Wetland mode recommendation method, electronic device, storage medium, and system

Abstract

This application relates to the field of intelligent driving technology, specifically providing a wetland mode recommendation method, electronic device, storage medium, and system, aiming to solve the technical problem of low reach rate of vehicle wetland mode switching, which affects user experience and driving safety. To this end, the method of this application includes: acquiring basic weather information, weather flow data, and short-term precipitation flow data for each area; acquiring comprehensive weather information for each area based on the weather flow data and short-term precipitation flow data; obtaining the water accumulation volume for each area based on the basic weather information and comprehensive weather information; and determining the recommended wetland mode status of driving equipment within each area based on the water accumulation volume. Through the above implementation, multi-source data can be integrated to calculate the water accumulation volume for each area, making the recommended wetland mode status more closely match actual driving scenarios, helping to improve the reach rate of wetland mode switching, safeguarding users' driving on slippery roads in rainy and snowy weather, and improving user experience and driving safety.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, specifically to a wetland mode recommendation method, electronic device, storage medium, and system. Background Technology

[0002] With the development of intelligent driving, vehicle safety in complex weather conditions is receiving increasing attention. To cope with slippery road conditions such as rain and snow, vehicles are usually equipped with a wet mode. This mode reduces the risk of skidding and improves driving stability by adjusting parameters such as power output and braking system.

[0003] However, the current rate of vehicle wet mode switching is low. When driving in rainy or snowy weather, it is difficult to switch to wet mode in time to improve driving safety, which increases the probability of skidding during driving and affects user experience and driving safety.

[0004] Accordingly, a new technical solution is needed in this field to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects, this application is made to provide a wet mode recommendation method, electronic device, storage medium and system that solves or at least partially solves the technical problem of low reach rate of vehicle wet mode switching, which affects user experience and driving safety.

[0006] In a first aspect, this application provides a wetland pattern recommendation method, the method comprising:

[0007] Acquire basic weather information, weather flow data, and short-term precipitation flow data for each region;

[0008] Comprehensive weather information for each region is obtained based on the aforementioned weather flow data and short-term precipitation flow data;

[0009] The water accumulation in each area is obtained based on the basic weather information and the comprehensive weather information.

[0010] Based on the water accumulation in each area, determine the recommended wetland mode status for the driving equipment within that area.

[0011] In one technical solution of the aforementioned wetland model recommendation method, the basic weather information includes basic water volume levels; obtaining the basic weather information for each region includes:

[0012] Based on a preset time window, acquire wiper data and positioning data for each driving device;

[0013] The wiper data is processed to obtain the number of wiper cycles for each driving device within the preset time window;

[0014] Based on the preset grid division information, the wiper data, and the positioning data, the number of high-speed wiper requests and the total number of wiper cycles in each area are obtained;

[0015] Based on the number of high-speed wiper requests and the total number of wiper cycles, the basic water level for each area is obtained.

[0016] In one technical solution of the aforementioned wetland pattern recommendation method, the step of obtaining the basic water volume level for each area based on the number of high-speed wiper requests and the total number of wiper strokes includes:

[0017] The wiper scene type is determined based on the number of high-speed wiper requests; the wiper scene type includes low-speed wiper-dominated scene or high-speed wiper-dominated scene.

[0018] The basic water volume level is determined based on the wiper scene type and the total number of wiper cycles.

[0019] In one technical solution of the aforementioned wetland pattern recommendation method, determining the wiper scene type based on the number of high-speed wiper requests includes:

[0020] Determine whether the number of high-speed wiper requests is less than a preset request threshold;

[0021] If so, the wiper scene type is determined to be the low-speed wiper-dominated scene; otherwise, the wiper scene type is determined to be the high-speed wiper-dominated scene.

[0022] In one technical solution of the above wetland pattern recommendation method, the processing of the wiper data includes:

[0023] The wiper data is filtered to select wiper data that meets the requirements of abnormal weather scenarios;

[0024] Acquire driving data and corresponding precipitation speed for each driving device; the driving data includes at least vehicle speed.

[0025] The filtered wiper data is normalized based on the driving data and the precipitation speed.

[0026] In one technical solution of the above wetland model recommendation method, obtaining weather flow data for each region includes:

[0027] Obtain weather data;

[0028] Based on the weather data and region ID, determine whether the basic weather information exists in each region, and set a first time threshold according to the determination result; Determine whether the weather data for each region is recent based on the first time threshold;

[0029] If so, then the weather flow data for the region is obtained based on the weather data; otherwise, real-time weather data is requested, and the weather data and the real-time weather data are merged to obtain the weather flow data for the region.

[0030] In one technical solution of the aforementioned wetland model recommendation method, obtaining short-term precipitation flow data for each region includes:

[0031] Obtain short-term precipitation data;

[0032] Based on the short-term precipitation data and the region ID, determine whether the basic weather information exists in each region, and set a second time threshold according to the determination result;

[0033] If so, then the short-term precipitation flow data of the region is obtained based on the short-term precipitation data; otherwise, real-time short-term precipitation data is requested, and the short-term precipitation flow data of the region is obtained based on the short-term precipitation data and the real-time short-term precipitation data.

[0034] In one technical solution of the aforementioned wetland model recommendation method, obtaining comprehensive weather information for each region based on the weather flow data and short-term precipitation flow data includes:

[0035] Obtain the first timestamp of the weather flow data and the second timestamp of the short-term precipitation flow data for each region;

[0036] The weather flow data and the short-term precipitation flow data are matched based on the first timestamp and the second timestamp;

[0037] If the first timestamp and the second time are the same, the precipitation intensity is obtained based on the short-term precipitation flow data, and the comprehensive weather information for each region is calculated based on the precipitation intensity.

[0038] In one technical solution of the above wetland model recommendation method, obtaining the water accumulation of each area based on the basic weather information and the comprehensive weather information includes:

[0039] Obtain the timestamp difference between the basic weather information and the comprehensive weather information for each region;

[0040] Determine whether the timestamp difference is within a preset threshold range;

[0041] If so, the water accumulation in each area is calculated based on the basic weather information and the comprehensive weather information.

[0042] In one technical solution of the above wetland model recommendation method, the calculation of water accumulation in each area based on the basic weather information and the comprehensive weather information includes:

[0043] Weight parameters are obtained based on the number of driving devices in each area;

[0044] The total water volume of each region is calculated based on the basic weather information, the comprehensive weather information, and the weighting parameters.

[0045] The total water volume is subjected to time decay filtering to obtain the water accumulation in each region.

[0046] In one technical solution of the above wetland pattern recommendation method, the step of performing time-attenuation filtering on the total water volume to obtain the water accumulation in each area includes:

[0047] The previous flood level and recording time are obtained based on historical data;

[0048] Determine whether the previous flood level was within the valid time range and whether the environmental parameters were complete; the environmental parameters include at least one of temperature, humidity and weather.

[0049] If so, the time difference between the current time and the recorded time is obtained, and the time decay coefficient is determined based on the environmental parameters; the time decay coefficient includes the water rise time constant or the water fall time constant.

[0050] The water volume of each area is calculated based on the relationship between the total water volume and the previous water level, as well as the time difference and the time decay coefficient.

