Vehicle cleaning prompting method and device, computer device and storage medium
By acquiring vehicle condition data and using a cleanliness and threshold prediction model to dynamically update the cleanliness threshold, the problem of unreasonable vehicle cleaning prompts in existing technologies is solved, realizing intelligent and customized cleaning prompt services, and improving the accuracy of prompts and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA FAW CO LTD
- Filing Date
- 2023-12-16
- Publication Date
- 2026-07-14
AI Technical Summary
The existing vehicle cleaning reminder system lacks customization, resulting in unrealistic reminders and causing inconvenience to car owners.
By acquiring vehicle condition data of the target vehicle within the target time period, and using a cleanliness prediction model and a threshold prediction model, the current cleanliness threshold is dynamically updated. Based on the vehicle condition data and historical cleanliness, the current cleanliness is predicted, and targeted cleaning prompts are output when the current cleanliness is not higher than the threshold.
It enables intelligent and customized push notifications for different vehicles and owners, providing more objective and reasonable cleaning reminders and improving the accuracy of the reminders and user experience.
Smart Images
Figure CN117894093B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence technology, and in particular to a vehicle washing prompt method, apparatus, computer equipment, and storage medium. Background Technology
[0002] The Internet of Vehicles (IoV) refers to the use of vehicles as information sensing objects and wireless communication technology to achieve network connection between vehicles and information network platforms, thereby enabling the effective use of vehicle dynamic information and providing corresponding functional services during vehicle operation.
[0003] With the continuous development of the Internet of Vehicles (IoV), the functional services that can be provided to vehicles are becoming increasingly powerful. For example, intelligent reminders for vehicle washing can be automatically pushed to the vehicle. However, the current method of pushing reminders often simply records the time of the vehicle's last wash and sends a reminder directly after a certain period of time. This method may give unrealistic reminder results, causing inconvenience and annoyance to car owners, and it cannot achieve customized push notifications for different vehicles and car owners. Summary of the Invention
[0004] Therefore, it is necessary to provide a vehicle cleaning reminder method, device, computer equipment, and storage medium that can provide customized vehicle cleaning reminders to address the above-mentioned technical problems.
[0005] Firstly, this application provides a vehicle washing reminder method, the method comprising:
[0006] Obtain vehicle condition data for the target vehicle within the target time period;
[0007] Based on vehicle condition data, predict the current cleanliness of the target vehicle;
[0008] If the current cleanliness level is not higher than the current cleanliness threshold, a cleaning prompt message for the target vehicle will be output. The current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness level of the target vehicle during previous cleanings.
[0009] In one embodiment, the vehicle condition data includes at least one of the following indicators: weather conditions during the target vehicle's operation, mileage, parking location, windshield wiper usage, camera cleanliness, and air quality of the environment in which the target vehicle is located.
[0010] Based on vehicle condition data, predict the current cleanliness of the target vehicle, including:
[0011] Based on vehicle condition data, the cleanliness prediction model is used to predict the current cleanliness of the target vehicle under various indicators in the vehicle condition data.
[0012] The current cleanliness of the target vehicle is obtained based on the weighting coefficients of each indicator in the vehicle condition data and the current cleanliness of the target vehicle under each indicator in the vehicle condition data.
[0013] In one embodiment, updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings includes:
[0014] Obtain the historical cleanliness level of the target vehicle when it was previously cleaned, as well as the previous cleanliness threshold of the target vehicle.
[0015] Based on historical cleanliness levels, predict the reference cleanliness level of the target vehicle;
[0016] The previous cleanliness threshold is updated based on the reference cleanliness level to obtain the current cleanliness threshold.
[0017] In one embodiment, predicting a reference cleanliness level for the target vehicle based on historical cleanliness levels includes:
[0018] Generate a time series of cleanliness based on historical cleanliness levels;
[0019] The threshold prediction model predicts the reference cleanliness of the target vehicle based on the cleanliness time series. The threshold prediction model is obtained by training a Long Short-Term Memory (LSTM) network.
[0020] In one embodiment, a cleaning prompt message for the target vehicle is output, including:
[0021] Output cleaning prompts for the target vehicle, along with corresponding cleaning queries.
[0022] In one embodiment, after outputting cleaning prompts for the target vehicle and corresponding cleaning queries, the method further includes:
[0023] If a cleaning confirmation message is received after a cleaning inquiry, the current location information of the target vehicle is obtained.
