediction model is described, which specifically includes two stages: the training stage 31 of the basic parameter prediction model and the training stage 32 of the personalized parameter prediction model.

[0061] In the training stage 31 of the basic parameter prediction model, the historical operating parameters set by multiple passengers for the functional module and / or other functional modules installed on other vehicles for realizing the preset cockpit function and their corresponding historical environmental data can be used as training data to construct a basic parameter prediction model.

[0062] In one embodiment, the historical operating parameters are used to characterize the operating parameters set by the corresponding occupant for any functional module within a preset historical period, and may specifically include the operating parameters of the functional module within the preset historical period, and the label parameters obtained by processing the operating parameters of the functional module within the preset historical period.

[0063] Specifically, the operating parameters of the functional module in the preset historical period are the parameters actually used by any functional module when it is running in the preset historical period. For example, if the temperature set for the air-conditioning module during operation is 20°C, then the corresponding operating parameters are 20°C; the label parameters are the parameters obtained after statistics, screening, comparison and other processing of the operating parameters in multiple preset historical periods. For example, if the air-conditioning temperature in the entire summer period is summarized and the highest air-conditioning temperature in the summer period is 26°C, then "the highest air-conditioning temperature in the summer period" can be used as a label, and the corresponding label parameter is 26°C. The technicians can set the parameter range covered by the direct operating parameters according to the actual needs of the training data during the subsequent model training, or adjust the meaning represented by each label and the corresponding processing rules. At the same time, the time range covered by the preset historical period can also be adjusted by the technicians according to relevant factors such as data transmission and reception restrictions and model training mechanisms. In the field of model-related technology, the amount of training data is usually proportional to the accuracy of the model prediction results, so the preset historical period is set to the entire time period from the first time the occupant used the car to the present.

[0064] At the same time, it can be understood that the historical operating parameters set by any occupant for a functional module can, to a certain extent, characterize the occupant's mode preference for the corresponding functional module. In a simple example, if the maximum air-conditioning temperature set by occupant A in the summer period is 22°C, and the maximum air-conditioning temperature set by occupant B in the summer period is 26°C, then the label parameter of occupant A for the label "maximum air-conditioning temperature in the summer period" is 22°C, and the label parameter of occupant B for the label "maximum air-conditioning temperature in the summer period" is 26°C. Based on these two different label parameters, it can be considered that occupant A prefers a lower air-conditioning temperature in the summer period, while occupant B prefers a higher air-conditioning temperature in the summer period. Therefore, the historical operating parameters and historical environmental data corresponding to each occupant can respectively characterize the mode preferences of each occupant for the corresponding functional module.

[0065] Specifically, in the process of building a basic parameter prediction model, multiple steps may be included, such as data collection, data preprocessing, model selection and training, and model evaluation.

[0066] In the data collection step, since the basic parameter prediction model is actually a universal parameter prediction model, which aims to provide an initial prediction model suitable for most users, it is necessary to collect the historical operating parameters and corresponding historical environmental data set by multiple different passengers for the functional modules in the historical period. The multiple passengers here can be multiple different passengers who use the current vehicle together, such as passenger A, passenger B, and passenger C using vehicle 1, or multiple different passengers using other vehicles, such as passenger A and passenger B using vehicle 1, passenger C using vehicle 2, etc.

[0067] Afterwards, the collected data can be preprocessed, specifically the collected data is cleaned and standardized, and divided into a training set, a validation set, and a test set. Specifically, data cleaning can include processing missing values, outliers, duplicate records, and data type conversion and consistency checks. For example, for missing values, you can choose to delete records containing missing values ​​or fill in missing values ​​(such as filling the mean, median, mode, etc. of existing values); for outliers, you can use statistical methods (such as Z-score, IQR) or visualization methods (such as box plots) to detect, and choose to delete or correct these values. Next, the data needs to be standardized to eliminate the dimensional differences between different features. After completing the data cleaning and standardization, the data needs to be divided into a training set, a validation set, and a test set, so as to be used for training, tuning, and evaluation of the basic parameter prediction model, respectively. When dividing the data, a random partitioning method can be used to simply randomly assign data to each subset, or a technician can perform a custom partition based on the collected data, which is not limited in this application.