[0051] In one technical solution of the above wetland mode recommendation method, the water accumulation includes water accumulation level; determining the wetland mode recommendation status of the driving equipment in each area based on the water accumulation includes:

[0052] When the water accumulation level is less than or equal to the first threshold, the recommended state for the wet mode of the driving equipment in the area is to turn off the wet mode.

[0053] When the water accumulation level is greater than or equal to the second threshold, the recommended state for the wet mode of the driving equipment in the area is to turn on the wet mode.

[0054] When the water accumulation level is greater than the first threshold and less than the second threshold, the recommended wetland mode state for the driving equipment in the area is determined to be to maintain the current driving mode.

[0055] Wherein, the first threshold is less than the second threshold.

[0056] In one technical solution of the aforementioned wetland model recommendation method, the method further includes:

[0057] When the water level is greater than or equal to the second threshold, and the driving mode of the driving device in the area is not the wetland mode, a reminder to switch driving modes is sent to the driving device, or the driving device is controlled to switch the driving mode to the wetland mode.

[0058] In one technical solution of the aforementioned wetland model recommendation method, the method further includes:

[0059] A wetland map is created based on the water accumulation to display the water accumulation in each area;

[0060] The wetland map includes at least a weather layer and a water accumulation layer.

[0061] In a second aspect, this application provides an electronic device including a processor and a memory, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and executed by the processor to perform the wetland pattern recommendation method described in any of the above-described technical solutions.

[0062] In a third aspect, this application provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the wetland pattern recommendation method described in any of the above-described technical solutions.

[0063] In a fourth aspect, this application provides a wetland mode recommendation system, the system comprising a cloud server and multiple driving devices communicatively connected to the cloud server; wherein,

[0064] The cloud server includes the electronic device described in the above-mentioned technical solution for the electronic device;

[0065] The multiple driving devices are configured to send wiper data and location data to the cloud server based on a preset time window.

[0066] Option 1. A wetland pattern recommendation method, characterized in that the method includes:

[0067] Acquire basic weather information, weather flow data, and short-term precipitation flow data for each region;

[0068] Comprehensive weather information for each region is obtained based on the aforementioned weather flow data and short-term precipitation flow data;

[0069] The water accumulation in each area is obtained based on the basic weather information and the comprehensive weather information.

[0070] Based on the water accumulation in each area, the recommended wetland mode status for driving equipment within that area is determined.

[0071] Option 2. The wetland model recommendation method according to Option 1, characterized in that the basic weather information includes basic water volume levels; the acquisition of basic weather information for each region includes:

[0072] Based on a preset time window, acquire wiper data and positioning data for each driving device;

[0073] The wiper data is processed to obtain the number of wiper cycles for each driving device within the preset time window;

[0074] Based on the preset grid division information, the wiper data, and the positioning data, the number of high-speed wiper requests and the total number of wiper cycles in each area are obtained;

[0075] Based on the number of high-speed wiper requests and the total number of wiper cycles, the basic water level for each area is obtained.

[0076] Option 3. The wetland pattern recommendation method according to Option 2, characterized in that, the step of obtaining the basic water volume level of each area based on the number of high-speed wiper requests and the total number of wiper strokes includes:

[0077] The wiper scene type is determined based on the number of high-speed wiper requests; the wiper scene type includes low-speed wiper-dominated scene or high-speed wiper-dominated scene.

[0078] The basic water volume level is determined based on the wiper scene type and the total number of wiper cycles.

[0079] Solution 4. The wetland mode recommendation method according to Solution 3, characterized in that determining the wiper scene type based on the number of high-speed wiper requests includes:

[0080] Determine whether the number of high-speed wiper requests is less than a preset request threshold;

[0081] If so, the wiper scene type is determined to be the low-speed wiper-dominated scene; otherwise, the wiper scene type is determined to be the high-speed wiper-dominated scene.

[0082] Option 5. The wetland pattern recommendation method according to Option 2, characterized in that the processing of the wiper data includes:

[0083] The wiper data is filtered to select wiper data that meets the requirements of abnormal weather scenarios;

[0084] Acquire driving data and corresponding precipitation speed for each driving device; the driving data includes at least vehicle speed.

[0085] The filtered wiper data is normalized based on the driving data and the precipitation speed.

[0086] Option 6. The wetland model recommendation method according to Option 2, characterized in that acquiring weather flow data for each region includes:

[0087] Obtain weather data;

[0088] Based on the weather data and region ID, determine whether the basic weather information exists in each region, and set a first time threshold according to the determination result;

[0089] Determine whether the weather data for each region is recent based on the first time threshold;

[0090] If so, then the weather flow data for the region is obtained based on the weather data; otherwise, real-time weather data is requested, and the weather data and the real-time weather data are merged to obtain the weather flow data for the region.

[0091] Option 7. The wetland model recommendation method according to Option 2, characterized in that, acquiring short-term precipitation flow data for each region includes:

[0092] Obtain short-term precipitation data;

[0093] Based on the short-term precipitation data and the region ID, determine whether the basic weather information exists in each region, and set a second time threshold according to the determination result;

[0094] Based on the second time threshold, determine whether the short-term precipitation data for each region is recent;

[0095] If so, then the short-term precipitation flow data of the region is obtained based on the short-term precipitation data; otherwise, real-time short-term precipitation data is requested, and the short-term precipitation flow data of the region is obtained based on the short-term precipitation data and the real-time short-term precipitation data.

[0096] Option 8. The wetland model recommendation method according to Option 1, characterized in that, the step of obtaining comprehensive weather information for each region based on the weather flow data and short-term precipitation flow data includes:

[0097] Obtain the first timestamp of the weather flow data and the second timestamp of the short-term precipitation flow data for each region;

[0098] The weather flow data and the short-term precipitation flow data are matched based on the first timestamp and the second timestamp;

[0099] If the first timestamp and the second time are the same, the precipitation intensity is obtained based on the short-term precipitation flow data, and the comprehensive weather information for each region is calculated based on the precipitation intensity.

[0100] Option 9. The wetland model recommendation method according to Option 1, characterized in that, obtaining the water accumulation of each area based on the basic weather information and the comprehensive weather information includes:

[0101] Obtain the timestamp difference between the basic weather information and the comprehensive weather information for each region;

[0102] Determine whether the timestamp difference is within a preset threshold range;

[0103] If so, the water accumulation in each area is calculated based on the basic weather information and the comprehensive weather information.

[0104] Option 10. The wetland model recommendation method according to Option 9, characterized in that the calculation of water accumulation in each area based on the basic weather information and the comprehensive weather information includes:

[0105] Weight parameters are obtained based on the number of driving devices in each area;

[0106] The total water volume of each region is calculated based on the basic weather information, the comprehensive weather information, and the weighting parameters.

[0107] The total water volume is subjected to time decay filtering to obtain the water accumulation in each region.

[0108] Solution 11. The wetland pattern recommendation method according to Solution 10, characterized in that, the step of performing time-attenuation filtering on the total water volume to obtain the water accumulation in each area includes:

[0109] The previous flood level and recording time are obtained based on historical data;

[0110] Determine whether the previous flood level was within the valid time range and whether the environmental parameters were complete; the environmental parameters include at least one of temperature, humidity and weather.