[0024] Navigation data is generated based on the current location information of the target vehicle and the cleaning location information of the target vehicle in the past.
[0025] In one embodiment, predicting the current cleanliness of a target vehicle based on vehicle condition data includes:
[0026] Obtain interior data of the target vehicle within the target time period;
[0027] Based on interior and vehicle condition data, predict the current cleanliness of the target vehicle.
[0028] Secondly, this application also provides a vehicle washing reminder device, which includes:
[0029] The data acquisition module is used to acquire vehicle condition data of the target vehicle within the target time period;
[0030] The first prediction module is used to predict the current cleanliness of the target vehicle based on vehicle condition data.
[0031] The cleaning prompt module is used to output cleaning prompt information for the target vehicle when the current cleanliness level is not higher than the current cleanliness threshold. The current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness level of the target vehicle in the past.
[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the first aspect.
[0033] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.
[0034] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.
[0035] The aforementioned vehicle cleaning reminder method, device, computer equipment, and storage medium acquire vehicle condition data of the target vehicle within a target time period; predict the current cleanliness of the target vehicle based on the vehicle condition data; if the current cleanliness is not higher than a current cleanliness threshold, output cleaning reminder information for the target vehicle; wherein, the current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings. This application predicts the current cleanliness based on vehicle condition data and combines it with a dynamically updated current cleanliness threshold to determine whether to output cleaning reminder information, enabling intelligent customized push notifications for different target vehicles and providing a more objective and reasonable cleaning reminder service. Attached Figure Description
[0036] Figure 1 This is an application scenario diagram of the vehicle washing reminder method in one embodiment;
[0037] Figure 2 This is a flowchart illustrating a vehicle washing reminder method in one embodiment;
[0038] Figure 3 This is a schematic diagram of the process for predicting the current cleanliness level in one embodiment;
[0039] Figure 4 This is a schematic diagram of the process for obtaining the current cleanliness threshold in one embodiment;
[0040] Figure 5 This is a schematic diagram of the process for predicting reference cleanliness in one embodiment;
[0041] Figure 6 This is a schematic diagram of the process for generating navigation data in one embodiment;
[0042] Figure 7 This is a schematic diagram of the process for predicting the current cleanliness level in another embodiment;
[0043] Figure 8 This is a flowchart illustrating the vehicle washing prompt method in another embodiment;
[0044] Figure 9 This is a structural block diagram of a vehicle washing reminder device in one embodiment;
[0045] Figure 10 This is a structural block diagram of the vehicle washing reminder device in another embodiment;
[0046] Figure 11 This is a structural block diagram of the vehicle washing reminder device in another embodiment;
[0047] Figure 12 This is a structural block diagram of the vehicle washing reminder device in another embodiment;
[0048] Figure 13 This is a structural block diagram of a computer device implementing a vehicle washing reminder method in one embodiment. Detailed Implementation
[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0050] The vehicle washing reminder method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the vehicle terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process, such as vehicle condition data. The data storage system can be integrated onto the server 104, or it can be located in the cloud or on another network server.
[0051] Specifically, server 104 acquires vehicle condition data of the target vehicle within the target time period; based on the vehicle condition data, it predicts the current cleanliness of the target vehicle; if the current cleanliness is not higher than the current cleanliness threshold, it outputs a cleaning prompt message for the target vehicle; wherein, the current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings. Server 104 can also interact with terminal 102 to feed back the text category corresponding to the target text data to terminal 102, which then displays the text classification result.
[0052] Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.
[0053] In one embodiment, such as Figure 2 As shown, a vehicle washing prompt method is provided, including the following steps:
[0054] S201, Obtain vehicle condition data of the target vehicle within the target time period.
[0055] The target vehicle is the vehicle for which a car wash notification is being pushed. The target vehicle can be either moving or stationary. When the target vehicle is activated, the vehicle management platform server corresponding to that vehicle can obtain real-time vehicle condition data for the target time period. The target time period refers to the time between the last car wash and the current time, and the vehicle condition data refers to data related to vehicle cleanliness, such as vehicle driving conditions and the vehicle's surrounding environment.
[0056] Optionally, the vehicle management platform is implemented based on SOA (Service-Oriented Architecture), which can provide vehicle cleaning reminder services for any vehicle under the vehicle management platform. Therefore, based on the vehicle cleaning reminder service, the vehicle management platform server can obtain the vehicle condition data of the target vehicle in real time within the target time period.
