Intelligent cabin control method and device, computer equipment and storage medium

Abstract

The invention relates to an intelligent cabin control method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring vehicle state data corresponding to a vehicle; inputting the vehicle state data into a cabin setting model, and performing feature extraction on the vehicle state data through the cabin setting model to obtain corresponding cabin setting parameters; and cabin setting corresponding to the vehicle is adjusted according to the cabin setting parameters. By adopting the method, the cabin setting of the vehicle can be dynamically adjusted according to the vehicle state data of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intelligent cockpit control method, device, computer equipment and storage medium. Background Art

[0002] At present, the cabin atmosphere lighting, volume and sound effect settings of most cars are static or executed according to the set fixed rules, and cannot be dynamically and intelligently adjusted according to the driving situation and the changes in the environment inside and outside the car. Although some high-end models provide preset driving modes (such as sports mode, comfort mode, etc.), these modes can only make limited adjustments to the driving experience and cannot respond to different driving situations in real time. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent cockpit control method, device, computer equipment and storage medium to address the above technical problems, which can dynamically adjust the vehicle's cockpit settings according to the vehicle status data of the vehicle.

[0004] A smart cockpit control method, the method comprising:

[0005] Obtain vehicle status data corresponding to the vehicle;

[0006] Inputting vehicle status data into a cockpit setting model, extracting features of the vehicle status data through the cockpit setting model, and obtaining corresponding cockpit setting parameters;

[0007] Adjust the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0008] In one embodiment, obtaining vehicle status data corresponding to the vehicle includes:

[0009] Obtaining the vehicle speed and the vehicle acceleration through a speed control unit of the vehicle;

[0010] Obtain battery charge through the vehicle's battery charge control unit;

[0011] Environmental data is acquired via the vehicle's environmental control unit.

[0012] In one embodiment, the cockpit setting model includes a speed prediction model, an acceleration prediction model, a battery power prediction model and an environment prediction model. The vehicle state data is input into the cockpit setting model, and the cockpit setting model is used to extract features of the vehicle state data to obtain corresponding cockpit setting parameters, including:

[0013] The vehicle speed is input into the speed prediction model, and the vehicle speed is feature extracted through the speed prediction model to obtain the speed feature;

[0014] The vehicle acceleration is input into the acceleration prediction model, and the vehicle acceleration is feature extracted by the acceleration prediction model to obtain acceleration features;

[0015] The battery power is input into the battery power prediction model, and the battery power feature is extracted by the battery power prediction model to obtain the battery power feature;

[0016] Inputting environmental data into an environmental prediction model, extracting features of the environmental data through the environmental prediction model, and obtaining environmental features;

[0017] The speed features, acceleration features, battery power features and environmental features are fused to obtain the corresponding cockpit setting parameters.

[0018] In one embodiment, the cockpit setting parameters include cockpit atmosphere light setting parameters, volume sound effect setting parameters and in-vehicle environment setting parameters, and adjusting the cockpit settings corresponding to the vehicle according to the cockpit setting parameters includes:

[0019] Control the corresponding cabin atmosphere light of the vehicle according to the cabin atmosphere light setting parameters;

[0020] Control the volume and sound effects corresponding to the vehicle according to the volume and sound effect setting parameters;

[0021] The interior environment of the vehicle is controlled according to the interior environment setting parameters.

[0022] In one embodiment, the steps of training the cockpit setting model include:

[0023] Acquire vehicle state training data, where the vehicle state training data is associated with corresponding cockpit setting parameter labels;

[0024] Inputting the vehicle state training data into an untrained initial cockpit setting model, extracting features of the vehicle state training data through the initial cockpit setting model, and obtaining corresponding cockpit setting training parameters;

[0025] The training loss value is calculated according to the cockpit setting training parameters and the cockpit setting parameter labels;

[0026] When the training loss value reaches the training convergence condition, the trained cockpit setting model is obtained;

[0027] When the training loss value does not reach the training convergence condition, the model parameters of the initial cockpit setting model are adjusted, and the step of obtaining the vehicle state training data is returned until the training loss value reaches the training convergence condition to obtain the trained cockpit setting model.

[0028] In one embodiment, the vehicle state training data includes a plurality of different types of vehicle state sub-data, the initial cockpit setting model includes a plurality of different state networks, the vehicle state training data is input into an untrained initial cockpit setting model, and the initial cockpit setting model is used to perform feature extraction on the vehicle state training data to obtain corresponding cockpit setting training parameters, including:

[0029] Input each vehicle state sub-data into the corresponding state network in the initial cockpit setting model, extract features of the corresponding vehicle state sub-data through each state network, and obtain corresponding state features;

[0030] The features of each state are fused to obtain the corresponding cockpit setting training parameters.

[0031] In one embodiment, after obtaining the vehicle state training data, the method further includes:

[0032] Performing data cleaning on the vehicle state training data to obtain cleaned vehicle state training data;

[0033] The cleaned vehicle state training data is normalized to obtain processed vehicle state training data.