[0111] If so, the time difference between the current time and the recorded time is obtained, and the time decay coefficient is determined based on the environmental parameters; the time decay coefficient includes the water rise time constant or the water fall time constant.

[0112] The water volume of each area is calculated based on the relationship between the total water volume and the previous water level, as well as the time difference and the time decay coefficient.

[0113] Solution 12. The wetland mode recommendation method according to Solution 1, characterized in that the water accumulation includes water accumulation level; determining the wetland mode recommendation status of the driving equipment in each area based on the water accumulation includes:

[0114] When the water accumulation level is less than or equal to the first threshold, the recommended state for the wet mode of the driving equipment in the area is to turn off the wet mode.

[0115] When the water accumulation level is greater than or equal to the second threshold, the recommended state for the wet mode of the driving equipment in the area is to turn on the wet mode.

[0116] When the water accumulation level is greater than the first threshold and less than the second threshold, the recommended wetland mode state for the driving equipment in the area is determined to be to maintain the current driving mode.

[0117] Wherein, the first threshold is less than the second threshold.

[0118] Option 13. The wetland pattern recommendation method according to Option 12, characterized in that the method further includes:

[0119] When the water level is greater than or equal to the second threshold, and the driving mode of the driving device in the area is not the wetland mode, a reminder to switch driving modes is sent to the driving device, or the driving device is controlled to switch the driving mode to the wetland mode.

[0120] Option 14. The wetland model recommendation method according to any one of Options 1 to 13, characterized in that the method further comprises:

[0121] A wetland map is created based on the water accumulation to display the water accumulation in each area;

[0122] The wetland map includes at least a weather layer and a water accumulation layer.

[0123] Scheme 15. An electronic device comprising a processor and a memory, the memory being adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by the processor to perform the wetland pattern recommendation method as described in any one of Schemes 1 to 14.

[0124] Scheme 16. A computer-readable storage medium storing a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by a processor to perform the wetland pattern recommendation method as described in any one of Schemes 1 to 14.

[0125] Option 17. A wetland mode recommendation system, characterized in that the system includes a cloud server and multiple driving devices communicatively connected to the cloud server; wherein,

[0126] The cloud server includes the electronic device described in scheme 15;

[0127] The multiple driving devices are configured to send wiper data and location data to the cloud server based on a preset time window.

[0128] The above-described technical solutions of this application have at least one or more of the following beneficial effects:

[0129] In implementing the technical solution of this application, the basic weather information, weather flow data, and short-term precipitation flow data of each region are first obtained. Then, based on the weather flow data and short-term precipitation flow data, comprehensive weather information of each region is obtained. Based on the basic weather information and comprehensive weather information, the water accumulation of each region is obtained. Finally, based on the water accumulation of each region, the recommended wetland mode status of driving equipment in the region is determined. Through the above implementation method, by integrating multi-source data to calculate the comprehensive weather and water accumulation of each region, and determining the recommended wetland mode status of driving equipment in the region based on the water accumulation, accurate recommendations for wetland mode switching can be achieved. This makes the recommended wetland mode status more consistent with actual driving scenarios, helps to improve the reach rate of wetland mode switching, and protects users driving on slippery roads in severe weather such as rain, snow, and ice, thereby improving user experience and driving safety. Attached Figure Description

[0130] The disclosure of this application will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Wherein:

[0131] Figure 1 This is a schematic flowchart of the main steps of a wetland pattern recommendation method according to an embodiment of this application;

[0132] Figure 2 This is a schematic diagram of the main steps for obtaining basic weather information for each region according to an embodiment of this application;

[0133] Figure 3 This is a schematic diagram of the main steps for calculating the water accumulation in each area based on basic weather information and comprehensive weather information according to an embodiment of this application;

[0134] Figure 4 This is a real-time data processing flowchart of a wetland pattern recommendation method according to an embodiment of this application;

[0135] Figure 5 This is a schematic diagram of the main flow of a wetland pattern recommendation method according to an embodiment of this application;

[0136] Figure 6 This is a schematic diagram of the main structure of an electronic device according to an embodiment of this application.

[0137] List of reference numerals in the attached diagram:

[0138] 61: Processor; 62: Memory. Detailed Implementation

[0139] Some embodiments of this application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of this application and are not intended to limit the scope of protection of this application.

[0140] In the description of this application, "module" and "processor" can include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory, and may also include software components such as program code, or a combination of software and hardware. A processor may be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor may be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc.

[0141] The term "A and / or B" refers to all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular forms of the terms "a" or "this" can also include plural forms.

[0142] As described in the background section, the current vehicle wet mode switching rate is low. When driving in rainy or snowy weather, it is difficult to switch to wet mode in time to improve driving safety, which increases the probability of skidding during driving and affects user experience and driving safety.

[0143] To address the aforementioned issues, this application provides a wetland pattern recommendation method, electronic device, storage medium, and system.

[0144] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a wetland pattern recommendation method according to an embodiment of this application. Figure 1 As shown, the wetland pattern recommendation method in this application embodiment mainly includes the following steps S101 to S104.

[0145] Step S101: Obtain basic weather information, weather flow data, and short-term precipitation flow data for each region;

[0146] Basic weather information can include basic rainfall information, basic snowfall information, and basic icing information.

[0147] Step S102: Obtain comprehensive weather information for each region based on weather flow data and short-term precipitation flow data;

[0148] The comprehensive weather information may include rainfall, snowfall, and icing information.

[0149] Step S103: Obtain the water accumulation in each area based on basic weather information and comprehensive weather information;

[0150] Step S104: Based on the water accumulation in each area, determine the recommended wetland mode status for the driving equipment in that area.

[0151] Based on the methods described in steps S101 to S104 above, the comprehensive weather and water accumulation of each area are calculated by integrating multi-source data, and the recommended wetland mode status of driving equipment in the area is determined according to the water accumulation. This enables accurate recommendations for switching to wetland mode, making the recommended wetland mode status more consistent with actual driving scenarios. This helps to improve the reach of wetland mode switching, protect users driving on slippery roads in severe weather such as rain, snow, and ice, and enhance user experience and driving safety.

[0152] The following provides further explanation of steps 101 to S104 above.

[0153] In some embodiments of step S101, basic weather information for each region can be obtained first, such as basic rainfall information, basic snowfall information, and basic icing information. The basic weather information can include basic water volume levels. Taking basic rainfall information as an example, basic water volume levels can include level 0 (no rain), level 1 (light rain), level 3 (moderate rain), level 5 (heavy rain), level 7 (heavy rain), level 9 (torrential rain), level 11 (very torrential rain), level 13 (extremely heavy rain), and level 15 (extreme torrential rain). The basic water volume levels corresponding to basic snowfall information and basic icing information are similar.

[0154] See appendix Figure 2 , Figure 2 This is a schematic diagram illustrating the main steps involved in obtaining basic weather information for each region according to an embodiment of this application. Figure 2 As shown, it mainly includes the following steps S201 to S204.

