Vehicle control method, device and equipment and storage medium

By using data from vehicles and objects of use, using neural networks to identify control intentions and generate seat ventilation control instructions, automated and intelligent seat ventilation control is realized, solving the problem of manual adjustment inconvenience, and improving the ride experience and seats Adaptability of ventilation.

CN119058502APending Publication Date: 2024-12-03CHONGQING JINKANG NEW ENERGY VEHICLE CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411202627.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

It is inconvenient for passengers to manually adjust the seat ventilation function during the ride, especially when the driver is driving or unfamiliar with the vehicle, it is difficult for the driver to adjust the seat ventilation easily, which affects the ride experience.

Method used

By obtaining vehicle data and usage objects, using pre-trained neural networks to identify vehicle control intentions and generate seat ventilation control instructions, realize automated and intelligent seat ventilation control, and dynamically adjust seat ventilation parameters to meet the passengers' need.

Benefits of technology

It improves the intelligence and personalization of seat ventilation control, improves the riding experience of passengers, simplifies the use of seat ventilation functions, and adapts to different environments and passengers' preferences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119058502A_ABST
    Figure CN119058502A_ABST
Patent Text Reader

Abstract

The invention relates to a vehicle control method and device, equipment and a storage medium. The vehicle control method comprises the steps that vehicle data of a vehicle are obtained, and vehicle control operation prediction is conducted according to the vehicle data; when the prediction result indicates that the seat ventilation control operation is to be executed, object data of a current use object of the vehicle are obtained, and the object data comprise an object portrait used for reflecting seat ventilation preference; and generating a seat ventilation control instruction for the vehicle according to the vehicle data, the prediction result and the object data, and performing seat ventilation control on the vehicle according to the seat ventilation control instruction. By means of the method, the automatic and intelligent control process of ventilation of the vehicle seat can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a vehicle control method, device, equipment and storage medium. Background Art

[0002] If passengers want to ventilate their seats during the ride, they need to turn on the seat ventilation function. Generally speaking, the driver can start the seat ventilation by pressing the seat ventilation switch. The seat ventilation function usually has different gear settings, and the appropriate gear can be manually selected according to personal comfort needs.

[0003] However, this method of manually adjusting seat ventilation reduces the riding experience of relevant passengers in some scenarios, for example, when the driver is not convenient to manually adjust the switch while driving or the driver is not familiar with the vehicle and does not know how to adjust the seat ventilation. Summary of the invention

[0004] The embodiments of the present application provide a vehicle control method, apparatus, computer equipment and storage medium, which can realize automatic and intelligent control of vehicle seat ventilation and enhance the user's riding experience.

[0005] According to a first aspect of an embodiment of the present application, a vehicle control method is provided, the method comprising: acquiring vehicle data of the vehicle, and predicting vehicle control operations based on the vehicle data; when the prediction result indicates that a seat ventilation control operation is to be performed, acquiring object data of a current user of the vehicle, wherein the object data includes an object portrait for reflecting a seat ventilation preference; generating a seat ventilation control instruction for the vehicle based on the vehicle data, the prediction result, and the object data, and performing seat ventilation control on the vehicle based on the seat ventilation control instruction.

[0006] In combination with the first aspect, in a first possible implementation manner of the first aspect, the vehicle data includes at least one of the following: outside vehicle temperature data, inside vehicle temperature data, meteorological data of the area where the vehicle is located, voice data of the user, and status data of the user; the object data also includes at least one of the following: a first riding record and a second riding record; the first riding record includes an operation record of using the object to adjust the temperature inside the vehicle during the current riding process and / or a voice record of using the object to adjust the temperature inside the vehicle during the current riding process, and the operation record of adjusting the temperature inside the vehicle does not include an operation record of manually adjusting seat ventilation; the second riding record includes an operation record of each time the object manually adjusted the seat ventilation during the historical riding process.

[0007] In combination with the first possible implementation mode of the first aspect, in the first possible implementation mode of the first aspect, predicting vehicle control operations based on vehicle data includes: inputting the vehicle data into a first neural network of a pre-trained vehicle control model; using the first neural network to identify vehicle control intentions on the vehicle data to obtain intention recognition results; the intention recognition results indicate control operations to be performed on the vehicle; and determining the intention recognition results as prediction results.

[0008] In combination with the first possible implementation of the first aspect, in a third possible implementation of the first aspect, seat ventilation control instructions for the vehicle are generated based on the vehicle data, prediction results, and object data, including: constructing a vehicle control instruction prompt text based on the vehicle data, prediction results, and object data; inputting the vehicle control instruction prompt text into a second neural network of a vehicle control model, wherein the second neural network and the first neural network are not the same neural network; and using the second neural network to perform vehicle control instruction prediction on the vehicle control instruction prompt text to obtain seat ventilation control instructions for the vehicle.

[0009] In combination with the second possible implementation or the third possible implementation of the first aspect, in a fourth possible implementation of the first aspect, after controlling the seat ventilation of the vehicle according to the seat ventilation control instruction, the method also includes: obtaining a third riding record of the user; the third riding record includes at least one of the following: an operation record of the user manually adjusting the seat ventilation during this riding process and / or a voice record of the user reflecting the seat ventilation status during this riding process; calculating the instruction prediction error of the seat ventilation control instruction according to the third riding record; and updating the vehicle control model using a back propagation algorithm based on the instruction prediction error.

[0010] In combination with the first aspect, in a fifth possible implementation manner of the first aspect, after controlling the seat ventilation of the vehicle according to the seat ventilation control instruction, the method also includes: obtaining a seat ventilation adjustment strategy corresponding to the user, the seat ventilation adjustment strategy is determined according to the seat ventilation adjustment habits of the user; dynamically adjusting the seat ventilation of the vehicle according to the relationship between the seat ventilation parameters indicated by the seat ventilation adjustment strategy and the seat ventilation time.

[0011] In combination with the first aspect, in a sixth possible implementation of the first aspect, after acquiring vehicle data of the vehicle, predicting vehicle control operations based on the vehicle data, and before obtaining the prediction results, it also includes: determining whether the vehicle data meets the trigger conditions for vehicle control operation prediction; when it is detected that the vehicle data meets the trigger conditions, triggering the step of predicting vehicle control operations based on the vehicle data to obtain the prediction results.