[0068] After that, you can select a suitable machine learning algorithm and use the training set data to train the basic parameter prediction model. During the training process, the performance of the basic parameter prediction model is optimized through cross-validation and parameter adjustment to ensure that it performs well on the validation set. After that, you can use the test set data to evaluate the performance of the basic parameter prediction model. If the performance does not meet the requirements, you may need to return to the previous steps for adjustment and improvement.

[0069] In the training phase 32 of the personalized parameter prediction model, when a basic parameter prediction model with satisfactory performance is obtained, a personalized parameter prediction model for each occupant can be further constructed on the basis of the basic parameter prediction model by incremental learning. It can be understood that when a specific occupant starts to use the vehicle, the historical operating parameters set by the occupant for the functional module and the corresponding historical environmental data will be generated. Since these data can characterize the occupant's preference for the functional module operation mode, the basic parameter prediction model can be incrementally learned using these data as training data to obtain a personalized parameter prediction model that better understands the occupant's preferences. For example, since the basic parameter prediction model is a general model trained based on the historical data of multiple occupants, an operating parameter of a functional module suitable for most occupants can be output, such as an air conditioning temperature of 24°C. However, occupant A usually uses the car at night and is accustomed to setting the air conditioning temperature to 26°C. After the basic parameter prediction model is incrementally learned based on the data, the obtained personalized parameter prediction model can understand the personal preferences of occupant A. When occupant A uses the car again at night, the operating parameter output by the personalized parameter prediction model may be an air conditioning temperature of 26°C.

[0070] It should be emphasized that the basic parameter prediction model here performs incremental learning based on the data of specific occupants, which is different from retraining the basic parameter prediction model. Incremental learning means that the model gradually updates itself when it receives new data, without the need to retrain the entire model. The data used in incremental learning is the new training data for specific occupants, and does not include the original training data used to train the basic parameter prediction model. Retraining refers to using all training data, including original training data and new training data, to retrain a brand new model. In the application scenario of the present application, the personalized parameter prediction model obtained by incremental learning can gradually adapt to the personal preferences of the corresponding occupants. If the basic parameter prediction model is retrained, the data of the specific occupants may be submerged in a large amount of original training data, and the obtained personalized parameter prediction model will not be able to adapt to the personal preferences of the specific occupants.

[0071] At the same time, the basic parameter prediction model can also adopt different methods such as online learning and batch incremental learning for incremental learning. Among them, online learning means that every time new data arrives, the model will be updated immediately. Although the computational overhead is large, it is more real-time; batch incremental learning refers to the periodic collection of a batch of new data, and then a one-time update of the model, which is more balanced in real-time and computational efficiency. Technicians can choose the appropriate incremental learning method based on actual conditions, such as the total amount of computing resources and the scale of new data, and this application does not limit this.

[0072] In addition, the basic parameter prediction model and the personalized parameter prediction model can have multiple levels of definition, which can be a comprehensive model including multiple sub-models and unit models, or an independent model corresponding to any functional module. Taking the personalized parameter prediction model as an example, for any occupant, there can be only one personalized parameter prediction model, but the personalized parameter prediction model includes sub-models corresponding to each functional module, and each sub-model can also include multiple unit models. For example, the personalized parameter prediction model can include a sub-model corresponding to the air conditioning module and a sub-model corresponding to the audio module, and the air conditioning sub-model can be further subdivided into a temperature unit model and a wind speed unit model. At the same time, for any occupant, there can also be multiple personalized parameter prediction models, each personalized parameter prediction model corresponds to each functional module, and the personalized parameter prediction model for any functional module can also include multiple unit models, such as the personalized parameter prediction model for the air conditioning module can include a temperature unit model, a humidity unit model, and an air volume unit model. Regardless of the level at which the personalized parameter prediction model is defined, it is essentially to make a refined personalized prediction of the operating parameters of each functional module. Technicians can flexibly split and combine sub-models and unit models according to actual needs, and this application does not impose any restrictions on this.

