Danger reminding method, device and equipment

Abstract

The invention provides a danger reminding method, device and equipment, and is applied to the field of intelligent interaction. The method comprises the steps that in the vehicle driving process, the target danger level of a road in front of a vehicle is determined firstly, then a reminding strategy corresponding to the current target cross-country level of the vehicle and the target danger level is determined from multiple reminding strategies, and finally the target reminding strategy is executed to remind a user. According to the method provided by the invention, in the vehicle driving process, when the user needs to be reminded, the user is reminded through the reminding strategy corresponding to the target cross-country grade of the vehicle and the target danger grade of the road, so that the accuracy in the danger reminding process can be improved, the possible interference of danger reminding on a driver can be reduced, and the user experience is improved. And the safety of the vehicle can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent interaction, and more particularly, to a danger reminding method, device and equipment in the field of intelligent interaction. BACKGROUND

[0002] At present, in order to improve the safety of the vehicle during driving, the common method is to detect whether there are dangerous factors such as pits, water, stones and smoke in front of the vehicle during driving, and if there are the above dangerous factors, a danger reminding is performed to remind the user to timely adjust the speed and / or direction of the vehicle, so as to reduce the probability of vehicle accidents. The problem of this method is that the danger reminding may cause interference to the driver, affect the normal driving of the user, and thus may reduce the safety of the vehicle. SUMMARY

[0003] The present application provides a danger reminding method, device and equipment, which can reduce the interference of danger reminding to the driver and improve the safety of the vehicle.

[0004] In a first aspect, a danger reminding method is provided, which comprises:

[0005] determining a target danger level of a road in front of the vehicle;

[0006] determining a first reminding strategy from a plurality of reminding strategies; wherein the plurality of reminding strategies correspond to different off-road levels and danger levels respectively, the first reminding strategy corresponds to a target off-road level of the vehicle currently and corresponds to the target danger level;

[0007] executing the first reminding strategy to remind the user.

[0008] In the present application, during driving of the vehicle, first, a target danger level of a road in front of the vehicle is determined, then a reminding strategy corresponding to a target off-road level of the vehicle currently and corresponding to the target danger level is determined from a plurality of reminding strategies, and finally the target reminding strategy is executed to remind the user.

[0009] The method provided by the present application can perform targeted danger reminding based on the danger level of the road and the off-road level of the vehicle when there is danger on the road, and at the same time of performing targeted reminding on roads with different danger levels, the reminding strategies of vehicles with different off-road levels are different for roads with the same danger level, which can perform differentiated reminding for vehicles with different off-road levels, so as to further refine the reminding strategy, improve the targeting and accuracy of danger reminding, so as to reduce the interference of danger reminding to the driver, and thus improve the safety of the vehicle.

[0010] For example, the road with smaller tunnels and water pools has a lower danger level, which may be dangerous for a vehicle with a lower off-road level, less dangerous for a vehicle with a higher off-road level, or even not dangerous. When the danger prompt is performed based on the method provided in the application, the prompt strategies for the vehicle with a lower off-road level and the vehicle with a higher off-road level are different, the differentiated danger prompt can be realized, the pertinence and accuracy of the danger prompt can be improved, the interference of the danger prompt on the driver in the vehicle with a higher off-road level can be reduced, and thus the safety of the vehicle can be improved.

[0011] Optionally, the determining the target danger level of the front road of the vehicle comprises: determining whether the visibility of the front road meets a standard; and if not, determining the target danger level of the front road.

[0012] In the embodiments of the application, in the case that the visibility of the front road of the vehicle does not meet the standard, the target danger level of the front road is determined, and the first prompt strategy corresponding to the target danger level and the target off-road level is performed, which can perform the danger prompt when the visibility in front of the vehicle is poor, and does not perform the danger prompt when the visibility in front of the vehicle is good and the danger prompt is not needed, thereby reducing unnecessary prompts and reducing the interference of the danger prompt on the user, to improve the safety of the vehicle.

[0013] Optionally, the determining whether the visibility of the front road meets the standard comprises: acquiring a visible light image of the front road; and in the case that the definition of the visible light image is less than a preset definition, determining that the visibility of the front road does not meet the standard.

[0014] In the embodiments of the application, whether the visibility of the front road meets the standard is determined by the definition of the visible light image of the front road, the visibility in front of the vehicle can be directly determined using the road image captured by the camera integrated in the vehicle, the visibility sensor does not need to be integrated in the vehicle for the parameter of visibility, the hardware cost of the vehicle can be avoided, and the visibility does not need to be acquired from the server according to the positioning information of the vehicle, thereby reducing the power consumption of the vehicle.

[0015] Optionally, the determining the target danger level of the front road comprises: in the case that the visibility of the front road is less than a preset visibility threshold, determining the target danger level according to the thermal imaging image and the radar data of the front road; and in the case that the visibility of the front road is greater than or equal to the visibility threshold, determining the target danger level according to the thermal imaging image or the radar data.

