Vehicle washing method, recommendation method, vehicle and wearable device

Abstract

The invention discloses a vehicle washing method, a recommendation method, a vehicle and wearable equipment, and belongs to the technical field of vehicle control. The vehicle washing method comprises the steps that in response to a received instruction for starting a vehicle washing mode, position information of the vehicle is obtained to serve as a text prompt, and external environment information of the vehicle serves as a picture prompt; the text prompt and the picture prompt are spliced to obtain an input prompt, and the weight of the text prompt is in direct proportion to the positioning precision and description definition of the position information; inputting the input prompt into a large-scale language model to obtain a vehicle washing place type of the vehicle output by the large-scale language model; and vehicle washing setting items corresponding to the vehicle washing place types are obtained, and vehicle state setting is carried out based on the vehicle washing setting items.

Description

Technical Field

[0001] The present application relates to the field of vehicle control, and in particular to a car washing method, a recommendation method, a vehicle and a wearable device. Background Art

[0002] With the development of car washing equipment and the updating and iteration of car washing functions, the way of car washing has evolved from manual car washing to semi-automatic car washing and then to unmanned car washing.

[0003] The control of the vehicle by the car computer has also changed with the development of car washing methods. At present, there are car washing control items designed to support unmanned car washing scenarios. However, the car computer does not consider the adaptation of manual car washing, semi-automatic car washing, etc., resulting in poor user experience. Summary of the invention

[0004] In a first aspect, an embodiment of the present application provides a car washing method, which is applied to a vehicle, comprising: In response to receiving an instruction to start a car wash mode, obtaining the location information of the vehicle as a text prompt and the external environment information of the vehicle as a picture prompt; splicing the text prompt and the picture prompt to obtain an input prompt, wherein the weight of the text prompt is proportional to the positioning accuracy and description clarity of the position information; Inputting the input prompt into a large language model to obtain the type of car wash location where the vehicle is located output by the large language model; A car wash setting item corresponding to the car wash location type is acquired, and a vehicle state setting is performed based on the car wash setting item.

[0005] In some embodiments, at least one of the following is also included: Determine the location information of the vehicle based on at least one of the latitude and longitude information of the vehicle and the location information of the vehicle; Based on the external camera of the vehicle, the external environment information of the vehicle is obtained.

[0006] In some embodiments, the obtaining of the car wash setting items corresponding to the car wash location type includes: If it is determined that the car wash location type is an automatic machine car wash or a self-service manual car wash, then car wash setting items corresponding to the controllable components supported by the car wash location type and the vehicle model are obtained.

[0007] In some embodiments, the vehicle status setting based on the car wash setting item includes: Determining that the type of the car wash location is an automatic machine car wash, closing at least one of the rearview mirror, sunroof, window, trunk and wiper of the vehicle; Determining that the type of the car wash location is a self-service manual car wash, disabling the vehicle lock function, and closing at least one of the rearview mirror, sunroof, window, trunk, and wiper of the vehicle; If it is determined that the car wash location type is a manual car wash in a car wash shop, the vehicle computer setting function is disabled, and at least one of the rearview mirror, sunroof, window, trunk and wiper of the vehicle is turned off.

[0008] In some embodiments, before setting the vehicle status based on the car wash setting item, the method further includes: Determining that the type of the car wash location is an automatic machine car wash or a self-service manual car wash, obtaining guidance information matching the car wash machine model in the car wash location where the vehicle is located; Playing the guidance information on the vehicle-mounted terminal of the vehicle; In response to detecting a shift of the vehicle owner's attention in one process of the guidance information, a device to which the vehicle owner's attention is shifted is determined, and the one process and subsequent processes of the guidance information are sent to the shifting device.

[0009] In some embodiments, it also includes: Determining that the type of the car wash place is a manual car wash in a car wash shop, summarizing the historical evaluations of the car wash places where the vehicle is located to obtain evaluation focus information of the car wash places; Receiving car body images before and after car washing sent by a wearable device; Car wash evaluation information is generated based on at least one of the evaluation focus point information and the vehicle body images before and after the car wash.

[0010] In a second aspect, an embodiment of the present application provides a method for recommending a car wash mode, which is applied to a wearable device that establishes a communication connection with a vehicle, including: In response to receiving a message from the vehicle indicating that the type of car wash place is a self-service manual car wash, the wearer is guided to take a photo of the body of the vehicle to obtain a body image of the vehicle; the type of car wash place is obtained by the vehicle based on inputting an input prompt into a large language model, the input prompt is obtained by splicing a text prompt and a picture prompt, the text prompt is the location information of the vehicle, the picture prompt is the external environment information of the vehicle, and the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; Based on the vehicle body image, a car wash mode is recommended to the wearer.

[0011] In some embodiments, it also includes: Determining that the type of the car wash location is an automatic machine car wash or a self-service manual car wash, and receiving guidance information sent by the vehicle; Collecting a status image of a car washing machine, and determining a real-time status of the car washing machine based on the status image; Based on the guidance information and the real-time status, operation prompts are provided.

[0012] In some embodiments, it also includes: During the car wash process, images of the car body area being washed are collected; Performing a dirt analysis on the vehicle body area image to obtain a dirt analysis result; At least one of a contamination prompt and a cleaning guidance is performed based on the contamination analysis result.

[0013] In a third aspect, an embodiment of the present application provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the methods described above is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a wearable device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described above is implemented.

[0015] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the methods described above.

[0016] In a sixth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements any of the methods described above when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic flow chart of a car washing method provided in accordance with an embodiment of the present application.

[0019] Figure 2 This is a schematic diagram of a car wash scene provided by an embodiment of the present application.

[0020] Figure 3 This is a schematic diagram of a car wash scene provided by an embodiment of the present application.

[0021] Figure 4 A schematic flow chart of a method for recommending a car wash mode according to an embodiment of the present application.

[0022] Figure 5 It is a schematic diagram of the structure of a vehicle provided in one embodiment of the present application.

[0023] Figure 6 It is a schematic diagram of the structure of a wearable device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0026] With the development of car washing equipment and the updating and iteration of car washing functions, the way of car washing has evolved from manual car washing to semi-automatic car washing and then to unmanned car washing.

[0027] The control of the vehicle by the car computer has also changed with the development of car washing methods. Currently, there are car wash control items designed to support unmanned car washing scenarios. For example, the car computer can send a command to enter the car wash mode to the body control system and air-conditioning system. The body control system controls the windows, sunroof, rearview mirrors, and wipers to close, and the air-conditioning system controls the air-conditioning to close, to adapt to the unmanned car washing scenario.

[0028] However, the car wash control items customized for unmanned car wash scenarios are not necessarily suitable for manual car wash, semi-automatic car wash and other situations, and may even cause problems for the execution of manual car wash and semi-automatic car wash. The current car computer does not consider the adaptation of manual car wash, semi-automatic car wash and other situations, resulting in poor user experience.

[0029] To this end, the present application provides a car washing method, which uses a large language model (LLM) to perceive the type of car wash place where the vehicle is located, and then sets the vehicle status based on the car wash setting items corresponding to the car wash place type. It can adapt to various car washing scenarios in a targeted manner, thereby optimizing the user experience.

[0030] In some embodiments, the car washing method can be implemented by the vehicle as the execution subject, specifically, by the vehicle computer inside the vehicle as the execution subject. The vehicle computer refers to the vehicle terminal, that is, the terminal set inside the vehicle for realizing human-computer interaction, providing various optional functions, such as viewing and controlling the vehicle status, booking and using vehicle-related services (such as car washing, refueling, etc.), and Internet-based applications such as online social networking, web browsing, etc. Another example is the vehicle's positioning and navigation function, multimedia playback function, etc.