[0034] An intelligent cockpit control device, the device comprising:

[0035] An acquisition module, used to acquire vehicle status data corresponding to the vehicle;

[0036] An input module, used to input vehicle status data into a cockpit setting model, extract features of the vehicle status data through the cockpit setting model, and obtain corresponding cockpit setting parameters;

[0037] The adjustment module is used to adjust the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0038] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0039] Obtain vehicle status data corresponding to the vehicle;

[0040] Inputting vehicle status data into a cockpit setting model, extracting features of the vehicle status data through the cockpit setting model, and obtaining corresponding cockpit setting parameters;

[0041] Adjust the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0042] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0043] Obtain vehicle status data corresponding to the vehicle;

[0044] Inputting vehicle status data into a cockpit setting model, extracting features of the vehicle status data through the cockpit setting model, and obtaining corresponding cockpit setting parameters;

[0045] Adjust the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0046] The above-mentioned intelligent cockpit control method, device, computer equipment and storage medium obtain vehicle status data corresponding to the vehicle, input the vehicle status data into the cockpit setting model, extract features of the vehicle status data through the cockpit setting model, obtain corresponding cockpit setting parameters, and adjust the corresponding cockpit settings of the vehicle according to the cockpit setting parameters. Therefore, the cockpit setting model predicts the vehicle status data, obtains the cockpit setting parameters that are most suitable for the current driving scenario of the vehicle, and adjusts the cockpit settings of the vehicle according to the cockpit setting parameters, which can provide the best cockpit settings for dynamic adjustment in different driving scenarios, dynamically adapt to the vehicle environment, and make real-time adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is an application environment diagram of a smart cockpit control method in one embodiment;

[0048] Figure 2 is a schematic flow chart of a smart cockpit control method in one embodiment;

[0049] Figure 3 A schematic flow chart of a vehicle status data acquisition step in one embodiment;

[0050] Figure 4 A flowchart of cockpit model setting processing steps in one embodiment;

[0051] Figure 5 A schematic diagram of a flow chart of vehicle cabin setting adjustment steps in one embodiment;

[0052] Figure 6 A flowchart of the training steps of a cockpit setting model in one embodiment;

[0053] Figure 7 A schematic diagram of a process flow of initial cockpit model setting processing steps in one embodiment;

[0054] Figure 8 A schematic diagram of a process flow of a vehicle state training data preprocessing step in one embodiment;

[0055] Fig. 9 is a structural block diagram of an intelligent cockpit control device in one embodiment;

[0056] Fig.10 is an internal structure diagram of a computer device in one embodiment;

[0057] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] The intelligent cockpit control method provided in this application can be applied to Figure 1 In the application environment shown, the vehicle terminal 102 communicates with the server 104 through a network. The vehicle terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices connected to the vehicle, and the server 104 can be implemented as an independent server or a server cluster composed of multiple servers.

[0060] Specifically, the vehicle-mounted terminal 102 obtains the vehicle status data corresponding to the vehicle and sends it to the server 104. The server 104 obtains the vehicle status data corresponding to the vehicle, inputs the vehicle status data into the cockpit setting model, extracts features of the vehicle status data through the cockpit setting model, obtains corresponding cockpit setting parameters, and sends the cockpit setting parameters to the vehicle-mounted terminal 102. The vehicle-mounted terminal 102 adjusts the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0061] In another embodiment, the vehicle terminal 102 obtains vehicle status data corresponding to the vehicle, inputs the vehicle status data into a cockpit setting model, extracts features of the vehicle status data through the cockpit setting model, obtains corresponding cockpit setting parameters, and adjusts the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0062] In one embodiment, Figure 2 As shown, a smart cockpit control method is provided, which is applied to Figure 1 The vehicle terminal or server in the example is used to illustrate, including the following steps:

[0063] Step 202, obtaining vehicle status data corresponding to the vehicle.

[0064] Among them, vehicle status data is data related to the status corresponding to the current driving scenario of the vehicle, which can reflect the current status of the vehicle, including but not limited to vehicle speed, vehicle acceleration, battery power and environmental data, etc. Among them, environmental data includes in-vehicle environmental data and out-vehicle environmental data. In-vehicle environmental data includes in-vehicle brightness, temperature, humidity, etc., and out-vehicle environmental data includes outside temperature, humidity, etc.

[0065] Among them, the vehicle status data can be obtained through the hardware devices corresponding to each status data, such as obtaining the vehicle speed through the vehicle speed sensor, obtaining the vehicle acceleration through the accelerometer, obtaining the battery power through the battery power detection device, and so on.

