Method, device, storage medium and electronic device for adjusting in-vehicle air quality

Abstract

The present invention discloses a method, device, storage medium and electronic device for adjusting the air quality inside a vehicle. Among them, the method includes: obtaining a target image associated with the target vehicle, where the target image is used to represent the environmental conditions where the target vehicle is currently located; identifying the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located; adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle. The present invention can be applied to the vehicle networking scenario and may also involve technologies such as wireless communication and image recognition. The present invention solves the technical problem of untimely adjustment of the air quality inside the vehicle.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular, to a method, device, storage medium, and electronic device for adjusting the air quality inside a vehicle. Background Art

[0002] The adjustment of the air quality inside a vehicle in the related art often relies on manual judgment. For example, when a user sees that the air color outside the vehicle through the window is abnormal, or when the user smells an abnormal smell inside the vehicle.

[0003] However, when a user is driving a vehicle, the user often only focuses on the road ahead to be traveled and ignores whether the air color in the external environment in other directions outside the vehicle is abnormal. And for the smell inside the vehicle, if the user can directly smell an abnormal smell inside the vehicle, then it is very likely that the abnormal smell has existed for a long time and has caused more or less damage to the user's body. Therefore, even if the user has discovered that the air quality inside the vehicle is poor at this moment and then manually operates to adjust the air quality inside the vehicle, the above-mentioned physical damage that has occurred cannot be compensated. That is, there is a technical problem of untimely adjustment of the air quality control inside the vehicle in the prior art.

[0004] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, storage medium, and electronic device for adjusting the air quality inside a vehicle, so as to at least solve the technical problem of untimely adjustment of the air quality inside the vehicle.

[0006] According to one aspect of the embodiments of the present invention, a method for adjusting the air quality inside a vehicle is provided, including: obtaining a target image associated with a target vehicle, where the target image is used to represent the environmental condition where the target vehicle is currently located; identifying the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located; and adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle.

[0007] According to another aspect of the embodiments of the present invention, there is also provided an in-vehicle air quality adjustment device, including: an acquisition unit for acquiring a target image associated with a target vehicle, where the target image is used to represent the environmental condition where the target vehicle is currently located; an identification unit for identifying the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located; and an adjustment unit for adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle.

[0008] As an optional solution, the identification unit includes: a second identification module for identifying the target image to obtain second image parameters, where the second image parameters are used to represent the environmental image category to which the target image belongs; a third determination module for determining the target environmental category of the environment where the target vehicle is currently located according to the second image parameters; and a fourth determination module for determining the target air parameters according to the air quality index and the target environmental category.

[0009] As an optional solution, the fourth determination module includes: a first determination sub-module for, when the air quality index reaches a target threshold, determining the air parameters corresponding to the air quality index as the target air parameters; and a second determination sub-module for, when the air quality index does not reach the target threshold, determining the predicted air parameters of the target vehicle according to the air quality index and the target environmental category, where the predicted air parameters are used to represent the air quality of the environment where the target vehicle is predicted to be located within a preset time period in the future.

[0010] As an optional solution, the adjustment unit includes: an operation module for acquiring the vehicle operation information of the target vehicle, where the vehicle operation information is used to represent the operation record of the target vehicle within a target time period; and a first adjustment module for adjusting the air conditioning parameters of the target vehicle according to the target air parameters and the vehicle operation information of the target vehicle.

[0011] As an alternative solution, the above adjustment unit includes at least one of the following: a first determination module, configured to determine whether to keep the target vehicle-mounted device in the on state according to the target air parameter when the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the on state, where the target vehicle-mounted device is used to adjust the air quality inside the target vehicle; a second adjustment module, configured to adjust the operating parameters of the target vehicle-mounted device according to the target air parameter when the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the on state, and the air conditioning parameter includes the operating parameter; a second determination module, configured to determine whether to adjust the target vehicle-mounted device to the on state according to the target air parameter when the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the off state, and adjust the operating parameter according to the target air parameter when the target vehicle-mounted device is adjusted to the on state.

[0012] As an alternative solution, the above recognition unit includes: a first input module, configured to input the target image into a first image recognition model, where the first image recognition model is a model for recognizing image pixels obtained by training with a plurality of sample image data; a first acquisition module, configured to acquire a first image recognition result output by the image recognition model, where the second image recognition result is used to represent the air quality index of the environment where the target vehicle is currently located; a second acquisition module, configured to acquire a first air parameter according to the first image recognition result.

[0013] As an alternative solution, the above second acquisition module includes: a first acquisition sub-module, configured to acquire historical image recognition results output by the first image recognition model within a predetermined time period; a second acquisition sub-module, configured to acquire a second air parameter according to the historical image recognition results; a third acquisition sub-module, configured to acquire the target air parameter according to the first air parameter and the second air parameter.

[0014] As an alternative solution, the above recognition unit further includes: a second input module, configured to input the target image into a second image recognition model, where the second image recognition model is a model for recognizing image categories obtained by training with a plurality of sample image data; a third acquisition module, configured to acquire a second image recognition result output by the image recognition model, where the second image recognition result is used to represent the environment category of the environment where the target vehicle is currently located; a fourth acquisition module, configured to acquire a third air parameter according to the second image recognition result.

[0015] As an alternative solution, it includes: a first display unit for displaying a first prompt message before adjusting the air conditioning parameters of the target vehicle according to the above-mentioned target air parameters, where the first prompt message is used to prompt that the air quality inside the current target vehicle has met the adjustment conditions of the air conditioning parameters; a second display unit for displaying a second prompt message during the process of adjusting the air conditioning parameters of the target vehicle according to the above-mentioned target air parameters, where the second prompt message is used to prompt the adjustment progress of the air conditioning parameters; a third display unit for displaying a third prompt message after adjusting the air conditioning parameters of the target vehicle according to the above-mentioned target air parameters, where the third prompt message is used to prompt that the air conditioning parameters have been adjusted completed.

[0016] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium storing a computer program, where the computer program is configured to execute the method for adjusting the in-vehicle air quality when running.

[0017] According to another aspect of the embodiments of the present invention, there is also provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the method for adjusting the in-vehicle air quality through the computer program.

[0018] In the embodiments of the present invention, a target image associated with the target vehicle is obtained, where the target image is used to represent the environmental conditions where the target vehicle is currently located; the target image is recognized to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located; the air conditioning parameters of the target vehicle are adjusted according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle, and the vehicle operation information is used to represent the operation record of the target vehicle during the target time period. The air parameters for adjusting the in-vehicle air quality are obtained by recognizing the collected vehicle-associated images to complete the automatic adjustment of the in-vehicle air quality, thereby achieving the purpose of timely adjusting the in-vehicle air quality, and thus realizing the technical effect of improving the timeliness of adjusting the in-vehicle air quality, and further solving the technical problem of untimely adjustment of the in-vehicle air quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and form a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0020] Figure 1Schematic diagram of an application environment of an optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0021] Figure 2 Schematic diagram of a process of an optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0022] Figure 3 Schematic diagram of an optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0023] Figure 4 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0024] Figure 5 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0025] Figure 6 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0026] Figure 7 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0027] Figure 8 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0028] Figure 9 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0029] Figure 10 Schematic diagram of another optional method for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0030] Figure 11 Schematic diagram of an optional device for adjusting in-vehicle air quality according to an embodiment of the present invention;

[0031] Figure 12 Schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. Detailed implementation manners

[0032] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] According to one aspect of the embodiments of the present invention, a method for adjusting the in-vehicle air quality is provided. Optionally, as an alternative implementation, the method for adjusting the in-vehicle air quality can be but is not limited to being applied to an environment as Figure 1 shown. Among them, it may include but is not limited to a user device 102, a network 110, and a server 112. Among them, the user device 102 may include but is not limited to a display 108, a processor 106, and a memory 104.