[0031] In some embodiments, a wearable device that establishes a communication connection with a vehicle can recommend a car wash mode based on the type of car wash location sent by the vehicle and the image of the vehicle body captured by the wearable device. Wearable devices can be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as gloves, watches, AR (Augmented Reality) head-mounted display devices, VR (Virtual Reality) head-mounted display devices, or MR (Mixed Reality) head-mounted display devices equipped with far-field communication modules and / or near-field communication modules.

[0032] Figure 1 A schematic diagram of a car washing method provided by an embodiment of the present application. Figure 1 As shown, a car washing method is provided, which can be applied to a vehicle. The method includes the following steps: step 110, step 120, step 130, and step 140. The method flow steps are only used as a possible implementation of the present application.

[0033] Step 110 , in response to receiving an instruction to start a car wash mode, obtaining the location information of the vehicle as a text prompt and the external environment information of the vehicle as a picture prompt.

[0034] Specifically, when the user is ready to wash the vehicle, he can input a command to start the car wash mode to the vehicle through human-computer interaction. Here, the form of human-computer interaction can be voice interaction, button interaction, touch screen interaction, gesture interaction, etc., which is not specifically limited in the embodiment of the present application.

[0035] Accordingly, the vehicle may receive an instruction to start the car wash mode. It is understandable that the instruction to start the car wash mode is a trigger signal for the vehicle to start the car wash mode. After receiving the instruction to start the car wash mode, the vehicle may respond to the instruction to start the car wash mode, and the specific response method is to obtain the vehicle's location information and the vehicle's external environment information.

[0036] The vehicle location information is used to reflect the location of the vehicle. The vehicle location information can be specifically expressed as the latitude and longitude information of the vehicle, such as the latitude and longitude of the vehicle, or can be expressed as the location information of the location of the vehicle, such as "XX car wash shop", or the street and house number of XX car wash shop, etc., which is not specifically limited in the embodiments of the present application.

[0037] The vehicle's external environment information is used to reflect the environment outside the vehicle. The vehicle's external environment information can be specifically represented as an image of the vehicle's external environment, or a video of the vehicle's external environment, etc., which is not specifically limited in the embodiments of the present application.

[0038] It is understandable that the location information of the vehicle can reflect the location of the vehicle, from which the type of location where the car is currently washed can be inferred. For example, some locations support automatic machine car washing, some locations may support self-service manual car washing, and some locations may support manual car washing in car wash shops. The location information of the vehicle can be represented in the form of text, so it can be used as a text prompt input into a large language model to predict the type of car wash location where the vehicle is located. The text prompt here is input into the large language model in the form of text to guide the large language model to determine the type of car wash location where the vehicle is located.

[0039] The vehicle's external environment information can reflect the environment outside the vehicle. Specifically, when the vehicle is about to be washed, the external environment information can reflect the environment of the car wash where the vehicle is located, from which the type of place where the car is currently being washed can be inferred. The vehicle's external environment information can be represented in the form of a picture, so it can be used as a picture prompt input into a large language model to predict the type of car wash place the vehicle is in. The picture prompt here is input into the large language model in the form of a picture to guide the large language model to determine the type of car wash place where the vehicle is located.

[0040] For example, Figure 2 Schematic diagram of a car wash scene provided by an embodiment of the present application. Figure 2 As shown, a camera may be provided outside the vehicle. Figure 2The dotted line in is the camera's field of view. The camera can capture the external environment where the vehicle is located. For example, when the vehicle is in a car wash, the camera can capture images of the car wash including "XX self-service car wash" as the external environment information of the vehicle.

[0041] Step 120: splicing the text prompt and the picture prompt to obtain an input prompt, wherein the weight of the text prompt is proportional to the positioning accuracy and description clarity of the position information.

[0042] Specifically, after obtaining the text prompt and the picture prompt respectively, the two can be spliced ​​together, and the spliced ​​result can be used as the input prompt. The input prompt here is the prompt input into the large language model to guide the large language model to determine the type of car wash place where the vehicle is located. It can be understood that the input prompt obtained in this way combines the content of the vehicle's location information as a text prompt and the vehicle's external environment information as a picture prompt, and can comprehensively reflect the relevant information of the car wash place where the vehicle is located from both text and picture modes, thereby providing rich reference information for predicting the type of car wash place where the vehicle is located based on the large language model.

[0043] Furthermore, when the text prompt and the picture prompt are combined, it can be realized based on the weight of the two. The weight of the text prompt is proportional to the positioning accuracy of the position information itself and the description clarity of the position information.

[0044] It is understandable that the positioning accuracy of the location information can reflect the degree of refinement of the vehicle's location representation by the location information. The higher the positioning accuracy, the finer the representation of the vehicle's location by the location information, and the more reliable the type of car wash location the vehicle is located in based on the location information analysis. Therefore, the weight of the text prompt can be proportional to the positioning accuracy of the location information, that is, the higher the positioning accuracy of the location information, the higher the weight of the text prompt, the greater the proportion of the text prompt in the input prompt, and the greater the reliance on the text prompt when inferring the type of car wash location the vehicle is located in based on the large language model.

[0045] The clarity of the description of the location information refers to the level of detail, accuracy, and ease of understanding of the information provided when describing the location of the vehicle. The higher the clarity of the description, the more accurate the representation of the vehicle's location by the location information, and the more reliable the type of car wash location the vehicle is located in based on the analysis of the location information. Therefore, the weight of the text prompt can be proportional to the clarity of the description of the location information, that is, the higher the clarity of the description of the location information, the higher the weight of the text prompt, the greater the proportion of the text prompt in the input prompt, and the greater the reliance on the text prompt when inferring the type of car wash location the vehicle is located in based on the large language model.

[0046] In addition, the weight of the picture prompt may be based on the weight of the text prompt. For example, the weight of the picture prompt may be expressed as the difference between 1 and the weight of the text prompt.

[0047] By weighting the text prompts and the picture prompts when they are concatenated, the resulting input prompts can carry not only the text prompts and the picture prompts, but also the degree of influence of the text prompts and the picture prompts on the type of car wash location where the vehicle is located as output by the final large language model, thereby controlling the reasoning process of the large language model and optimizing the reasoning effect of the large language model.

[0048] Step 130: input the input prompt into a large language model to obtain the type of car wash location where the vehicle is located output by the large language model.

[0049] Specifically, after obtaining the input prompt, the input prompt can be input into the large language model as a prompt, and the large language model infers the type of car wash location where the vehicle is located based on the input prompt, thereby obtaining the type of car wash location where the vehicle is located output by the large language model.

[0050] Here, the large language model is trained based on large-scale text data and can understand and generate human language, including answering questions, translating texts, summarizing articles, creating content, and other tasks. Large language models usually contain billions or even trillions of parameters, and capture the statistical laws and patterns of language through complex neural network structures. Applying a large language model to the embodiment of the present application and inferring the type of car wash where the vehicle is located under the guidance of input prompts can greatly improve the efficiency and accuracy of judging the type of car wash.

[0051] It is understandable that the type of car wash place thus obtained, that is, the type of car wash place where the vehicle is currently located, can be, for example, any one of automatic machine car wash, self-service manual car wash and manual car wash in a car wash shop. Among them, automatic machine car wash is aimed at unmanned car wash scenarios, self-service manual car wash and manual car wash in a car wash shop are aimed at manual car wash scenarios, and the difference between self-service manual car wash and manual car wash in a car wash shop is that self-service manual car wash requires the car owner to wash the car by himself, while manual car wash in a car wash shop is performed by the staff of the car wash shop.