[0016] In the embodiments of the present application, one or both of the thermal imaging image and the radar data can be selected to determine the target danger level of the front road according to the visibility of the front road, so that only one of the thermal imaging image and the radar data is selected to determine the danger level when the visibility of the front road is good, thereby avoiding using the radar data and the thermal imaging image at the same time, so as to reduce the power consumption of the vehicle in the danger reminding process. When the visibility of the front road is poor, the thermal imaging image and the radar data are selected to determine the danger level, and the danger level is determined in combination with the thermal imaging image and the radar data, so as to accurately predict the danger level of the road when the visibility is poor, thereby timely reminding the danger when the danger exists in front of the vehicle, improving the reliability of the danger reminding, and further improving the safety of the vehicle.

[0017] Optionally, the method further comprises: in the case that the visibility of the front road meets the standard, determining whether there is a movable target object on the front road; and if there is the movable target object, outputting prompt information to prompt the user.

[0018] In the embodiments of the present application, in the case that the visibility of the front road meets the standard, if it is detected that there is a movable target object on the front road, prompt information is outputted to prompt the user, and the output of the prompt information can improve the attention of the driver in the vehicle to the movable target object in front of the vehicle, reduce the risk of collision between the vehicle and the movable target object, and thus improve the safety of the vehicle.

[0019] Optionally, the outputting prompt information to prompt the user if there is the movable target object comprises:

[0020] If there is the movable target object, the distance between the movable target object and the vehicle is acquired; and in the case that the distance is less than or equal to a preset distance, the prompt information is outputted to prompt the user.

[0021] In the embodiments of the present application, when there is a movable target object in front of the vehicle, and the distance between the movable target object and the vehicle is small and the probability of collision with the vehicle is high, prompt information is outputted to prompt the user, and when the distance between the movable target object and the vehicle is large and the probability of collision with the vehicle is low, no prompt information is outputted, which can reduce unnecessary prompt information, reduce power consumption, and reduce the interference of the prompt information on the user, thereby improving the safety of the vehicle.

[0022] Optionally, the method further comprises: determining the target off-road level matched with the front road from a plurality of off-road levels that the vehicle can reach; and setting the off-road level of the vehicle to the target off-road level when the off-road level currently set for the vehicle is lower than the target off-road level.

[0023] In the embodiments of the present application, the target off-road level matching the road ahead is determined from a plurality of off-road levels reachable by the vehicle, and when the off-road level currently set for the vehicle is lower than the target off-road level, the off-road level of the vehicle is set to the target off-road level, so that the off-road level of the vehicle can match the road ahead, thereby improving the applicability of the vehicle to the road ahead, and further improving the safety of the vehicle when driving on the road ahead.

[0024] Optionally, the first reminding strategy is determined from the plurality of reminding strategies when the off-road level currently set for the vehicle is higher than the target off-road level.

[0025] In the embodiments of the present application, when the off-road level currently set for the vehicle is higher than the target off-road level matching the road ahead, the first reminding strategy corresponding to the off-road level currently set for the vehicle and corresponding to the target danger level is determined from the plurality of reminding strategies, so that the first reminding strategy can correspond to the actual off-road level of the vehicle, and thereby the danger reminding strategy can correspond to the actual off-road performance of the vehicle.

[0026] Optionally, the first reminding strategy is executed when the driving speed of the vehicle is greater than a preset speed threshold, and after the first reminding strategy is executed, if it is determined that the falling amplitude of the driving speed of the vehicle is less than a preset amplitude threshold, a second reminding strategy is executed, wherein the second reminding strategy is a reminding strategy corresponding to a danger level higher than the first reminding strategy in the plurality of reminding strategies.

[0027] In the embodiments of the present application, the first reminding strategy is executed when the driving speed of the vehicle is greater than a preset speed threshold, and a higher second reminding strategy is executed when the driving speed of the vehicle is relatively low after the first reminding strategy is executed, so that the reminding strength can be improved in time when the vehicle is driving at a high speed, thereby improving the safety of the vehicle.

[0028] In a second aspect, a danger reminding device is provided, which comprises:

[0029] A determining module is configured to determine a target danger level of a road ahead of a vehicle, and determine a first reminding strategy from a plurality of reminding strategies, wherein the plurality of reminding strategies correspond to different off-road levels and danger levels respectively, and the first reminding strategy corresponds to a target off-road level currently set for the vehicle and corresponds to the target danger level.

[0030] An executing module is configured to execute the first reminding strategy to remind a user.

[0031] In a third aspect, an electronic device is provided, the device comprising:

[0032] a memory for storing executable program code;

[0033] a processor for invoking and running the executable program code from the memory, so that the electronic device performs the method in any possible implementation manner of the first aspect.