[0073] It can be seen from the above embodiments that the hierarchical modeling method provided by the technical solution of the present application, that is, the method of first training the basic parameter prediction model and then constructing the personalized parameter prediction model through incremental learning, combines the advantages of versatility and personalization, and can not only provide good initial model performance and ensure the generalization ability of the model, but also can be gradually optimized to adapt to the special needs of each occupant, so that the target operating parameters output by the personalized parameter prediction model are more matched with the personal preferences of the corresponding occupants for the operating model of the functional module, thereby improving the training efficiency and prediction performance of the personalized parameter prediction model.

[0074] In one embodiment, any model in the personalized parameter prediction model or the basic parameter prediction model can be constructed by a machine learning algorithm such as a decision tree algorithm, a random forest algorithm or a logistic regression algorithm. Among them, the model constructed by the random forest algorithm is an integrated model composed of multiple decision trees, each of which is a decision tree. It is worth noting that the random forest can capture the complex nonlinear relationship existing in a large number of parameters, automatically consider the interaction between multiple input parameters, and can find important parameter combinations in a large number of parameters; while the logistic regression algorithm assumes that there is a linear relationship between the input feature and the output, and can output the probability of each possible result. Therefore, in the case where the functional module is an air-conditioning module, the personalized parameter prediction model needs to output various operating parameters of the air-conditioning module, which is relatively complex, so the random forest algorithm can be used to construct the corresponding basic parameter prediction model and the personalized parameter prediction model; and in the case where the functional module is an audio module, it is only necessary to determine the most likely playback mode used by the user in a specific situation, so the logistic regression algorithm can be used to construct the corresponding basic parameter prediction model and the personalized parameter prediction model. Of course, the technicians can make adjustments according to the application scenario and data characteristics, or choose other algorithms to construct the corresponding model, and this application does not limit this.

[0075] It should be noted that when selecting a specific algorithm, it is necessary to ensure that the basic parameter prediction model and the personalized parameter prediction model use the same algorithm to ensure the consistency and compatibility of the models. If the basic parameter prediction model is trained using the random forest algorithm, then the personalized parameter prediction model obtained by the corresponding incremental learning must also use the random forest algorithm. Similarly, if the basic parameter prediction model is trained using the logistic regression algorithm, the personalized parameter prediction model should also use the logistic regression algorithm to improve the overall performance and reliability of the personalized parameter prediction model.

[0076] In one embodiment, the target operating parameters can also be obtained in different ways, which are specifically related to the deployment location of the personalized parameter prediction model. In the deployment and use of the personalized parameter prediction model, there are two main ways: one is to deploy the model on a cloud server (such as Figure 1 Another method is to deploy the model on the cloud server 13) in the vehicle.

[0077] Specifically, when the personalized parameter prediction model is deployed on a cloud server, after obtaining the module-related information of the functional module, the vehicle can obtain the module-related information of the functional module through the network (such as Figure 1The network 10 in the vehicle initiates a target parameter acquisition request containing module-related information to the cloud server, and receives the target operating parameters returned by the server. After receiving the target parameter acquisition request, the cloud server inputs the environmental data and module-related information into the personalized parameter prediction model for inference calculation, and returns the target operating parameters output by the model to the vehicle through the network. In this way, since the cloud server usually has stronger computing power and storage resources, it can run more complex models and can efficiently process large amounts of data. In the case where the personalized parameter prediction model is deployed locally in the vehicle, the vehicle can directly input the environmental data and module-related information into the local personalized parameter prediction model for inference calculation, and directly obtain the target operating parameters output by the model. Since all calculations are performed locally and do not need to rely on the network, the response speed is faster and the real-time performance is better. The technician can deploy the personalized parameter prediction model in a suitable manner according to the complexity of the model and specific needs. For example, a relatively simple personalized parameter prediction model can be deployed locally in the vehicle, and a relatively simple personalized parameter prediction model can be deployed on the cloud server, which takes into account reliability and real-time performance to a certain extent, ensuring that the occupants have a good vehicle use experience.