[0066] In one embodiment, the vehicle's CAN bus connects multiple electronic control units that monitor and transmit various status data of the vehicle in real time. The Controller Area Network (CAN) is a serial communication protocol bus for real-time applications. It can use twisted pair cables to transmit signals and is one of the most widely used field buses in the world. The CAN protocol is used for communication between various components in the car to replace expensive and bulky distribution harnesses. The robustness of the protocol extends its use to other automation and industrial applications. The features of the CAN protocol include complete serial data communication, real-time support, a transmission rate of up to 1Mb / s, and 11-bit addressing and error detection capabilities.

[0067] Step 204 , input the vehicle state data into the cockpit setting model, extract features of the vehicle state data through the cockpit setting model, and obtain corresponding cockpit setting parameters.

[0068] The cockpit setting model is used to predict appropriate cockpit setting parameters based on vehicle status data. The cockpit setting model can be an LSTM (Long Short-Term Memory, time recurrent neural network) or other neural network models. It can be trained in advance with a large amount of training data, and the network model parameters can be continuously adjusted until the training convergence conditions are met, and the trained cockpit setting model is obtained and stored.

[0069] Specifically, after obtaining the vehicle status data in the current driving scenario of the vehicle, a trained cockpit setting model is obtained, and the vehicle status data is input into the cockpit setting model. The cockpit setting model extracts features from the input vehicle status data and outputs the cockpit setting parameters that are most suitable for the current driving scenario.

[0070] Step 206: adjusting the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0071] Among them, the cockpit setting is the setting related to the vehicle cockpit. After obtaining the cockpit setting parameters output by the cockpit setting model, the cockpit setting corresponding to the vehicle is adjusted according to the cockpit setting parameters, so that the adjusted cockpit setting conforms to the current driving scene of the vehicle. Among them, the cockpit setting parameters may include multiple sub-parameters, and the corresponding cockpit setting is adjusted according to each sub-parameter. Among them, the sub-parameters may be volume and sound effect setting parameters, environment setting parameters, ambient light setting parameters, etc.

[0072] In the above-mentioned intelligent cockpit control method, the vehicle state data corresponding to the vehicle is obtained, the vehicle state data is input into the cockpit setting model, the vehicle state data is feature extracted by the cockpit setting model, the corresponding cockpit setting parameters are obtained, and the cockpit settings corresponding to the vehicle are adjusted according to the cockpit setting parameters. Therefore, the vehicle state data is predicted by the cockpit setting model, the cockpit setting parameters that are most suitable for the current driving scenario of the vehicle are obtained, and the cockpit settings of the vehicle are adjusted according to the cockpit setting parameters, so that the best cockpit settings can be provided in different driving scenarios for dynamic adjustment, dynamic adaptation to the vehicle environment, and real-time adjustment.

[0073] In one embodiment, Figure 3 As shown, the vehicle status data corresponding to the vehicle is obtained, including:

[0074] Step 302: Acquire the vehicle speed and vehicle acceleration through the vehicle speed control unit.

[0075] Step 304 , obtaining the battery power through the battery power control unit of the vehicle.

[0076] Step 306 , obtaining environmental data through the vehicle's environmental control unit.

[0077] Among them, the vehicle's CAN bus system is connected to multiple electronic control units, which monitor and transmit various status data of the vehicle in real time, that is, the corresponding vehicle status data is obtained through the corresponding electronic control units.

[0078] Specifically, the vehicle speed can be acquired through a speed control unit, such as a speed sensor, to obtain the current vehicle speed of the vehicle, and the vehicle current vehicle acceleration can also be acquired through a speed control unit, such as an accelerometer.

[0079] At the same time, the remaining power status of the vehicle battery can be obtained through the vehicle's battery power control unit, that is, the battery power. Environmental data can also be obtained through the environmental control unit, where the environmental data may include brake status, steering angle, window opening, road condition information, cabin environment brightness, indoor and outdoor temperature and humidity, etc. Among them, brake status: detect the status of the brake pedal (whether it is stepped on, strength, etc.), steering angle: the steering sensor records the angle of the steering wheel, window opening: the window lifting motor feedback window opening information, road condition information: urban roads, rural roads, etc., cabin environment brightness: bright, dim, etc., indoor and outdoor temperature and humidity: temperature and humidity sensors provide environmental data inside and outside the car.

[0080] Finally, the vehicle status data is obtained based on the vehicle speed, vehicle acceleration, battery power and environmental data.

[0081] In one embodiment, Figure 4 As shown, the cockpit setting model includes a speed prediction model, an acceleration prediction model, a battery power prediction model and an environment prediction model. The vehicle state data is input into the cockpit setting model, and the cockpit setting model is used to extract features of the vehicle state data to obtain corresponding cockpit setting parameters, including:

[0082] Step 402: input the vehicle speed into a speed prediction model, extract features of the vehicle speed through the speed prediction model, and obtain speed features.

[0083] Step 404: input the vehicle acceleration into the acceleration prediction model, extract the features of the vehicle acceleration through the acceleration prediction model, and obtain the acceleration features.

[0084] Step 406: input the battery power into a battery power prediction model, extract features of the battery power through the battery power prediction model, and obtain battery power features.