[0057] It is understandable that the vehicle condition data of the target vehicle within the target time period can be obtained by the on-board terminal equipped on the target vehicle and sent to the server, or the server can obtain it itself through the network. For example, if the vehicle condition data is the vehicle's driving status, then the vehicle condition data can be obtained by the on-board terminal and sent to the server; if the vehicle condition data is the environment in which the vehicle is located, then the vehicle condition data can be obtained by the server itself.
[0058] Optionally, the server sends a vehicle condition data acquisition instruction to the vehicle terminal of the target vehicle to obtain the vehicle condition data of the target vehicle within the target time period returned by the vehicle terminal.
[0059] Optionally, the on-board terminal of the target vehicle periodically reports the vehicle's status data for the target time period to the server.
[0060] S202, based on vehicle condition data, predicts the current cleanliness of the target vehicle.
[0061] Since vehicle condition data is related to vehicle cleanliness, the current cleanliness of the target vehicle can be predicted based on this data. The current cleanliness can be expressed as a percentage or a preset level; this embodiment does not impose any limitation on this. For example, a higher percentage value indicates a cleaner target vehicle, or a higher level indicates a cleaner target vehicle.
[0062] Specifically, vehicle condition data is input into the cleanliness prediction model to obtain the current cleanliness level output by the model. The cleanliness prediction model is a pre-defined neural network model.
[0063] Vehicle condition data can include data from multiple aspects. Predicting the current cleanliness level based on vehicle condition data can ensure the objectivity and accuracy of the prediction results.
[0064] S203, if the current cleanliness level is not higher than the current cleanliness threshold, output cleaning prompt information for the target vehicle.
[0065] The current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings. In other words, the current cleanliness threshold is dynamically updated; the current cleanliness threshold may differ for the same vehicle at different times, and the current cleanliness threshold may also differ for different vehicles.
[0066] Historical cleanliness levels of a target vehicle during past washes can, to some extent, indicate the owner's or driver's tolerance for vehicle cleanliness. Furthermore, this historical cleanliness level can include the cleanliness level of each previous wash. Therefore, updating the previous cleanliness threshold based on historical cleanliness levels allows for a more accurate determination of the current cleanliness threshold by combining wash frequency and cleanliness levels at the time of wash.
[0067] Furthermore, it determines whether the current cleanliness level is higher than the current cleanliness threshold. If the current cleanliness level is not higher than the current cleanliness threshold, a cleaning prompt message for the target vehicle is output; otherwise, no prompt message is output.
[0068] Cleaning reminders can be text or voice prompts. For example, if it is determined that a cleaning reminder needs to be sent, a text reminder will pop up on the center console of the target vehicle, along with a corresponding voice prompt.
[0069] The above scheme acquires vehicle condition data of the target vehicle within a target time period; predicts the current cleanliness of the target vehicle based on the vehicle condition data; if the current cleanliness is not higher than the current cleanliness threshold, it outputs a cleaning prompt message for the target vehicle; wherein, the current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings. This embodiment predicts the current cleanliness based on vehicle condition data and combines it with a dynamically updated current cleanliness threshold to determine whether to output a cleaning prompt message, enabling intelligent customized push notifications for different target vehicles and providing a more objective and reasonable cleaning prompt service.
[0070] To improve the accuracy of predicting the current cleanliness of target vehicles, based on the above embodiments, in one embodiment, the current cleanliness can be predicted by sub-indicators, such as... Figure 3 As shown, S202 above includes:
[0071] S301 uses a cleanliness prediction model to predict the current cleanliness of a target vehicle based on vehicle condition data for various indicators within the vehicle condition data.
[0072] The vehicle condition data includes at least one of the following indicators: driving weather, mileage, parking location, windshield wiper usage, camera cleanliness, and air quality of the target vehicle's environment. Driving weather refers to the duration of sunny, rainy, foggy, or dusty weather encountered by the target vehicle during its journey; mileage refers to the distance traveled since the last car wash; parking location refers to whether the target vehicle is parked indoors or outdoors; windshield wiper usage refers to the number of times and the duration of wiper usage; camera cleanliness can indicate the cleanliness of the vehicle's exterior components to some extent; and air quality refers to the air quality of the urban or rural area where the target vehicle is located.
[0073] The vehicle condition data corresponding to each indicator is input into the cleanliness prediction model to obtain the current cleanliness of the target vehicle under each indicator, as output by the cleanliness prediction model. The cleanliness prediction model can be implemented using algorithms such as convolutional neural networks, generative adversarial networks, recurrent neural networks, long short-term memory networks, or quantum neural networks.