[0012] According to a second aspect of an embodiment of the present application, a vehicle control device is provided, which includes: an acquisition module for acquiring vehicle data of a vehicle; a processing module for predicting vehicle control operations based on the vehicle data; the acquisition module is also used to acquire object data of a current user of the vehicle when a prediction result indicates that a seat ventilation control operation is to be performed, wherein the object data includes an object portrait that reflects a seat ventilation preference; the processing module is also used to generate a seat ventilation control instruction for the vehicle based on the vehicle data, the prediction result, and the object data, and perform seat ventilation control on the vehicle based on the seat ventilation control instruction.

[0013] According to a third aspect of an embodiment of the present application, a device is provided, comprising a processor and a memory, wherein the memory stores programs or instructions, and when the programs or instructions are executed by the processor, the aforementioned vehicle control method is implemented.

[0014] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a program or an instruction. When the program or the instruction is executed on a device, the device executes the aforementioned vehicle control method.

[0015] In summary, the control operations to be performed on the vehicle are predicted through vehicle data, and when the seat ventilation operation is to be performed on the vehicle, the seat ventilation control instructions are generated by combining the vehicle data, the prediction results, and the object data, thereby realizing the automation and intelligence of the vehicle seat ventilation control process, making the use of the seat ventilation function more convenient and effectively improving the riding experience of the passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of a vehicle control process in one embodiment;

[0017] Figure 2 A schematic flow chart of a vehicle control method in one embodiment;

[0018] Figure 3 is a flow chart of a vehicle control method in another embodiment;

[0019] Figure 4 is a schematic structural diagram of a vehicle control device in one embodiment;

[0020] Figure 5 Schematic diagram of the structure of a device in one embodiment. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is described 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.

[0022] It should be noted that the diagram provided in the present embodiment only illustrates the basic concept of the present invention in a schematic manner, so the diagram only shows the components related to the present invention rather than drawing according to the number, shape and size of the components during actual implementation. The type, quantity and ratio of each component during actual implementation can be a random change, and the component layout type may also be more complicated. The structure, ratio, size, etc. illustrated in the drawings of the present specification are only used to match the content disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions that the present invention can implement, so they have no technical substantive significance. Any modification of the structure, change of the proportional relationship or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the effect that the present invention can produce and the purpose that can be achieved. At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of narration, and are not used to limit the scope of the present invention. The change or adjustment of its relative relationship should also be regarded as the scope of the present invention without substantially changing the technical content.

[0023] The present application provides a vehicle control method, which can realize automatic and intelligent control of vehicle seat ventilation and improve the riding experience of passengers. The vehicle control method can be applied to devices such as servers or vehicles. The server can be a single server or a server cluster. The vehicle can be an unmanned vehicle or a manned vehicle. In some embodiments, the vehicle control method can also be applied to an electronic device or system installed in the vehicle for executing the vehicle control method.

[0024] Specifically, the vehicle control method comprises: obtaining vehicle data of the vehicle; predicting vehicle control operations according to the vehicle data to obtain prediction results. The prediction results indicate the control operations to be performed on the vehicle. When the prediction results indicate that the seat ventilation control operations are to be performed on the vehicle, the object data of the current user of the vehicle is obtained. According to the vehicle data, the prediction results, and the object data, a seat ventilation control instruction for the vehicle is generated for controlling the seat ventilation of the vehicle. The vehicle control solution significantly improves the intelligence and personalization level of seat ventilation control, can better meet the actual needs of passengers, and improves the passenger's experience of using the vehicle.

[0025] In some embodiments, the vehicle control method may involve Figure 1 One or more of the following technologies. Figure 1 The various techniques shown are described below:

[0026] Multi-mode perception: Collect corresponding types of data through sensors corresponding to different types of data to obtain vehicle data.

[0027] Data recognition: Use a large model to recognize vehicle data and obtain recognition results as prediction results about vehicle control operations. The large model can be a large language model. For example, it can be the vehicle control model mentioned in this article. Specifically, the large model can be used to recognize vehicle control intentions based on vehicle data, and obtain intention recognition results as prediction results. Using a large model for intention recognition can more accurately understand the needs of passengers and is no longer limited to simple preset condition control.

[0028] Data supplement: Obtain object data for generating seat ventilation control instructions.

[0029] Prompt enhancement: Construct vehicle control instruction prompt text based on vehicle data, prediction results, and object data. The use of vehicle control instruction prompt text can be used to guide large models to generate instructions that better meet requirements. In some embodiments, during the stage of constructing vehicle control instruction prompt text, function call technology can be used to construct vehicle control instruction prompt text based on vehicle data, prediction results, and object data. The function call technology can call specific functions or modules to process complex logic and calculations. The language expression of the vehicle control instruction prompt text generated using this technology is more standardized.

[0030] Task planning: By analyzing the vehicle control instruction prompt text, the vehicle control instruction is obtained. Specifically, the large model can be used to perform the analysis task to obtain the vehicle control instruction. Specifically, the large model can be used to analyze the vehicle control instruction prompt text to obtain the vehicle control instruction.

[0031] Tool usage: Transmit vehicle control instructions to the cockpit domain controller (CDC) through a specific communication protocol. The cockpit domain controller can be an intelligent cockpit domain controller. In some embodiments, the target vehicle control interface can also be called to transmit seat ventilation control instructions to the cockpit domain controller. Among them, the target vehicle control interface is a control interface used by the cockpit domain controller to receive seat ventilation instructions and other instructions. Depending on actual needs, the target vehicle control interface can also realize some other functions, which will not be repeated here.

[0032] Instruction issuance: The cockpit domain controller controls the seat ventilation of the vehicle according to the seat ventilation control instructions. Specifically, the intelligent cockpit domain controller can issue the seat ventilation control instructions to the seat adjustment execution device, so that the seat adjustment execution device can use the seat ventilation instructions to control the seat ventilation. It should be noted that the embodiment of the present application can quickly and accurately generate and use seat ventilation control instructions through advanced technical architecture and algorithms, and adjust the seat ventilation status in time. The use of the embodiment of the present application significantly improves the effect of seat ventilation control and brings a more comfortable riding experience to passengers.