[0034] In a fourth aspect, a program product is provided, the program product comprising: program code, when the program code is run on an electronic device, so that the electronic device performs the method in any possible implementation manner of the first aspect.

[0035] In a fifth aspect, a readable storage medium is provided, the readable storage medium stores program code, when the program code is run on an electronic device, so that the electronic device performs the method in any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 is a step schematic diagram of a danger reminding method provided by an embodiment of the present application;

[0037] Figure 2 is a flow schematic diagram of a danger reminding method provided by an embodiment of the present application;

[0038] Figure 3 is a structure schematic diagram of a danger reminding device provided by an embodiment of the present application;

[0039] Figure 4 is a structure schematic diagram of a device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the present application will be described in detail below with reference to the drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B: "and / or" in the text only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0041] Hereinafter, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as implying or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more features.

[0042] Currently, in order to improve the safety during the driving of a vehicle, it is a common practice to detect whether there are dangerous factors such as pits, water pools, stones and smoke in front of the vehicle during the driving of the vehicle, and if there are the above dangerous factors, the user is reminded to timely adjust the speed and / or direction of the vehicle, and the higher the dangerous degree of the dangerous factors, the greater the reminding strength. In actual application, the higher the off-road level of the vehicle, the better the performance of the vehicle, and the stronger the adaptability of the vehicle to the road. The same dangerous factor can cause danger to a vehicle of a certain off-road level, but can not cause danger to a vehicle of a higher off-road level by one or more levels. In simple terms, some smaller pits, water pools and the like can constitute a greater danger to a vehicle of a lower off-road level, but constitute a smaller danger or even no danger to a vehicle of a higher off-road level. If the same reminding method is used for the danger reminding of a vehicle of a higher off-road level and a vehicle of a lower off-road level, the danger reminding is meaningless to the vehicle of the higher off-road level, and can even cause interference to the driver in the vehicle of the higher off-road level, affect the attention of the driver, and thus can reduce the safety of the vehicle.

[0043] In order to solve the above technical problem, the present application provides a danger reminding method, which can be executed by a host in a vehicle. In the method, the division of the reminding strategy is performed according to the off-road level of the vehicle and the dangerous level of the road, so that the reminding strategy corresponds to the dangerous level of the road and the off-road level of the vehicle. Based on the danger reminding based on the dangerous level, the danger reminding can be further refined according to the off-road level, so as to improve the accuracy and precision of the danger reminding. Based on this, during the danger reminding, the host first determines the dangerous level of the road in front of the vehicle, then determines the reminding strategy corresponding to the current off-road level of the vehicle and corresponding to the dangerous level from a plurality of reminding strategies, and finally executes the reminding strategy to remind the user. The method provided by the present application can perform targeted danger reminding based on the dangerous level of the road and the off-road level of the vehicle when there is danger on the road, and while performing targeted reminding on roads of different dangerous levels, the reminding strategies of vehicles of different off-road levels are different for roads of the same dangerous level, so that the vehicles of different off-road levels can be reminded differently, so as to further refine the reminding strategy, improve the targeting and accuracy of the danger reminding, so as to reduce the interference that the danger reminding can cause to the driver, and thus the safety of the vehicle can be improved.

[0044] In combination with the above examples, the road with small tunnels and water pools has a lower danger level, which can pose a greater danger to a vehicle with a lower off-road level, a smaller danger to a vehicle with a higher off-road level, and even no danger. When danger is reminded based on the method provided in the application, the reminding strategies for vehicles with lower off-road levels and vehicles with higher off-road levels are different, which can realize differentiated danger reminding, improve the pertinence and accuracy of danger reminding, thereby reducing the interference that danger reminding may cause to the driver in a vehicle with a higher off-road level, and further improving the safety of the vehicle.

[0045] In related technologies, in order to improve the off-road performance of a vehicle, multiple off-road levels are configured for the vehicle, and the functions available to the vehicle are different when the vehicle is in different off-road levels, so that the vehicle can be suitable for different off-road scenes. For example, the off-road levels of the vehicle can be sequentially divided from low to high as off-road level 1, off-road level 2, off-road level 3, and off-road level 4. Among them, off-road level 4 is professional off-road, which refers to an off-road level that can reliably operate in extreme environments, and when the vehicle is in professional off-road, it can safely pass through the extreme environment; off-road level 3 is strong off-road, which refers to an off-road level that can cope with various complex road conditions, and when the vehicle is in strong off-road, it can be suitable for various terrains; off-road level 2 is a general off-road, which refers to an off-road level that can adapt to more terrains, and when the vehicle is in general off-road, it can be suitable for more terrains; off-road level 1 is urban off-road, which refers to the off-road level corresponding to a sport utility vehicle (SUV), and when the vehicle is in urban off-road, it can be suitable for part of the terrain.