[0155] Step S201: Based on a preset time window, acquire wiper data and positioning data for each driving device;

[0156] Specifically, a preset time window of 30 seconds can be set as the basic unit for data collection and processing to ensure that relevant data from the driving equipment is acquired periodically and regularly. The cloud server receives data reported by each driving device in real time every 30 seconds via data stream, which may include wiper data and positioning data from the driving device.

[0157] The wiper data can include the number of wiper operations and gear distribution information, which can be collected by the rain light sensor (RLS) of the driving device. The location data can be collected by the positioning module (such as GPS, Beidou, etc.) on the driving device to determine the geographical location of the driving device and provide spatial coordinates for subsequent area division.

[0158] Step S202: Process the wiper data to obtain the number of wiper cycles for each driving device within a preset time window;

[0159] In some implementations, step S202 may include steps S2021 to S2023.

[0160] Step S2021: Filter the wiper data to select wiper data that meets the abnormal weather scenario;

[0161] Abnormal weather scenarios can include rainfall, snowfall, icing, fog, and hail.

[0162] Specifically, it can filter wiper operations that are not in abnormal weather conditions, including windshield cleaning, wiper replacement, and when the vehicle is not in motion, to obtain wiper data that meets the requirements of abnormal weather scenarios.

[0163] Step S2022: Obtain the driving data and corresponding precipitation rate for each driving device;

[0164] The driving data can include vehicle driving status information such as vehicle speed, which is collected and uploaded by the vehicle control system of the driving equipment; the precipitation rate includes the rate of rainfall, the rate of snowfall, the rate of hailfall, etc., which can be obtained through the precipitation rate sensor or relevant meteorological platform based on the timestamp of the driving data.

[0165] Step S2023: Normalize the filtered wiper data based on driving data and precipitation speed.

[0166] In some implementations, the filtered wiper data can be normalized using the following formula (1):

[0167] Normalized value = (Number of wiper cycles²) / [1 + (Average vehicle speed² / Rainfall rate²)] (1)

[0168] The normalized value is the number of wiper cycles obtained after normalization, which is the number of wiper cycles performed by the driving device within a preset time window; the average vehicle speed is the average speed of the driving device within the preset time window.

[0169] The above is an explanation of step S202.

[0170] Step S203: Based on the preset grid division information, wiper data and positioning data, obtain the number of high-speed wiper requests and the total number of wiper cycles in each area;

[0171] Specifically, based on the preset basic grid division information and the positioning data of each driving device, the area to which each device belongs can be determined. Then, within each area, all wiper data in that area can be statistically analyzed to obtain the number of high-speed wiper requests and the total number of wiper operations in each area. Among them, the number of high-speed wiper requests is the total number of requests reported by all driving devices in that area for the wiper system to be in high-speed mode.

[0172] Step S204: Based on the number of high-speed wiper requests and the total number of wiper cycles, obtain the basic water volume level for each area.

[0173] In some implementations, step S204 may include steps S2041 to S2042.

[0174] Step S2041: Determine the wiper scene type based on the number of high-speed wiper requests;

[0175] Among them, the wiper scene types include low-speed wiper-dominated scene or high-speed wiper-dominated scene.

[0176] Specifically, it can be determined whether the number of high-speed wiper requests is less than a preset request threshold (e.g., 9); further, if the number of high-speed wiper requests is less than the preset request threshold, the wiper scene type is determined to be the low-speed wiper-dominated scene; if the number of high-speed wiper requests is greater than or equal to the preset request threshold, the wiper scene type is determined to be the high-speed wiper-dominated scene.

[0177] Step S2042: Classify the basic water volume level based on wiper scene type and total wiper strokes.

[0178] Specifically, for scenarios dominated by low-speed wipers (such as when the number of high-speed wiper requests is less than 9), the basic water volume level can be divided based on the normalized total number of wiper requests (stateCount), and when stateCount is high, fine-tuning can be made by combining the number of high-speed wiper requests and the proportion of low-speed wipers.

[0179] Taking basic weather information as basic rainfall information as an example, when stateCount < 1, the basic rainfall level can be determined as level 0 (no rain); when 1 <= stateCount < 5, the basic rainfall level can be determined as level 1 (light rain); when 5 <= stateCount < 10, the basic rainfall level can be determined as level 3 (moderate rain); when 10 <= stateCount < 29, the basic rainfall level can be determined as level 5 (heavy rain); when stateCount >= 29, fine-tuning logic is entered, which can include: if the proportion of high-speed wiper requests is greater than 0.66 (i.e., 66%), the basic rainfall level can be determined as level 9 (heavy rain); if the proportion of low-speed wipers is greater than 0.33 (33%), the basic rainfall level can be determined as level 7 (heavy rain); otherwise, the basic rainfall level can be determined as level 5 (heavy rain).

[0180] For scenarios dominated by low-speed wipers (such as when the number of high-speed wiper requests is >= 9), the base water level can be increased by one level and divided according to stateCount.

[0181] Taking basic weather information as basic rainfall information as an example, when stateCount < 3, the basic water volume level can be determined as level 7 (heavy rain); when 3 <= stateCount < 10, the basic water volume level can be determined as level 9 (rainstorm); when 10 <= stateCount < 19, the basic water volume level can be determined as level 11 (heavy rainstorm); when 19 <= stateCount < 29, the basic water volume level can be determined as level 13 (extremely heavy rainstorm); and when stateCount >= 29, the basic water volume level can be determined as level 15 (extreme rainstorm).

[0182] It should be noted that the above examples of classifying basic water volume levels are merely illustrative. In practical applications, those skilled in the art can classify basic water volume levels according to specific scenarios, and no limitations are imposed here.

[0183] The above explains how to obtain basic weather information for each region.

[0184] Furthermore, in some embodiments of step S101, weather data can be acquired, and based on the weather data and the region ID, it can be determined whether basic weather information exists in each region, and a first time threshold can be set according to the determination result; based on the first time threshold, it can be determined whether the weather data of each region is fresh; if so, the weather flow data of the region can be obtained based on the weather data; otherwise, real-time weather data is requested, and the weather data and real-time weather data are merged to obtain the weather flow data of the region.

[0185] Specifically, the cloud server can asynchronously read hourly / minute-level weather data for each region stored in a database (such as the open-source in-memory data storage system Redis). Based on the region ID, it determines whether basic weather information exists for each region and sets a first time threshold accordingly. This threshold varies depending on whether the region has basic rainfall. For example, the first time threshold is set to 1 hour if basic weather information exists, and 2 hours if it doesn't. Then, based on the first time threshold, it determines whether the weather data for each region is recent, i.e., whether the timestamp exceeds the first time threshold.

[0186] Furthermore, different labels can be assigned to the region ID based on the judgment result. For example, if the update time is fresh, the label "storedOutputTag" can be assigned, and if the update time is not fresh enough, the label "requestedOutputTag" can be assigned.

[0187] For sufficiently recent regions, weather data already stored in Redis can be passed as part of the weather stream data to downstream modules for processing. For regions that are not recent enough, real-time weather data needs to be asynchronously requested from an external meteorological service platform or data source that provides real-time weather data via Hypertext Transfer Protocol (HTTP). The asynchronously requested real-time weather data includes latitude and longitude information, which can be used to match the real-time weather data to the corresponding region in the base grid. Furthermore, the weather data already stored in Redis can be merged with the asynchronously requested real-time weather data and passed as part of the weather stream data to downstream modules for processing.