[0085] Step 408: input the environmental data into the environmental prediction model, extract features from the environmental data through the environmental prediction model, and obtain environmental features.

[0086] Step 410 , fusing the velocity features, acceleration features, battery power features and environmental features to obtain corresponding cockpit setting parameters.

[0087] Among them, since the vehicle status data includes vehicle speed, vehicle acceleration, battery power and environmental data, in order to improve the prediction accuracy, the corresponding data can be processed through different networks. Among them, the cockpit setting model can include multiple parallel sub-models, and different models focus on different features, that is, the cockpit setting model can include a speed prediction model, an acceleration prediction model, a battery power prediction model and an environmental prediction model. The corresponding vehicle status data is processed through these models, and the features output by these models are fused to obtain the cockpit setting parameters, thereby improving the accuracy of the cockpit setting parameters.

[0088] Specifically, the vehicle speed is input into the speed prediction model, and the speed prediction model is used to extract the features of the vehicle speed and output the corresponding speed features. At the same time, the vehicle acceleration is input into the acceleration prediction model, and the acceleration prediction model is used to extract the features of the vehicle acceleration and obtain the acceleration features. At the same time, the battery power is input into the battery power prediction model, and the battery power features are output. Similarly, the environmental data is input into the environmental prediction model, and the environmental features are output.

[0089] Finally, the speed features, acceleration features, battery power features and environmental features are fused to obtain the corresponding cockpit setting parameters. Through multiple parallel sub-models in the cockpit setting model, each sub-model focuses on different features or driving scenarios, and the features output by each sub-model are fused to obtain the cockpit setting parameters, which can improve the prediction accuracy.

[0090] Among them, the speed prediction model is specifically used to process feature data related to vehicle speed. The acceleration prediction model processes acceleration and braking data to identify the driver's intention to accelerate or decelerate. The battery power prediction model monitors the battery power and determines whether it is necessary to enter energy-saving mode. The environment prediction model analyzes data such as temperature and humidity inside and outside the vehicle, and window opening. Based on the actual situation of the vehicle, more modules can be supported to build parallel models.

[0091] In one embodiment, Figure 5 As shown, the cockpit setting parameters include cockpit atmosphere light setting parameters, volume sound effect setting parameters and in-vehicle environment setting parameters. The cockpit settings corresponding to the vehicle are adjusted according to the cockpit setting parameters, including:

[0092] Step 502: Control the corresponding cabin atmosphere light of the vehicle according to the cabin atmosphere light setting parameters.

[0093] Step 504 , controlling the volume and sound effects corresponding to the vehicle according to the volume and sound effect setting parameters.

[0094] Step 506, controlling the interior environment of the vehicle according to the interior environment setting parameters.

[0095] Among them, the cockpit setting parameters output by the cockpit setting model may include multiple sub-parameters, and different sub-parameters correspond to different settings, so that the vehicle's cockpit settings can be more in line with the current driving situation. Among them, the cockpit setting parameters include cockpit atmosphere light setting parameters, volume sound effect setting parameters, and in-vehicle environment setting parameters. Specifically, the vehicle's current cockpit atmosphere light parameters, including the color and brightness of the cockpit atmosphere light, are adjusted according to the cockpit atmosphere light setting parameters. For example, when driving at high speeds, the system may recommend the use of cool colors and lower brightness lights to reduce driver fatigue.

[0096] Similarly, the current volume and sound effects of the vehicle are adjusted according to the volume and sound effect setting parameters, including the volume and volume effect, so that the volume and sound effects of the vehicle are consistent with the current driving scenario of the vehicle. For example, on urban roads, due to dense traffic, the system may recommend lowering the volume to enhance the perception of external sounds and improve safety.

[0097] Furthermore, the vehicle's current interior environment, including air conditioning settings, can be adjusted according to the interior environment setting parameters to make the interior environment consistent with the vehicle's current driving scenario. For example, when the battery is low, it can be suggested to lower the air conditioning power, reduce the light brightness and the frequency of dynamic effects to save energy.

[0098] In one embodiment, Figure 6 As shown, the training steps of the cockpit setting model include:

[0099] Step 602, obtaining vehicle state training data, wherein the vehicle state training data is associated with a corresponding cockpit setting parameter label.

[0100] Step 604 , input the vehicle state training data into an untrained initial cockpit setting model, perform feature extraction on the vehicle state training data through the initial cockpit setting model, and obtain corresponding cockpit setting training parameters.

[0101] Step 606, calculating the training loss value according to the cockpit setting training parameters and the cockpit setting parameter label.

[0102] Among them, the vehicle state training data here is the vehicle state data used for training. Each vehicle state training data is associated with a corresponding cockpit setting parameter label. The cockpit setting parameter label is based on a large amount of historical data and expert advice, and different vehicle state data are labeled with corresponding cockpit setting parameters.