[0046] It can be understood that the higher the off-road level, the more vehicle functions available to the vehicle. For example, the vehicle functions corresponding to professional off-road include the crawl mode, steep slope slow descent function, uphill assist function, electronic limited slip function, and part-time four-wheel drive function, and when the vehicle is in professional off-road, one or more of the crawl function, steep slope slow descent function, uphill assist function, electronic limited slip function, and part-time four-wheel drive function can be turned on. For another example, the vehicle functions corresponding to general off-road include the part-time four-wheel drive function and the electronic limited slip function, and when the vehicle is in general off-road, one or more of the part-time four-wheel drive function and the electronic limited slip function can be started. It should be understood that the above are only exemplary examples, and the vehicle functions corresponding to each off-road level can include but are not limited to the above examples.

[0047] It can be understood that for each vehicle, the more hardware configurations and software configurations the vehicle has, the higher the highest off-road level the vehicle can reach. The fewer hardware configurations and software configurations the vehicle has, the lower the highest off-road level the vehicle can reach.

[0048] In the related art, the dangerous levels of a road are divided into multiple levels from low to high. For example, the dangerous levels can be divided into dangerous level 0, dangerous level 1, dangerous level 2, dangerous level 3, and dangerous level 4 from low to high. Among them, dangerous level 0 represents no danger, dangerous level 2 represents extremely low danger, dangerous level 3 represents certain danger, dangerous level 4 represents greater danger, and dangerous level 5 represents extremely great danger. From low to high, the higher the level, the greater the probability of danger.

[0049] It should be understood that the above is only an example, and the specific division method of the off-road level and the dangerous level can include but is not limited to the above example.

[0050] Referring to Figure 1 , Figure 1 is a step flowchart of a dangerous reminding method provided by an embodiment of the present application. The method can be executed by a host (HUT) in a vehicle, as shown in Figure 1 , the method can include the following steps:

[0051] Step 101, determining a target dangerous level of a road in front of the vehicle.

[0052] Exemplarily, a front-view camera is installed in the vehicle, and during driving of the vehicle, the host can obtain a front-view image of the road in front of the vehicle through the front-view camera, and then input the front-view image into a neural network model to obtain a dangerous level output by the neural network model based on the front-view image, that is, a target dangerous level. In combination with the foregoing example, the target dangerous level can be one of dangerous level 0, dangerous level 1, dangerous level 2, and dangerous level 3. Alternatively, a radar system is installed in the vehicle, and during driving of the vehicle, the host detects the road in front of the vehicle through the radar system to obtain radar data (also referred to as point cloud data), and then inputs the radar data into the neural network model to obtain a target dangerous level output by the neural network model based on the radar data. Alternatively, the neural network model can be a multi-modal neural network model, which can input images and radar data at the same time. During driving of the vehicle, the host obtains a front-view image through a front-view camera and radar data of the road in front of the vehicle through a radar, and inputs the front-view image and the radar data into the neural network model to obtain a target dangerous level output by the neural network model based on the front-view image and the radar data.

[0053] Among them, the neural network model described above can be a neural network model for danger classification obtained by pre-training, and the input data of the neural network model includes images and / or radar data. The neural network model can be installed in the host, and after the host obtains the images and / or radar data, the host can input the images and / or radar data into the neural network model, and the neural network model can determine the dangerous level of the road in front of the vehicle based on the images and / or radar data.

[0054] Exemplarily, the host can detect a target object existing in the front road through radar data and / or images to obtain a detection result, which can include data such as the distance between the target object and the vehicle, the size of the target object, and the type of the target object. The target object can include objects that can cause a safety accident, such as a pit, a puddle, a stone, an animal, a pedestrian, etc., but is not limited thereto. After obtaining the detection result, the host can further determine the target danger level of the front road based on data such as the distance between the target object and the vehicle, the size of the target object, and the type of the target object included in the detection result.

[0055] Exemplarily, during the driving of the vehicle, the host can establish a communication connection between the vehicle and the server, and the server can provide the vehicle with a real-time updated map data identifying the danger level of each road at the current time. The host can obtain the positioning information of the vehicle during the driving of the vehicle, then determine the position of the front road of the vehicle from the map data according to the positioning information, and obtain the danger level of the front road, i.e., the target danger level, from the map data.

[0056] It should be understood that the above is only an exemplary example, and the host determining the danger level of the front road of the vehicle can include but is not limited to the above example.

[0057] Step 102, determining a first reminding strategy from a plurality of reminding strategies.

[0058] Among them, the plurality of reminding strategies correspond to different off-road levels and danger levels respectively, the first reminding strategy corresponds to the target off-road level of the vehicle at present and corresponds to the target danger level.

[0059] Exemplarily, the host can pre-store a plurality of reminding strategies and a plurality of off-road levels and a plurality of danger levels in the host, after determining the danger level of the front road, the host determines the target off-road level of the vehicle at present, and then determines the reminding strategy corresponding to the target off-road level and the target danger level at the same time from the stored corresponding relationship, i.e., the first reminding strategy. As shown in Table 1, Table 1 shows the corresponding relationship between the off-road level, the danger level and the reminding strategy.