[0052] Step 140: Acquire car wash setting items corresponding to the type of the car wash place, and set the vehicle status based on the car wash setting items.

[0053] Specifically, since there are differences in the way of washing a car in different types of car wash places, corresponding car wash setting items can be pre-configured for different types of car wash places, so that each type of car wash place has corresponding car wash setting items that can specifically adapt to the car washing method under the type of car wash place.

[0054] Therefore, after obtaining the type of car wash place where the vehicle is located, the car wash setting items corresponding to the type of car wash place can be obtained, and based on the obtained car wash setting items corresponding to the type of car wash place, corresponding status settings can be performed for the vehicle, so that the vehicle after the status setting can be more adapted to the car wash operation under the type of car wash place.

[0055] For example, the car wash setting items may include status setting items for the vehicle's rearview mirror, sunroof, trunk, wipers, etc., and the vehicle status setting may be performed based on the car wash setting items, and the vehicle's rearview mirror, sunroof, trunk, wipers, etc. may be controlled to be closed.

[0056] In the embodiment of the present application, the vehicle's location information and the vehicle's external environment information are used as text prompts and picture prompts respectively, and the text prompts and picture prompts are spliced ​​to obtain input prompts, and the input prompts are input into a large language model to infer the type of car wash place for the vehicle, thereby achieving accurate and reliable judgment of the type of car wash place and improving the efficiency of judging the type of car wash place. Thus, a car wash setting item corresponding to the type of car wash place can be set for the vehicle, so that the vehicle can automatically adapt to the car wash operation under the type of car wash place after the state setting, thereby improving the intelligence of the vehicle in the car wash scene and optimizing the user experience.

[0057] It should be noted that each implementation method of the present application can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0058] In some embodiments, the above-mentioned car washing method further comprises: The location information of the vehicle is determined based on at least one of the latitude and longitude information of the vehicle and the location information of the vehicle.

[0059] Specifically, the location information of the vehicle can be determined based on at least one of the latitude and longitude information of the vehicle and the location information of the vehicle.

[0060] The latitude and longitude information of the vehicle is obtained through the Global Positioning System (GPS) or other similar satellite positioning technologies. The latitude and longitude information directly provides the precise position of the vehicle on the surface of the earth. The latitude and longitude are usually expressed in the form of degrees (°), minutes ('), and seconds (").

[0061] The location information of the vehicle refers to the specific location or area where the vehicle is currently located, such as "XX Car Wash Shop in City A", "CC Self-service Car Wash Center in City B", etc. The location information is usually obtained through at least one of the following technical means: map matching, Wi-Fi positioning, Bluetooth beacon, mobile network base station positioning, etc., or can also be obtained through user input (such as manual location selection).

[0062] After obtaining the latitude and longitude information of the vehicle or the location information of the vehicle, the latitude and longitude information of the vehicle or the location information of the vehicle can be directly used as the location information of the vehicle; or, when both the latitude and longitude information of the vehicle and the location information of the vehicle are obtained, the two can be combined to obtain accurate vehicle location information obtained through multi-source positioning.

[0063] In some embodiments, the above-mentioned car washing method further comprises: Based on the external camera of the vehicle, the external environment information of the vehicle is obtained.

[0064] Specifically, the vehicle's external cameras are mainly used to capture visual information around the vehicle. The visual information collected is crucial for the vehicle's environmental perception, path planning, obstacle detection and safe driving.

[0065] The external camera can capture optical images around the vehicle. Specifically, when the vehicle is about to be washed, the optical image captured by the external camera may contain environmental information of the car wash location, such as the model of the car wash machine. The collected optical image can be used as external environmental information to assist the large language model in determining the type of car wash location where the vehicle is located.

[0066] In some embodiments, in step 140, obtaining the car wash setting items corresponding to the car wash location type includes: If it is determined that the car wash location type is an automatic machine car wash or a self-service manual car wash, then car wash setting items corresponding to the controllable components supported by the car wash location type and the vehicle model are obtained.

[0067] Specifically, when it is determined that the type of car wash location where the vehicle is located is an automatic machine car wash or a self-service manual car wash, when obtaining the car wash setting items corresponding to the type of car wash location, the model of the vehicle also needs to be considered.

[0068] It is understandable that different models of vehicles may support different control components. For example, for some models of vehicles, these vehicles support automatic switching of rearview mirrors, while for other models of vehicles, these vehicles do not support automatic switching of rearview mirrors.

[0069] Therefore, when obtaining car wash setting items corresponding to the car wash location type, it is necessary not only to consider which components the car wash location type itself needs to control, but also to consider which components the vehicle model actually supports controlling, thereby obtaining car wash setting items that are consistent with the car wash location type where the vehicle is located and that the vehicle itself can support controlling. For example, the car wash setting items under the car wash location type suitable for the vehicle model can be obtained from the cloud or vehicle-side database.

[0070] In the embodiment of the present application, the car wash setting items are determined in combination with the type of car wash location and the model of the vehicle, thereby ensuring the feasibility of setting the vehicle status based on the car wash setting items, and enabling the vehicle after the vehicle status is set in this way to automatically adapt to the car wash operation under the car wash location type, thereby improving the intelligence of the vehicle in the car wash scenario and optimizing the user experience.

[0071] In some embodiments, in step 140, the vehicle status setting based on the car wash setting item includes: Determining that the type of the car wash location is an automatic machine car wash, closing at least one of the rearview mirror, sunroof, window, trunk and wiper of the vehicle; Determining that the type of the car wash location is a self-service manual car wash, disabling the vehicle lock function, and closing at least one of the rearview mirror, sunroof, window, trunk, and wiper of the vehicle; If it is determined that the car wash location type is a manual car wash in a car wash shop, the vehicle computer setting function is disabled, and at least one of the rearview mirror, sunroof, window, trunk and wiper of the vehicle is turned off.

[0072] Specifically, when it is determined that the type of car wash place is an automatic machine car wash, the car wash setting items include at least one of the vehicle's rearview mirror, sunroof, window, trunk and wiper. After determining the car wash setting items, at least one of the vehicle's rearview mirror, sunroof, window, trunk and wiper can be directly controlled to be closed, or after prompting the user to confirm, at least one of the vehicle's rearview mirror, sunroof, window, trunk and wiper can be controlled to be closed, thereby completing the vehicle state setting for the automatic machine car wash, so that the vehicle environment after the state setting can adapt to the fully automatic car wash machine used in the self-service machine car wash, ensuring that the vehicle parts will not be scratched, and preventing the vehicle from getting water during the automatic machine car wash process.

[0073] In the case where the type of car wash place is determined to be a self-service manual car wash, the car wash setting items may include a car lock function, and may also include at least one of the vehicle's rearview mirrors, sunroofs, windows, trunks, and wipers. After determining the car wash setting items, the car lock function may be directly disabled, and at least one of the vehicle's rearview mirrors, sunroofs, windows, trunks, and wipers may be controlled to be closed, or after prompting the user to confirm, the car lock function may be disabled, and at least one of the vehicle's rearview mirrors, sunroofs, windows, trunks, and wipers may be controlled to be closed, thereby completing the vehicle status setting for self-service manual car washes, so that the vehicle environment after the status setting can adapt to the needs of self-service manual car washes, and ensure that the doors, windows, and trunks can be opened and closed at any time during the self-service manual car wash process, so that users can take items from the vehicle.