[0033] The above vehicle control method is briefly described below in combination with actual application scenarios.

[0034] In the actual application scenario, suppose the temperature inside the car is 32°C, and the driver says: "It's a bit stuffy inside the car, and the ventilation inside the car needs to be strengthened." The big model is used to accurately analyze the control intention of the vehicle based on the vehicle data (the temperature data inside the car and the driver's voice data), so as to determine that the control operation to be performed on the vehicle is the seat ventilation operation. Then, the big model can generate accurate vehicle control instructions based on data such as the driver's portrait. The vehicle control instructions here are seat ventilation control instructions. Then, the vehicle control instructions are sent to the cockpit domain controller to enhance the seat ventilation intensity.

[0035] In some application scenarios, after the vehicle seat ventilation is controlled, for example, the driver gives voice feedback that "the ventilation is too weak", the large model can adjust the network parameters of the large model through the back propagation algorithm based on the feedback voice data to optimize the large model. Here, the driver's feedback information on the seat ventilation can be recorded within 1 hour, and the seat ventilation intensity can be adjusted based on this, and then the large model can be optimized by continuously learning the user's habits based on the feedback information. The feedback information can be, for example, the operation of manually adjusting the seat ventilation level, or voice reflecting the seat ventilation status.

[0036] It should be noted that in a complex environment, the temperature inside the car fluctuates frequently and the feedback from passengers is diverse. The large model relies on a powerful neural network architecture and fine-tuning optimization to accurately understand the passengers' riding needs and generate appropriate vehicle control instructions. At the same time, it can also use agent technology to ensure its own stable operation and provide passengers with a comfortable ventilation experience.

[0037] Next, combine Figure 2 and Figure 3 The above-mentioned vehicle control method is specifically described in the embodiment of FIG.

[0038] See also Figure 2, is a flow chart of a vehicle control method provided in an embodiment of the present application. The method can be executed by a device. The method is specifically described below by taking the device as a vehicle as an example. Specifically, the method includes the following steps:

[0039] S201. Obtain vehicle data of a vehicle.

[0040] The vehicle may obtain vehicle data. Specifically, the vehicle may continuously collect vehicle data. Alternatively, the vehicle may collect vehicle data at a fixed time. Alternatively, the vehicle may periodically read vehicle data that has been collected within a target period. For example, the vehicle may read vehicle data that has been collected within the past minute from the area storing vehicle data at intervals of 1 minute.

[0041] The vehicle data referred to herein includes at least one of the following: vehicle exterior temperature data and vehicle interior temperature data. The vehicle exterior temperature data may be, for example, a vehicle exterior temperature value. The vehicle exterior temperature value may be obtained through installed weather software or the like, or may be collected through a temperature sensor disposed outside the vehicle. The vehicle interior temperature data may be, for example, a vehicle interior temperature value. The vehicle interior temperature value may be collected through a temperature sensor disposed inside the vehicle.

[0042] In some embodiments, the vehicle data may also include at least one of the following: weather data of the area where the vehicle is located, voice data of the user, and status data of the user. It should be noted that using more abundant vehicle data for vehicle control operation prediction and seat ventilation control command generation helps to generate more accurate prediction results and seat ventilation control commands.

[0043] The meteorological data includes at least one of season data and weather data. Season data may be data describing the current season, such as spring, summer, and autumn. Weather data may be data describing the current weather, such as sunny, rainy, and cloudy. In some embodiments, the meteorological data also includes abnormal weather warning information, such as yellow warning information for high temperature, orange warning information for high temperature, red warning information for high temperature, blue warning information for heavy rain, yellow warning information for heavy rain, orange warning information for heavy rain, and red warning information for heavy rain.

[0044] The user object refers to the passengers. For example, the user object may be the main driver, the co-driver, or the passengers in the back seat. It should be noted that, depending on the application scenario, the user object may be any one or more of all passengers, such as all passengers, or one or more specified passengers, such as the main driver and the co-driver.

[0045] Among them, the voice data can be collected by a voice collector such as a microphone installed inside the vehicle during the ride. Since the types of prediction results obtained based on different in-vehicle temperature data and / or outside vehicle temperature data may be different, the introduction of voice data plays an important role in the accurate prediction of vehicle control operations. Vehicle data containing voice data has a clearer direction for vehicle control operations, making the prediction results closer to actual operation requirements.

[0046] The state data includes at least one of data reflecting whether the user is in a commuting state and data reflecting whether the user is in a specified facial state. The specified facial state may be, for example, a sweating state or an overheating state. In some embodiments, the data on whether the user is in a commuting state may be obtained after analyzing whether the current location of the vehicle is a workplace or whether the destination of the vehicle is a workplace. The data on whether the user is in a specified facial state may be determined by analyzing the facial features of a portrait image of the user after the user has taken the portrait image through a camera.

[0047] In some embodiments, the vehicle can obtain vehicle data when there is a user inside the vehicle to avoid performing seat ventilation control operations when no one is in the vehicle, thereby reducing the vehicle's energy consumption. Whether there is a user in the vehicle can be determined by whether the user's face image is detected, or by whether a prompt message indicating that the passenger has been successfully received is received and whether a prompt message indicating the end of the trip is received.

[0048] S202: Predict vehicle control operations based on vehicle data.

[0049] The vehicle may generate a prediction result about a vehicle control operation based on the vehicle data, wherein the prediction result indicates a control operation to be performed on the vehicle, and the prediction result may be, for example, seat ventilation.

[0050] In some embodiments, the vehicle may create a first correspondence between the vehicle data and the vehicle control operation before executing step S202, so that in step S202, the vehicle control operation corresponding to the vehicle data may be determined according to the first correspondence as a prediction result. The first correspondence refers to the correspondence between the vehicle data and the vehicle control operation.

[0051] In some embodiments, the vehicle may determine whether the vehicle data meets the triggering condition of the vehicle control operation prediction, and after detecting that the vehicle data meets the triggering condition, execute step S202. Considering that in the case where the vehicle frequently collects vehicle data, if the vehicle control operation prediction is performed once each time the vehicle data is acquired, it will bring a great computing burden to the vehicle. Therefore, here, the vehicle control operation prediction is performed after detecting that the vehicle data meets the triggering condition, which can reduce the waste of computing resources caused by excessively frequent vehicle control operation prediction.