[0060] Danger level 0 Danger level 1 Danger level 2 Danger level 3 Danger level 4 Off-road level 1 No alert Light alert Medium alert Heavy alert Danger alert Off-road level 2 No alert No alert Light alert Medium alert Heavy alert Off-road level 3 No alert No alert Light alert Light alert Medium alert …… …… …… …… …… Off-road level n No alert No alert No alert Light alert Medium alert

[0061] Table 1

[0062] As shown in Table 1, in order of reminder intensity from low to high, the reminder strategies can be divided into no reminder, mild reminder, moderate reminder, severe reminder, and dangerous reminder in turn. The higher the reminder intensity corresponding to the reminder strategy is, the later it is. Generally, for the same danger level, the higher the off-road intensity is, the lower the reminder intensity of the corresponding reminder strategy is; for the same off-road level, the higher the danger level is, the higher the reminder intensity of the corresponding reminder strategy is. It should be understood that Table 1 is only an exemplary example, and the division method of the reminder strategy can include but is not limited to that shown in Table 1.

[0063] In combination with the above example, after the host determines the target danger level of the road ahead based on image and / or radar data, the first reminder strategy can be determined from Table 1 based on the target danger level and the target off-road level. For example, when it is determined that the target danger level of the road ahead is 2 and the target off-road level of the vehicle is currently 3, by looking up Table 1, it can be determined that the first reminder strategy is mild reminder.

[0064] Step 103, execute the first reminder strategy to remind the user.

[0065] In this embodiment, for different reminder strategies, corresponding reminder methods can be set respectively to make the reminder intensity of different reminder strategies different. As shown in Table 2, Table 2 shows an example of a reminder method of a reminder strategy.

[0066] Display alert Speaker alert No alert No operation No operation Light alert Mark the road condition in the display No operation Medium alert Mark the road condition in the display + alert text No operation Heavy alert Mark the road condition in the display + alert text Alert voice report Danger alert Mark the road condition in the display + alert text + screen flicker Alert voice + alarm sound

[0067] Table 2

[0068] Taking dangerous reminder as an example, the reminder method includes display screen reminder and speaker reminder, the road condition of the road ahead is marked in the display screen of the host, the text for reminding the user is displayed (the text can be enlarged and / or marked red), and the screen of the display screen is controlled to flash. At the same time, the reminder voice and alarm sound can be output through the speaker. Taking mild reminder as an example, the reminder method includes marking the road condition of the road ahead in the display screen. It should be understood that Table 2 is only an exemplary example, and the specific method of the reminder strategy can include but is not limited to the above examples.

[0069] Exemplarily, when it is determined that the first reminder strategy is no reminder, the host controls the display screen to be inactive and controls the speaker to be inactive, that is, no reminder is given to the user (generally the driver). And when it is determined that the first reminder strategy is dangerous reminder, the host marks the road condition of the road ahead in the display screen and outputs the text for reminding the user through the display screen, and controls the screen of the display screen to flash. At the same time, the host controls the speaker to output the reminder voice and alarm sound.

[0070] In the embodiments of the present application, during the driving of the vehicle, the target danger level of the road ahead of the vehicle is first determined, then the reminding strategy corresponding to the target danger level and the target off-road level of the vehicle is determined from the plurality of reminding strategies, and finally the target reminding strategy is executed to remind the user. In this method, when there is danger on the road, the danger reminding can be carried out in a targeted manner based on the danger level of the road and the off-road level of the vehicle. While the road with different danger levels is reminded in a targeted manner, for the road with the same danger level, the reminding strategies of the vehicles with different off-road levels are different, and the vehicles with different off-road levels can be reminded in a differentiated manner. Therefore, the reminding strategy can be further refined, the targeting and accuracy of the danger reminding can be improved, and thus the interference of the danger reminding on the driver can be reduced, and the safety of the vehicle can be improved.

[0071] Optionally, the step of determining the target danger level of the road ahead of the vehicle can include:

[0072] determining whether the visibility of the road ahead meets the standard;

[0073] if not, determining the target danger level of the road ahead.

[0074] In the embodiments, before determining the first reminding strategy, it can be determined whether the visibility of the road ahead of the vehicle meets the standard. In the case that the visibility of the road ahead does not meet the standard, the target danger level of the road ahead and the target off-road level of the vehicle are further determined, and then the first reminding strategy corresponding to the target danger level and the target off-road level is determined from the plurality of reminding strategies.

[0075] In an embodiment, the visibility sensor is integrated in the vehicle. During the driving of the vehicle, the host can detect the visibility ahead of the vehicle through the visibility sensor, and then determine whether the detected visibility is greater than a preset reference visibility. When the detected visibility is greater than the reference visibility, it can be determined that the visibility of the road ahead is high, the visibility of the road ahead meets the standard, and the user can accurately determine whether there is danger ahead of the vehicle through the eyes, without the need for the host to perform danger reminding. At this time, the host does not execute the steps 101-103.