[0035] The specific process can be as follows:

[0036] Step S102, the user device 102 acquires a target image associated with the target vehicle 1022;

[0037] Steps S104 - S106, the user device 102 sends the target image to the server 112 through the network 110;

[0038] Step S108, the server 112 processes the target image through the processing engine 116 to generate an adjustment instruction for the air conditioning parameters of the target vehicle;

[0039] Steps S110 - S112, the server 112 sends an adjustment instruction to the user device 102 via the network 110. The processor 106 in the user device 102 adjusts the air conditioning parameters of the target vehicle 1022 according to the adjustment instruction, and displays the adjusted air conditioning parameters on the display 108, and stores the adjusted air conditioning parameters in the memory 104.

[0040] In addition to Figure 1 the example shown, the steps can be independently completed by the user device 102, that is, the user device 102 executes steps such as image processing and judgment of normal or abnormal acquisition postures, thereby reducing the processing pressure on the server. The user device 102 includes but is not limited to handheld devices (such as mobile phones), laptop computers, desktop computers, in-vehicle devices, etc. The present invention does not limit the specific implementation manner of the user device 102.

[0041] Optionally, as an alternative implementation, as Figure 2 shown, the method for adjusting the in-vehicle air quality includes:

[0042] S202, obtain a target image associated with the target vehicle, where the target image is used to represent the environmental conditions where the target vehicle is currently located;

[0043] S204, identify the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located;

[0044] S206, adjust the air conditioning parameters of the target vehicle according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle.

[0045] Optionally, in this embodiment, the above method for adjusting the in-vehicle air quality can be applied but is not limited to operations related to synchronizing air quality information relying on positioning combined with network synchronization, such as sending the current vehicle GPS position to the background, and the background queries the air quality index of the current position and then issues an air quality adjustment strategy to adjust the air conditioning parameters of the target vehicle, etc.

[0046] Optionally, in this embodiment, the method for adjusting the in-vehicle air quality may be, but is not limited to, implemented by an in-vehicle vision system. Among them, the in-vehicle vision system may be, but is not limited to, related to technologies such as face recognition, gesture recognition, expression recognition, gaze tracking, vehicle detection, lane line detection, and image acquisition. Moreover, the in-vehicle vision system may also be, but is not limited to, combined with the collected visual information and the current operating state of the vehicle to determine the current scene of the vehicle, and generate a complete execution plan for this scene to solve most of the problems that can be encountered in the in-vehicle scenario. For example, the in-vehicle vision system can identify whether the user driving the vehicle is the owner through face recognition; for another example, it can detect the number of passing vehicles outside the vehicle to judge the driving risk on the current road; for another example, it can detect the lane lines to determine the type of road on which the vehicle is currently driving, etc.

[0047] Optionally, in this embodiment, the target image may be, but is not limited to, an image collected by an image acquisition device, or may also be, but is not limited to, an image obtained after processing the image collected by the image acquisition device. Among them, the image acquisition device may be, but is not limited to, a device installed on the target vehicle, such as a camera configured inside the target vehicle or a camera configured outside the target vehicle, etc.; in addition, the image acquisition device may also be, but is not limited to, a device installed outside the target vehicle, such as a camera assembled on the road or a satellite, etc.

[0048] For further illustration by way of example, optionally, as Figure 3 shown, the image acquisition device 302 is a camera installed inside the target vehicle. This camera can collect the environmental conditions inside the target vehicle, and can also, but is not limited to, collect the environmental conditions outside the target vehicle.

[0049] For further illustration by way of example, assume that the image acquisition device is a camera installed outside the target vehicle. This camera can collect the environmental conditions outside the target vehicle. Optionally, as Figure 4 shown, it can collect images of various perspectives centered on the target vehicle 402, such as a front view image 404, a rear view image 406, a left view image 408, and a right view image 408.

[0050] Optionally, in this embodiment, the environmental conditions of the target vehicle at the current moment may be, but is not limited to, the environmental conditions of the current in-vehicle environment of the target vehicle, such as Figure 5 the in-vehicle environment 502 shown. Furthermore, the target image may be, but is not limited to, showing direct measurement information of air quality such as gas concentration and pollution degree in the in-vehicle environment 502, and may also be, but is not limited to, showing passenger information in the in-vehicle environment 502 (such as the higher the number of people, the higher the requirement for air quality), etc.

[0051] Furthermore, the environmental conditions in which the target vehicle is currently located may also, but are not limited to, the environmental conditions of the current in-vehicle environment of the target vehicle. For example, Figure 6 the out-of-vehicle environment in which the target vehicle 602 is currently located as shown. Furthermore, the target image may, but is not limited to, represent direct measurement information of air quality such as gas concentration and pollution degree in the out-of-vehicle environment, and may also, but is not limited to, represent relevant information indirectly measuring air quality such as road information (such as whether it is crowded), vehicle form information (such as vehicle speed), and driving route (whether it is a tunnel or about to enter a tunnel) in the out-of-vehicle environment.

[0052] Optionally, in this embodiment, identifying the target image may, but is not limited to, identifying color information, combination information, distribution information, etc. of each pixel in the image. For example, the air quality of the current environment can be identified by identifying the color information of the pixels (usually the darker the color, the lower the air quality). For another example, the environmental category of the current environment (such as night, sunny, cloudy, rainy, snowy, etc.) can be identified by the combination information of the pixels. For another example, the more accurate air quality of the current environment can be identified by the distribution information of the pixels (such as in the case of clarifying the current environmental category, determining the air quality of the current environment according to the strategy under this environmental category).

[0053] Optionally, in this embodiment, the target air parameter may, but is not limited to, be understood as a numerical value used to evaluate the air quality condition, which is in the form of simplifying the concentrations of several common air pollutants detected into a single conceptual index value. Among them, for example, soot, total suspended particulate matter, inhalable suspended particulate matter, sulfur dioxide, nitrogen dioxide, nitric oxide, ozone, volatile organic compounds, etc.

[0054] Optionally, in this embodiment, the air conditioning parameter may, but is not limited to, be the working parameter of relevant vehicle-mounted devices in the target vehicle that can realize the function of adjusting the air quality inside the vehicle. Among them, the above vehicle-mounted devices such as air conditioners, air purifiers, windows, air circulation systems, etc. Further taking the air conditioner as an example, adjusting the air conditioning parameter of the air conditioner may, but is not limited to, be understood as turning on / off the air conditioner, and adjusting the operation mode, mode operation parameters, etc. of the turned-on air conditioner; taking the window as an example, adjusting the air conditioning parameter of the window may, but is not limited to, be understood as turning on / off the window, and adjusting the opening degree of the turned-on window, etc.

[0055] It should be noted that by identifying the vehicle-associated image collected to obtain the air parameter for adjusting the air quality inside the vehicle, automatic adjustment of the air quality inside the vehicle can be realized. Compared with manual adjustment, automatic adjustment not only has the advantage of high timeliness, but also improves the adjustment accuracy of the air quality inside the vehicle because image recognition is more accurate than human eye recognition.

[0056] For further illustration by example, optionally such asFigure 7 As shown in the figure, the specific steps are as follows:

[0057] S702, collect the initial image associated with the target vehicle;

[0058] S704, preprocess the initial image to obtain the target image;

[0059] S706, input the target image into the image recognition model to obtain the output target air parameters;

[0060] S708, determine whether the target air parameters meet the first condition. If so, execute step S710; if not, execute step S712;

[0061] S710, output the adjustment result of the air conditioning parameters according to the target air parameters;

[0062] S712, obtain the vehicle operation information of the target vehicle;

[0063] S714, determine whether the vehicle operation information meets the second condition. If so, execute step S716; if not, execute step S702;

[0064] S716, start the auxiliary verification, where the auxiliary verification uses the vehicle operation information as the auxiliary reference information, and different auxiliary reference information can correspond to different judgment strategies in S718, as well as different verification thresholds, and the verification threshold is used to determine whether the auxiliary verification passes in S718;

[0065] S718, determine whether the auxiliary verification passes. If so, execute step S720; if not, execute step S702;

[0066] S720, output the adjustment result of the air conditioning parameters according to the target air parameters and the vehicle operation information.