[0188] The above explains how to obtain weather flow data for each region.

[0189] Further, in some embodiments of step S101, short-term precipitation data can be acquired, and based on the short-term precipitation data and the region ID, it can be determined whether basic weather information exists in each region, and a second time threshold can be set according to the determination result; based on the second time threshold, it can be determined whether the short-term precipitation data of each region is fresh; if so, the short-term precipitation flow data of the region can be obtained based on the short-term precipitation data; otherwise, real-time short-term precipitation data can be requested, and the short-term precipitation flow data of the region can be obtained based on the short-term precipitation data and the real-time short-term precipitation data.

[0190] Specifically, the cloud server can asynchronously read minute-level / hourly-level short-term precipitation data for each region stored in Redis. Based on the region ID, it determines whether basic weather information exists for each region and sets a second time threshold accordingly. For example, the second time threshold is set to 24 minutes if basic weather information exists, and to 114 minutes if it does not. Then, based on the second time threshold, it determines whether the short-term precipitation data for each region is recent, i.e., whether the timestamp exceeds the second time threshold.

[0191] Furthermore, different labels can be assigned to the region ID based on the judgment result. For example, if the update time is fresh, the label "storedOutputTag" can be assigned, and if the update time is not fresh enough, the label "requestedOutputTag" can be assigned.

[0192] For sufficiently fresh regions, the short-term precipitation data already stored in Redis can be passed to downstream modules as part of the short-term precipitation stream data for processing. For regions that are not fresh enough, it is necessary to asynchronously request real-time short-term precipitation data from an external meteorological service platform or data source that provides such data via HTTP. The asynchronously requested real-time short-term precipitation data also includes latitude and longitude information, which can be used to match the real-time weather data to the corresponding region in the base grid. Furthermore, the short-term precipitation data already stored in Redis and the asynchronously requested real-time short-term precipitation data can be combined as part of the weather stream data and passed to downstream modules for processing.

[0193] The above is a further explanation of step S101. The following is a further explanation of step S102.

[0194] In some embodiments of step S102 above, a weather state backend (weatherState) and a short-term state backend (shortTermState) can be created on a cloud server. Weather flow data is stored in weatherState, and short-term precipitation flow data is stored in shortTermState. When either weather flow data or short-term precipitation flow data is input, the corresponding data for that area can be read from the other state backend.

[0195] Furthermore, the system can obtain the first timestamp of weather flow data and the second timestamp of short-term precipitation flow data for each region, and match the weather flow data and short-term precipitation flow data based on the first and second timestamps. If the first and second timestamps are the same, the precipitation intensity is obtained based on the short-term precipitation flow data, and comprehensive weather information for each region is calculated based on the precipitation intensity. This comprehensive weather information may include rainfall, snowfall, and icing information.

[0196] Specifically, if the first timestamp recording the weather data update time and the second timestamp recording the short-term precipitation data update time are the same, it means that the two types of data belong to the observation results of the same time node. At this time, the precipitation intensity parameter can be extracted from the fields carried by the short-term precipitation flow data. If the intensity is not extracted from the short-term precipitation flow data, the specific precipitation intensity value can also be obtained by converting the precipitation level and the preset precipitation intensity range (e.g., light rain corresponds to 0.1-10 mm / hour, moderate rain corresponds to 10-25 mm / hour, etc.), and finally used for the calculation of comprehensive weather.

[0197] Taking comprehensive weather information as rainfall information as an example, in some implementation methods, the rainfall information for each region can be calculated using the following formula (2):

[0198] Rainfall = 54.713 × intensity 4 -100.91×intensity 3 +49.806×intensity 2 +11.492×intensity+0.1022(2)

[0199] Furthermore, the comprehensive weather information for each region can be calculated and output to downstream modules for processing.

[0200] The above is a further explanation of step S102. The following is a further explanation of step S103.

[0201] In some implementations of step S103 above, a grid comprehensive weather state backend (gridWeatherState) and a water accumulation state backend (pongdingState) can be created on a cloud server. The gridWeatherState stores the comprehensive weather information for each region, and the pongdingState stores the water accumulation for each region.

[0202] Specifically, the comprehensive weather information input from the upstream module can be stored in gridWeatherState. This allows the comprehensive weather information for the corresponding area to be retrieved from gridWeatherState when basic weather information is received.

[0203] Furthermore, the timestamp difference between the basic weather information and the comprehensive weather information for each region can be obtained, and it can be determined whether the timestamp difference is within a preset threshold range; if so, the water accumulation in each region can be calculated based on the basic weather information and the comprehensive weather information.

[0204] Specifically, if the timestamp difference between the basic weather information and the comprehensive weather information for the same area is within a preset threshold range, it indicates that the two types of information belong to the same time interval. In this case, the water accumulation in each area can be calculated based on the basic weather information and the comprehensive weather information.

[0205] In some implementations, see Appendix Figure 3 , Figure 3 This is a schematic flowchart illustrating the main steps of calculating the water accumulation in each area based on basic weather information and comprehensive weather information, according to an embodiment of this application. Figure 3 As shown, it mainly includes the following steps S301 to S303.

[0206] Step S301: Obtain weight parameters based on the number of driving devices in each area;

[0207] Specifically, the weight parameter can be obtained using the following formula (3):

[0208] weight=carNumber / processVehicleCountWeight (3)

[0209] Among them, carNumber is the total number of driving devices participating in the wiper data statistics in the current area; processVehicleCountWeight is a configurable constant that can be configured according to the area size, driving device density, and other scenarios. It is mainly used to limit the range of weight parameters to avoid the weight parameters being too large when there are too many driving devices or too small when there are too few driving devices.

[0210] Step S302: Calculate the total water volume for each region based on basic weather information, comprehensive weather information, and weighting parameters;

[0211] Taking a rainfall scenario as an example, in some implementations, the total water volume (rainfall) of each area can be calculated using the following formula (4):

[0212] rainfall=baseRainfall*weight+weatherRainfall*(1-weight)(4)

[0213] Among them, baseRainfall is the basic rainfall information (basic weather information); weatherRainfall is the weather rainfall information (comprehensive weather information); and weight is the weight parameter.

[0214] Step S303: Perform time decay filtering on the total water volume to obtain the water volume of each area.

[0215] In some implementations, step S303 may include steps S3031 to S3034.

[0216] Step S3031: Obtain the previous flood level and recording time based on historical data;

[0217] Specifically, the previous water level (pondingLastTime.f0) and recording time (pondingLast Time) can be obtained from the data stored in the water level status backend (pongdingState).

[0218] Step S3032: Determine whether the previous water level was within the valid time range and whether the environmental parameters were complete;

[0219] The environmental parameters include at least one of temperature, humidity, and weather.

[0220] This means that the previous waterlogging level was confirmed and the recording time has not expired; in addition, environmental parameters such as temperature, humidity, and weather code are complete (and not null).