[0078] In one embodiment, when the functional module is an air conditioning module, the vehicle will periodically obtain the air quality index in the vehicle. If the air quality index in the vehicle reaches a preset adjustment threshold, the vehicle will control the air conditioning module to operate according to the operating parameters of the fresh air mode.

[0079] Specifically, the air quality sensor equipped in the vehicle will regularly detect and record the air quality index inside the vehicle, including PM2.5 concentration, CO2 concentration, volatile organic compound (VOCs) concentration, etc., and transmit these data to the vehicle in real time. After receiving the in-vehicle air quality index, the vehicle will compare it with the preset adjustment threshold. If one or more air quality indicators exceed the preset adjustment threshold, the vehicle will trigger the corresponding control logic. Here, the preset adjustment threshold can be a fixed value set based on a general standard, or it can be a personalized threshold for the occupants. When the in-vehicle air quality index reaches or exceeds the preset adjustment threshold, the vehicle will control the air conditioning module to switch to the fresh air mode. The specific operating parameters of the fresh air mode (such as intake volume, purification intensity, etc.) can be output by the personalized parameter prediction model. For example, if the historical data corresponding to the occupant indicates that the occupant prefers a higher fresh air volume, the model may output a larger intake volume. After that, after the air conditioning module switches to the fresh air mode for operation, the vehicle can continue to monitor the air quality index in the vehicle. If the air quality index still exceeds the preset threshold, the vehicle can further adjust the operating parameters of the air conditioning module, or remind the occupants to take other manual measures through voice broadcasts, interface displays, etc., such as opening windows for ventilation, etc. In this embodiment, the vehicle can automatically respond to changes in the air quality in the vehicle and adjust the operating mode of the air conditioning module in time, thereby providing a healthier and more comfortable driving environment for the occupants.

[0080] Step 206: Control the functional module to operate according to the target operating parameters.

[0081] In one embodiment, after the personalized parameter prediction model outputs the target operating parameters for the functional module, the vehicle can control the corresponding functional module to operate according to the target operating parameters. Here, the vehicle can verify the received target operating parameters to ensure that these parameters are within a safe and reasonable range. To exclude certain unsafe operating parameters. Specifically, the vehicle can determine whether the acquired target operating parameters are within the safe range interval, and control the functional module to operate according to the target parameters when the target operating parameters are actually within the safe range interval. For example, the safe range interval for air-conditioning temperature is 0℃-35℃. After receiving the target operating parameters, it will check whether the parameters for air-conditioning temperature are within the range. If the air-conditioning temperature of the target operating parameters is within the range, the subsequent steps will be executed; if the air-conditioning temperature of the target operating parameters is not within the range, a series of corresponding measures can be taken, such as prompting the occupants through a display interface or voice, recording error logs for subsequent investigation, and sending a target parameter acquisition request to the personalized parameter prediction model again to make it try to output again, etc. After the vehicle verifies the target operating parameters, it can send the verified target operating parameters to the corresponding functional module controller, so that the corresponding controller can execute specific settings. For example, the air conditioning controller will adjust the working status of the compressor, fan and other related components according to the target operating parameters to achieve the desired temperature environment in the car; the audio controller will adjust the equalizer settings according to the target operating parameters to play music in the car according to the desired playback mode. In addition, after adjusting to the target operating parameters, the functional module can send feedback information to the vehicle to confirm that the settings have been successfully completed. The vehicle can monitor these feedback information to ensure that all functional modules are operating as expected.