[0067] Through the embodiments provided in this application, the target image associated with the target vehicle is obtained, where the target image is used to represent the environmental conditions where the target vehicle is currently located; the target image is recognized to obtain the target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located; the air conditioning parameters of the target vehicle are adjusted according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle. By recognizing the collected vehicle-associated image to obtain the air parameters for adjusting the air quality inside the vehicle, the automatic adjustment of the air quality inside the vehicle is completed, and thus the purpose of timely adjusting the air quality inside the vehicle is achieved, thereby realizing the technical effect of improving the timeliness of adjusting the air quality inside the vehicle.

[0068] As an optional solution, recognizing the target image to obtain the target air parameters includes:

[0069] S1. Identify the target image to obtain a first image parameter, where the first image parameter is used to represent the distribution of pixels in the target image;

[0070] S2. Determine the air quality index of the environment where the target vehicle is currently located according to the first image parameter;

[0071] S3. Determine the target air parameter according to the air quality index.

[0072] Optionally, in this embodiment, a pixel may but is not limited to being composed of small squares of an image, and each small square will have a definite position and an assigned color value, and the distribution of pixels in the target image may but is not limited to including the distribution of the positions and the assigned color values of each pixel in the target image.

[0073] It should be noted that the distribution of pixels determines the appearance presented by the target image, and thus naturally can also represent the appearance of the air quality presented by the target image. Furthermore, by identifying the pixels in the target image to determine the air quality index of the environment where the target vehicle is currently located, the target air parameter can be efficiently determined.

[0074] Through the embodiment provided by this application, the target image is identified to obtain a first image parameter, where the first image parameter is used to represent the distribution of pixels in the target image; the air quality index of the environment where the target vehicle is currently located is determined according to the first image parameter; and the target air parameter is determined according to the air quality index, achieving the purpose of efficiently determining the target air parameter and realizing the effect of improving the determination efficiency of the target air parameter.

[0075] As an alternative solution, identifying the target image to obtain the target air parameter includes:

[0076] S1. Identify the target image to obtain a second image parameter, where the second image parameter is used to represent the environmental image category to which the target image belongs;

[0077] S2. Determine the target environmental category of the environment where the target vehicle is currently located according to the second image parameter;

[0078] S3. Determine the target air parameter according to the air quality index and the target environmental category.

[0079] Optionally, in this embodiment, the environmental image category may but is not limited to corresponding one-to-one with the environmental category. In other words, the corresponding relationship between each environmental image category and the environmental category may but is not limited to being created in advance, so that when the environmental image category is determined, the corresponding environmental category can be quickly determined.

[0080] It should be noted that each environmental category usually has its performance characteristics, and these performance characteristics are often presented in the form of images. For example, the performance characteristics of a tunnel are that the overall color is relatively dim and it is surrounded by obstacles at a relatively close distance. Then, through target image recognition to determine the environmental category of the current environment where the target vehicle is located, high recognition accuracy can be ensured.

[0081] Through the embodiments provided in this application, the target image is recognized to obtain a second image parameter, where the second image parameter is used to represent the environmental image category to which the target image belongs; the target environmental category of the current environment where the target vehicle is located is determined according to the second image parameter; and the target air parameter is determined according to the air quality index and the target environmental category, achieving the purpose of efficiently determining the target air parameter and realizing the effect of improving the determination efficiency of the target air parameter.

[0082] As an optional solution, determining the target air parameter according to the air quality index and the target environmental category includes:

[0083] S1. When the air quality index reaches the target threshold, determine the air parameter corresponding to the air quality index as the target air parameter;

[0084] S2. When the air quality index does not reach the target threshold, determine the predicted air parameter of the target vehicle according to the air quality index and the target environmental category, where the predicted air parameter is used to represent the air quality of the environment where the target vehicle is predicted to be located within a preset time period in the future.

[0085] It should be noted that considering that even if the air quality where the current target vehicle is located is in a healthy state, it is very likely that the air quality in this environment will change foreseeably in a short period of time. For example, assume that the target vehicle has just entered a relatively enclosed environment, and the air quality in the enclosed environment usually has problems such as poor air circulation and resulting in poor air quality. However, if the above problems are not reflected in the form of poor air quality at the current moment, then it is necessary to predict the air quality in the preset time period in the future to make a quick adjustment response when the air quality deteriorates.

[0086] Through the embodiments provided in this application, when the air quality index reaches the target threshold, the air parameter corresponding to the air quality index is determined as the target air parameter; when the air quality index does not reach the target threshold, the predicted air parameter of the target vehicle is determined according to the air quality index and the target environmental category, where the predicted air parameter is used to represent the air quality of the environment where the target vehicle is predicted to be located within a preset time period in the future, achieving the purpose of making timely adjustments to the possible future air quality and realizing the effect of improving the comprehensiveness of the adjustment of the air quality inside the vehicle.

[0087] As an alternative, adjust the air conditioning parameters of the target vehicle according to the target air parameters, including:

[0088] S1. Obtain the vehicle operation information of the target vehicle, where the vehicle operation information is used to represent the operation record of the target vehicle within the target time period;

[0089] S2. Adjust the air conditioning parameters of the target vehicle according to the target air parameters and the vehicle operation information of the target vehicle.

[0090] Optionally, in this embodiment, the vehicle operation information may include, but is not limited to, the relevant information generated when the target vehicle is driving, such as the driving speed, driving position, driving route, driving road type, etc. of the target vehicle; it may also include, but is not limited to, the relevant information generated when the target vehicle is stationary, such as the target vehicle; it may further include, but is not limited to, the relevant information generated when the in-vehicle device associated with the target vehicle is operating or about to operate, such as the operation history information of the air conditioner, etc.

[0091] It should be noted that, to improve the comprehensiveness of the adjustment of the air conditioning parameters, the vehicle operation information in the vehicle dimension is also introduced. Thus, even in scenarios where image recognition is inconvenient (such as a dim and enclosed environment), the accurate adjustment of the air conditioning parameters of the target vehicle can still be completed.

[0092] Through the embodiments provided in this application, obtain the vehicle operation information of the target vehicle, where the vehicle operation information is used to represent the operation record of the target vehicle within the target time period; adjust the air conditioning parameters of the target vehicle according to the target air parameters and the vehicle operation information of the target vehicle, achieving the effect of improving the adjustment accuracy of the air conditioning parameters of the target vehicle.

[0093] As an alternative, adjust the air conditioning parameters of the target vehicle according to the target air parameters and the vehicle operation information of the target vehicle, including at least one of the following:

[0094] S1. When the vehicle operation information indicates that the target in-vehicle device in the target vehicle is in the on state, determine whether to keep the target in-vehicle device in the on state according to the target air parameters, where the target in-vehicle device is used to adjust the air quality inside the target vehicle;

[0095] S2. When the vehicle operation information indicates that the target in-vehicle device in the target vehicle is in the on state, adjust the working parameters of the target in-vehicle device according to the target air parameters, and the air conditioning parameters include the working parameters;

[0096] S3. When the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the off state, determine whether to adjust the target vehicle-mounted device to the on state according to the target air parameter, and when the target vehicle-mounted device is adjusted to the on state, adjust the working parameter according to the target air parameter.

[0097] Optionally, in this embodiment, the target vehicle-mounted device may include, but is not limited to, relevant vehicle-mounted devices in the target vehicle that can implement the function of adjusting the air quality inside the vehicle, such as air conditioners, air purifiers, windows, air circulation systems, etc.

[0098] It should be noted that corresponding operations or suggestions are made according to the actual conditions of the current target vehicle. For example, the possibility of adjusting the internal and external circulation of the vehicle only involves after the user turns on the vehicle air conditioner or air supply function, and it is only possible to turn on or off the air purifier on the premise that the air purifier is equipped.