[0103] Specifically, vehicle state training data is obtained, and the vehicle state training data is input into an untrained initial cockpit setting model. The initial cockpit setting model extracts features from the input vehicle state training data to obtain corresponding cockpit setting training parameters.

[0104] Among them, the initial cockpit setting model can be an LSTM model. The LSTM model can include an input layer, an LSTM layer, a fully connected layer and an output layer. The input layer is used to receive input data. The LSTM layer includes multiple LSTM units, which can remember and forget data and capture long-term and short-term dependencies. The fully connected layer is used to convert the LSTM layer output into a predicted value, and the output layer is used to output the cockpit setting parameters.

[0105] The LSTM layer consists of multiple units (LSTM cells), each of which contains the following three gates: Forget Gate: determines how much memory from the previous time step is discarded. Input Gate: determines how much new information is updated to the cell state. Output Gate: determines how much of the current cell state is output as a hidden state.

[0106] Furthermore, after obtaining the cockpit setting training parameters output by the initial cockpit setting model, the training loss value is calculated according to the cockpit setting training parameters and the cockpit setting parameter labels. The training loss value is used to reflect whether the initial cockpit setting model has achieved the training effect. It is an indicator for measuring the difference between the predicted results of the cockpit setting model and the true label. The high or low loss value reflects the degree of fit of the model to the training data under the current parameters.

[0107] Step 608, when the training loss value reaches the training convergence condition, the trained cockpit setting model is obtained.

[0108] Step 610, when the training loss value does not reach the training convergence condition, adjust the model parameters of the initial cockpit setting model, return to the step of obtaining vehicle state training data, until the training loss value reaches the training convergence condition, and obtain the trained cockpit setting model.

[0109] Among them, the training convergence condition is an indicator used to judge whether the cockpit setting model has achieved the training purpose. The training convergence condition can avoid overfitting or underfitting of the cockpit setting model. According to the training loss value and the training convergence condition, it is judged whether the initial cockpit setting model has achieved the training purpose. Specifically, it is judged whether the training loss value reaches the training convergence condition. If it does, it means that the initial cockpit setting model has achieved the training purpose and a trained cockpit setting model is obtained. On the contrary, if the training convergence condition is not met, the model parameters of the initial cockpit setting model are adjusted, and the step of obtaining vehicle status training data is returned until the training loss value reaches the training convergence condition and a trained cockpit setting model is obtained.

[0110] Among them, the training convergence condition can be determined according to actual business needs, actual product needs or actual application scenarios. The training convergence condition can be that the number of training times reaches a preset training time threshold, or the training loss value reaches a training loss value threshold, or the training loss value no longer changes, etc.

[0111] In one embodiment, Figure 7 As shown, the vehicle state training data includes a plurality of different types of vehicle state sub-data, and the initial cockpit setting model includes a plurality of different state networks. The vehicle state training data is input into the untrained initial cockpit setting model, and the initial cockpit setting model is used to extract features of the vehicle state training data to obtain corresponding cockpit setting training parameters, including:

[0112] Step 702: input each vehicle state sub-data into the corresponding state network in the initial cockpit setting model, and extract features from the corresponding vehicle state sub-data through each state network to obtain corresponding state features.

[0113] Step 704: perform feature fusion on each state feature to obtain corresponding cockpit setting training parameters.

[0114] The vehicle state training data includes different types of vehicle state sub-data, such as vehicle speed, vehicle acceleration, battery power and environmental data. Environmental data may include indoor and outdoor temperature and humidity, road condition information, brake status, window opening, etc. The initial cockpit setting model includes multiple different state networks, each of which focuses on different features to improve the accuracy of prediction.

[0115] Specifically, each vehicle state sub-data is input into the corresponding state network in the initial cockpit setting model, for example, the vehicle speed is input into the vehicle speed prediction model, the vehicle acceleration is input into the vehicle acceleration prediction model, the battery power is input into the vehicle battery power prediction model, and the environmental data is input into the vehicle environment prediction model. Furthermore, the input vehicle state sub-data is subjected to feature extraction through each state network to obtain the corresponding state feature, and finally, the state features output by each state network are subjected to feature fusion to obtain the corresponding cockpit setting training parameters.

[0116] In one embodiment, Figure 8 As shown, after obtaining the vehicle state training data, it also includes:

[0117] Step 802, performing data cleaning on the vehicle state training data to obtain cleaned vehicle state training data.

[0118] Step 804 , normalizing the cleaned vehicle state training data to obtain processed vehicle state training data.

[0119] Among them, in order to ensure the quality and consistency of the training data, after obtaining the vehicle state training data, preprocessing is required, and the preprocessing includes data cleaning and normalization. Specifically, the vehicle state training data is cleaned to remove abnormal data points, such as sensor error readings or data loss, to obtain cleaned vehicle state training data.

[0120] Furthermore, the cleaned vehicle state training data is normalized, and the vehicle state training data of different scales are normalized to facilitate cockpit setting model processing. For example, the vehicle speed (km / h) and steering angle (degrees) are converted into values ​​between 0 and 1 to obtain the processed vehicle state training data, which are finally input into the initial cockpit setting model for training.