[0221] Furthermore, if the previous water level was within the valid time range and the environmental parameters were complete, then step S3033 is executed for dynamic calculation; otherwise, step S3031 is returned.

[0222] Step S3033: Obtain the time difference between the current time and the recorded time, and determine the time decay coefficient based on environmental parameters;

[0223] The time decay coefficient includes the time constant for water level rise or the time constant for water level fall.

[0224] Specifically, the time difference (in minutes) timeDiff = (currentProcessingTime - pondingLastTime.f1) / 60000; where currentProcessingTime is the current time.

[0225] Furthermore, based on temperature and humidity, parameter k1 can be found in the K1Cache table (see Table 1 below) or calculated by interpolation. k1 is a coefficient that reflects the influence of temperature and humidity on the rate of water receding.

[0226] Table 1

[0227] Using Table 1 above, you can find the corresponding value based on the current humidity (row) and temperature (column). If the temperature / humidity is not in the enumerated values ​​in the table, you can calculate it using interpolation (such as linear interpolation) to obtain K1.

[0228] Furthermore, based on the weather code, the road surface drying speed coefficient k2 and the water accumulation rise time constant tcUp (i.e., road surface water accumulation speed coefficient, unit: minutes) in the time decay coefficient can be found through the K2Cache table (see Table 2 below).

[0229] Table 2

[0230] Using Table 2 above, you can find the corresponding road surface drying speed coefficient k2 and water accumulation rise time constant tcUp in the time decay coefficient based on the weather code.

[0231] Step S3034: Calculate the water volume of each area based on the relationship between the total water volume and the previous water level, as well as the time difference and time decay coefficient.

[0232] Specifically, you can first compare the current total water volume with the previous water level.

[0233] If the current total water volume is greater than or equal to the previous water level (i.e., the water volume is increasing), the water level in the area can be calculated using the following formula (5):

[0234] ponding=rainfall+(pondingLastTime.f0-rainfall)*exp(-timeDiff / tcUp)(5)

[0235] Where rainfall is the total water volume, pondingLastTime.f0 is the previous water level, exp is the exponential function, timeDiff is the time difference between the current time and the previous water level record time, and tcUp is the water level rise time constant.

[0236] If the current total water volume is less than the previous water level (i.e., the water volume is decreasing), the water level drop time constant tcDown in the time decay coefficient can be calculated first using the following formula (6):

[0237] tcDown=k1*k2 (6)

[0238] Where k1 is a coefficient reflecting the influence of temperature and humidity on the rate of water receding, and k2 is the road surface drying rate coefficient.

[0239] Furthermore, the ponding volume of the area can be calculated using the following formula (7):

[0240] ponding=rainfall+(pondingLastTime.f0-rainfall)*exp(-timeDiff / tcDown)(7)

[0241] Where rainfall is the total water volume, pondingLastTime.f0 is the previous water level, exp is the exponential function, timeDiff is the time difference between the current time and the previous water level record time, and tcDown is the water level drop time constant.

[0242] The ponding calculated by the above formula (5) or formula (7) is the water accumulation level for each area. Taking the rainfall scenario as an example, it can include level 0 (no rain), level 1 (light rain), level 3 (moderate rain), level 5 (heavy rain), level 7 (heavy rain), level 9 (rainstorm), level 11 (heavy rainstorm), level 13 (extremely heavy rainstorm), level 15 (extreme rainstorm), etc.

[0243] The above steps S3031 to S3034, combined with the time decay formula to dynamically calculate the water accumulation level, can make the results more consistent with the actual physical process, such as the rapid receding of water accumulation under high temperature and low humidity, and the rapid accumulation of water accumulation during precipitation, thus providing accurate water accumulation data support for wetland model recommendations.

[0244] The above is a further explanation of step S103. The following is a further explanation of step S104.

[0245] In some implementations of step S104 above, it can be determined whether the driving equipment in the area should enter wetland mode, exit wetland mode, or remain unchanged, based on the calculated water level of each area.

[0246] Specifically, when the water level is less than or equal to the first threshold, the recommended state for the wet mode of the driving device in the area can be determined to be exiting the wet mode; when the water level is greater than or equal to the second threshold, the recommended state for the wet mode of the driving device in the area can be determined to be entering the wet mode; when the water level is greater than the first threshold and less than the second threshold, the recommended state for the wet mode of the driving device in the area can be determined to be maintaining the current driving mode; wherein, the first threshold is less than the second threshold.

[0247] For example, when the first threshold is 1 and the second threshold is 3, if the current water level of a certain area is ≤1, it is recommended that the driving device in the area turn off the wet mode; if the water level is ≥3, it is recommended that the driving device in the area turn on the wet mode; otherwise (i.e., when 1 < water level < 3), the current driving mode is maintained.

[0248] Furthermore, in some implementations, when the water level is greater than or equal to the second threshold and the driving mode of the driving device in the area is not wet mode, a reminder to switch driving mode can be sent to the driving device, or the driving device can be controlled to switch the driving mode to wet mode.

[0249] Specifically, when it is determined that the location of the driving device requires the wet mode to be turned on but the wet mode is not turned on, the driver can be reminded to switch to wet mode through pop-up windows on the driving device display, or the driver can be helped to switch to wet mode more easily through active switching, so as to improve user experience and driving safety.

[0250] Furthermore, in some embodiments, after obtaining the water volume of each area, a wetland map can be built based on the water volume to display the water volume of each area; wherein, the wetland map includes at least a weather layer and a water volume layer.

[0251] Specifically, a wetland map based on S2 can be built on a cloud server. (S2 is a spatial indexing technology that divides the Earth's surface into multi-level grids, similar to the fine division of latitude and longitude grids. Each grid corresponds to a unique geographical region, enabling efficient geospatial positioning, indexing, and regional division.) In the cloud server, a geographical region is divided into several small units based on the S2 grid. Each unit is associated with data such as weather and water accumulation in that region, forming a dynamically updated wetland map. This map can include weather layers (such as water volume layers, snow volume layers, and icing layers) and water accumulation layers, visually displaying the weather and water accumulation status of different areas.

[0252] The above is a further explanation of steps S101 to S104.

[0253] The following is in conjunction with the appendix Figure 4 and attached Figure 5This application introduces the wetland model recommendation method.

[0254] See appendix Figure 4 , Figure 4 This is a flowchart illustrating the real-time data processing of a wetland pattern recommendation method according to an embodiment of this application. Figure 4 As shown, it mainly includes the following steps S401 to S4015.

[0255] Step S401: Start the Flink environment and set up the RocksDB state backend;

[0256] Flink is a distributed stream processing framework that provides the foundation for real-time data processing; RocksDB serves as the state backend, used to reliably store and manage the data state in Flink jobs, ensuring the consistency and recoverability of data processing.

[0257] Step S402: Kafka Source reads basic weather information for each region;

[0258] Kafka is a distributed message queue. Kafka Source, as a data input interface, can read basic weather information for each region from the Kafka cluster, providing a data source for subsequent processing.

[0259] Step S403: Group by region ID and verify the region data using a verification function;

[0260] Specifically, data can be grouped based on region ID, allowing data from the same region to enter the same processing unit. The verification function is used to verify the legality and integrity of the region data, ensuring the quality of data in subsequent processing.