[0052] Specifically, when the vehicle data includes the outside temperature data, the trigger condition may be that the outside temperature data is detected to be in the first temperature range. For example, the first temperature range may be a range greater than or equal to 20 degrees. When the outside temperature data is greater than or equal to 20 degrees, it indicates that the user may have seat ventilation and other needs. When the vehicle data includes the in-car temperature data, the trigger condition may be that the in-car temperature data is detected to be in the second temperature range. For example, the second temperature range may be a range greater than or equal to 20 degrees. When the in-car temperature data is greater than or equal to 20 degrees, it indicates that the user may have seat ventilation needs. It should be noted that the first temperature range may be the same as the second temperature range, or may be different, and may be set in combination with actual conditions. When the vehicle data includes the voice data of the user, the trigger condition may be that the voice data reflects that the current temperature in the car is high. Voice data reflecting the current high temperature in the car may be, for example, "It's so hot in the car", "It's too hot, why doesn't this air conditioner work". The voice reflects that the current temperature in the car is high, indicating that the user may have seat ventilation needs.

[0053] S203: When the prediction result indicates that a seat ventilation control operation is to be performed on the vehicle, obtain object data of a current user of the vehicle.

[0054] When the prediction result indicates that a seat ventilation control operation is to be performed on the vehicle, the vehicle may obtain the object data of the current user of the vehicle stored locally or query the object data of the current user of the vehicle from a designated server.

[0055] Among them, the object data includes an object portrait. The object portrait reflects the seat ventilation preference of the user. In some embodiments, the object portrait may include seat ventilation parameter preference data. The seat ventilation parameter preference data is, for example, a preferred seat ventilation level or a score for each seat ventilation level provided by the vehicle, where a higher score indicates a higher degree of preference for the seat ventilation level. It should be noted that, depending on the vehicle, the seat ventilation parameters may also be other seat ventilation parameters in addition to the seat ventilation level, which is not limited in the embodiments of the present application.

[0056] In some embodiments, the object data also includes at least one of the following: a first ride record and a second ride record. The first ride record includes an operation record of using the object to adjust the temperature inside the vehicle during this ride. The operation record of using the object to adjust the temperature inside the vehicle includes various operations of using the object to adjust the temperature inside the vehicle, and the operation of adjusting the temperature inside the vehicle may be, for example, an operation of opening a window for ventilation or an operation of turning on the air conditioner. Among them, the operation record of adjusting the temperature inside the vehicle does not include an operation record of manually adjusting seat ventilation. The first ride record can be used to analyze seat ventilation requirements.

[0057] In some embodiments, the first ride record may also include a voice record of the user adjusting the temperature in the car. The voice record of adjusting the temperature in the car may include a voice instructing the vehicle to adjust the temperature in the car. The voice instructing the vehicle to adjust the temperature in the car may be, for example, a voice instructing the vehicle to open the window for ventilation, a voice instructing the vehicle to turn on the air conditioner, a voice instructing the vehicle to increase the seat ventilation intensity, and a voice instructing the vehicle that the seat ventilation intensity is too weak. The second ride record includes an operation record of each manual adjustment of the seat ventilation by the user during the historical ride process. The historical ride process may be, for example, one or more ride processes before the current ride process, or may be a specified number of ride processes closest to the user to the current ride process (such as the last five ride processes), or may be all ride processes of the user before the current ride. In some embodiments, the historical ride process may include not only the ride process before the current ride process, but also the current ride process.

[0058] In some embodiments, the method for obtaining the current user of the vehicle may be: when the user's riding method is unlocking the vehicle, the first object identifier of the user is obtained according to the unlocking result, and the object portrait of the user is queried according to the first object identifier. Among them, unlocking the vehicle includes but is not limited to scanning a code to ride or riding through a virtual key. Among them, the first object identifier may be the name, mobile phone number or ID number of the user, which is information that uniquely identifies the user. Alternatively, the method for obtaining the current user of the vehicle may be: turning on the camera set inside the vehicle, performing face recognition on the face image of the user captured by the camera, and obtaining the recognition result, the recognition result carries the second object identifier of the user, and the object portrait of the user is queried according to the second object identifier. The second object identifier may be the name, mobile phone number or ID number of the user, which is information that uniquely identifies the user. It should be noted that the first object identifier and the second object identifier may be the same or different, and may be set in combination with actual conditions.

[0059] S204: Generate a seat ventilation control instruction for the vehicle according to the vehicle data, the prediction result, and the object data, and perform seat ventilation control on the vehicle according to the seat ventilation control instruction.

[0060] The vehicle can analyze vehicle data, prediction results, and object data to obtain seat ventilation instructions for the vehicle. This process introduces object data to generate seat ventilation instructions, making the seat ventilation instructions more personalized and targeted. Combining vehicle data, prediction results, and object data also makes the seat ventilation instructions more comprehensive and accurate, which can greatly improve the riding experience of passengers.

[0061] Among them, the seat ventilation control instruction referred to is an instruction for controlling the seat ventilation of the vehicle. The seat ventilation instruction may carry seat ventilation parameters to be adjusted. The seat ventilation parameters may be seat ventilation levels. The seat ventilation level may be level 1, level 2, level 3, etc., or may be low-end, mid-range, high-end, etc., depending on the application scenario. Here, the higher the seat ventilation level, the more significant the ventilation effect. It should be noted that, depending on the vehicle model, the seat ventilation parameters may also adopt other parameters besides the seat ventilation level, which are not listed one by one in the embodiments of the present application. In some embodiments, the seat ventilation control instruction may also carry the seat identification to be adjusted, and the seat identification may be information that uniquely identifies the seat inside the vehicle, such as the seat number or the position information of the seat inside the vehicle. Among them, the seat identification may realize targeted control of seat ventilation.

[0062] In some embodiments, before executing step S204, the vehicle may create a second correspondence between the vehicle data, the prediction result, the object data, and the seat ventilation command, so that in step S204, the seat ventilation control command corresponding to the vehicle data, the prediction result, and the object data may be determined according to the second correspondence as the seat ventilation command for the vehicle. The second correspondence refers to the correspondence between the vehicle data, the prediction result, the object data, and the seat ventilation command.