[0074] Optionally, the cleanliness prediction model is an LSTM (Long Short Term Memory) model. Historical and current vehicle condition data are input into the cleanliness prediction model, allowing it to analyze the data over time. The cleanliness prediction model can extract the correlation between factors such as driving weather, mileage, parking location, wiper usage, camera cleanliness, and the air quality of the target vehicle's environment, as well as the degree of correlation between these factors and cleanliness. Furthermore, it can extract the correlation between car wash frequency and cleanliness based on the time between each car wash, thus outputting a highly accurate current cleanliness level.
[0075] S302. Based on the weight coefficients corresponding to each indicator in the vehicle condition data, and the current cleanliness of the target vehicle under each indicator in the vehicle condition data, the current cleanliness of the target vehicle is obtained.
[0076] Each indicator in the vehicle condition data is pre-assigned a corresponding weight coefficient to balance the contribution of each indicator to the final current cleanliness level. Optionally, the weight coefficients for each indicator can be calculated iteratively using an algorithm; this embodiment does not limit the method for determining the weight coefficients for each indicator.
[0077] Obtain the pre-set weight coefficients for each indicator, and calculate the current cleanliness of the target vehicle under each indicator based on the corresponding weight coefficients to obtain the final current cleanliness of the target vehicle.
[0078] As an optional implementation method in this embodiment, instead of assigning corresponding weight coefficients to each indicator, the cleanliness prediction model is used to analyze the vehicle condition data under all indicators and directly output the final current cleanliness of the target vehicle.
[0079] In this embodiment, vehicle condition data is further subdivided, and the current cleanliness of the target vehicle is comprehensively analyzed from multiple aspects. The resulting prediction results have higher objectivity and reliability. For different vehicles, the cleanliness prediction model can be used to predict their current cleanliness and obtain corresponding prediction results. The cleanliness prediction model can be improved in accuracy through training and is easily corrected, enabling the vehicle management platform to provide vehicle cleaning reminder services long-term.
[0080] To obtain a push notification result that better reflects the current situation, based on the above embodiments, in one embodiment, the current cleanliness threshold can be dynamically corrected, such as... Figure 4 As shown, updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings can include:
[0081] S401, obtain the historical cleanliness of the target vehicle when it was cleaned in the past, and the previous cleanliness threshold of the target vehicle.
[0082] The historical cleanliness of the target vehicle during past cleaning sessions can be either the cleanliness level at the time the owner or driver consented to the car wash, or the cleanliness level at the actual time of the wash. For example, after each vehicle wash notification is sent, if the target vehicle is washed or starts washing mode within a preset time, the historical cleanliness level at the time the vehicle wash notification is sent is recorded. Another example is obtaining and recording the historical cleanliness level of the target vehicle when it is being washed or when it starts washing mode.
[0083] The previous cleanliness threshold of the target vehicle is the cleanliness threshold used for comparison when the target vehicle was last washed or the car wash mode was activated. It can be understood that the cleanliness threshold of the target vehicle is dynamically adjusted; the cleanliness threshold of the target vehicle at different times is adjusted based on the cleanliness threshold used for comparison when the vehicle was last washed or the car wash mode was activated.
[0084] S402, based on historical cleanliness levels, predicts the reference cleanliness level of the target vehicle.
[0085] Historical cleanliness refers to the user's historical tolerance for the cleanliness of the vehicle body. The historical cleanliness recorded by the server includes the target vehicle's cleanliness during every previous historical cleaning. Optionally, historical cleanliness includes the target vehicle's cleanliness during cleanings within a preset time period. Users can also send a command to the server via the in-vehicle terminal to delete recorded historical cleanliness data, thereby initiating the vehicle cleaning reminder service for the target vehicle.
[0086] The reference cleanliness is the value used to correct the previous cleanliness threshold. The reference cleanliness predicted in this embodiment is different from the current cleanliness predicted in the previous embodiment. The reference cleanliness can better represent the user's current tolerance for the cleanliness of the vehicle body, while the current cleanliness is predicted based on the actual cleanliness of the target vehicle body.
[0087] Specifically, the historical cleanliness level is input into the threshold prediction model to obtain the reference cleanliness level output by the threshold prediction model. The threshold prediction model is another pre-defined neural network model.