[0261] Step S404: Asynchronously read weather data from Redis;

[0262] Furthermore, if the weather data stored in Redis is not timely enough, then step S406 is executed;

[0263] Step S405: Asynchronously read short-term precipitation data from Redis;

[0264] Furthermore, if the short-term precipitation data stored in Redis is not timely enough, then step S407 is executed;

[0265] Step S406: Asynchronously request real-time weather data via the HTTP interface; then proceed to step S408;

[0266] Real-time weather data is obtained asynchronously via an HTTP interface, and the data is supplemented and updated to ensure real-time performance and accuracy.

[0267] Step S407: Asynchronously request real-time short-term precipitation data via the HTTP interface; then proceed to step S409;

[0268] By asynchronously obtaining real-time short-term precipitation data via HTTP interface, it is possible to supplement and update the data, ensuring real-time performance and accuracy.

[0269] Step S408: Write the real-time weather data back to Redis; then execute step S4010;

[0270] Step S409: Write the real-time short-term precipitation data back to Redis; then execute step S4010;

[0271] Step S4010: Merge weather flow data and short-term precipitation flow data to obtain comprehensive weather information;

[0272] Step S4011: Obtain comprehensive weather information for each region based on the region ID;

[0273] Step S4012: Obtain the water accumulation in each area based on basic weather information and comprehensive weather information;

[0274] Step S4013: Perform wetland detection based on the water accumulation in each area to determine the recommended wetland mode status for driving equipment within the area;

[0275] Step S4014: Write the detection results to the Kafka cluster;

[0276] Step S4015: Data stream processing completed, waiting for the next batch of data;

[0277] Specifically, after completing the processing of the current batch of data, it waits to receive the next batch of data and continues to conduct real-time data monitoring and wetland pattern recommendations.

[0278] The above is about Figure 4 Further explanation.

[0279] See appendix Figure 5 , Figure 5 This is a schematic diagram of the main flow of a wetland pattern recommendation method according to an embodiment of this application. Figure 5 As shown, it mainly includes driving equipment data links, weather data links, and data fusion and wetland pattern recommendation links.

[0280] The driving device data link mainly includes: transmitting driving device-related data from the "vehicle gateway" on the driving device side through the "remote service platform" to the "driving device's Kafka message queue" on the cloud server to obtain the driving device's "location data," "wiper data," and "current driving mode." The "wiper data" undergoes statistical and normalization processing of group data through the "Flink wiper processing task" to generate "wiper data for each region," providing data support for basic weather information calculations.

[0281] The weather data link mainly includes: the cloud server uses "real-time weather service" as the source of meteorological data, and collects real-time weather data for each region through the "real-time weather acquisition task" to form "weather flow data and short-term precipitation flow data for each region" for subsequent fusion calculation.

[0282] The data fusion and wetland detection link mainly includes: the cloud server uses "Flink regional merging processing" to merge wiper data, weather flow data, and short-term precipitation flow data of each region by region ID, generating a "Flink regional data stream" containing multi-dimensional information. This data stream is input into the "wetland mode recommendation module," which, combined with the "group wetland model" (a wetland model trained based on historical data), calculates the water accumulation and wetland mode recommendation status of each region. The calculation results are written to the "Kafka message queue of the driving device" and transmitted to the "group wiper decision app" on the driving device side. This interacts with the "in-vehicle interaction system" (such as the in-vehicle intelligent assistant NOMI, UX, etc.) of the driving device to realize the display and application of wetland mode recommendation results.

[0283] The aforementioned wetland mode recommendation method achieves swarm intelligence by integrating information from a large number of vehicle sensors, such as windshield wipers, and combines real-time weather flow data and short-term precipitation flow data to achieve real-time analysis of weather rainfall and water accumulation, providing data support for wetland mode recommendations and thus ensuring safe driving for users on slippery roads in rainy or snowy weather.

[0284] The above is a further explanation of the wetland model recommendation method provided in this application.

[0285] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of this application.

[0286] Those skilled in the art will understand that all or part of the processes in the method of the above-described embodiment can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0287] Furthermore, this application also provides an electronic device. (See appendix) Figure 6 , Figure 6 This is a schematic diagram of the main structure of an electronic device according to an embodiment of this application. Figure 6 As shown, the electronic device in this embodiment mainly includes a processor 61 and a memory 62. The memory 62 can be configured to store a program for executing the wetland pattern recommendation method of the above method embodiments, and the processor 61 can be configured to execute the program in the memory 62. This program includes, but is not limited to, a program for executing the wetland pattern recommendation method of the above method embodiments. For ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application.

[0288] In some possible embodiments of this application, the electronic device may include multiple processors 61 and multiple memories 62. The program executing the wetland mode recommendation method of the above method embodiments can be divided into multiple subroutines, each of which can be loaded and run by a processor 61 to perform different steps of the wetland mode recommendation method of the above method embodiments. Specifically, each subroutine can be stored in a different memory 62, and each processor 61 can be configured to execute programs in one or more memories 62 to jointly implement the wetland mode recommendation method of the above method embodiments; that is, each processor 61 executes different steps of the wetland mode recommendation method of the above method embodiments to jointly implement the wetland mode recommendation method of the above method embodiments.

[0289] The aforementioned multiple processors 61 can be processors deployed on the same device. For example, the aforementioned electronic device can be a high-performance device composed of multiple processors, and the aforementioned multiple processors 61 can be processors configured on that high-performance device. Alternatively, the aforementioned multiple processors 61 can also be processors deployed on different devices. For example, the aforementioned electronic device can be a server cluster, and the aforementioned multiple processors 61 can be processors on different servers within the server cluster. Or, the aforementioned computer device can be a driving equipment cluster, and the aforementioned multiple processors 901 can be processors on different driving devices within the driving equipment cluster.

[0290] Furthermore, this application also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to this application, the computer-readable storage medium can be configured to store a program that performs the wetland pattern recommendation method of the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described wetland pattern recommendation method. For ease of explanation, only the parts related to the embodiments of this application are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of this application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, in the embodiments of this application, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0291] Furthermore, this application also provides a wetland mode recommendation system. In one embodiment of the wetland mode recommendation system according to this application, the system may include a cloud server and multiple driving devices communicatively connected to the cloud server.

[0292] The cloud server includes the electronic device described in the above-mentioned electronic device embodiments;

[0293] Multiple driving devices are configured to send wiper data and location data to a cloud server based on preset time windows.

[0294] The aforementioned wetland pattern recommendation system is used for execution. Figure 1 The wetland pattern recommendation method embodiments shown are similar in technical principle, the technical problems solved, and the technical effects produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the wetland pattern recommendation system can be found in the embodiments of the wetland pattern recommendation method, and will not be repeated here.

[0295] It should be noted that the relevant user personal information involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and is personal information that users actively provide or generate during the use of the product / service, as well as personal information obtained with user authorization.

[0296] The personal information processed in this application will vary depending on the specific product / service scenario and will be subject to the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, sensor information, or other relevant information. This application will treat the user's personal information and its processing with the utmost diligence.