[0063] In some embodiments, after the vehicle generates a seat ventilation control instruction for the vehicle, the vehicle performs seat ventilation control according to the seat ventilation instruction. Here, it should be noted that for the server, after generating the seat ventilation control instruction, the seat ventilation instruction will be sent to the vehicle, and then the vehicle performs seat ventilation control according to the seat ventilation instruction.

[0064] In some embodiments, when there is only one user, the embodiment of the present application can realize seat ventilation control for the seat where the user is located based on the object portrait of the user, and can also realize seat ventilation control for the seats where other users are located in the vehicle based on the object portrait of the user, so as to achieve the purpose of unified seat ventilation control. When there are multiple users, obtaining the object portrait of the user can be understood as obtaining the respective object portraits of the multiple users, so as to achieve the purpose of controlling the seat ventilation for the seats where the respective users are located based on the respective object portraits.

[0065] exist Figure 2 In the embodiment shown, the vehicle can determine the seat ventilation control operation to be performed on the vehicle by analyzing the vehicle data, and then control the seat ventilation of the vehicle in combination with the object data of the object currently using the vehicle, thereby realizing the automation process of the vehicle seat ventilation control. The introduction of object data makes the vehicle seat ventilation more flexible and targeted, which greatly improves the riding experience of the passengers.

[0066] See also Figure 3 , is a flow chart of another vehicle control method provided in an embodiment of the present application. The method can be executed by a device. The method is specifically described below by taking the device as a vehicle as an example. Specifically, the method includes the following steps:

[0067] S301. Obtain vehicle data of a vehicle.

[0068] Step S301 can be found in Figure 2 Step S201 in the embodiment will not be described in detail in this embodiment of the application.

[0069] S302, inputting vehicle data into a first neural network of a pre-trained vehicle control model, and using the first neural network to perform vehicle control intent recognition on the vehicle data to obtain an intent recognition result.

[0070] S303: Determine the intention recognition result as the prediction result.

[0071] In step S301 to step S303, the vehicle inputs the vehicle data into the vehicle control model for processing to obtain the intention recognition result as the prediction result. The intention recognition result indicates the control operation to be performed on the vehicle. Specifically, the vehicle control model includes a first neural network, and the vehicle can input the vehicle data into the vehicle control model, and then use the first neural network to perform intent recognition on the vehicle data to obtain the intention recognition result, and then use the intention recognition result as the prediction result. The above method can infer accurate prediction results based on vehicle data.

[0072] In some embodiments, the first neural network includes an input layer, a hidden layer, and an output layer. The input layer is used to receive vehicle data. The hidden layer is used to extract feature vectors of vehicle data. The output layer is used to obtain intent recognition results based on feature vector processing. It should be noted that, depending on different actual application scenarios, the first neural network can be one or more.

[0073] In some embodiments, since the vehicle data includes not only text-type data (such as in-vehicle temperature data) but also audio-type data (such as voice data of the user object) and other types of data, the vehicle data can be multimodally processed by the first neural network to obtain the intention recognition result. For example, the pattern recognition methods corresponding to the various types of data in the vehicle data can be determined, and then the pattern recognition methods corresponding to the various types of data can be used to extract the feature vectors of the data of that type, and then the feature vectors of the various types of data are fused to obtain the fused feature vector, and then the fused feature vector is classified to obtain the intention recognition result.

[0074] S304: When the prediction result indicates that a seat ventilation control operation is to be performed on the vehicle, obtain object data of a current user of the vehicle.

[0075] Step S304 can be found in Figure 2 Step S203 in the embodiment will not be described in detail in this embodiment of the application.

[0076] S305: Generate a seat ventilation control instruction for the vehicle according to the vehicle data, the prediction result, and the object data, and perform seat ventilation control on the vehicle according to the seat ventilation control instruction.

[0077] In step S305, the vehicle can input the vehicle data into the vehicle control model for processing to obtain the seat ventilation control instructions for the vehicle. In some embodiments, the vehicle control model includes a second neural network, and step S305 can specifically be to first construct a vehicle control instruction prompt text according to the vehicle data, the prediction result, and the object data, and then input the vehicle control instruction prompt text into the vehicle control model, so as to use the second neural network in the vehicle control model to predict the vehicle control instruction prompt text and obtain the seat ventilation control instructions for the vehicle. The introduction of the vehicle control instruction prompt text in this process makes the input data of the second neural network more professional and standardized, thereby making the seat ventilation control instructions more accurate.

[0078] Among them, the second neural network referred to is not the same neural network as the first neural network. The vehicle control instruction prompt text referred to is a text used to instruct the vehicle control model to generate seat control instructions. The vehicle control instruction prompt text may include vehicle data, prediction results, object data, or data converted from vehicle data, prediction results, and object data for easy understanding and processing by the second neural network. In some embodiments, the vehicle control instruction prompt text may also include role information and command information associated with seat ventilation control. For example, the role information may be a vehicle control expert or a seat ventilation control expert. The command information may be please generate seat ventilation control instructions. The vehicle control instruction prompt text is: Assuming that you are an expert responsible for vehicle control, you will use vehicle data for intelligent control of seat ventilation, please generate seat ventilation control instructions. It should be noted that the above is only an example of a vehicle control prompt text, and the vehicle control prompt text may also be in other forms.

[0079] In some embodiments, the vehicle control model includes a third neural network, and step S305 specifically includes the vehicle inputting vehicle data, prediction results, and object data into the vehicle control model, and then using the third neural network to predict vehicle control instructions for the vehicle data, prediction results, and object data to obtain seat ventilation control instructions for the vehicle. Among them, the first neural network, the second neural network, and the third neural network are not the same neural network. Compared with the previous method of generating seat ventilation control instructions based on the second neural network, the method of generating seat ventilation control instructions based on the third neural network here is simpler in terms of logic of generating seat ventilation control instructions, and the speed of generating seat ventilation control instructions is improved.