[0121] It should be understood that, although the various steps in the above-mentioned flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flow chart may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0122] In one embodiment, Fig. 9 As shown, a smart cockpit control device 900 is provided, including: an acquisition module 902, an input module 904 and an adjustment module 906, wherein:

[0123] The acquisition module 902 is used to acquire vehicle status data corresponding to the vehicle.

[0124] The input module 904 is used to input the vehicle status data into the cockpit setting model, and extract features of the vehicle status data through the cockpit setting model to obtain corresponding cockpit setting parameters.

[0125] The adjustment module 906 is used to adjust the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0126] In one embodiment, the acquisition module 902 acquires the vehicle speed and the vehicle acceleration through the vehicle's speed control unit, acquires the battery power through the vehicle's battery power control unit, and acquires environmental data through the vehicle's environment control unit.

[0127] In one embodiment, the cockpit setting model includes a speed prediction model, an acceleration prediction model, a battery power prediction model and an environment prediction model. The input module 904 inputs the vehicle speed into the speed prediction model, extracts features of the vehicle speed through the speed prediction model, and obtains speed features. The vehicle acceleration is input into the acceleration prediction model, and features of the vehicle acceleration are extracted through the acceleration prediction model to obtain acceleration features. The battery power is input into the battery power prediction model, and features of the battery power are extracted through the battery power prediction model to obtain battery power features. The environmental data is input into the environment prediction model, and features of the environmental data are extracted through the environment prediction model to obtain environmental features. The speed features, acceleration features, battery power features and environmental features are feature fused to obtain corresponding cockpit setting parameters.

[0128] In one embodiment, the cabin setting parameters include cabin atmosphere light setting parameters, volume sound effect setting parameters and in-vehicle environment setting parameters. The adjustment module 906 controls the cabin atmosphere light corresponding to the vehicle according to the cabin atmosphere light setting parameters, controls the volume sound effect corresponding to the vehicle according to the volume sound effect setting parameters, and controls the in-vehicle environment corresponding to the vehicle according to the in-vehicle environment setting parameters.

[0129] In one embodiment, the intelligent cockpit control device 900 obtains vehicle state training data, which is associated with a corresponding cockpit setting parameter label, and inputs the vehicle state training data into an untrained initial cockpit setting model. The initial cockpit setting model performs feature extraction on the vehicle state training data to obtain corresponding cockpit setting training parameters, and calculates a training loss value based on the cockpit setting training parameters and the cockpit setting parameter label. When the training loss value reaches a training convergence condition, a trained cockpit setting model is obtained. When the training loss value does not reach the training convergence condition, the model parameters of the initial cockpit setting model are adjusted, and the process returns to the step of obtaining the vehicle state training data until the training loss value reaches the training convergence condition to obtain a trained cockpit setting model.

[0130] In one embodiment, the vehicle state training data includes a plurality of different types of vehicle state sub-data, and the initial cockpit setting model includes a plurality of different state networks. The intelligent cockpit control device 900 inputs each vehicle state sub-data into the corresponding state network in the initial cockpit setting model, performs feature extraction on the corresponding vehicle state sub-data through each state network to obtain corresponding state features, performs feature fusion on each state feature to obtain corresponding cockpit setting training parameters.

[0131] In one embodiment, the intelligent cockpit control device 900 performs data cleaning on the vehicle state training data to obtain cleaned vehicle state training data, and performs normalization processing on the cleaned vehicle state training data to obtain processed vehicle state training data.

[0132] For the specific definition of the intelligent cockpit control device, please refer to the definition of the intelligent cockpit control method above, which will not be repeated here. Each module in the above-mentioned intelligent cockpit control device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0133] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store a cockpit setting model. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent cockpit control method is implemented.

[0134] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.11 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent cockpit control method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0135] Those skilled in the art will understand that Fig.10 or Fig.11The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0136] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining vehicle status data corresponding to the vehicle; inputting the vehicle status data into a cockpit setting model, performing feature extraction on the vehicle status data through the cockpit setting model to obtain corresponding cockpit setting parameters; and adjusting the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0137] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0138] Obtaining the vehicle speed and the vehicle acceleration through a speed control unit of the vehicle;

[0139] Obtain battery charge through the vehicle's battery charge control unit;

[0140] Environmental data is acquired via the vehicle's environmental control unit.