[0297] This application attaches great importance to the security of users' personal information and has taken reasonable and feasible security protection measures that comply with industry standards to protect users' information and prevent unauthorized access, disclosure, use, modification, damage or loss of personal information.

[0298] The technical solution of this application has been described above with reference to one embodiment shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. Without departing from the principles of this application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of this application.

Claims

1. A wetland pattern recommendation method, characterized in that, The method includes: Acquire basic weather information, weather flow data, and short-term precipitation flow data for each region; Comprehensive weather information for each region is obtained based on the aforementioned weather flow data and short-term precipitation flow data; The water accumulation in each area is obtained based on the basic weather information and the comprehensive weather information. Based on the water accumulation in each area, the recommended wetland mode status for the driving equipment in that area is determined. The basic weather information includes basic water volume levels; obtaining the basic weather information for each region includes: Based on a preset time window, acquire wiper data and positioning data for each driving device; The wiper data is processed to obtain the number of wiper cycles for each driving device within the preset time window; Based on the preset grid division information, the wiper data, and the positioning data, the number of high-speed wiper requests and the total number of wiper cycles in each area are obtained; Based on the number of high-speed wiper requests and the total number of wiper cycles, the basic water level for each area is obtained; The process of obtaining weather flow data for each region includes: acquiring weather data; determining whether the weather data for each region is recent; if so, obtaining the weather flow data for that region based on the weather data; otherwise, requesting real-time weather data and merging the weather data and the real-time weather data to obtain the weather flow data for that region. The process of obtaining short-term precipitation flow data for each region includes: obtaining short-term precipitation data; determining whether the short-term precipitation data for each region is fresh; if so, obtaining the short-term precipitation flow data for the region based on the short-term precipitation data; otherwise, requesting real-time short-term precipitation data, and obtaining the short-term precipitation flow data for the region based on the short-term precipitation data and the real-time short-term precipitation data.

2. The wetland pattern recommendation method according to claim 1, characterized in that, The basic water volume level for each area, derived from the number of high-speed wiper requests and the total number of wiper cycles, includes: The wiper scene type is determined based on the number of high-speed wiper requests; the wiper scene type includes low-speed wiper-dominated scene or high-speed wiper-dominated scene. The basic water volume level is determined based on the wiper scene type and the total number of wiper cycles.

3. The wetland pattern recommendation method according to claim 2, characterized in that, The method of determining the wiper scenario type based on the number of high-speed wiper requests includes: Determine whether the number of high-speed wiper requests is less than a preset request threshold; If so, the wiper scene type is determined to be the low-speed wiper-dominated scene; otherwise, the wiper scene type is determined to be the high-speed wiper-dominated scene.

4. The wetland pattern recommendation method according to claim 1, characterized in that, The processing of the wiper data includes: The wiper data is filtered to select wiper data that meets the requirements of abnormal weather scenarios; Acquire driving data and corresponding precipitation speed for each driving device; the driving data includes at least vehicle speed. The filtered wiper data is normalized based on the driving data and the precipitation speed.

5. The wetland pattern recommendation method according to claim 1, characterized in that, Determining whether the weather data for each region is recent includes: Based on the weather data and region ID, determine whether the basic weather information exists in each region, and set a first time threshold according to the determination result; The freshness of weather data for each region is determined based on the first time threshold.

6. The wetland pattern recommendation method according to claim 1, characterized in that, Determining whether the short-term precipitation data for each region is recent includes: Based on the short-term precipitation data and the region ID, determine whether the basic weather information exists in each region, and set a second time threshold according to the determination result; The freshness of short-term precipitation data for each region is determined based on the second time threshold.

7. The wetland pattern recommendation method according to claim 1, characterized in that, The process of obtaining comprehensive weather information for each region based on the weather flow data and short-term precipitation flow data includes: Obtain the first timestamp of the weather flow data and the second timestamp of the short-term precipitation flow data for each region; The weather flow data and the short-term precipitation flow data are matched based on the first timestamp and the second timestamp; If the first timestamp and the second time are the same, the precipitation intensity is obtained based on the short-term precipitation flow data, and the comprehensive weather information for each region is calculated based on the precipitation intensity.

8. The wetland pattern recommendation method according to claim 1, characterized in that, The water accumulation in each region, obtained based on the basic weather information and the comprehensive weather information, includes: Obtain the timestamp difference between the basic weather information and the comprehensive weather information for each region; Determine whether the timestamp difference is within a preset threshold range; If so, the water accumulation in each area is calculated based on the basic weather information and the comprehensive weather information.

9. The wetland pattern recommendation method according to claim 8, characterized in that, The calculation of water accumulation in each area based on the basic weather information and the comprehensive weather information includes: Weight parameters are obtained based on the number of driving devices in each area; The total water volume of each region is calculated based on the basic weather information, the comprehensive weather information, and the weighting parameters. The total water volume is subjected to time decay filtering to obtain the water accumulation in each region.

10. The wetland pattern recommendation method according to claim 9, characterized in that, The process of applying time-attenuation filtering to the total water volume to obtain the water accumulation in each region includes: The previous flood level and recording time are obtained based on historical data; Determine whether the previous flood level was within the valid time range and whether the environmental parameters were complete; the environmental parameters include at least one of temperature, humidity and weather. If so, the time difference between the current time and the recorded time is obtained, and the time decay coefficient is determined based on the environmental parameters; the time decay coefficient includes the water rise time constant or the water fall time constant. The water volume of each area is calculated based on the relationship between the total water volume and the previous water level, as well as the time difference and the time decay coefficient.

11. The wetland pattern recommendation method according to claim 1, characterized in that, The water accumulation includes water accumulation level; determining the recommended wetland mode status for driving equipment within each area based on the water accumulation includes: When the water accumulation level is less than or equal to the first threshold, the recommended state for the wet mode of the driving equipment in the area is to turn off the wet mode. When the water accumulation level is greater than or equal to the second threshold, the recommended state for the wet mode of the driving equipment in the area is to turn on the wet mode. When the water accumulation level is greater than the first threshold and less than the second threshold, the recommended wetland mode state for the driving equipment in the area is determined to be to maintain the current driving mode. Wherein, the first threshold is less than the second threshold.

12. The wetland pattern recommendation method according to claim 11, characterized in that, The method further includes: When the water level is greater than or equal to the second threshold, and the driving mode of the driving device in the area is not the wetland mode, a reminder to switch driving modes is sent to the driving device, or the driving device is controlled to switch the driving mode to the wetland mode.

13. The wetland model recommendation method according to any one of claims 1 to 12, characterized in that, The method further includes: A wetland map is created based on the water accumulation to display the water accumulation in each area; The wetland map includes at least a weather layer and a water accumulation layer.

14. An electronic device comprising a processor and a memory, the memory being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the wetland pattern recommendation method according to any one of claims 1 to 13.

15. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the wetland pattern recommendation method as described in any one of claims 1 to 13.

16. A wetland pattern recommendation system, characterized in that, The system includes a cloud server and multiple driving devices communicatively connected to the cloud server; wherein, The cloud server includes the electronic device as described in claim 14; The multiple driving devices are configured to send wiper data and location data to the cloud server based on a preset time window.

Images