[0074] In the case where the type of car wash place is determined to be manual car wash at a car wash shop, the car wash setting items may include the car machine setting function, and may also include at least one of the vehicle's rearview mirror, sunroof, window, trunk, and wiper. After determining the car wash setting items, the car machine setting function may be directly disabled, and at least one of the vehicle's rearview mirror, sunroof, window, trunk, and wiper may be controlled to be closed, or after prompting the user for confirmation, the car machine setting function may be disabled, and at least one of the vehicle's rearview mirror, sunroof, window, trunk, and wiper may be controlled to be closed, thereby completing the vehicle status setting for manual car wash at a car wash shop, so that the vehicle environment after the status setting can adapt to the needs of manual car wash at a car wash shop, and ensure that the setting adjustments of the car machine are not changed during the manual car wash at a car wash shop, thereby ensuring the privacy and security of the car owner.

[0075] In some embodiments, in step 140, before setting the vehicle status based on the car wash setting item, the method further includes: Determining that the type of the car wash location is an automatic machine car wash or a self-service manual car wash, obtaining guidance information matching the car wash machine model in the car wash location where the vehicle is located; Playing the guidance information on the vehicle-mounted terminal of the vehicle; In response to detecting a shift of the vehicle owner's attention in one process of the guidance information, a device to which the vehicle owner's attention is shifted is determined, and the one process and subsequent processes of the guidance information are sent to the shifting device.

[0076] Specifically, when the car wash location type is automatic machine car wash, the user needs to operate the fully automatic car wash machine to ensure the normal use of the fully automatic car wash machine, and settle the bill after the full automatic car wash machine is used. In addition, when the car wash location type is self-service manual car wash, the user also needs to operate the self-service manual car wash machine to ensure the normal use of the self-service manual car wash machine, and settle the bill after the self-service manual car wash machine is used.

[0077] That is, whether the car wash location is an automatic machine car wash or a self-service manual car wash, the user is required to perform a series of operations on the car wash machine. In order to ensure that the user can use the car wash machine normally, guidance information matching the car wash machine model under the car wash location where the vehicle is located can be obtained. The guidance information here is information used to guide the user to correctly operate the car wash machine of this model to ensure the normal use of the car wash machine. For example, it can include steps for using the car wash machine, and can also include corresponding solution operations when the car wash machine is in various states. The embodiments of the present application do not specifically limit this.

[0078] After obtaining the guidance information, the guidance information can be played on the vehicle terminal. The vehicle terminal referred to here is the vehicle computer on the vehicle. The implementation form of playing the guidance information on the vehicle terminal can be to broadcast the guidance information in the form of voice, or to play the guidance information in the form of video or text, or to play the guidance information in the form of a combination of video and audio, which is not specifically limited in the embodiment of the present application.

[0079] It can be explained that the guidance information itself can be understood as a combination of multiple processes, that is, the guidance information itself contains the complete process of operating the car washing machine, which can be divided into multiple processes, that is, corresponding to multiple operation steps. For example, the first process can be to determine the vehicle model (such as sedan, SUV or more specific brand plus model, etc.) on the display area of ​​the car washing machine, the second process is to select the car washing mode, such as general washing, fine washing, etc., the third process is to make further selections on the car washing mode, such as selecting the brand of detergent, foam volume, water pressure strength, car washing time, etc., and the fourth process can be to start the car washing and scan the QR code for payment.

[0080] In the process of guiding information, the driver's attention can be detected in real time, and it can be determined whether the driver's attention is diverted. Here, the driver's attention refers to the attention state of the vehicle user. The driver's attention detection can be achieved through the in-vehicle camera. For example, the in-vehicle camera can be used to capture the driver's face in real time, especially the driver's eye movement, and then by analyzing the driver's eye tracking data, it can be determined whether the driver's line of sight deviates from the on-board terminal, thereby inferring whether the driver's attention has been diverted.

[0081] When it is detected that the driver's attention has shifted, the device to which the driver's attention has been shifted can be determined. The shifting device here refers to the electronic device to which the driver's attention has been shifted from the vehicle-mounted terminal, for example, it can be the electronic device to which the driver's sight is directed after it has shifted away from the vehicle-mounted terminal. For example, if the driver is not watching the guidance information played by the vehicle-mounted device, but is operating a mobile phone, the mobile phone can be used as a shifting device.

[0082] After determining the transfer device, a process of the guidance information being played on the vehicle-mounted terminal and the subsequent processes of the process can be sent to the transfer device, so that the transfer device can continue the playback progress of the guidance information by the vehicle-mounted terminal and continue to play the guidance information, thereby ensuring that the user can understand the usage guidance of the car wash machine through the transfer device, so that the user can use the car wash machine correctly.

[0083] In some embodiments, the car washing method further comprises: Determining that the type of the car wash place is a manual car wash in a car wash shop, summarizing the historical evaluations of the car wash places where the vehicle is located to obtain evaluation focus information of the car wash places; Receiving car body images before and after car washing sent by a wearable device; Car wash evaluation information is generated based on at least one of the evaluation focus point information and the vehicle body images before and after the car wash.

[0084] Specifically, when the car wash location type is a manual car wash in a car wash shop, after the manual car wash is completed, it is necessary to inspect the car wash effect and evaluate the car wash shop. In an embodiment of the present application, a method for intelligently generating car wash evaluation information is provided, thereby realizing intelligent evaluation of the car wash experience.

[0085] When evaluating a car wash, you can refer to the historical evaluation of the car wash where the vehicle is located. Specifically, you can collect a large number of historical users' historical evaluations of the car wash where the vehicle is located from the Internet, for example, you can crawl the historical evaluations of the car wash where the vehicle is located. After obtaining the historical evaluation of the car wash where the vehicle is located, you can summarize the historical evaluations and obtain the evaluation focus information of the car wash from them. Here, summarizing the historical evaluations can specifically identify high-frequency words, phrases or themes in the historical evaluations, or count the number of each type of evaluation indicators in the historical evaluations, and then summarize the good review rate, bad review rate, etc. of each type of evaluation indicators. The embodiment of the present application does not specifically limit this. The evaluation focus information thus obtained, that is, the information obtained based on the historical evaluation that prompts the user to pay attention to, can specifically be the information extracted based on the historical evaluation that can accurately reflect the general evaluation of the car wash by historical users. It can be understood that the evaluation focus information thus obtained can prompt the user to focus on the possible problems of the car wash when accepting the car wash results.

[0086] In addition, when evaluating a car wash, you can also refer to the vehicle body images before and after the car wash. Here, the vehicle body images before and after the car wash can be taken by the user through the wearable device carried by the user before and after the car wash. It can be understood that by comparing the vehicle body images before and after the car wash, the car wash effect can be intuitively displayed.

[0087] Thus, the car wash evaluation information can be generated based on the evaluation focus information or the car body images before and after the car wash, or the car wash evaluation information can be generated by combining the evaluation focus information and the car body images before and after the car wash. For example, at least one of the evaluation focus information and the car body images before and after the car wash can be input into the large language model, and the large language model outputs the car wash evaluation information. Moreover, after the large language model outputs the car wash evaluation information, the user can also adjust the content of the car wash evaluation information.

[0088] In an embodiment of the present invention, car wash evaluation information can be generated based on at least one of the evaluation focus point information and the car body images before and after car washing, thereby realizing the intelligent generation of car wash experience evaluation, greatly improving the intelligence level of car wash experience evaluation, and optimizing user experience.