[0080] In some embodiments, the vehicle may also optimize the vehicle control model by the following method: the vehicle obtains the third riding record of the user, and then calculates the instruction prediction error of the seat ventilation control instruction according to the third riding record, thereby updating the vehicle control model according to the instruction prediction error by using the back propagation algorithm. This process optimizes the vehicle control model through the instruction prediction error and the back propagation algorithm, and greatly improves the prediction accuracy of the vehicle control model. Among them, the third riding record includes at least one of the following: the operation record of the user manually adjusting the seat ventilation during this riding process and / or the voice record of the user reflecting the seat ventilation status during this riding process. The operation record of manually adjusting the seat ventilation may include, for example, the seat ventilation parameters manually adjusted. For example, after the user manually adjusts the seat ventilation level from level 3 to level 4, the operation record of manually adjusting the seat ventilation includes the seat ventilation level 4. In some embodiments, the operation record of manually adjusting the seat ventilation may also include: the in-vehicle temperature data after the seat ventilation is manually adjusted. In some embodiments, the operation record of manually adjusting the seat ventilation may also include the in-vehicle temperature data and the seat ventilation parameters before the seat ventilation is manually adjusted. The data in the third riding record is recorded after the seat ventilation of the vehicle is controlled by the seat ventilation control command. For example, the data in the third riding record is recorded within one hour after the seat ventilation of the vehicle is controlled by the seat ventilation control command. The voice record reflecting the seat ventilation status may be, for example, a voice record reflecting that the seat ventilation intensity is low or high.

[0081] In some embodiments, the vehicle may calculate the command prediction error of the seat ventilation control command based on the third ride record in the following manner: the vehicle obtains the standard seat ventilation command corresponding to the third ride record, and then determines the deviation between the standard seat ventilation command and the generated seat ventilation control command as the command prediction error of the generated seat ventilation control command. For example, the use object is the primary driver, and the vehicle may obtain the third ride record after adjusting the seat ventilation level of the primary driver to level 3 using the generated seat ventilation control command. Assume that the third ride record includes a voice record of the primary driver reflecting that "the seat ventilation intensity is too low" and / or includes an operation record of the primary driver manually adjusting the seat ventilation level from level 3 to level 4. The vehicle may obtain the standard seat ventilation control command corresponding to the seat ventilation level 4 based on the third operation record, and then calculate the deviation between the standard seat ventilation control command and the generated seat ventilation command as the command prediction error of the generated seat ventilation control command.

[0082] In some embodiments, the third ride record can be used not only to optimize the vehicle control model, but also to update the object portrait. In some embodiments, the vehicle uses the third ride record to update the object portrait, which can be determined according to the third ride record. The target seat ventilation parameters preferred by the user in this ride process are updated using the target seat ventilation parameters. In some embodiments, the vehicle uses the target seat ventilation parameters to update the object portrait in a manner that accumulates the frequency of use of the target seat ventilation parameters or increases the score of the target seat ventilation parameters. If the target seat ventilation parameters are the most frequently used among all seat ventilation parameters or the target seat ventilation parameters are the highest scored among all seat ventilation parameters, the original seat ventilation parameters in the seat ventilation preference data are updated to the target seat ventilation parameters. For example, if it is determined according to the third ride record that the seat ventilation level preferred by the user in this ride is level 4, the frequency of use of seat ventilation level 4 can be accumulated or the score of seat ventilation level 4 can be increased. When seat ventilation level 4 is the most frequently used seat ventilation level among all seat ventilation levels or the highest score for seat ventilation level 4 is the highest score for seat ventilation level among all seat ventilation levels, the original seat ventilation level in the seat ventilation parameter preference data is updated to seat ventilation level 4. In some embodiments, after the vehicle updates the object portrait using the third ride record, the updated object portrait can be used in the subsequent generation process of seat ventilation control instructions.

[0083] In some embodiments, after the seat ventilation of the vehicle is controlled by the seat ventilation control instruction, the seat ventilation parameters of the vehicle can also be dynamically adjusted according to the seat ventilation adjustment habits of the user. Specifically, the vehicle can determine the seat ventilation adjustment strategy for the user, and dynamically adjust the seat ventilation of the vehicle according to the relationship between the seat ventilation parameters indicated by the seat ventilation adjustment strategy and the seat ventilation time. Among them, the seat ventilation adjustment strategy is preset. Alternatively, the seat ventilation adjustment strategy is determined based on the seat ventilation adjustment habits of the user. In some embodiments, the seat ventilation adjustment habits of the user can be generated based on the operation records of the user manually adjusting the seat ventilation within the target time range, and / or can be generated based on the operation records of the vehicle automatically adjusting the seat ventilation within the target time range. Among them, the target time range may be the same time range as the specified time range mentioned above, or it may not be the same time range.

[0084] For example, if the user is a driver, the vehicle can adjust the seat ventilation level of the seat to level 4 according to the seat ventilation instruction, and then the vehicle can obtain the corresponding seat ventilation adjustment strategy for the driver. The vehicle dynamically adjusts the seat ventilation of the vehicle according to the relationship between the seat ventilation parameters indicated by the seat ventilation adjustment strategy and the seat ventilation time. Suppose the seat ventilation adjustment strategy indicates to keep the seat ventilation level at level 4 for half an hour, and then keep the seat ventilation level at level 3. Then, the vehicle can switch the seat ventilation level to level 3 after keeping the seat ventilation level at level 4 for half an hour, and keep the seat ventilation level at level 3 thereafter.

[0085] exist Figure 3 In the embodiment shown, the vehicle can introduce a large model to realize the prediction of vehicle control operations and the generation of seat ventilation control instructions. Since slight differences in data may also cause the vehicle to perform different vehicle control operations, the introduction of a large model can realize the refined prediction of vehicle control operations and seat ventilation control instructions instead of simply judging according to the configuration conditions, thereby making the vehicle's seat ventilation control more accurate.

[0086] It should be understood that although Figure 1-Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-Figure 3 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0087] See also Figure 4 , is a schematic diagram of the structure of a vehicle control device provided in an embodiment of the present application. The device can be set in a device. The device includes an acquisition module 401 and a processing module 402. Specifically:

[0088] The acquisition module 401 is used to acquire vehicle data of the vehicle; the processing module 402 is used to predict vehicle control operations based on the vehicle data; the acquisition module 401 is also used to acquire object data of the current user of the vehicle when the prediction result indicates that a seat ventilation control operation is to be performed, wherein the object data includes an object portrait reflecting seat ventilation preferences; the processing module 402 is also used to generate seat ventilation control instructions for the vehicle based on the vehicle data, the prediction result, and the object data, and perform seat ventilation control on the vehicle based on the seat ventilation control instructions.