[0088] Historical cleanliness can include long-term historical data of the target vehicle. Predicting reference cleanliness based on historical cleanliness ensures the accuracy of the prediction results and avoids the influence of accidental circumstances on the prediction results.
[0089] S403, based on the reference cleanliness, update the previous cleanliness threshold to obtain the current cleanliness threshold.
[0090] The previous cleanliness threshold was also updated when the car was washed or the car wash mode was activated last time. By combining the current predicted reference cleanliness with the previous cleanliness threshold updated based on the prediction results, a more accurate current cleanliness threshold is obtained, making the current cleanliness threshold more in line with the user's car washing habits.
[0091] For example, determine the scaling factor between the reference cleanliness level and the previous cleanliness threshold, and calculate the current cleanliness threshold based on the scaling factor.
[0092] Optionally, the previous cleanliness threshold can be directly replaced with a reference cleanliness threshold and used as the current cleanliness threshold.
[0093] In this embodiment, the reference cleanliness for the next cleaning of the target vehicle is predicted based on the historical cleanliness of the target vehicle in the past. Then, the previous cleanliness threshold is dynamically corrected using the reference cleanliness. This can more accurately identify the user's tolerance for the cleanliness of the vehicle body and determine the current cleanliness threshold that matches the user's car washing habits.
[0094] To accurately predict the reference cleanliness of the target vehicle and identify the user's intention to wash the car, based on the above embodiments, in one embodiment, prediction can be performed using an LSTM model, such as... Figure 5 As shown, the above vehicle washing reminder method may also include:
[0095] S501 generates a cleanliness time series based on historical cleanliness levels.
[0096] By determining the appropriate time interval based on the historical cleanliness levels, the historical cleanliness levels are then divided into corresponding time intervals to generate a cleanliness time series. Compared to discrete historical cleanliness levels, cleanliness time series can better reflect the long-term changes in the historical cleanliness of the target vehicle, and can, to a certain extent, represent the consistency of the historical cleanliness of the target vehicle.
[0097] S502 uses a threshold prediction model to predict the reference cleanliness of the target vehicle based on the cleanliness time series.
[0098] The cleanliness time series data is input into the threshold prediction model to obtain the reference cleanliness of the target vehicle output by the threshold prediction model. The threshold prediction model is trained using a Long Short-Term Memory (LSTM) network, which can solve the gradient vanishing and gradient exploding problems during long-sequence training.
[0099] Specifically, the cleanliness features of each time interval in the cleanliness time series are extracted. The cleanliness features of the previous time interval and the cleanliness features of the current time interval are used as the input of the current time interval. The cleanliness features of the previous time interval are selectively forgotten, and the cleanliness features of the current time interval are selectively remembered, so as to obtain the output of the current time interval. The analysis and calculation are performed according to the time series until the output of the last time interval is obtained, which is the output of the threshold prediction model.
[0100] Optionally, historical cleanliness can be directly input into the threshold prediction model to generate a cleanliness time series and analyze and calculate a reference cleanliness.
[0101] As an optional implementation method in this embodiment, the training steps of the threshold prediction model include:
[0102] A number of sample cleanliness data points are obtained, which come from different vehicles in different areas. To improve the quality of the sample cleanliness data, sample cleanliness data of vehicles for which users are relatively satisfied with the vehicle cleaning reminder service can be selected.
[0103] Add corresponding labels to the sample cleanliness data. For example, sample cleanliness can be represented by preset levels. For each sample cleanliness data point, the corresponding cleanliness level is determined based on the user's car washing habits. Optionally, the cleanliness levels range from 0 to 5, with higher levels indicating cleaner vehicles.
[0104] Furthermore, the labeled sample cleanliness data is input into the initial threshold prediction model to predict the reference cleanliness corresponding to the sample cleanliness data. Then, the initial threshold prediction model is trained in reverse iteration based on the predicted reference cleanliness and labels until a threshold prediction model that meets the training termination condition is obtained.
[0105] Understandably, the training steps for cleanliness prediction models are similar and will not be repeated here.
[0106] In this embodiment, the reference cleanliness of the target vehicle is predicted by an LSTM model to identify the user's tolerance for the cleanliness of the vehicle body. This solves the gradient vanishing and gradient exploding problems that exist in conventional neural networks, resulting in higher accuracy in the final prediction results.