[0099] For further illustration by example, optionally, such as Figure 8 As shown, assume that the target vehicle-mounted device 802 is a vehicle air conditioner. When the vehicle operation information indicates that the target vehicle-mounted device 802 in the target vehicle is in the on state, determine whether to keep the target vehicle-mounted device 802 in the on state according to the target air parameter, where the target vehicle-mounted device 802 is used to adjust the air quality inside the target vehicle; when the vehicle operation information indicates that the target vehicle-mounted device 802 in the target vehicle is in the on state, adjust the working parameter of the target vehicle-mounted device 802 according to the target air parameter, and the air conditioning parameter includes the working parameter; when the vehicle operation information indicates that the target vehicle-mounted device 802 in the target vehicle is in the off state, determine whether to adjust the target vehicle-mounted device 802 to the on state according to the target air parameter, and when the target vehicle-mounted device 802 is adjusted to the on state, adjust the working parameter according to the target air parameter.

[0100] Through the embodiments provided in this application, when the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the on state, determine whether to keep the target vehicle-mounted device in the on state according to the target air parameter, where the target vehicle-mounted device is used to adjust the air quality inside the target vehicle; when the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the on state, adjust the working parameter of the target vehicle-mounted device according to the target air parameter, and the air conditioning parameter includes the working parameter; when the vehicle operation information indicates that the target vehicle-mounted device in the target vehicle is in the off state, determine whether to adjust the target vehicle-mounted device to the on state according to the target air parameter, and when the target vehicle-mounted device is adjusted to the on state, adjust the working parameter according to the target air parameter, achieving the effect of improving the comprehensiveness of the adjustment of the air conditioning parameters of the target vehicle.

[0101] As an alternative solution, the target image is recognized to obtain the target air parameter, including:

[0102] S1. Input the target image into the first image recognition model, where the first image recognition model is a model for recognizing image pixels obtained by training with multiple sample image data;

[0103] S2. Obtain the first image recognition result output by the image recognition model, where the second image recognition result is used to represent the air quality index of the environment where the target vehicle is currently located;

[0104] S3. Obtain the first air parameter according to the first image recognition result.

[0105] Optionally, in this embodiment, the first image recognition model can be, but is not limited to, a classification model of discrete quantities, and the output content is the scene category represented in the input image. It can also be just a binary result (whether air purification is required), or a multi-classification result (whether to turn off the external circulation of the air conditioner, whether to turn on the air purifier, whether to close the window).

[0106] It should be noted that to improve the accuracy and efficiency of image recognition, it is completed by using a model. In addition, before inputting the target image into the first image recognition model, the initial first image recognition model needs to be trained with multiple sample image data before the first image recognition model can be put into use to ensure the output accuracy of the first image recognition model.

[0107] Through the embodiment provided by this application, the target image is input into the first image recognition model, where the first image recognition model is a model for recognizing image pixels obtained by training with multiple sample image data; the first image recognition result output by the image recognition model is obtained, where the second image recognition result is used to represent the air quality index of the environment where the target vehicle is currently located; the first air parameter is obtained according to the first image recognition result, achieving the effect of improving the accuracy of image recognition.

[0108] As an alternative solution, obtaining the first air parameter according to the first image recognition result includes:

[0109] S1. Obtain the historical image recognition results output by the first image recognition model within a predetermined time period;

[0110] S2. Obtain the second air parameter according to the historical image recognition results;

[0111] S3. Obtain the target air parameter according to the first air parameter and the second air parameter.

[0112] It should be noted that considering that the output of the first image recognition model may still be inaccurate, the model output is corrected accordingly to achieve a double-insurance effect. For example, the average of the outputs of the historical images of the most recent x frames of the first image recognition model is calculated to obtain the average pollution range, or the outputs of the most recent x frames of the first image recognition model are voted on, and the current scenario is determined according to the majority principle. Eventually, the purpose of preventing outliers from interfering is achieved.

[0113] Through the embodiments provided in this application, the historical image recognition results output by the first image recognition model within a predetermined time period are obtained; the second air parameter is obtained according to the historical image recognition results; and the target air parameter is obtained according to the first air parameter and the second air parameter, achieving the effect of improving the accuracy of image recognition.

[0114] As an alternative solution, for the recognition of the target image to obtain the target air parameter, it further includes:

[0115] S1, input the target image into the second image recognition model, where the second image recognition model is a model for recognizing image categories obtained by training with multiple sample image data;

[0116] S2, obtain the second image recognition result output by the image recognition model, where the second image recognition result is used to represent the environmental category of the environment where the target vehicle is currently located;

[0117] S3, obtain the third air parameter according to the second image recognition result.

[0118] Optionally, in this embodiment, the second image recognition model may be, but is not limited to, an image segmentation model with an output of pixel categories (each pixel or every few pixels corresponds to an air quality or air quality control strategy classification), and finally corresponding operations can be performed according to the mj image range with poor air quality or the image range requiring different air control strategies by voting.

[0119] It should be noted that to improve the accuracy and efficiency of image recognition, it is completed by using a model. In addition, before inputting the target image into the second image recognition model, the initial second image recognition model needs to be trained with multiple sample image data before the second image recognition model can be put into use to ensure the output accuracy of the second image recognition model;

[0120] In addition, to fully ensure the accuracy of the model output, the model output can also be, but is not limited to, corrected. For example, the average of the outputs of the historical images of the most recent x frames of the second image recognition model is calculated to obtain the average pollution range, or the outputs of the most recent x frames of the second image recognition model are voted on, and the current scenario is determined according to the majority principle.

[0121] Through the embodiments provided in this application, the target image is input into the second image recognition model, where the second image recognition model is a model for recognizing image categories obtained by training using a plurality of sample image data; the second image recognition result output by the image recognition model is obtained, where the second image recognition result is used to represent the environmental category of the environment where the target vehicle is currently located; and the third air parameter is obtained according to the second image recognition result, achieving the effect of improving the accuracy of image recognition.

[0122] As an optional solution, before adjusting the air conditioning parameters of the target vehicle according to the target air parameter, it includes: displaying a first prompt message, where the first prompt message is used to prompt that the air quality inside the current target vehicle has met the adjustment condition of the air conditioning parameters;

[0123] As an optional solution, during the process of adjusting the air conditioning parameters of the target vehicle according to the target air parameter, it includes: displaying a second prompt message, where the second prompt message is used to prompt the adjustment process of the air conditioning parameters;

[0124] As an optional solution, after adjusting the air conditioning parameters of the target vehicle according to the target air parameter, it includes: displaying a third prompt message, where the third prompt message is used to prompt that the air conditioning parameters have been adjusted.

[0125] Optionally, in this embodiment, after displaying the first prompt message, the air conditioning parameters of the target vehicle can be adjusted according to the target air parameter, but not limited to, when a regulation instruction triggered by the user terminal is received.

[0126] Optionally, in this embodiment, the display carrier of the prompt message can be, but not limited to, a terminal device with a display function associated with the target vehicle, such as a mobile terminal (mobile phone, mobile computer), in-vehicle display, etc.; in addition, in addition to prompting through the display method, the prompt message can also be prompted in forms such as voice broadcast, video playback, etc., which is not limited here.

[0127] For further illustration by way of example, optionally, for example Figure 9 As shown, assuming that the display carrier of the prompt message is the in-vehicle display 904 configured on the target vehicle 902, it can be, but not limited to, at least one of the following: displaying on the in-vehicle display 904 a first prompt message for prompting that the air quality inside the current target vehicle has met the adjustment condition of the air conditioning parameters, displaying on the in-vehicle display 904 a second prompt message for prompting the adjustment process of the air conditioning parameters, and displaying on the in-vehicle display 904 a third prompt message for prompting that the air conditioning parameters have been adjusted.

[0128] It should be noted that the display of the first prompt message, the display of the second prompt message, or the display of the third prompt message can be used in parallel or in combination, and there is no limitation here.