[0076] On the contrary, when the detected visibility is less than or equal to the reference visibility, it can be determined that the visibility of the road ahead is low, the visibility of the road ahead does not meet the standard, and the user cannot accurately determine whether there is danger ahead of the vehicle through the eyes. At this time, the host needs to perform danger reminding. Further, the host determines the target danger level of the road ahead of the vehicle to execute the steps 101-103, and performs danger reminding to the user in the vehicle when there is danger ahead of the vehicle.

[0077] The host can also determine the visibility of the road in front of the vehicle in other ways. For example, the host can send a data request to a meteorological data server in real time, and the data request includes the positioning information of the vehicle. After receiving the data request, the meteorological data server determines the visibility of the location where the vehicle is located according to the positioning information in the data request, and then sends the visibility to the host. After the host receives the visibility sent by the meteorological server, if the visibility is less than or equal to the reference visibility, the host determines that the visibility of the road in front of the vehicle is not up to standard, and executes steps 101-103.

[0078] For another example, the host can obtain a front view image of the vehicle by using a front-view camera, and analyze the features in the front view image such as the concentration of fog and the scattering of light by using image processing and deep learning algorithms, so as to determine the visibility of the road in front of the vehicle. Similarly, after the host determines the visibility of the road in front, if the visibility is less than or equal to the reference visibility, the host determines that the visibility of the road in front of the vehicle is not up to standard, and executes steps 101-103.

[0079] It should be understood that the above is only an example, and the method of obtaining the visibility of the road in front can include but is not limited to the above examples.

[0080] In the embodiments of the present application, in the case where it is determined that the visibility of the road in front of the vehicle is not up to standard, the target danger level of the road in front is determined, and the first reminding strategy corresponding to the target danger level and the target off-road level is executed. When the visibility in front of the vehicle is poor, the danger reminding can be performed, and when the visibility in front of the vehicle is good, the danger reminding is not performed, thereby reducing unnecessary reminders and reducing the interference that the danger reminding may cause to the user, so as to improve the safety of the vehicle.

[0081] Optionally, determining whether the visibility of the road in front is up to standard comprises:

[0082] Obtaining a visible light image of the road in front;

[0083] In the case where the definition of the visible light image is less than a preset definition, it is determined that the visibility of the road in front is not up to standard.

[0084] In the embodiments, in the process of determining whether the visibility in front of the vehicle is up to standard, the visible light image of the road in front can be obtained by the camera integrated in the vehicle, and whether the visibility in front of the vehicle is up to standard is determined based on the definition of the visible light image.

[0085] In an embodiment, an around view monitor (AVM) can be integrated in the vehicle. During driving of the vehicle, the host can acquire a visible light image of the surroundings of the vehicle through a camera in the AVM, and then analyze the definition of the visible light image to determine the definition of the visible light image. After determining the definition of the visible light image, it can be determined whether the definition of the visible light image is less than a preset definition. If the definition of the visible light image is less than the preset definition, it can be determined that the visibility of the road in front of the vehicle is low, the visibility of the road in front of the vehicle does not meet the standard, and the user cannot accurately determine whether there is a danger in front of the vehicle through the eyes. On the contrary, if it is determined that the definition of the visible light image is greater than or equal to the preset definition, it can be determined that the visibility of the road in front of the vehicle is high, the visibility of the road in front of the vehicle meets the standard, and the user can accurately determine whether there is a danger in front of the vehicle through the eyes.

[0086] In the embodiment, the visible light image can also be acquired through a front camera integrated in the vehicle or other cameras in the vehicle, and the acquisition method of the visible light image is not limited in the embodiment.

[0087] In the embodiment, the definition of the visible light image of the road in front of the vehicle is used to determine whether the visibility of the road in front of the vehicle meets the standard. The visibility of the road in front of the vehicle can be directly determined through the camera integrated in the vehicle, without the need to integrate a visibility sensor in the vehicle for the parameter of the visibility. The hardware cost of the vehicle can be avoided, and the power consumption of the vehicle can be reduced without acquiring the visibility from the server according to the positioning information of the vehicle.

[0088] Optionally, the target danger level of the road in front of the vehicle is determined, including:

[0089] When the visibility of the road in front of the vehicle is less than a preset visibility threshold, the target danger level is determined according to the thermal imaging image and the radar data of the road in front of the vehicle.

[0090] When the visibility of the road in front of the vehicle is greater than or equal to the visibility threshold, the target danger level is determined according to the thermal imaging image or the radar data.

[0091] In the embodiment, the visibility threshold is less than the reference visibility.