[0089] In an optional embodiment, the vehicle data includes at least one of the following: outside temperature data, inside temperature data, meteorological data of the area where the vehicle is located, voice data of the user, and status data of the user; the object data also includes at least one of the following: a first ride record and a second ride record; the first ride record includes an operation record of using the object to adjust the temperature inside the vehicle during the current ride and / or a voice record of using the object to adjust the temperature inside the vehicle during the current ride, and the operation record of adjusting the temperature inside the vehicle does not include an operation record of manually adjusting seat ventilation; the second ride record includes an operation record of each time the object manually adjusted the seat ventilation during the historical ride.

[0090] In an optional embodiment, the processing module 402 predicts vehicle control operations based on vehicle data, specifically by inputting the vehicle data into a first neural network of a pre-trained vehicle control model; using the first neural network to identify vehicle control intentions on the vehicle data to obtain intention recognition results; the intention recognition results indicate control operations to be performed on the vehicle; and determining the intention recognition results as prediction results.

[0091] In an optional implementation, the processing module 402 generates seat ventilation control instructions for the vehicle based on the vehicle data, prediction results, and object data, specifically constructing a vehicle control instruction prompt text based on the vehicle data, prediction results, and object data; inputting the vehicle control instruction prompt text into a second neural network of a vehicle control model, wherein the second neural network is not the same neural network as the first neural network; and using the second neural network to perform vehicle control instruction prediction on the vehicle control instruction prompt text to obtain seat ventilation control instructions for the vehicle.

[0092] In an optional embodiment, the acquisition module 401 is also used to obtain a third riding record of the user after the seat ventilation of the vehicle is controlled according to the seat ventilation control instruction; the third riding record includes at least one of the following: an operation record of the user manually adjusting the seat ventilation during this riding process and / or a voice record of the user reflecting the seat ventilation status during this riding process; calculating the instruction prediction error of the seat ventilation control instruction according to the third riding record; and updating the vehicle control model using a back propagation algorithm based on the instruction prediction error.

[0093] In an optional embodiment, after controlling the seat ventilation of the vehicle according to the seat ventilation control instruction, the processing module 402 obtains the seat ventilation adjustment strategy corresponding to the user, and the seat ventilation adjustment strategy is determined according to the seat ventilation adjustment habits of the user; according to the relationship between the seat ventilation parameters indicated by the seat ventilation adjustment strategy and the seat ventilation time, the vehicle is dynamically seated. Adjust the ventilation.

[0094] In an optional embodiment, the processing module 402 is also used to determine whether the vehicle data meets the triggering conditions for vehicle control operation prediction after acquiring the vehicle data of the vehicle and before obtaining the prediction results; when it is detected that the vehicle data meets the triggering conditions, the step of predicting the vehicle control operation based on the vehicle data and obtaining the prediction results is triggered.

[0095] exist Figure 4 In the embodiment shown, the vehicle control device can determine the seat ventilation control operation to be performed on the vehicle by analyzing the vehicle data, and then control the seat ventilation of the vehicle in combination with the object data of the current user of the vehicle and other data, thereby realizing an automated and intelligent process of vehicle seat ventilation control. The introduction of object data makes vehicle seat ventilation more flexible and targeted, which greatly improves the riding experience of passengers.

[0096] See also Figure 5 , is a schematic diagram of a device provided in an embodiment of the present application. The device may be a vehicle or a server. The device may include: a processor 501 and a memory 502. The processor 501 and the memory 502 include but are not limited to a bus (in Figure 5 The processor 501 is used to execute multiple instructions; the memory 502 stores programs or instructions, and when the programs or instructions are executed by the processor 501, the vehicle control method of the above embodiment is implemented.

[0097] Among them, the processor 501 can be an electronic control unit (Electronic Control Unit, ECU), a central processing unit (central processing unit, CPU), a general processor, a coprocessor, a digital signal processor (digital signal processor, DSP), an application-specific integrated circuit (application-specific integrated circuit, ASIC), a field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The processor 501 can also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of 5SP and a microprocessor, etc. In this embodiment, the processor 501 can use a single-chip microcomputer, and various control functions can be realized by programming the single-chip microcomputer. In the embodiment of the present application, the processor 501 is used to execute the functions of the acquisition module 401 and is also used to execute the functions of the processing module 402.

[0098] The memory 501 is used to provide a storage space in which programs or instructions and / or data can be stored. The memory 501 can be a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a portable read-only memory (CD-ROM), etc., or a combination of multiple thereof.

[0099] In a specific implementation, the processor 502 calls the program or instruction stored in the memory 1203 to perform the following operations: obtaining vehicle data of the vehicle, and predicting vehicle control operations based on the vehicle data; when the prediction result indicates that a seat ventilation control operation is to be performed, obtaining object data of the current user of the vehicle, wherein the object data includes an object portrait reflecting seat ventilation preferences; generating seat ventilation control instructions for the vehicle based on the vehicle data, the prediction result, and the object data, and performing seat ventilation control on the vehicle based on the seat ventilation control instructions.

[0100] In one possible implementation, the vehicle data includes at least one of the following: outside temperature data, inside temperature data, weather data of the area where the vehicle is located, voice data of the user, and status data of the user; the object data also includes at least one of the following: a first ride record and a second ride record; the first ride record includes an operation record of using the object to adjust the temperature inside the vehicle during the current ride and / or a voice record of using the object to adjust the temperature inside the vehicle during the current ride, and the operation record of adjusting the temperature inside the vehicle does not include an operation record of manually adjusting seat ventilation; the second ride record includes an operation record of each time the object was used to manually adjust the seat ventilation during historical rides.

[0101] In one possible implementation, the processor 502 is specifically used to input vehicle data into a first neural network of a pre-trained vehicle control model; use the first neural network to identify vehicle control intentions on the vehicle data to obtain intention recognition results; the intention recognition results indicate control operations to be performed on the vehicle; and determine the intention recognition results as prediction results.