[0129] Through the embodiments provided in the present application, before adjusting the air conditioning parameters of the target vehicle according to the target air parameters, it includes: displaying a first prompt message, where the first prompt message is used to prompt that the air quality inside the current target vehicle has met the adjustment conditions of the air conditioning parameters; during the process of adjusting the air conditioning parameters of the target vehicle according to the target air parameters, it includes: displaying a second prompt message, where the second prompt message is used to prompt the adjustment process of the air conditioning parameters; after adjusting the air conditioning parameters of the target vehicle according to the target air parameters, it includes: displaying a third prompt message, where the third prompt message is used to prompt that the air conditioning parameters have been adjusted, achieving the effect of improving the intuitiveness of the adjustment of the air conditioning parameters.

[0130] As an alternative solution, for ease of understanding, a specific embodiment of adjusting the vehicle's air control strategy based on the air quality inside the vehicle using an in-vehicle camera is described. For example, by inputting the images captured by the in-vehicle camera into a deep learning model to obtain the current external environment situation of the vehicle, and adopting appropriate in-vehicle air quality control strategies according to the external situation to achieve the purpose of optimizing the in-vehicle air quality. For example, when the model determines that there is traffic congestion or dust outside the vehicle, it automatically reminds or turns off the external circulation of the air conditioner and turns on the in-vehicle air purifier, etc.

[0131] Optionally, in this embodiment, relevant operations can be synchronized by relying on positioning combined with network-synchronized air quality information, such as sending the current vehicle GPS position to the background, and the background queries the pm2.5 value of the current location and then issues an air quality adjustment strategy, etc.

[0132] It should be noted that the prior art cannot respond to some situations with high real-time performance and strong locality. For example, when a customer drives into a congested section, the air quality may be poor only in a small area near the vehicle and may disappear during the driving process. At this time, timely suggestions cannot be given based on the air quality information in the cloud region. In addition, the content of the air quality information in the cloud is limited, such as only including pm2.5 values, sulfur dioxide concentrations, etc. However, pollutants in some situations, such as various harmful chemical substances in congested situations, are not included in the monitoring scope, and in such situations, relevant responses cannot be made to achieve the purpose of controlling air quality;

[0133] To address the related problems existing in the prior art, an in-vehicle air quality adjustment method is used. When the user drives to an area with poor air quality, such as a congested road or a construction site with severe dust, the in-vehicle camera captures relevant images and calculates the type and level of air pollution according to the model, and finally makes appropriate air quality control strategies according to the information, such as turning off the external circulation of the air conditioner.

[0134] For further illustration, optionally, as Figure 10 shown, the specific steps are as follows:

[0135] S1002, the vehicle-mounted image acquisition device acquires images of the vehicle's surrounding environment at a certain frame rate;

[0136] S1004, perform necessary preprocessing on the acquired images;

[0137] S1006, input the images acquired in the previous step into a deep learning model to obtain the current scene type;

[0138] S1008, determine an appropriate air control strategy according to the scene type and the current vehicle condition;

[0139] Among them, optionally for S1002, it can include but is not limited to at least one of the following: the image acquisition device needs to be able to capture color images with sufficient clarity, the image acquisition device needs to be able to acquire the conditions on the road surface, the viewing angle cannot be too inclined downward or upward, the image acquisition device preferably has a shorter focal length to obtain a wider range of road surface information, etc.;

[0140] Furthermore, optionally for S1004, it can include but is not limited to at least one of the following: scale the acquired images to use a smaller model more suitable for vehicles, crop the acquired images, such as cropping areas unrelated to the outdoor air quality like the engine hood, enhance the acquired images, such as increasing the contrast, performing histogram equalization or normalization, etc.;

[0141] Further, optionally for S1006, it can include but is not limited to at least one of the following: a classification model with a discrete output, and the output content is the detailed scene represented by the captured content, such as cloudy day, rainy day, tunnel, underground parking lot, etc., or it can just be a binary result (whether air purification is required), or it can be a multi-classification result (whether to turn off the external air circulation of the air conditioner, whether to turn on the air purifier, whether to close the windows), an image segmentation model with the output quantity being pixel categories (each pixel or every few pixels corresponds to an air quality or air quality control strategy classification), and finally corresponding operations can be made according to the mj image range with poor air quality or the image range requiring different air control strategies by voting;

[0142] Furthermore, optionally for S1008, it may include, but is not limited to, at least one of the following: correcting the model output, such as averaging the outputs of the most recent x frames of the segmentation model to obtain the average pollution range, or voting on the outputs of the most recent x frames of the classification model and determining the current scenario according to the majority principle, ultimately achieving the purpose of preventing outliers from interfering, making corresponding operations or giving corresponding suggestions based on the current vehicle condition. For example, the possibility of adjusting the vehicle's internal and external circulation is only involved after the user turns on the in-vehicle air conditioner or air supply function, and it is only possible to turn on or off the air purifier if the vehicle is equipped with an air purifier, etc.

[0143] Optionally, in this embodiment, the air control strategy may be one or a set of methods that take the model output, map information, road condition information, vehicle speed, weather, and air pollution level as inputs and adjust vehicle hardware such as the internal and external circulation of the air conditioner, the air purifier, or give user reminders (such as closing the window) as outputs. The specific process may be as follows:

[0144] S1, the model regularly obtains image inputs and generates outputs, and determines whether it is necessary to enter the next process according to the output content. The outputs for entering the next process include, but are not limited to, the scene classification model indicating traffic jams, the object detection model detecting a large number of vehicles / continuously detecting a large number of vehicles in multiple consecutive frames / the license plate of the vehicle ahead remaining unchanged, the semantic segmentation model outputting a large proportion of the dust area, etc. Another basis for judgment is the congestion level of the current location obtained from the cloud server (Tencent Map has this function, specifically manifested as the road section being yellow or red). If the congestion level is higher than the threshold, start model-assisted verification (so the model can be started at a lower frequency under normal conditions to save resources. Here, due to the inaccuracy or lag of the congestion level, the model self-start cannot be aborted), and enter the next process;

[0145] S2, after determining the possibility of traffic jams or poor air quality through the steps, further judge the credibility of the traffic jams or poor air quality in combination with the location, map information, vehicle speed, air quality, etc. The judgment methods here include, but are not limited to, the vehicle owner frequently closing the air conditioner or switching to the internal circulation at the current location of the vehicle, querying the map information of the vehicle's location and finding that the environment here is relatively enclosed (such as a tunnel), or the current vehicle speed being low for a long time and frequently accelerating and decelerating, the pm2.5 / sulfur dioxide concentration being high at the current location, the congestion distance / time being long, etc.; if there is a situation, increase the current possibility level or probability of traffic jams or poor air quality to provide a reference for subsequent decisions;

[0146] S3. If the method determines that the probability of congestion or poor air quality is relatively high or low and the degree exceeds a certain threshold (this threshold can be preset or dynamically changed according to the user profile. For example, if a user is particularly sensitive to air quality and often turns on the air purifier, the threshold is lowered), then determine the specific output content. The specific output content includes two categories: mechanical operations and user reminders. Mechanical operations include turning off the air conditioner / outside air circulation of the air conditioner, turning on / off the in-vehicle air purifier, etc. User reminders include prompting mechanical operations or prompting to close the window, wear a mask, etc. Generally speaking, when the probability of congestion is high, the main pollutant in the air is nitrogen oxides. At this time, prompting or turning off the outside air circulation / window of the air conditioner can achieve a better purpose of isolating pollutants. An air purifier based on activated carbon (there are also air purifiers with other filter materials) can also filter nitrogen oxides. At this time, the user can be prompted or advised to turn it on. If the model outputs a large dust area, the outside air circulation of the air conditioner can also be turned off to save the life of the air filter, or the user can be prompted to close the window. If only the PM2.5 in the air is too high, the user can be prompted to turn on a non-activated carbon type purifier (this function is available in some vehicle models and is not within the scope of this patent solution).

[0147] In addition to the strategy, a machine learning model such as a decision tree that takes information as input and strategy as output can also be used to perform the judgment to avoid the deviation between the manual strategy and the actual situation.