[0082] It can be seen from the above embodiments that the technical solution provided by the present application can infer and output the target operating parameters of the functional modules that match the personal preferences of the target occupants by the personalized prediction model corresponding to the target occupants, so that the corresponding functional modules can operate according to the target operating parameters. Since the personalized prediction model and the occupants have a one-to-one correspondence, the target operating parameters output by the personalized prediction model can accurately match the personal preferences of the occupants, and the occupants do not need to manually adjust the operating parameters of the functional modules in the cockpit, which reduces the operating burden of the occupants and significantly improves the occupants' car experience.

[0083] It should also be noted that the method proposed in this application can be implemented from the application level and the system level based on different software carriers. Specifically, in one way, the carrier of the method is an application that can be installed on the user operating system equipped with the vehicle. The application can be pre-installed on the vehicle, or it can be downloaded and installed by the occupant through the application store or other channels. After the occupant opens the application, or opens the application and performs the triggering operation of the relevant function, the operating parameter adjustment method of the functional module recorded in the aforementioned embodiment of the present application is executed. In this way, the occupant can choose whether to use the method as needed, without forcibly opening it, and can more flexibly meet the actual needs of the occupant. In another way, the method is directly integrated into the underlying code of the user operating system equipped with the vehicle as part of the user operating system. When the vehicle is started or the preset specific conditions are met, the operating parameter adjustment method of the functional module recorded in the above embodiment will be automatically executed. In this way, the user operating system will automatically execute the relevant functions without the occupant having to perform operations such as manually opening the application, thereby reducing the operating burden of the occupant.

[0084] Based on the same concept as the above method, the present application also provides a vehicle, wherein the cockpit of the vehicle is associated with a functional module installed in the vehicle for realizing preset cockpit functions, and the vehicle is used to realize the steps of the method described in any of the above embodiments.

[0085] Figure 4 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 4 At the hardware level, the electronic device includes a processor 402, an internal bus 404, a network interface 406, a memory 408, and a non-volatile memory 410, and may also include hardware required for other services. The processor 402 reads the corresponding computer program from the non-volatile memory 410 into the memory 408 and then runs it, forming a health monitoring device at the logical level. Of course, in addition to software implementations, this application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0086] Corresponding to the above method embodiments, the present application also provides device embodiments. Figure 5 The operating parameter adjustment device of the functional module can be applied to Figure 4 The device shown in the figure is used to implement the technical solution of the present application. The operating parameter adjustment device of the functional module may include an acquisition unit 51, a model unit 52 and a control unit 53, wherein:

[0087] An acquisition unit 51 is used to acquire environmental data and module-related information of the functional module, wherein the module-related information includes current operating parameters set by the target occupant in the cabin for the functional module;

[0088] A model unit 52, configured to input the module-related information and the environmental data into a personalized parameter prediction model corresponding to the target occupant, so as to obtain a target operating parameter of the functional module output by the personalized parameter prediction model;

[0089] The control unit 53 is used to control the functional modules to operate according to the target operating parameters.

[0090] Optionally, the personalized parameter prediction model is obtained by incrementally learning a basic parameter prediction model based on historical operating parameters set by the target occupant for the functional module and their corresponding historical environmental data.

[0091] Optionally, the historical operating parameters include: operating parameters of the functional module within a preset historical period, and / or label parameters obtained by processing the operating parameters of the functional module within a preset historical period.

[0092] Optionally, the device further comprises:

[0093] The passenger determination unit 54 is configured to determine, when there are multiple candidate passengers in the cabin, the candidate passenger with the highest priority in a preset passenger priority sequence as the target passenger.

[0094] Optionally, the device further comprises an acquisition subunit 55, for acquiring personal status data of the target occupant and / or location data of the vehicle;

[0095] The model unit 52 is specifically used for: the module-related information also includes the personal status data of the occupant and / or the location data of the vehicle.