[0092] In an embodiment, the host can select a data source according to the visibility of the road ahead, and determine the target danger level of the road ahead according to the data source matching the visibility of the road ahead. In combination with the above example, the vehicle is integrated with a far-infrared system and a radar system. After obtaining the visibility of the road ahead of the vehicle, if it is determined that the visibility is less than the reference visibility, the host can further determine whether the visibility ahead of the vehicle is less than a preset visibility threshold. If it is less than the preset visibility threshold, the host can obtain a thermal imaging image of the road ahead through the far-infrared system, and obtain radar data through the radar system, and then input the thermal imaging image and the radar data into the multi-modal neural network model to obtain the target danger level output by the multi-modal neural network model based on the thermal imaging image and the radar data.

[0093] In addition, after obtaining the visibility of the road ahead of the vehicle, if it is determined that the visibility is less than the reference visibility, when the host determines that the visibility ahead of the vehicle is greater than or equal to the preset visibility threshold, the host can obtain a thermal imaging image of the road ahead through the far-infrared system, and then input the thermal imaging image into the neural network model to obtain the target danger level output by the neural network model based on the thermal imaging image. Alternatively, when the host determines that the visibility ahead of the vehicle is greater than or equal to the preset visibility threshold, the host can obtain radar data of the road ahead through the radar system, and then input the radar data into the neural network model to obtain the target danger level output by the neural network model based on the radar data.

[0094] In another embodiment, during the driving of the vehicle, the host first determines whether the visibility ahead of the vehicle meets the standard. If the visibility does not meet the standard, the host determines the target danger level according to the thermal imaging image and / or the radar data of the road ahead, and then determines a first reminding strategy corresponding to the target danger level and the target off-road level, and executes the first reminding strategy. If the visibility meets the standard, the host does not execute the above steps, i.e., does not remind the user of the danger.

[0095] In the embodiments of the present application, one or both of the thermal imaging image and the radar data can be selected to determine the target danger level of the road ahead according to the visibility of the road ahead. In this way, when the visibility of the road ahead is good, only one of the thermal imaging image and the radar data is selected to determine the danger level, so as to avoid using both the radar data and the thermal imaging image at the same time, thereby reducing the power consumption of the vehicle during the danger reminding process. When the visibility of the road ahead is poor, the thermal imaging image and the radar data are selected to determine the danger level, and the danger level can be determined in combination with the thermal imaging image and the radar data, so as to accurately predict the danger level of the road when the visibility is poor, thereby reminding the user of the danger in a timely manner when there is a danger ahead of the vehicle, improving the reliability of the danger reminding, and further improving the safety of the vehicle.

[0096] Optionally, the method can further include:

[0097] in the case that the visibility of the road ahead meets the standard, determining whether there is a movable target in the road ahead;

[0098] if there is a movable target, outputting prompt information to prompt the user.

[0099] The movable target can be a pedestrian, a bicycle, an animal, or any object that can move and may collide with the vehicle.

[0100] In this embodiment, in the case that the visibility of the road ahead does not meet the standard, the target danger level of the road ahead is determined, and a first prompting strategy is determined from a plurality of prompting strategies, and the first prompting strategy is executed. In the case that the visibility of the road ahead meets the standard, the target danger level of the road ahead is not determined, and the first prompting strategy is not determined and executed. At this time, it is determined whether there is a movable target in the road ahead, and when it is determined that there is a movable target in front of the vehicle, prompt information is outputted to prompt the user.

[0101] In combination with the above example, in the case that the visibility of the road ahead meets the standard, the user can determine whether there is a danger in the road ahead through the eyes, and the vehicle does not need to prompt the danger. At this time, the user needs to pay attention to the movable target in front of the vehicle to prevent the vehicle from colliding with the movable target.

[0102] In one embodiment, in the case that it is determined that the visibility of the road ahead meets the standard, the host can obtain a thermal imaging image of the road ahead through a far-infrared system, and then input the thermal imaging image into a neural network model for target detection, determine whether there is a movable target in the road ahead through the neural network model, and if there is a movable target, output prompt information.

[0103] In another embodiment, in the case that it is determined that the visibility of the road ahead meets the standard, the host can obtain radar data of the road ahead through a radar system, and then input the radar data into a neural network model for target detection, determine whether there is a movable target in the road ahead through the neural network model, and if there is a movable target, output prompt information.

[0104] In another embodiment, in the case that it is determined that the visibility of the road ahead meets the standard, the host can obtain a front view image of the road ahead through a front view camera, and then input the front view image into a neural network model for target detection, determine whether there is a movable target in the road ahead through the neural network model, and if there is a movable target, output prompt information.

[0105] In actual application, the energy consumption of the far-infrared system is usually higher than that of the common camera. When detecting whether there is a movable target in front of the vehicle, the image captured by the common camera such as the forward-looking camera can be used to determine whether there is a movable target in front of the vehicle, so as to reduce the power consumption of the vehicle.