[0089] Figure 3 This is a schematic diagram of a car wash scene provided by an embodiment of the present application. Figure 3 A car wash scenario is provided, which reflects the car wash situation when the car wash location type is a self-service manual car wash. Figure 3 The vehicle, the personnel, and the car washing tools held by the personnel are included. The personnel are the owners of the vehicle, and the owners wear smart glasses that have established a communication connection with the vehicle. In the case of this self-service manual car wash, the smart glasses worn by the owner can interact with the vehicle, thereby providing guidance for the owner to wash the car by himself.

[0090] Figure 4 A flow chart of a method for recommending a car wash mode according to an embodiment of the present application. Figure 4 As shown, a method for recommending a car wash mode is provided, which can be applied to a wearable device that has a communication connection with a vehicle, for example, Figure 3 The smart glasses worn by the car owner are shown. The method includes the following steps: step 410, step 420. The steps of the method flow are only a possible implementation of the present application.

[0091] Step 410, in response to receiving the information sent by the vehicle that the type of car wash place is a self-service manual car wash, guiding the wearer to take a picture of the body of the vehicle to obtain a body image of the vehicle; the type of car wash place is the output of the vehicle based on inputting the input prompt into a large language model, the input prompt is obtained by splicing a text prompt and a picture prompt, the text prompt is the location information of the vehicle, the picture prompt is the external environment information of the vehicle, and the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information.

[0092] Specifically, when preparing to clean the vehicle, the vehicle can obtain the vehicle's location information and the vehicle's external environment information.

[0093] The vehicle location information is used to reflect the location of the vehicle. The vehicle location information can be specifically expressed as the latitude and longitude information of the vehicle, such as the latitude and longitude of the vehicle, or can be expressed as the location information of the location of the vehicle, such as "XX car wash shop", or the street and house number of XX car wash shop, etc., which is not specifically limited in the embodiments of the present application.

[0094] The vehicle's external environment information is used to reflect the environment outside the vehicle. The vehicle's external environment information can be specifically represented as an image of the vehicle's external environment, or a video of the vehicle's external environment, etc., which is not specifically limited in the embodiments of the present application.

[0095] It is understandable that the location information of the vehicle can reflect the location of the vehicle, from which the type of location where the car is currently washed can be inferred. For example, some locations support automatic machine car washing, some locations may support self-service manual car washing, and some locations may support manual car washing in car wash shops. The location information of the vehicle can be represented in the form of text, so it can be used as a text prompt input into a large language model to predict the type of car wash location where the vehicle is located. The text prompt here is input into the large language model in the form of text to guide the large language model to determine the type of car wash location where the vehicle is located.

[0096] The vehicle's external environment information can reflect the environment outside the vehicle. Specifically, when the vehicle is about to be washed, the external environment information can reflect the environment of the car wash where the vehicle is located, from which the type of place where the car is currently being washed can be inferred. The vehicle's external environment information can be represented in the form of a picture, so it can be used as a picture prompt input into a large language model to predict the type of car wash place the vehicle is in. The picture prompt here is input into the large language model in the form of a picture to guide the large language model to determine the type of car wash place where the vehicle is located.

[0097] After obtaining the text prompt and the picture prompt respectively, the vehicle can splice the two together and use the spliced ​​result as the input prompt. The input prompt here is the prompt input into the large language model to guide the large language model to determine the type of car wash place where the vehicle is located. It can be understood that the input prompt obtained in this way combines the location information of the vehicle as a text prompt and the external environment information of the vehicle as a picture prompt. It can fully reflect the relevant information of the car wash place where the vehicle is located from both text and picture modes, thereby providing rich reference information for predicting the type of car wash place where the vehicle is located based on the large language model.

[0098] Furthermore, when combining text prompts and image prompts, the vehicle can be realized based on the weight of the two. Among them, the weight of the text prompt is proportional to the positioning accuracy of the location information itself and the description clarity of the location information.

[0099] It is understandable that the positioning accuracy of the location information can reflect the degree of refinement of the vehicle's location representation by the location information. The higher the positioning accuracy, the finer the representation of the vehicle's location by the location information, and the more reliable the type of car wash location the vehicle is located in based on the location information analysis. Therefore, the weight of the text prompt can be proportional to the positioning accuracy of the location information, that is, the higher the positioning accuracy of the location information, the higher the weight of the text prompt, the greater the proportion of the text prompt in the input prompt, and the greater the reliance on the text prompt when inferring the type of car wash location the vehicle is located in based on the large language model.

[0100] The clarity of the description of the location information refers to the level of detail, accuracy, and ease of understanding of the information provided when describing the location of the vehicle. The higher the clarity of the description, the more accurate the representation of the vehicle's location by the location information, and the more reliable the type of car wash location the vehicle is located in based on the analysis of the location information. Therefore, the weight of the text prompt can be proportional to the clarity of the description of the location information, that is, the higher the clarity of the description of the location information, the higher the weight of the text prompt, the greater the proportion of the text prompt in the input prompt, and the greater the reliance on the text prompt when inferring the type of car wash location the vehicle is located in based on the large language model.

[0101] In addition, the weight of the picture prompt may be based on the weight of the text prompt. For example, the weight of the picture prompt may be expressed as the difference between 1 and the weight of the text prompt.

[0102] By weighting the text prompts and the picture prompts by the vehicle when splicing them, the input prompts obtained in this way can carry not only the text prompts and the picture prompts, but also the degree of influence of the text prompts and the picture prompts on the type of car wash place where the vehicle is located as output by the final large language model, thereby controlling the reasoning process of the large language model and optimizing the reasoning effect of the large language model.

[0103] Subsequently, the vehicle can input the input prompt as a prompt into the large language model, and the large language model infers the type of car wash location where the vehicle is located based on the input prompt, thereby obtaining the type of car wash location where the vehicle is located output by the large language model.

[0104] Here, the large language model is trained based on large-scale text data and can understand and generate human language, including answering questions, translating texts, summarizing articles, creating content, and other tasks. Large language models usually contain billions or even trillions of parameters, and capture the statistical laws and patterns of language through complex neural network structures. Applying a large language model to the embodiment of the present application and inferring the type of car wash where the vehicle is located under the guidance of input prompts can greatly improve the efficiency and accuracy of judging the type of car wash.

[0105] It is understandable that the type of car wash place thus obtained, that is, the type of car wash place where the vehicle is currently located, can be, for example, any one of automatic machine car wash, self-service manual car wash and manual car wash in a car wash shop. Among them, automatic machine car wash is aimed at unmanned car wash scenarios, self-service manual car wash and manual car wash in a car wash shop are aimed at manual car wash scenarios, and the difference between self-service manual car wash and manual car wash in a car wash shop is that self-service manual car wash requires the car owner to wash the car by himself, while manual car wash in a car wash shop is performed by the staff of the car wash shop.

[0106] When determining that the car wash location type is a self-service car wash type, the vehicle can send information that the car wash location type is an automatic car wash type to the wearable device. Accordingly, the wearable device can receive the information that the car wash location type is an automatic car wash type sent by the vehicle.

[0107] When receiving information that the type of car wash location is an automatic car wash type, the wearable device can respond to the received information, and specifically can issue a prompt message, and guide the wearer of the wearable device to photograph the body of the vehicle through the wearable device through the prompt message, thereby, the wearable device obtains the body image of the vehicle before washing.

[0108] The wearer here is usually the car owner himself, that is, the user who washes the car when the car wash place type is an automatic car wash type. The prompt information can be in the form of voice, image, etc. to prompt and guide the wearer to take the car body image.

[0109] Step 420: recommend a car wash mode to the wearer based on the vehicle body image.