[0107] In one embodiment, the vehicle cleaning prompt method is implemented interactively. When the target vehicle is started, the server acquires the vehicle's condition data in real time within a target time period, predicts the current cleanliness based on the vehicle condition data, and then compares the current cleanliness with a dynamically corrected current cleanliness threshold. If the current cleanliness is not higher than the current cleanliness threshold, the server instructs the output of cleaning prompt information for the target vehicle, as well as corresponding cleaning query information.
[0108] Specifically, the in-vehicle terminal receives instructions from the server and controls the center console of the target vehicle to display cleaning prompts and corresponding cleaning queries. For example, interactive controls are displayed on the center console, which can respond to user clicks, allowing them to either confirm or refuse cleaning the target vehicle.
[0109] In one embodiment, such as Figure 6 As shown, after outputting the cleaning prompt information for the target vehicle and the corresponding cleaning inquiry information, it also includes:
[0110] S601, upon receiving a cleaning confirmation message from a cleaning inquiry, obtains the current location information of the target vehicle.
[0111] In other words, if a cleaning confirmation message is received from a cleaning inquiry, the current location information of the target vehicle is obtained. For example, if a user clicks the cleaning confirmation button on the center console, triggering the cleaning confirmation message corresponding to the cleaning inquiry, the server receives the cleaning confirmation message uploaded by the in-vehicle terminal and obtains the current location information of the target vehicle.
[0112] Optionally, the server receives the current location information of the target vehicle, which is uploaded synchronously with the cleaning confirmation information.
[0113] S602 generates navigation data based on the current location information of the target vehicle and the cleaning location information of the target vehicle in the past.
[0114] Using the current location information of the target vehicle as the starting point and the historical cleaning location information of the target vehicle as the ending point, navigation data to the car wash point is automatically generated.
[0115] Optionally, if there is cleaning location information for multiple historical target vehicles, the more suitable cleaning location information can be selected based on the user's historical preference for car wash locations or the distance between the cleaning location information of each car wash location and the current location information, and then the corresponding navigation data can be generated.
[0116] Optionally, navigation data can be generated based on the target vehicle's current location information. For example, the location information of car wash locations near the current location can be obtained to generate corresponding navigation data.
[0117] Furthermore, the server sends navigation data to the in-vehicle terminal, which then displays the navigation data on the center console or controls the target vehicle to drive automatically to the car wash location according to the navigation data.
[0118] In this embodiment, the interactive vehicle cleaning reminder service can optimize the user experience. The vehicle cleaning reminder service can be reused in each vehicle under the vehicle management platform, and there is no need to add new sensors to the vehicle.
[0119] In one embodiment, such as Figure 7 As shown, the above vehicle washing reminder method may also include:
[0120] S701, acquire interior data of the target vehicle within the target time period.
[0121] Among them, the interior data is data related to the cleanliness of the vehicle, which corresponds to the vehicle condition data and can reflect the cleanliness of the target vehicle's interior.
[0122] Optionally, sensors are installed inside the target vehicle to collect interior data, and the interior data transmitted by the sensors is uploaded to a server via onboard equipment.
[0123] Understandably, in some situations, car owners or drivers, i.e., users, may need to wash their cars due to the cleanliness of the interior. Therefore, by combining the interior data of the target vehicle and analyzing its current cleanliness, it can be determined whether a vehicle cleaning reminder should be sent to the user.
[0124] S702 predicts the current cleanliness of a target vehicle based on interior and vehicle condition data.
[0125] Specifically, interior data and vehicle condition data are input into the cleanliness prediction model to obtain the current cleanliness output by the cleanliness prediction model.
[0126] Optionally, the current cleanliness includes the current interior cleanliness and the current exterior cleanliness. If either the current interior cleanliness or the current exterior cleanliness is not higher than the corresponding current cleanliness threshold, a cleaning prompt message for the target vehicle will be output.
[0127] In this embodiment, interior data of the target vehicle within a target time period is obtained, and the current cleanliness of the target vehicle is predicted based on the interior data and vehicle condition data. This allows for a comprehensive analysis of the cleanliness of the target vehicle's interior and exterior, resulting in a current cleanliness level that better reflects the user's intent.
[0128] In one embodiment, an optional example of a vehicle washing reminder method is provided, such as... Figure 8 As shown, the vehicle washing instructions include the following steps:
[0129] S801, obtain vehicle condition data of the target vehicle within the target time period.
[0130] The vehicle condition data includes at least one of the following indicators: weather conditions during which the target vehicle was driven, mileage, parking location, windshield wiper usage, camera cleanliness, and air quality of the environment in which the target vehicle is located.