[0141] In one embodiment, the cabin setting model includes a speed prediction model, an acceleration prediction model, a battery power prediction model, and an environment prediction model, and the processor further implements the following steps when executing the computer program:

[0142] The vehicle speed is input into the speed prediction model, and the vehicle speed is feature extracted through the speed prediction model to obtain the speed feature;

[0143] The vehicle acceleration is input into the acceleration prediction model, and the vehicle acceleration is feature extracted by the acceleration prediction model to obtain acceleration features;

[0144] The battery power is input into the battery power prediction model, and the battery power feature is extracted by the battery power prediction model to obtain the battery power feature;

[0145] Inputting environmental data into an environmental prediction model, extracting features of the environmental data through the environmental prediction model, and obtaining environmental features;

[0146] The speed features, acceleration features, battery power features and environmental features are fused to obtain the corresponding cockpit setting parameters.

[0147] In one embodiment, the cockpit setting parameters include cockpit atmosphere light setting parameters, volume sound effect setting parameters and in-vehicle environment setting parameters, and the processor further implements the following steps when executing the computer program:

[0148] Control the corresponding cabin atmosphere light of the vehicle according to the cabin atmosphere light setting parameters;

[0149] Control the volume and sound effects corresponding to the vehicle according to the volume and sound effect setting parameters;

[0150] The interior environment of the vehicle is controlled according to the interior environment setting parameters.

[0151] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0152] Acquire vehicle state training data, where the vehicle state training data is associated with corresponding cockpit setting parameter labels;

[0153] Inputting the vehicle state training data into an untrained initial cockpit setting model, extracting features of the vehicle state training data through the initial cockpit setting model, and obtaining corresponding cockpit setting training parameters;

[0154] The training loss value is calculated according to the cockpit setting training parameters and the cockpit setting parameter labels;

[0155] When the training loss value reaches the training convergence condition, the trained cockpit setting model is obtained;

[0156] When the training loss value does not reach the training convergence condition, the model parameters of the initial cockpit setting model are adjusted, and the step of obtaining the vehicle state training data is returned until the training loss value reaches the training convergence condition to obtain the trained cockpit setting model.

[0157] In one embodiment, the vehicle state training data includes a plurality of different types of vehicle state sub-data, the initial cockpit setting model includes a plurality of different state networks, and the processor further implements the following steps when executing the computer program:

[0158] Input each vehicle state sub-data into the corresponding state network in the initial cockpit setting model, extract features of the corresponding vehicle state sub-data through each state network, and obtain corresponding state features;

[0159] The features of each state are fused to obtain the corresponding cockpit setting training parameters.

[0160] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0161] Performing data cleaning on the vehicle state training data to obtain cleaned vehicle state training data;

[0162] The cleaned vehicle state training data is normalized to obtain processed vehicle state training data.

[0163] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining vehicle status data corresponding to the vehicle; inputting the vehicle status data into a cockpit setting model, performing feature extraction on the vehicle status data through the cockpit setting model, and obtaining corresponding cockpit setting parameters; and adjusting the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] Obtaining the vehicle speed and the vehicle acceleration through a speed control unit of the vehicle;

[0166] Obtain battery charge through the vehicle's battery charge control unit;

[0167] Environmental data is acquired via the vehicle's environmental control unit.

[0168] In one embodiment, the cabin setting model includes a speed prediction model, an acceleration prediction model, a battery power prediction model, and an environment prediction model, and the processor further implements the following steps when executing the computer program:

[0169] The vehicle speed is input into the speed prediction model, and the vehicle speed is feature extracted through the speed prediction model to obtain the speed feature;

[0170] The vehicle acceleration is input into the acceleration prediction model, and the vehicle acceleration is feature extracted by the acceleration prediction model to obtain acceleration features;

[0171] The battery power is input into the battery power prediction model, and the battery power feature is extracted by the battery power prediction model to obtain the battery power feature;

[0172] Inputting environmental data into an environmental prediction model, extracting features of the environmental data through the environmental prediction model, and obtaining environmental features;

[0173] The speed features, acceleration features, battery power features and environmental features are fused to obtain the corresponding cockpit setting parameters.

[0174] In one embodiment, the cockpit setting parameters include cockpit atmosphere light setting parameters, volume sound effect setting parameters and in-vehicle environment setting parameters, and the processor further implements the following steps when executing the computer program:

[0175] Control the corresponding cabin atmosphere light of the vehicle according to the cabin atmosphere light setting parameters;

[0176] Control the volume and sound effects corresponding to the vehicle according to the volume and sound effect setting parameters;

[0177] The interior environment of the vehicle is controlled according to the interior environment setting parameters.

[0178] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0179] Acquire vehicle state training data, where the vehicle state training data is associated with corresponding cockpit setting parameter labels;

[0180] Inputting the vehicle state training data into an untrained initial cockpit setting model, extracting features of the vehicle state training data through the initial cockpit setting model, and obtaining corresponding cockpit setting training parameters;

[0181] The training loss value is calculated according to the cockpit setting training parameters and the cockpit setting parameter labels;

[0182] When the training loss value reaches the training convergence condition, the trained cockpit setting model is obtained;

[0183] When the training loss value does not reach the training convergence condition, the model parameters of the initial cockpit setting model are adjusted, and the step of obtaining the vehicle state training data is returned until the training loss value reaches the training convergence condition to obtain the trained cockpit setting model.