[0110] Specifically, the vehicle body image thus captured can intuitively reflect the dirtiness of the vehicle body, so the car wash mode can be determined based on the vehicle body image, and then the car wash mode can be recommended to the wearer. The car wash mode here can be a normal, high pressure, foam and other vehicle washing modes. In the process of determining the car wash mode, the image analysis model can be applied to analyze the vehicle body image, thereby realizing the recognition and classification of the dirty areas in the vehicle body image. After obtaining the types of dirty areas in the vehicle body image, the corresponding car wash modes can be configured for various types of dirty areas, thereby realizing intelligent car wash mode recommendation.

[0111] In the embodiment of the present application, the vehicle's location information and the vehicle's external environment information are used as text prompts and picture prompts respectively, and the text prompts and picture prompts are spliced ​​to obtain input prompts, which are input into a large language model to infer the type of car wash place for the vehicle, thereby achieving accurate and reliable judgment of the type of car wash place and improving the efficiency of judging the type of car wash place. When the type of car wash place is determined to be a self-service manual car wash, the car wash mode is recommended by collecting the car body image, thereby achieving intelligent car wash mode recommendation and further optimizing the user experience.

[0112] In some embodiments, the car washing method further comprises: Determining that the type of the car wash location is an automatic machine car wash or a self-service manual car wash, and receiving guidance information sent by the vehicle; Collecting a status image of a car washing machine, and determining a real-time status of the car washing machine based on the status image; Based on the guidance information and the real-time status, operation prompts are provided.

[0113] Specifically, when the car wash location type is automatic machine car wash, the wearer needs to operate the fully automatic car wash machine to ensure the normal use of the fully automatic car wash machine, and settle the bill after the full automatic car wash machine is used. In addition, when the car wash location type is self-service manual car wash, the wearer also needs to operate the self-service manual car wash machine to ensure the normal use of the self-service manual car wash machine, and settle the bill after the self-service manual car wash machine is used.

[0114] That is, whether the car wash location is an automatic machine car wash or a self-service manual car wash, the wearer is required to perform a series of operations on the car wash machine. In order to ensure that the wearer can use the car wash machine normally, the vehicle can obtain guidance information that matches the model of the car wash machine under the car wash location where the vehicle is located. The guidance information here is information used to guide the user to correctly operate the car wash machine of this model to ensure the normal use of the car wash machine. For example, it may include steps for using the car wash machine, and may also include corresponding solution operations when the car wash machine is in various states. The embodiment of the present application does not specifically limit this.

[0115] Thus, after obtaining the guidance information, the vehicle can send the guidance information to the wearable device. Correspondingly, the wearable device can receive the guidance information sent by the vehicle.

[0116] The wearable device itself can collect images of the car washing machine in the car washing place where the vehicle is located, thereby obtaining a status image of the car washing machine. It can be understood that the status image here is an image that can reflect the status of the car washing machine, for example, it can be an image containing the content displayed on the screen of the car washing machine. After collecting the status image of the car washing machine, the wearable device can analyze the real-time status of the car washing machine based on the status image. Here, the analysis of the real-time status of the car washing machine can be obtained by classifying the status image or performing OCR (Optical Character Recognition) on the text content in the status image, and the embodiments of the present application do not specifically limit this. For example, the real-time status of the car washing machine obtained in this way can be one of the states of vehicle model selection, car washing mode selection, car washing details selection, payment, etc.

[0117] After obtaining the real-time status of the car washing machine, the real-time status of the car washing machine can be combined with the guidance information received from the vehicle to provide operation prompts, thereby prompting the wearer to operate the car washing machine according to the prompts. Furthermore, the guidance information can be divided into different operation prompts according to the different states of the car washing machine, so that after determining the real-time status of the car washing machine, the operation prompts corresponding to the real-time status can be matched from the guidance information and played and displayed. For example, when the real-time status is vehicle model selection, the operation prompts in the guidance information can prompt the wearer to select the model of the vehicle to be washed from the various vehicle models displayed by the car washing machine; for another example, when the real-time status is car washing mode selection, the operation prompts in the guidance information can prompt the wearer to select a car washing mode that is suitable for the dirtiness of the vehicle body from the various car washing modes displayed by the car washing machine. The embodiments of the present application do not specifically limit this.

[0118] In an embodiment of the present application, by combining the guidance information with the real-time status of the car washing machine, the wearable device can provide the wearer with timely and reliable operation prompts, thereby guiding the wearer to use the car washing machine correctly.

[0119] In some embodiments, the car washing method further comprises: During the car wash process, images of the car body area being washed are collected; Performing a dirt analysis on the vehicle body area image to obtain a dirt analysis result; At least one of a contamination prompt and a cleaning guidance is performed based on the contamination analysis result.

[0120] Specifically, for the case of a self-service robot manual car wash, when the wearer is washing the vehicle, the wearable device can collect an image of the vehicle body area being washed. It can be understood that the vehicle body area image here refers to the image of the area on the vehicle body being washed.

[0121] After obtaining the vehicle body area image, a dirt analysis can be performed on the vehicle body area image to obtain a dirt analysis result. The dirt analysis here can be performed by applying an image analysis model to analyze the vehicle body area image, thereby realizing the recognition and classification of the dirty area in the vehicle body area image. The image analysis model here can be GooLeNet, Vision Transformer, Swin Transformer, etc. In the dirt analysis result thus obtained, the dirty area in the vehicle body area image can be framed, for example, the upper left corner and lower right corner coordinates of the dirty area obtained by the image analysis model can be used to generate an identification frame, and the dirty area can be framed through the identification frame. In addition, in the dirt analysis results, the dirty areas in the vehicle body area image can also be classified according to the severity of the dirt. For example, the severity of the dirty areas can be classified through an image analysis model. After the dirt severity is obtained, the dirt severity can be directly identified, or identification frames of different colors can be used to reflect different dirt severity levels. For example, the dirt severity can be divided into 1-3 categories, with category 1 being the most serious and category 3 being the lightest. A red identification frame is used for category 1 dirt severity, a yellow identification frame is used for category 2 dirt severity, and a green identification frame is used for category 3 dirt severity. The embodiments of the present application do not make specific limitations on this.

[0122] After obtaining the dirt analysis results, the wearer can be prompted for dirt based on the dirt analysis results. The dirt prompt here can be to display the body area image through the wearable device, and identify the dirty area and the severity of the dirt in the dirty area in the body area image. It can also be that when the wearer cleans the dirty area, the wearer is prompted to focus on cleaning by vibration, sound, etc.

[0123] In addition, the wearer can also be guided to clean based on the results of the dirt analysis. The cleaning guidance here can be implemented through vibration, sound, image, etc. The specific guidance content may include the cleaning method of the dirty area, such as the recommended spraying conditions of a water gun or a foam gun, the appropriate car washing angle and pressure, the recommended cleaning steps and the direction of water spraying, etc. When providing cleaning guidance, the wearable device can broadcast in the form of voice how to deal with the current type of stains, and display the current degree of attention to cleaning on the display screen and in the glasses, and combine the spraying conditions of the water gun and foam gun of the car washing machine to dynamically and intelligently recommend the appropriate car washing angle and pressure, the appropriate car washing steps and the direction of water spraying, etc. in the form of voice or image, and through real-time detection, feedback on the cleaning situation in the form of voice, image, or vibration. For example, after the cleaning is completed, the wearer can be prompted to clean the next area in the form of vibration.

[0124] In addition, after cleaning is completed, the wearable device can also prompt the wearer how to check the cleanliness and how to deal with water stains, etc.