[0131] S802 uses a cleanliness prediction model to predict the current cleanliness of a target vehicle based on vehicle condition data for various indicators within the vehicle condition data.
[0132] S803 calculates the current cleanliness of the target vehicle based on the weighting coefficients of each indicator in the vehicle condition data and the current cleanliness of the target vehicle under each indicator in the vehicle condition data.
[0133] Optionally, obtain the interior data of the target vehicle within the target time period; based on the interior data and vehicle condition data, predict the current cleanliness of the target vehicle.
[0134] S804, obtain the historical cleanliness of the target vehicle when it was cleaned in the past, and the previous cleanliness threshold of the target vehicle.
[0135] S805 generates a cleanliness time series based on historical cleanliness levels.
[0136] S806 uses a threshold prediction model to predict the reference cleanliness of a target vehicle based on a cleanliness time series.
[0137] The threshold prediction model is obtained by training a Long Short-Term Memory (LSTM) network.
[0138] S807, based on the reference cleanliness, update the previous cleanliness threshold to obtain the current cleanliness threshold.
[0139] S808 outputs cleaning prompts for the target vehicle and corresponding cleaning queries when the current cleanliness level is not higher than the current cleanliness threshold.
[0140] S809, upon receiving a cleaning confirmation message from a cleaning inquiry, obtains the current location information of the target vehicle.
[0141] S810 generates navigation data based on the current location information of the target vehicle and the cleaning location information of the target vehicle in the past.
[0142] The specific process of the above steps can be found in the description of the above method embodiments. The implementation principle and technical effect are similar, and will not be repeated here.
[0143] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0144] Based on the same inventive concept, this application also provides a vehicle washing reminder device for implementing the vehicle washing reminder method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle washing reminder device embodiments provided below can be found in the limitations of the vehicle washing reminder method described above, and will not be repeated here.
[0145] In one embodiment, such as Figure 9 As shown, a vehicle washing reminder device 1 is provided, including a data acquisition module 10, a first prediction module 20, and a washing reminder module 30, wherein:
[0146] The data acquisition module 10 is used to acquire vehicle condition data of the target vehicle within the target time period.
[0147] The first prediction module 20 is used to predict the current cleanliness of the target vehicle based on vehicle condition data.
[0148] The cleaning prompt module 30 is used to output cleaning prompt information for the target vehicle when the current cleanliness level is not higher than the current cleanliness threshold.
[0149] The current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness of the target vehicle during previous cleanings.
[0150] In one embodiment, vehicle condition data includes at least one of the following indicators: weather conditions during vehicle operation, mileage, parking location, windshield wiper usage, camera cleanliness, and air quality of the environment in which the target vehicle is located; Figure 9 On the basis of, such as Figure 10 As shown, the first prediction module 20 described above may include:
[0151] The first prediction unit 21 is used to predict the current cleanliness of the target vehicle under various indicators in the vehicle condition data based on the vehicle condition data using a cleanliness prediction model.
[0152] The second prediction unit 22 is used to obtain the current cleanliness of the target vehicle based on the weight coefficients corresponding to each indicator in the vehicle condition data and the current cleanliness of the target vehicle under each indicator in the vehicle condition data.
[0153] In one embodiment, in Figure 9 On the basis of, such as Figure 11 As shown, the vehicle washing reminder device 1 may further include:
[0154] The threshold acquisition module 40 is used to acquire the historical cleanliness of the target vehicle when it was cleaned in the past, as well as the previous cleanliness threshold of the target vehicle.
[0155] The second prediction module 50 is used to predict the reference cleanliness of the target vehicle based on historical cleanliness levels.
[0156] The threshold update module 60 is used to update the previous cleanliness threshold based on the reference cleanliness to obtain the current cleanliness threshold.
[0157] In one embodiment, in Figure 11 On the basis of, such as Figure 12 As shown, the second prediction module 50 may include:
[0158] The third prediction unit 51 is used to generate a cleanliness time series based on historical cleanliness.
[0159] The fourth prediction unit 52 is used to predict the reference cleanliness of the target vehicle based on the cleanliness time series using a threshold prediction model; wherein, the threshold prediction model is obtained by training a long short-term memory (LSTM) network.
[0160] In one embodiment, the cleaning prompt module 30 can be used to output cleaning prompt information for the target vehicle, as well as cleaning inquiry information corresponding to the cleaning prompt information.