[0148] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0149] According to another aspect of the embodiments of the present invention, there is also provided an in-vehicle air quality adjustment device for implementing the in-vehicle air quality adjustment method. As Figure 11 shown, the device includes:

[0150] An acquisition unit 1102, configured to acquire a target image associated with the target vehicle, where the target image is used to represent the environmental condition of the target vehicle at present;

[0151] An identification unit 1104, configured to identify the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located;

[0152] An adjustment unit 1106, configured to adjust the air adjustment parameters of the target vehicle according to the target air parameters, where the air adjustment parameters are used to adjust the air quality inside the target vehicle.

[0153] Optionally, in this embodiment, the in-vehicle air quality adjustment device may be, but is not limited to, applied to operations related to air quality information synchronization relying on positioning combined with network synchronization, such as sending the current vehicle GPS position to the background, and after the background queries the air quality index of the current position, issuing an air quality adjustment strategy to adjust the air conditioning parameters of the target vehicle, etc.

[0154] Optionally, in this embodiment, the above-mentioned in-vehicle air quality adjustment method may be, but is not limited to, implemented by an in-vehicle vision system. Among them, the in-vehicle vision system may be, but is not limited to, related to technologies such as face recognition, gesture recognition, expression recognition, gaze tracking, vehicle detection, lane line detection, image acquisition, etc. Moreover, the in-vehicle vision system may also be, but is not limited to, combining the acquired visual information and the current operating state of the vehicle to determine the current scene of the vehicle, and generating a complete execution plan for this scene to solve most of the problems that can be encountered in the in-vehicle scenario. For example, the in-vehicle vision system can identify whether the user driving the current vehicle is the owner through face recognition; for another example, it can detect the number of passing vehicles outside the vehicle to judge the driving risk on the current road; for another example, it can detect the lane lines to determine the type of road on which the vehicle is currently driving, etc.

[0155] Optionally, in this embodiment, the target image may be, but is not limited to, an image acquired by an image acquisition device, or may also be, but is not limited to, an image obtained after processing the image acquired by the image acquisition device. Among them, the image acquisition device may be, but is not limited to, a device installed on the target vehicle, such as a camera configured inside the target vehicle or a camera configured outside the target vehicle, etc.; in addition, the image acquisition device may also be, but is not limited to, a device installed outside the target vehicle, such as a camera assembled on the road or a satellite, etc.

[0156] Optionally, in this embodiment, the environmental condition of the target vehicle at the current moment may be, but is not limited to, the environmental condition of the current in-vehicle environment of the target vehicle, such as Figure 5 the in-vehicle environment 502 shown in the figure. Furthermore, the target image may be, but is not limited to, showing direct measurement information of air quality such as gas concentration and pollution degree in the in-vehicle environment 502, and may also be, but is not limited to, showing passenger information in the in-vehicle environment 502 (such as the higher the number of people, the higher the requirement for air quality), etc.

[0157] Furthermore, the environmental condition of the target vehicle at the current moment may also be, but is not limited to, the environmental condition of the current in-vehicle environment of the target vehicle, such as Figure 6The external environment in which the target vehicle 602 is currently located. Furthermore, the target image can, but is not limited to, represent direct measurement information of air quality in the external environment, such as gas concentration and pollution level, and can also, but is not limited to, represent relevant information indirectly measuring air quality in the external environment, such as road information (e.g., whether it is congested), vehicle form information (e.g., vehicle speed), and driving route (whether it is a tunnel or about to enter a tunnel).

[0158] Optionally, in this embodiment, the recognition of the target image can, but is not limited to, be the recognition of color information, combination information, distribution information, etc. of each pixel in the image. For example, the air quality of the current environment can be recognized by recognizing the color information of the pixels (usually the darker the color, the lower the air quality). Another example is that the environmental category of the current environment (such as night, sunny, cloudy, rainy, snowy, etc.) can be recognized through the combination information of the pixels. Another example is that the more accurate air quality of the current environment can be recognized through the distribution information of the pixels (for example, in the case of clarifying the current environmental category, the air quality of the current environment is determined according to the strategy under this environmental category).

[0159] Optionally, in this embodiment, the target air parameter can, but is not limited to, be understood as a numerical value used to evaluate the air quality status, which simplifies the concentrations of several common air pollutants detected into a single conceptual index value form. Among them, for example, soot, total suspended particulates, inhalable suspended particulates, sulfur dioxide, nitrogen dioxide, nitric oxide, ozone, volatile organic compounds, etc.

[0160] Optionally, in this embodiment, the air conditioning parameter can, but is not limited to, be the working parameter of the in-vehicle device in the target vehicle that can realize the function of adjusting the air quality in the vehicle. Among them, the above in-vehicle devices are such as air conditioners, air purifiers, windows, air circulation systems, etc. Taking the air conditioner as an example, adjusting the air conditioning parameter of the air conditioner can, but is not limited to, be understood as turning on / off the air conditioner, and adjusting the operating mode, mode operation parameters, etc. of the turned-on air conditioner; taking the window as an example, adjusting the air conditioning parameter of the window can, but is not limited to, be understood as turning on / off the window, and adjusting the opening degree of the turned-on window, etc.

[0161] It should be noted that by recognizing the vehicle-related images collected to obtain the air parameters for adjusting the air quality in the vehicle, the automatic adjustment of the air quality in the vehicle can be realized. Compared with manual adjustment, automatic adjustment not only has the advantage of high timeliness, but also improves the adjustment accuracy of the air quality in the vehicle because image recognition is more accurate than human eye recognition.

[0162] For specific embodiments, reference can be made to the examples shown in the device for adjusting the air quality in the vehicle, and these examples will not be elaborated here.

[0163] Through the embodiments provided in this application, a target image associated with a target vehicle is obtained, where the target image is used to represent the environmental conditions where the target vehicle is currently located; the target image is recognized to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located; the air conditioning parameters of the target vehicle are adjusted according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle. By recognizing the collected vehicle-associated images to obtain air parameters for adjusting the air quality inside the vehicle, the automatic adjustment of the air quality inside the vehicle is completed, thereby achieving the purpose of timely adjusting the air quality inside the vehicle, and thus realizing the technical effect of improving the timeliness of adjusting the air quality inside the vehicle.

[0164] As an alternative solution, the recognition unit 1104 includes:

[0165] A first recognition module, configured to recognize the target image to obtain first image parameters, where the first image parameters are used to represent the distribution of pixels in the target image;

[0166] A first determination module, configured to determine the air quality index of the environment where the target vehicle is currently located according to the first image parameters;

[0167] A second determination module, configured to determine the target air parameters according to the air quality index.

[0168] For specific embodiments, reference may be made to the examples shown in the method for adjusting the air quality inside the vehicle, and details are not described herein again.

[0169] As an alternative solution, the recognition unit 1104 includes:

[0170] A second recognition module, configured to recognize the target image to obtain second image parameters, where the second image parameters are used to represent the environmental image category to which the target image belongs;

[0171] A third determination module, configured to determine the target environmental category of the environment where the target vehicle is currently located according to the second image parameters;

[0172] A fourth determination module, configured to determine the target air parameters according to the air quality index and the target environmental category.

[0173] For specific embodiments, reference may be made to the examples shown in the method for adjusting the air quality inside the vehicle, and details are not described herein again.

[0174] As an alternative solution, the fourth determination module includes:

[0175] A first determination sub-module, configured to, when the air quality index reaches a target threshold, determine the air parameters corresponding to the air quality index as the target air parameters;

[0176] A second determination sub-module, configured to determine a predicted air parameter of a target vehicle according to an air quality index and a target environment category when the air quality index does not reach a target threshold, where the predicted air parameter is used to represent the air quality of the environment where the target vehicle is predicted to be located within a preset time period in the future.

[0177] For specific embodiments, reference may be made to the examples shown in the method for adjusting the in-vehicle air quality, and the examples are not elaborated herein.