[0102] In one possible implementation, the processor 502 is specifically used to construct a vehicle control instruction prompt text based on vehicle data, prediction results, and object data; input the vehicle control instruction prompt text into a second neural network of a vehicle control model, wherein the second neural network is not the same neural network as the first neural network; and use the second neural network to predict vehicle control instructions for the vehicle control instruction prompt text to obtain seat ventilation control instructions for the vehicle.

[0103] In one possible implementation, processor 502 is also used to obtain a third riding record of the user; the third riding record includes at least one of the following: an operation record of the user manually adjusting the seat ventilation during the current riding process and / or a voice record of the user reflecting the seat ventilation status during the current riding process; calculating the instruction prediction error of the seat ventilation control instruction based on the third riding record; and using a back propagation algorithm to update the vehicle control model based on the instruction prediction error.

[0104] In one possible implementation, the processor 502 is specifically used to obtain a seat ventilation adjustment strategy corresponding to the user according to a seat ventilation control instruction, where the seat ventilation adjustment strategy is determined based on the seat ventilation adjustment habits of the user; and dynamically adjust the seat ventilation of the vehicle according to the relationship between the seat ventilation parameters indicated by the seat ventilation adjustment strategy and the seat ventilation time.

[0105] In one possible implementation, the processor 502 is also used to determine whether the vehicle data meets the triggering conditions for vehicle control operation prediction; when it is detected that the vehicle data meets the triggering conditions, the step of predicting the vehicle control operation based on the vehicle data to obtain the prediction result is triggered.

[0106] In addition, the embodiment of the present application also provides a computer-readable storage medium, which is used to store programs or instructions. When the programs or instructions are executed on the device, the device executes the aforementioned vehicle control method. For technical details not disclosed in the embodiment of the computer-readable storage medium, please refer to the description of the embodiment of the method of the present application. In addition, the description of the beneficial effects of the same method in the embodiment of the present application can also refer to the description of the embodiment of the method of the present application, and will not be repeated here.

[0107] 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.

[0108] The above 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 vehicle control method, characterized in that: The vehicle control method comprises: Acquiring vehicle data of the vehicle and predicting vehicle control operations based on the vehicle data; When the prediction result indicates that the seat ventilation control operation is to be performed, obtaining object data of a current user of the vehicle, wherein the object data includes an object portrait for reflecting a seat ventilation preference; A seat ventilation control instruction for the vehicle is generated according to the vehicle data, the prediction result, and the object data, and seat ventilation control is performed on the vehicle according to the seat ventilation control instruction.

2. The method according to claim 1, characterized in that The vehicle data includes at least one of the following: vehicle exterior temperature data, vehicle interior temperature data, weather data of the area where the vehicle is located, voice data of the user, and status data of the user; The object data also includes at least one of the following: a first riding record and a second riding record; the first riding record includes the operation record of the user adjusting the temperature inside the vehicle during this riding process and / or the voice record of the user adjusting the temperature inside the vehicle during this riding process, and the operation record of adjusting the temperature inside the vehicle does not include the operation record of manually adjusting the seat ventilation; the second riding record includes the operation record of each time the user manually adjusted the seat ventilation during the historical riding process.

3. The method according to claim 2, characterized in that The predicting of the vehicle control operation according to the vehicle data comprises: Inputting the vehicle data into a first neural network of a pre-trained vehicle control model; Using the first neural network to perform vehicle control intention recognition on the vehicle data to obtain an intention recognition result; the intention recognition result indicates a control operation to be performed on the vehicle; The intention recognition result is determined as a prediction result.

4. The method according to any one of claim 2, characterized in that The generating, according to the vehicle data, the prediction result, and the object data, a seat ventilation control instruction for the vehicle comprises: Constructing a vehicle control instruction prompt text according to the vehicle data, the prediction result, and the object data; Inputting the vehicle control instruction prompt text into a second neural network of the vehicle control model, wherein the second neural network is not the same neural network as the first neural network; The second neural network is used to predict the vehicle control instruction prompt text to obtain a seat ventilation control instruction for the vehicle.

5. The method according to claim 3 or 4, characterized in that After controlling the seat ventilation of the vehicle according to the seat ventilation control instruction, the method further includes: Acquiring a third riding record of the user; the third riding record includes at least one of the following: an operation record of the user manually adjusting the seat ventilation during the current riding process and / or a voice record of the user reflecting the seat ventilation status during the current riding process; calculating a command prediction error of the seat ventilation control command according to the third riding record; According to the instruction prediction error, a back propagation algorithm is used to update the vehicle control model.

6. The method according to claim 1, characterized in that After controlling the seat ventilation of the vehicle according to the seat ventilation control instruction, the method further includes: Acquiring a seat ventilation adjustment strategy corresponding to the user, wherein the seat ventilation adjustment strategy is determined according to the seat ventilation adjustment habit of the user; The seat ventilation of the vehicle is dynamically adjusted according to the relationship between the seat ventilation parameter indicated by the seat ventilation adjustment strategy and the seat ventilation time.

7. The method according to claim 1, characterized in that After acquiring the vehicle data of the vehicle, and performing vehicle control operation prediction according to the vehicle data, before obtaining the prediction result, the method further includes: determining whether the vehicle data satisfies a trigger condition for vehicle control operation prediction; When it is detected that the vehicle data meets the trigger condition, the step of predicting the vehicle control operation according to the vehicle data to obtain a prediction result is triggered.

8. A vehicle control device, characterized in that: The device comprises: An acquisition module, used for acquiring vehicle data of a vehicle; A processing module, used for predicting vehicle control operations based on the vehicle data; The acquisition module is further used to acquire object data of a current user of the vehicle when the prediction result indicates that a seat ventilation control operation is to be performed, wherein the object data includes an object portrait for reflecting a seat ventilation preference; The processing module is further used to generate a seat ventilation control instruction for the vehicle according to the vehicle data, the prediction result, and the object data, and to perform seat ventilation control on the vehicle according to the seat ventilation control instruction.

9. A device, characterized in that: The device comprises a processor and a memory, wherein the memory stores a program or an instruction, and when the program or the instruction is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes the program or the instructions, and when the program or the instructions are executed on a device, the device is caused to perform the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Riding code recommendation method and device, equipment, storage medium and program product

    CN120011647A