[0125] In an embodiment of the present application, by performing a dirt analysis on the image of the vehicle body area and providing the wearer with at least one of a dirt prompt and a cleaning guidance, the intelligence level of vehicle cleaning in the self-service robotic manual car wash scenario is effectively improved, and the user experience is optimized.

[0126] In some embodiments, the step of collecting an image of a vehicle body area being washed during a vehicle washing process includes: During the car washing process, the wearer's eyes are tracked, and images of the car body area being washed are collected based on the eye tracking results.

[0127] Specifically, while the wearer is washing the vehicle, the wearable device can track the wearer's eyes. Here, eye tracking is also called gaze tracking, which is a technology that uses sensors (such as infrared devices, image acquisition devices, etc.) set on wearable devices to capture and extract eye feature information, measure eye movement, and estimate the line of sight direction or the position of the eye's gaze point.

[0128] When the wearer is washing the vehicle, the wearer's eyes will notice the dirty area of ​​the vehicle body, that is, the area on the vehicle body to be cleaned. Therefore, the wearable device can track the wearer's eyes and locate the area of ​​the vehicle body that the wearer is looking at, that is, the area of ​​the vehicle body that is currently being cleaned. In this case, the wearable device can capture images based on the area of ​​the vehicle body indicated by the eye tracking results, thereby obtaining an image of the area of ​​the vehicle body being cleaned.

[0129] In the embodiment of the present application, the image of the vehicle body area is collected through eye tracking technology, thereby providing a basis for providing dirt prompts and cleaning guidance in a timely manner.

[0130] In some embodiments, the car washing method may include the following steps: First, determine the type of car wash location the vehicle is in by looking at the vehicle: The vehicle can collect its own location information as text prompts and collect external environment information as picture prompts, and input the text prompts and picture prompts into a large language model to apply the text parsing and recognition technology and image recognition and parsing technology of the large language model to infer the text prompts and picture prompts, thereby obtaining the type of car wash place where the vehicle is located, for example, it can be any one of automatic machine car wash, self-service manual car wash and manual car wash in a car wash shop.

[0131] On this basis, for the case where the car wash location type is an automatic machine car wash, the car washing method may also include the following steps: The vehicle can obtain the car wash setting items suitable for the vehicle model and adapted to the fully automatic car wash machine from the cloud / vehicle database. After prompting the user to confirm, the car wash setting items are executed, which may include closing the vehicle's rearview mirror, sunroof, windows, trunk, automatic wipers, etc. By executing the car wash setting items, the vehicle's environment is adapted to the fully automatic car wash machine, ensuring that the vehicle's rearview mirror, tail wing, and other parts will not be scratched.

[0132] In addition, the vehicle can match the model of the car wash machine from the cloud / vehicle-side database, obtain the corresponding guidance information suitable for novices, and display the guidance information through the vehicle system to inform the owner how to operate the current car wash machine and realize normal use of the car wash machine. After use, the vehicle system will prompt the owner to perform settlement operations.

[0133] In addition, the vehicle can also detect whether the owner's attention is diverted. If the vehicle system is displaying guidance information but the owner's attention is diverted, causing the owner to fail to view the guidance information displayed by the vehicle system, the vehicle can display the remaining guidance information through the owner's smart phone to inform the owner how to operate the current car wash machine and use the car wash machine normally. After use, the vehicle system can prompt the owner to perform settlement operations.

[0134] Alternatively, the vehicle can also match the model of the car wash machine from the cloud / vehicle database, obtain the corresponding guidance information suitable for novices, and transmit the guidance information to the AR smart glasses worn by the car owner, which will display the guidance information and provide the car owner with operation prompts for using the car wash machine. In this process, the AR smart glasses can obtain the real-time status of the car wash machine through the camera, and superimpose the operation guidance and sound prompts in the guidance information corresponding to the real-time status. Through real-time operation guidance, the car owner is gradually guided to operate the car wash machine and settle the account after completion, so that the car owner wearing AR smart glasses can directly perform the corresponding operation.

[0135] In the case where the car wash location type is a self-service robot manual car wash, the car wash method may further include the following steps: The vehicle can obtain the car wash settings that are suitable for the vehicle model and adapted to the manual automatic car wash machine from the cloud / vehicle database. After prompting the user to confirm, the association is executed to unlock the vehicle, close the windows, trunk, turn off the air conditioner, etc. By executing the car wash settings, the vehicle can keep the doors and windows open and close, and the trunk vacuumed at any time during the self-service car wash.

[0136] In addition, the vehicle can also match the model of the car wash machine through the database to obtain the corresponding guidance information for novices. In addition, the guidance information can be displayed through the car system, mobile phone or AR smart glasses to prompt the owner how to operate the current car wash machine. Among them, the specific method of displaying the guidance information is the same as that of the automatic machine car wash, which will not be repeated here.

[0137] In addition, car owners can use their mobile phones to collect information about the dirtiness of different parts and angles of the car body, and the mobile phone can intelligently recommend the appropriate car wash mode (normal, high pressure, foam). During the car wash process, when the mobile phone is matched with the UWB (Ultra Wide Band) of the car body, the vehicle can determine whether the mobile phone holder is passing through a specific location with severe dirt. Moreover, when it is determined that the mobile phone holder is passing through a specific location with severe dirt, the vehicle can control the mobile phone to play a prompt tone or vibrate the phone to remind the owner that the current location needs to be cleaned.

[0138] In addition, if the car owner is wearing AR smart glasses, the AR smart glasses can also collect the dirtiness of different parts and angles of the car body, and intelligently recommend the appropriate car wash mode (normal, high pressure, foam). During the car wash process, when the AR smart glasses pass by a specific dirty location, the AR smart glasses can also play a prompt tone or vibrate the glasses to remind the owner that the current location needs to be cleaned.

[0139] In the process of judging and analyzing dirt based on the real-time viewing function of AR smart glasses, the AR smart glasses can capture the current image (such as any one of the left body image, the right body image, the rear body image, the front cover body image and the top body image) through the camera when the wearer is washing the vehicle, and can use the image analysis model to classify the current image, thereby realizing the recognition and classification of the dirty area in the current image, and displaying the dirty area and the degree of dirtiness in the current image.

[0140] In addition, AR smart glasses also have eye tracking function. When the wearer's eyes notice a dirty area, the wearer will generally clean the dirty area. AR smart glasses can provide cleaning prompts through vibration / sound / image guidance, and after cleaning, they can prompt the owner through analysis on how to check the cleanliness and how to deal with water stains.

[0141] In the case where the car washing location type is a manual car washing shop, the car washing method may further include the following steps: The vehicle can obtain car wash settings suitable for the vehicle model and adapted to manual car washes at car wash shops from the cloud / car database. After prompting the user to confirm, the associated privacy mode is activated, and adjustments to the vehicle settings are not allowed. Only the doors, windows, rearview mirrors, trunks, etc. are allowed to be opened and closed. By executing the car wash settings, the privacy of the owner is guaranteed and the settings are not changed or adjusted.

[0142] Moreover, after the car wash is completed, the vehicle can search for historical reviews on the Internet, thereby summarizing and commenting on the historical reviews of the current car wash shop, prompting the car owner to pay attention to the problems of the car wash shop.

[0143] In addition, the method also supports the use of mobile phones or AR smart glasses to collect the cleaning conditions before and after the car wash, and compares the cleaning conditions before and after through artificial intelligence capabilities, and then intelligently generates a car wash experience evaluation. Moreover, the generated car wash experience evaluation supports car owners to adjust information, thereby realizing intelligent scoring and evaluation of the car wash experience.