[0178] As an alternative solution, the adjustment unit 1106 includes:

[0179] An operation module, configured to obtain vehicle operation information of a target vehicle, where the vehicle operation information is used to represent the operation record of the target vehicle within a target time period;

[0180] A first adjustment module, configured to adjust an air conditioning parameter of the target vehicle according to the target air parameter and the vehicle operation information of the target vehicle.

[0181] For specific embodiments, reference may be made to the examples shown in the method for adjusting the in-vehicle air quality, and the examples are not elaborated herein.

[0182] As an alternative solution, the first adjustment module includes at least one of the following:

[0183] A first judgment module, configured to judge whether to keep a target in-vehicle device in an on state according to the target air parameter when the vehicle operation information indicates that the target in-vehicle device in the target vehicle is in an on state, where the target in-vehicle device is used to adjust the air quality in the vehicle of the target vehicle;

[0184] A second adjustment module, configured to adjust the working parameter of the target in-vehicle device according to the target air parameter when the vehicle operation information indicates that the target in-vehicle device in the target vehicle is in an on state, and the air conditioning parameter includes the working parameter;

[0185] A second judgment module, configured to judge whether to adjust the target in-vehicle device to an on state according to the target air parameter when the vehicle operation information indicates that the target in-vehicle device in the target vehicle is in an off state, and adjust the working parameter according to the target air parameter when the target in-vehicle device is adjusted to an on state.

[0186] For specific embodiments, reference may be made to the examples shown in the method for adjusting the in-vehicle air quality, and the examples are not elaborated herein.

[0187] As an alternative solution, the identification unit 1104 includes:

[0188] A first input module for inputting a target image into a first image recognition model, where the first image recognition model is a model for recognizing image pixels obtained by training with multiple sample image data;

[0189] A first acquisition module for acquiring a first image recognition result output by the image recognition model, where the second image recognition result is used to represent the air quality index of the environment where the target vehicle is currently located;

[0190] A second acquisition module for acquiring a first air parameter according to the first image recognition result.

[0191] For specific embodiments, reference may be made to the examples shown in the method for adjusting the air quality inside a vehicle, and these examples will not be elaborated here.

[0192] As an alternative solution, the second acquisition module includes:

[0193] A first acquisition sub-module for acquiring historical image recognition results output by the first image recognition model within a predetermined time period;

[0194] A second acquisition sub-module for acquiring a second air parameter according to the historical image recognition results;

[0195] A third acquisition sub-module for acquiring a target air parameter according to the first air parameter and the second air parameter.

[0196] For specific embodiments, reference may be made to the examples shown in the method for adjusting the air quality inside a vehicle, and these examples will not be elaborated here.

[0197] As an alternative solution, the recognition unit 1104 further includes:

[0198] A second input module for inputting the target image into a second image recognition model, where the second image recognition model is a model for recognizing image categories obtained by training with multiple sample image data;

[0199] A third acquisition module for acquiring a second image recognition result output by the image recognition model, where the second image recognition result is used to represent the environmental category of the environment where the target vehicle is currently located;

[0200] A fourth acquisition module for acquiring a third air parameter according to the second image recognition result.

[0201] For specific embodiments, reference may be made to the examples shown in the method for adjusting the air quality inside a vehicle, and these examples will not be elaborated here.

[0202] As an alternative solution, it includes:

[0203] The first display unit is configured to display a first prompt message before adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the first prompt message is used to prompt that the air quality inside the current target vehicle has met the adjustment conditions of the air conditioning parameters;

[0204] The second display unit is configured to display a second prompt message during the process of adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the second prompt message is used to prompt the adjustment progress of the air conditioning parameters;

[0205] The third display unit is configured to display a third prompt message after adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the third prompt message is used to prompt that the air conditioning parameters have been adjusted.

[0206] For specific embodiments, reference can be made to the examples shown in the method for adjusting the in-vehicle air quality, and these examples will not be elaborated here.

[0207] According to another aspect of the embodiments of the present invention, there is also provided an electronic device for implementing the method for adjusting the in-vehicle air quality, as Figure 12 shown. The electronic device includes a memory 1202 and a processor 1204. A computer program is stored in the memory 1202, and the processor 1204 is configured to execute the steps in any one of the method embodiments through the computer program.

[0208] Optionally, in this embodiment, the electronic device can be at least one network device among multiple network devices in a computer network.

[0209] Optionally, in this embodiment, the processor can be configured to execute the following steps through the computer program:

[0210] S1. Obtain a target image associated with the target vehicle, where the target image is used to represent the environmental conditions where the target vehicle is currently located;

[0211] S2. Identify the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located;

[0212] S3. Adjust the air conditioning parameters of the target vehicle according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle.

[0213] Optionally, those of ordinary skill in the art can understand that, Figure 12The structure shown is only schematic. The electronic device can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a personal digital assistant, and terminal devices such as Mobile Internet Devices (MID), PAD, etc. Figure 12 It does not limit the structure of the electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, etc.) than those shown Figure 12 in the figure, or have a different configuration from that Figure 12 shown.

[0214] Among them, the memory 1202 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for adjusting the in-vehicle air quality in the embodiments of the present invention. The processor 1204 executes various functional applications and data processing by running the software programs and modules stored in the memory 1202, that is, realizes the method for adjusting the in-vehicle air quality. The memory 1202 may include a high-speed random access memory, and may further include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 1202 may further include a memory remotely disposed relative to the processor 1204, and these remote memories can be connected to the terminal through a network. Examples of the network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof. Among them, the memory 1202 can specifically but not limitedly be used to store information such as a target image, target air parameters, and air conditioning parameters. As an example, as Figure 12 shown, the memory 1202 may but not limitedly include the acquisition unit 1202, the recognition unit 1204, and the adjustment unit 1206 in the device for adjusting the in-vehicle air quality. In addition, it may further include but not limited to other module units in the device for adjusting the in-vehicle air quality, which will not be elaborated in this example.

[0215] Optionally, the transmission device 1206 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one instance, the transmission device 1206 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and a router through a network cable so as to communicate with the Internet or a local area network. In one instance, the transmission device 1206 is a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0216] In addition, the electronic device further includes: a display 1208, which is used to display information such as a target image, target air parameters, and air conditioning parameters; and a connection bus 1210, which is used to connect each module component in the electronic device.

[0217] In other embodiments, the terminal device or the server may be a node in a distributed system. The distributed system may be a blockchain system, which may be a distributed system formed by connecting the multiple nodes in a form of network communication. Among them, the nodes may form a peer-to-peer (P2P) network, and any form of computing device, such as electronic devices like servers and terminals, can become a node in the blockchain system by joining the peer-to-peer network.

[0218] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for adjusting the in-vehicle air quality. Among them, the computer program is set to execute the steps in any method embodiment when running.

[0219] Optionally, in this embodiment, the computer-readable storage medium may be set to store a computer program for executing the following steps:

[0220] S1, obtaining a target image associated with a target vehicle, where the target image is used to represent the environmental condition where the target vehicle is currently located;

[0221] S2, identifying the target image to obtain target air parameters, where the target air parameters are used to represent the air quality of the environment where the target vehicle is currently located;

[0222] S3, adjusting the air conditioning parameters of the target vehicle according to the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle.