[0184] In one embodiment, the vehicle state training data includes a plurality of different types of vehicle state sub-data, the initial cockpit setting model includes a plurality of different state networks, and the processor further implements the following steps when executing the computer program:

[0185] Input each vehicle state sub-data into the corresponding state network in the initial cockpit setting model, extract features of the corresponding vehicle state sub-data through each state network, and obtain corresponding state features;

[0186] The features of each state are fused to obtain the corresponding cockpit setting training parameters.

[0187] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0188] Performing data cleaning on the vehicle state training data to obtain cleaned vehicle state training data;

[0189] The cleaned vehicle state training data is normalized to obtain processed vehicle state training data.

[0190] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0191] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0192] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A smart cockpit control method, the method comprising: Obtain vehicle status data corresponding to the vehicle; Inputting the vehicle state data into a cockpit setting model, performing feature extraction on the vehicle state data through the cockpit setting model, and obtaining corresponding cockpit setting parameters; The cockpit settings corresponding to the vehicle are adjusted according to the cockpit setting parameters.

2. The method according to claim 1, characterized in that The obtaining of vehicle status data corresponding to the vehicle includes: acquiring a vehicle speed and a vehicle acceleration by a speed control unit of the vehicle; obtaining the battery power through a battery power control unit of the vehicle; Environmental data is acquired by an environmental control unit of the vehicle.

3. The method according to claim 2, characterized in that The cockpit setting model includes a speed prediction model, an acceleration prediction model, a battery power prediction model and an environment prediction model. The vehicle state data is input into the cockpit setting model, and features of the vehicle state data are extracted by the cockpit setting model to obtain corresponding cockpit setting parameters, including: Inputting the vehicle speed into the speed prediction model, extracting features of the vehicle speed through the speed prediction model to obtain speed features; Inputting the vehicle acceleration into the acceleration prediction model, and extracting features of the vehicle acceleration through the acceleration prediction model to obtain acceleration features; Inputting the battery power into the battery power prediction model, extracting features of the battery power through the battery power prediction model to obtain battery power features; Inputting the environmental data into the environmental prediction model, extracting features from the environmental data through the environmental prediction model to obtain environmental features; The speed feature, the acceleration feature, the battery power feature and the environment feature are fused to obtain corresponding cockpit setting parameters.

4. The method according to claim 1, characterized in that The cockpit setting parameters include cockpit atmosphere light setting parameters, volume sound effect setting parameters and in-vehicle environment setting parameters, and adjusting the cockpit settings corresponding to the vehicle according to the cockpit setting parameters includes: Controlling the cabin atmosphere light corresponding to the vehicle according to the cabin atmosphere light setting parameters; Controlling the volume sound effect corresponding to the vehicle according to the volume sound effect setting parameters; The interior environment of the vehicle is controlled according to the interior environment setting parameters.

5. The method according to claim 1, characterized in that The training steps of the cockpit setting model include: Acquire vehicle state training data, wherein the vehicle state training data is associated with a corresponding cockpit setting parameter label; Inputting the vehicle state training data into an untrained initial cockpit setting model, performing feature extraction on the vehicle state training data through the initial cockpit setting model, and obtaining corresponding cockpit setting training parameters; A training loss value is calculated according to the cockpit setting training parameter and the cockpit setting parameter label; When the training loss value reaches the training convergence condition, a trained cockpit setting model is obtained; When the training loss value does not reach the training convergence condition, the model parameters of the initial cockpit setting model are adjusted, and the step of obtaining vehicle state training data is returned to until the training loss value reaches the training convergence condition to obtain a trained cockpit setting model.

6. The method according to claim 5, characterized in that The vehicle state training data includes a plurality of different types of vehicle state sub-data, the initial cockpit setting model includes a plurality of different state networks, and the vehicle state training data is input into an untrained initial cockpit setting model, and features of the vehicle state training data are extracted by the initial cockpit setting model to obtain corresponding cockpit setting training parameters, including: Inputting each of the vehicle state sub-data into a corresponding state network in the initial cockpit setting model, and extracting features from the corresponding vehicle state sub-data through each of the state networks to obtain corresponding state features; The state features are fused to obtain corresponding cockpit setting training parameters.

7. The method according to claim 5, characterized in that After the vehicle state training data is obtained, the method further includes: Performing data cleaning on the vehicle state training data to obtain cleaned vehicle state training data; The cleaned vehicle state training data is normalized to obtain processed vehicle state training data.

8. An intelligent cockpit control device, characterized in that: The device comprises: An acquisition module, used to acquire vehicle status data corresponding to the vehicle; An input module, used for inputting the vehicle state data into a cockpit setting model, performing feature extraction on the vehicle state data through the cockpit setting model, and obtaining corresponding cockpit setting parameters; An adjustment module is used to adjust the cockpit settings corresponding to the vehicle according to the cockpit setting parameters.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images