[0144] Figure 5 An example of a physical structure diagram of a vehicle is shown below: Figure 5 As shown, the vehicle may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the car washing method, which includes: in response to receiving an instruction to start the car washing mode, obtaining the location information of the vehicle as a text prompt and the vehicle exterior environment information as a picture prompt; splicing the text prompt and the picture prompt to obtain an input prompt, wherein the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; inputting the input prompt into a large language model to obtain the type of car wash place where the vehicle is located output by the large language model; obtaining a car wash setting item corresponding to the type of car wash place, and setting the vehicle state based on the car wash setting item.

[0145] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0146] Figure 6 An example of a physical structure diagram of a wearable device is shown below. Figure 6 As shown, the wearable device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the car washing method, which includes: in response to receiving the information that the type of the car washing place sent by the vehicle is a self-service manual car washing, guiding the wearer to shoot the body of the vehicle to obtain the body image of the vehicle; the type of the car washing place is the output of the vehicle based on inputting the input prompt into the large language model, the input prompt is obtained by splicing the text prompt and the picture prompt, the text prompt is the location information of the vehicle, the picture prompt is the external environment information of the vehicle, and the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; based on the body image, determining the car washing mode.

[0147] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0148] On the other hand, the present application also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the methods provided by the above-mentioned method embodiments, the method including: in response to receiving an instruction to start a car wash mode, obtaining the location information of the vehicle as a text prompt and the external environment information of the vehicle as a picture prompt; splicing the text prompt and the picture prompt to obtain an input prompt, wherein the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; inputting the input prompt into a large language model to obtain the type of car wash place where the vehicle is located output by the large language model; obtaining a car wash setting item corresponding to the car wash place type, and setting the vehicle status based on the car wash setting item.

[0149] Alternatively, the method includes: in response to receiving information sent by a vehicle that the type of car wash place is a self-service manual car wash, guiding the wearer to photograph the body of the vehicle to obtain a body image of the vehicle; the car wash place type is the output of the vehicle based on inputting an input prompt into a large language model, the input prompt is obtained by splicing a text prompt and a picture prompt, the text prompt is the location information of the vehicle, the picture prompt is the external environment information of the vehicle, and the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; based on the body image, determining the car wash mode.

[0150] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the method provided by the above-mentioned method embodiments, the method comprising: in response to receiving an instruction to start a car wash mode, obtaining the location information of the vehicle as a text prompt and the external environment information of the vehicle as a picture prompt; splicing the text prompt and the picture prompt to obtain an input prompt, wherein the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; inputting the input prompt into a large language model to obtain the type of car wash place where the vehicle is located output by the large language model; obtaining a car wash setting item corresponding to the type of car wash place, and setting the vehicle status based on the car wash setting item.

[0151] Alternatively, the method includes: in response to receiving information sent by a vehicle that the type of car wash place is a self-service manual car wash, guiding the wearer to photograph the body of the vehicle to obtain a body image of the vehicle; the car wash place type is the output of the vehicle based on inputting an input prompt into a large language model, the input prompt is obtained by splicing a text prompt and a picture prompt, the text prompt is the location information of the vehicle, the picture prompt is the external environment information of the vehicle, and the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; based on the body image, determining the car wash mode.

[0152] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A car washing method, applied to a vehicle, comprising: In response to receiving an instruction to start a car wash mode, obtaining the location information of the vehicle as a text prompt and the external environment information of the vehicle as a picture prompt; splicing the text prompt and the picture prompt to obtain an input prompt, wherein the weight of the text prompt is proportional to the positioning accuracy and description clarity of the position information; Inputting the input prompt into a large language model to obtain the type of car wash location where the vehicle is located output by the large language model; A car wash setting item corresponding to the car wash location type is obtained, and a vehicle state setting is performed based on the car wash setting item.

2. The car washing method according to claim 1, further comprising at least one of the following: Determine the location information of the vehicle based on at least one of the latitude and longitude information of the vehicle and the location information of the vehicle; Based on the external camera of the vehicle, the external environment information of the vehicle is obtained.

3. The car washing method according to claim 1, wherein the step of obtaining the car washing setting items corresponding to the type of the car washing place comprises: If it is determined that the car wash location type is an automatic machine car wash or a self-service manual car wash, then car wash setting items corresponding to the controllable components supported by the car wash location type and the vehicle model are obtained.

4. The car washing method according to claim 1, wherein: The vehicle status setting based on the car wash setting item includes: Determining that the type of the car wash location is an automatic machine car wash, closing at least one of the rearview mirror, sunroof, window, trunk and wiper of the vehicle; Determining that the type of the car wash location is a self-service manual car wash, disabling the vehicle lock function, and closing at least one of the rearview mirror, sunroof, window, trunk, and wiper of the vehicle; If it is determined that the car wash location type is a manual car wash in a car wash shop, the vehicle computer setting function is disabled, and at least one of the rearview mirror, sunroof, window, trunk and wiper of the vehicle is turned off.

5. The car washing method according to claim 1, wherein: Before setting the vehicle status based on the car wash setting item, the method further includes: Determining that the type of the car wash location is an automatic machine car wash or a self-service manual car wash, obtaining guidance information matching the car wash machine model in the car wash location where the vehicle is located; Playing the guidance information on the vehicle-mounted terminal of the vehicle; In response to detecting a shift of the vehicle owner's attention in one process of the guidance information, a device to which the vehicle owner's attention is shifted is determined, and the one process and subsequent processes of the guidance information are sent to the shifting device.

6. The car washing method according to claim 1, further comprising: Determining that the type of the car wash place is a manual car wash in a car wash shop, summarizing the historical evaluations of the car wash places where the vehicle is located to obtain evaluation focus information of the car wash places; Receiving car body images before and after car washing sent by a wearable device; Car wash evaluation information is generated based on at least one of the evaluation focus point information and the vehicle body images before and after the car wash.

7. A method for recommending a car wash mode, applied to a wearable device that establishes a communication connection with a vehicle, comprising: In response to receiving a message from the vehicle indicating that the type of the car wash location is a self-service manual car wash, guiding the wearer to photograph the body of the vehicle to obtain a body image of the vehicle; The car wash place type is obtained by inputting an input prompt into a large language model based on the vehicle, wherein the input prompt is obtained by splicing a text prompt and a picture prompt, wherein the text prompt is the location information of the vehicle, and the picture prompt is the external environment information of the vehicle, and the weight of the text prompt is proportional to the positioning accuracy and description clarity of the location information; Based on the vehicle body image, a car wash mode is recommended to the wearer.

8. The method for recommending a car wash mode according to claim 7, further comprising: Determining that the type of the car wash location is an automatic machine car wash or a self-service manual car wash, and receiving guidance information sent by the vehicle; Collecting a status image of a car washing machine, and determining a real-time status of the car washing machine based on the status image; Based on the guidance information and the real-time status, operation prompts are provided.

9. The method for recommending a car wash mode according to claim 7, further comprising: During the car wash process, images of the car body area being washed are collected; Performing a dirt analysis on the vehicle body area image to obtain a dirt analysis result; At least one of a contamination prompt and a cleaning guidance is performed based on the contamination analysis result.

10. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the car washing method according to any one of claims 1 to 6 is implemented.

11. A wearable device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for recommending a car wash mode as described in any one of claims 7 to 9 is implemented.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the car washing method according to any one of claims 1 to 6 is implemented, or the car washing mode recommendation method according to any one of claims 7 to 9 is implemented.

Images