[0161] In one embodiment, the vehicle washing reminder device 1 may further include:
[0162] The location acquisition module is used to obtain the current location information of the target vehicle upon receiving a cleaning confirmation message from a cleaning inquiry.
[0163] The navigation generation module is used to generate navigation data based on the current location information of the target vehicle and the cleaning location information of the target vehicle in the past.
[0164] In one embodiment, the data acquisition module 10 can also be used to acquire interior data of the target vehicle within a target time period; the first prediction module 20 can also be used to predict the current cleanliness of the target vehicle based on the interior data and vehicle condition data.
[0165] The various modules in the aforementioned vehicle washing reminder device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0166] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 13 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data such as historical cleanliness levels. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a vehicle washing reminder method.
[0167] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0168] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the vehicle cleaning reminder method described above.
[0169] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle cleaning reminder method described above.
[0170] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the vehicle cleaning reminder method described above.
[0171] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0173] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A vehicle washing reminder method, characterized in that, The method includes: Obtain vehicle condition data for the target vehicle within the target time period; Based on the vehicle condition data, predict the current cleanliness of the target vehicle; If the current cleanliness level is not higher than the current cleanliness threshold, a cleaning prompt message for the target vehicle is output. The current cleanliness threshold is obtained by updating the previous cleanliness threshold based on the historical cleanliness levels when the target vehicle was previously cleaned. Updating the previous cleanliness threshold based on the historical cleanliness levels when the target vehicle was previously cleaned includes: obtaining the historical cleanliness levels when the target vehicle was previously cleaned, and the previous cleanliness threshold for the target vehicle; predicting a reference cleanliness level for the target vehicle based on the historical cleanliness levels; and updating the previous cleanliness threshold based on the reference cleanliness level to obtain the current cleanliness threshold.
2. The method according to claim 1, characterized in that, The vehicle condition data includes at least one of the following indicators: driving weather, mileage, parking location, windshield wiper usage, camera cleanliness, and air quality of the environment in which the target vehicle is located. The step of predicting the current cleanliness of the target vehicle based on the vehicle condition data includes: Using a cleanliness prediction model, the current cleanliness of the target vehicle under various indicators in the vehicle condition data is predicted based on the vehicle condition data. The current cleanliness of the target vehicle is obtained based on the weight coefficients corresponding to each indicator in the vehicle condition data and the current cleanliness of the target vehicle under each indicator in the vehicle condition data.
3. The method according to claim 1, characterized in that, The step of predicting the reference cleanliness of the target vehicle based on the historical cleanliness includes: Based on the historical cleanliness levels, a cleanliness time series is generated; The reference cleanliness of the target vehicle is predicted using a threshold prediction model based on the cleanliness time series; wherein the threshold prediction model is obtained by training a Long Short-Term Memory (LSTM) network.
4. The method according to claim 1, characterized in that, The output includes cleaning prompts for the target vehicle, including: Output cleaning prompts for the target vehicle, as well as corresponding cleaning queries.
5. The method according to claim 4, characterized in that, After outputting the cleaning prompt information for the target vehicle and the corresponding cleaning inquiry information, the method further includes: If a cleaning confirmation message is received from the cleaning inquiry, the current location information of the target vehicle is obtained. Navigation data is generated based on the current location information of the target vehicle and the cleaning location information of the target vehicle in the past.
6. The method according to claim 1, characterized in that, The step of predicting the current cleanliness of the target vehicle based on the vehicle condition data includes: Obtain interior data of the target vehicle within the target time period; Based on the interior data and the vehicle condition data, the current cleanliness of the target vehicle is predicted.
7. A vehicle washing reminder device, characterized in that, The device includes: The data acquisition module is used to acquire vehicle condition data of the target vehicle within the target time period; The first prediction module is used to predict the current cleanliness of the target vehicle based on the vehicle condition data. A cleaning prompt module is used to output cleaning prompt information for the target vehicle when the current cleanliness level is not higher than the current cleanliness threshold. The current cleanliness threshold is obtained by updating a previous cleanliness threshold based on historical cleanliness levels when the target vehicle was previously cleaned. Updating the previous cleanliness threshold based on historical cleanliness levels when the target vehicle was previously cleaned includes: obtaining the historical cleanliness levels when the target vehicle was previously cleaned, and the previous cleanliness threshold for the target vehicle; predicting a reference cleanliness level for the target vehicle based on the historical cleanliness levels; and updating the previous cleanliness threshold based on the reference cleanliness level to obtain the current cleanliness threshold.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.