[0096] Optionally, the model unit 52 is specifically used for:

[0097] In the case where the personalized parameter prediction model is deployed on a cloud server, a target parameter acquisition request including the module-related information is initiated to the cloud server, and the target operating parameter output by the model is returned after the cloud server inputs the environment data and the module-related information into the personalized parameter prediction model; or,

[0098] In the case where the personalized parameter prediction model is deployed locally in the vehicle, the environmental data and the module-related information are input into the personalized parameter prediction model, and the target operating parameters output by the model are obtained.

[0099] Optionally, the functional module is an air conditioning module, and the device further includes a control subunit 56, which is used to:

[0100] Obtaining an in-vehicle air quality index of the vehicle;

[0101] When the in-vehicle air quality index reaches a preset adjustment threshold, the air conditioning module is controlled to operate according to the operating parameters of the fresh air mode.

[0102] Optionally, the device further comprises:

[0103] A safety determination unit 57, used to determine whether the target operating parameter is within a safety range;

[0104] The control unit 53 is specifically configured to: when the target operating parameter is within a safe range, control the functional module to operate according to the target operating parameter.

[0105] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0106] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0107] Correspondingly, the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for adjusting the operating parameters of the functional module described in any of the above embodiments is implemented.

[0108] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0109] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0110] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0111] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

Claims

1. A method for adjusting operating parameters of a functional module, characterized in that: Applied to a vehicle, the cockpit of the vehicle is associated with a functional module installed in the vehicle for realizing a preset cockpit function, and the method comprises: Acquiring environmental data and module-related information of the functional module, wherein the module-related information includes current operating parameters set by the target occupant in the cabin for the functional module; Inputting the environmental data and the module-related information into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model; Control the functional modules to operate according to the target operating parameters.

2. The method according to claim 1, characterized in that The personalized parameter prediction model is obtained by incrementally learning a basic parameter prediction model based on the historical operating parameters set by the target occupant for the functional module and the corresponding historical environmental data.

3. The method according to claim 2, characterized in that The historical operating parameters include: operating parameters of the functional module within a preset historical period, and / or label parameters obtained by processing the operating parameters of the functional module within a preset historical period.

4. The method according to claim 1, characterized in that: Also includes: In the case where there are multiple candidate occupants in the cabin, the candidate occupant with the highest priority in a preset occupant priority sequence is determined as the target occupant.

5. The method according to claim 1, characterized in that Also includes: Acquiring personal status data of the target occupant and / or location data of the vehicle; The module-related information, the environmental data, the personal status data and / or the position data are input into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model.

6. The method according to claim 1, characterized in that The step of inputting the environmental data and the module-related information into a personalized parameter prediction model corresponding to the target occupant to obtain the target operating parameters of the functional module output by the personalized parameter prediction model includes: In the case where the personalized parameter prediction model is deployed on a cloud server, a target parameter acquisition request including the module-related information is initiated to the cloud server, and the target operating parameter output by the model is returned after the cloud server inputs the environment data and the module-related information into the personalized parameter prediction model; or, In the case where the personalized parameter prediction model is deployed locally in the vehicle, the environmental data and the module-related information are input into the personalized parameter prediction model, and the target operating parameters output by the model are obtained.

7. The method according to claim 1, characterized in that The functional module is an air conditioning module, and the method further includes: Obtaining an in-vehicle air quality index of the vehicle; When the in-vehicle air quality index reaches a preset adjustment threshold, the air conditioning module is controlled to operate according to the operating parameters of the fresh air mode.

8. The method according to claim 1, characterized in that: Also includes: Determining whether the target operating parameter is within a safe range; The controlling the functional module to operate according to the target operating parameters includes: When the target operating parameter is within a safe range, the functional module is controlled to operate according to the target operating parameter.

9. A vehicle, characterized in that: The cockpit of the vehicle is associated with a functional module installed in the vehicle for implementing a preset cockpit function, and the vehicle is used to implement the method as described in any one of claims 1-8.

10. An electronic device comprising a memory, a processor, and executable instructions stored in the memory and executable on the processor, characterized in that: The processor implements the method according to any one of claims 1 to 8 by executing the executable instructions.

11. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images