[0223] Optionally, in this embodiment, those of ordinary skill in the art can understand that all or part of the steps in the above various methods can be completed by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0224] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0225] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in the storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0226] In the above embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0227] In the several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0228] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0229] In addition, the functional units in the various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0230] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for adjusting the in-vehicle air quality, characterized in that, it includes: Obtain the image data collected by the on-vehicle image acquisition device of the target vehicle, and preprocess the collected image data to obtain the target image associated with the target vehicle, where the target image is used to represent the environmental conditions where the target vehicle is currently located. The preprocessing is to perform cropping processing on the collected image data to crop the area irrelevant to the out-of-vehicle air quality, and to perform contrast enhancement processing on the collected image data; Input the target image into a deep learning model, identify the target image, and obtain a model output, where the model output includes the air quality index of the environment where the target vehicle is currently located and the target environmental category of the environment where the target vehicle is currently located; In the case where the deep learning model is a discrete quantity classification model, vote on the outputs of the classification model in the most recent x frames to obtain a voting result that conforms to the majority principle, where the voting result is used to correct the model output; In the case where the deep learning model is an image segmentation model of pixel categories, average the outputs of the image segmentation model in the most recent x frames to obtain an average pollution range, where the average pollution range is used to correct the model output; In the case where the air quality index reaches the target threshold, determine the air parameters corresponding to the air quality index as the target air parameters, and the target air parameters are used to represent the air quality of the current out-of-vehicle environment; In the case where the air quality index does not reach the target threshold, determine the predicted air parameters of the target vehicle according to the air quality index and the target environmental category, where the predicted air parameters are used to represent the air quality of the environment where the target vehicle is predicted to be located within a preset time period in the future, and the target air parameters include the predicted air parameters; In the case where the target air parameters indicate the possibility of poor air quality, obtain the credibility of the target air parameters through multi-dimensional information, where the multi-dimensional information includes the location of the target vehicle, map information, and the driving speed of the target vehicle, and the credibility of the target air parameters is used to represent the probability of poor air quality; Adjust the air conditioning parameters of the target vehicle according to the target air parameters and the credibility of the target air parameters, where the air conditioning parameters are used to adjust the air quality inside the target vehicle.

2. The method according to claim 1, characterized in that, in the process of inputting the target image into a deep learning model, identifying the target image, and obtaining a model output, it includes: Identify the target image to obtain first image parameters, where the first image parameters are used to represent the pixel distribution in the target image; Determine the air quality index according to the first image parameters.

3. The method according to claim 2, characterized in that, in the process of inputting the target image into a deep learning model, identifying the target image, and obtaining a model output, it includes: Identify the target image to obtain second image parameters, where the second image parameters are used to represent the environmental image category to which the target image belongs; Determine the target environmental category according to the second image parameters.

4. The method according to claim 1, wherein, In the process of adjusting the air conditioning parameters of the target vehicle according to the target air parameters and the credibility of the target air parameters, it includes: Obtain the vehicle operation information of the target vehicle, where the vehicle operation information is used to represent the operation record of the target vehicle within a target time period; Adjust the air conditioning parameters of the target vehicle according to the target air parameters and the vehicle operation information of the target vehicle.

5. The method according to claim 4, wherein, The adjusting the air conditioning parameters of the target vehicle according to the target air parameters and the credibility of the target air parameters includes at least one of the following: When the vehicle operation information indicates that a target in-vehicle device in the target vehicle is in an on state, determine whether to keep the target in-vehicle device in the on state according to the target air parameters, where the target in-vehicle device is used to adjust the air quality inside the target vehicle; When the vehicle operation information indicates that a target in-vehicle device in the target vehicle is in an on state, adjust the working parameters of the target in-vehicle device according to the target air parameters, and the air conditioning parameters include the working parameters; When the vehicle operation information indicates that a target in-vehicle device in the target vehicle is in an off state, determine whether to adjust the target in-vehicle device to the on state according to the target air parameters, and when the target in-vehicle device is adjusted to the on state, adjust the working parameters according to the target air parameters.

6. The method according to any one of claims 1 to 5, wherein, The inputting the target image into a deep learning model to identify the target image and obtaining a model output includes: Input the target image into a first image recognition model, where the first image recognition model is a model for recognizing image pixels obtained by training with a plurality of sample image data; Obtain a first image recognition result output by the image recognition model, where the first image recognition result is used to represent the air quality index of the environment where the target vehicle is currently located; after the inputting the target image into a deep learning model to identify the target image and obtaining a model output, it includes: Obtain first air parameters according to the first image recognition result.

7. The method according to claim 6, wherein, The obtaining first air parameters according to the first image recognition result includes: Obtain historical image recognition results output by the first image recognition model within a predetermined time period; Obtain second air parameters according to the historical image recognition results; Obtain the target air parameters according to the first air parameters and the second air parameters.

8. The method according to claim 6, It is characterized in that inputting the target image into a deep learning model, recognizing the target image, and obtaining a model output, further comprising: inputting the target image into a second image recognition model, wherein the second image recognition model is a model for recognizing image categories obtained by training with a plurality of sample image data; obtaining a second image recognition result output by the image recognition model, wherein the second image recognition result is used to represent the environmental category of the environment where the target vehicle is currently located; after inputting the target image into the deep learning model, recognizing the target image, and obtaining the model output, comprising: obtaining a third air parameter according to the second image recognition result.

9. The method according to any one of claims 1 to 5, It is characterized in that before adjusting the air conditioning parameters of the target vehicle according to the target air parameter and the credibility of the target air parameter, comprising: displaying a first prompt message, wherein the first prompt message is used to prompt that the air quality inside the target vehicle currently meets the adjustment condition of the air conditioning parameters; during the process of adjusting the air conditioning parameters of the target vehicle according to the target air parameter and the credibility of the target air parameter, comprising: displaying a second prompt message, wherein the second prompt message is used to prompt the adjustment process of the air conditioning parameters; after adjusting the air conditioning parameters of the target vehicle according to the target air parameter and the credibility of the target air parameter, comprising: displaying a third prompt message, wherein the third prompt message is used to prompt that the air conditioning parameters have been adjusted.

10. An in-vehicle air quality adjustment device, It is characterized in that comprising: an acquisition unit, configured to acquire image data collected by an in-vehicle image acquisition device of a target vehicle, preprocess the collected image data, and acquire a target image associated with the target vehicle, wherein the target image is used to represent the environmental condition where the target vehicle is currently located, and the environmental condition where the target vehicle is currently located includes the environmental condition of the current in-vehicle environment of the target vehicle and the environmental condition of the current out-of-vehicle environment, and the preprocessing is to perform cropping processing on the collected image data, crop the area irrelevant to the out-of-vehicle air quality, and perform contrast enhancement processing on the collected image data; a recognition unit, configured to input the target image into a deep learning model, recognize the target image, and obtain a model output, wherein the model output includes the air quality index of the environment where the target vehicle is currently located and the target environmental category of the environment where the target vehicle is currently located; the device is further configured to vote on the outputs of the classification model in the most recent x frames when the deep learning model is a discrete quantity classification model, and obtain a voting result that conforms to the majority principle, wherein the voting result is used to correct the model output. The device is further configured to, when the deep learning model is an image segmentation model of a pixel category, average the outputs of the most recent x frames of the image segmentation model to obtain an average pollution range, where the average pollution range is used to correct the model output; The first determination sub-module is configured to, when the air quality index reaches a target threshold, determine the air parameter corresponding to the air quality index as the target air parameter; The second determination sub-module is configured to, when the air quality index does not reach the target threshold, determine the predicted air parameter of the target vehicle according to the air quality index and the target environmental category, where the predicted air parameter is used to represent the air quality of the environment where the target vehicle is predicted to be in a preset time period in the future; The device is further configured to, when the target air parameter indicates that there is poor air quality, obtain the credibility of the target air parameter through multi-dimensional information, where the multi-dimensional information includes the location where the target vehicle is located, map information, and the driving speed of the target vehicle, and the credibility of the target air parameter is used to represent the probability of poor air quality outside the vehicle; The adjustment unit is configured to adjust the air conditioning parameter of the target vehicle according to the target air parameter and the credibility of the target air parameter, where the air conditioning parameter is used to adjust the air quality inside the target vehicle.

11. A computer-readable storage medium, characterized in that, the computer-readable storage medium includes a stored program, where the program, when running, executes the method described in any one of claims 1 to 9 above.

12. An electronic device, including a memory and a processor, characterized in that, a computer program is stored in the memory, and the processor is configured to execute the method described in any one of claims 1 to 9 through the computer program.

Images