[0106] The prompt information can be voice prompt output by a loudspeaker, or text prompt or pattern prompt output by a display screen. It should be understood that the prompt strength of the prompt information is lower than that of the reminding strategy. When the prompt information is output, the user can pay attention to the prompt information or not. When the reminding strategy is executed, the user needs to pay attention to the reminding strategy.

[0107] In the embodiment of the present application, if a movable target is detected on the front road when the visibility of the front road meets the standard, a prompt information is output to prompt the user. The output of the prompt information can improve the attention of the driver in the vehicle to the movable target in front of the vehicle, reduce the risk of collision between the vehicle and the movable target, and thus improve the safety of the vehicle.

[0108] Optionally, if there is a movable target, a prompt information is output to prompt the user, comprising:

[0109] If there is a movable target, the distance between the movable target and the vehicle is obtained.

[0110] If the distance is less than or equal to the preset distance, a prompt information is output to prompt the user.

[0111] In an embodiment, while detecting whether there is a movable target in front of the vehicle, the host can determine the distance between the movable target and the vehicle. For example, after obtaining the radar data, the host inputs the radar data into a neural network model for target detection, determines whether there is a movable target on the front road through the neural network model, and determines the distance between the movable target and the vehicle. If it is determined that there is a movable target in front of the vehicle, and the distance between the movable target and the vehicle is less than a preset distance, the host can output a prompt information to prompt the user.

[0112] In actual application, only when the distance between the movable target and the vehicle is less than the preset distance, the collision between the movable target and the vehicle is possible. When the distance between the movable target and the vehicle is greater than or equal to the preset distance, the probability of collision between the movable target and the vehicle is extremely low.

[0113] In the embodiments of the present application, when a movable target exists in front of the vehicle and the distance between the movable target and the vehicle is small, the probability of collision with the vehicle is high, the prompt information is output to prompt the user, and when the distance between the movable target and the vehicle is large, the probability of collision with the vehicle is low, the prompt information is not output, unnecessary prompts can be reduced, power consumption can be reduced, the interference of the prompt information on the user can be reduced, and thus the safety of the vehicle can be improved.

[0114] Optionally, the method can further include:

[0115] determining a target off-road level matching the road ahead from a plurality of off-road levels reachable by the vehicle;

[0116] setting the off-road level of the vehicle to the target off-road level when the off-road level currently set for the vehicle is lower than the target off-road level.

[0117] In the embodiments, before determining the first reminding strategy, the target off-road level matching the road ahead is first determined from a plurality of off-road levels reachable by the vehicle, and then the off-road level of the vehicle is set to the target off-road level when the off-road level currently set for the vehicle is lower than the target off-road level, so that the off-road level of the vehicle can be adjusted. After the off-road level of the vehicle is adjusted, the first reminding strategy is determined from a plurality of reminding strategies, and the first reminding strategy is executed.

[0118] The plurality of off-road levels reachable by the vehicle refer to off-road levels to which the vehicle can be configured. For example, the off-road levels are divided into off-road level 1, off-road level 2, off-road level 3 and off-road level 4, and when the vehicle is provided with related configurations of each off-road level, the off-road level of the vehicle can be set to one of off-road level 1, off-road level 2, off-road level 3 and off-road level 4. Moreover, when the off-road level is set to one of off-road level 1, off-road level 2, off-road level 3 and off-road level 4, the off-road level of the vehicle can be adjusted to another according to requirements.

[0119] In combination with the foregoing examples, off-road level 4 is professional off-road, and the vehicle functions corresponding to professional off-road include the crawl mode, the steep slope slow descent function, the uphill assist function, the electronic limited slip function and the part-time four-wheel drive function, etc. When the vehicle is provided with the crawl mode, the steep slope slow descent function, the uphill assist function, the electronic limited slip function and the part-time four-wheel drive function and other vehicle functions related to the professional off-road level, and these functions are in an available state, the vehicle is in the professional off-road level, and when these functions are disabled, the vehicle is in one of off-road level 1, off-road level 2 and off-road level 3.

[0120] When the vehicle is in one of the off-road levels 1, 2, and 3, and the vehicle is configured with the functions related to the off-road level 4, such as the crawling mode, the steep slope slow descent function, the uphill assist function, the electronic limited slip function, and the part-time four-wheel drive function, the functions related to the off-road level 4 can be controlled to be in an available state, so that the vehicle is switched from the other off-road levels to the off-road level 4. It can be understood that different off-road levels are applicable to different environments, and the higher the off-road level, the worse the environment applicable to the vehicle, and the more difficult the driving.

[0121] Exemplarily, the corresponding target off-road level can be determined based on the environment type of the external environment in which the front road is located. For example, a correspondence relationship between the off-road levels and the corresponding environment types can be pre-set and stored in the host. During the driving of the vehicle, the host can first acquire the positioning information of the vehicle, and can also acquire the map data, in which the environment types of different environments can be marked, and the environment types can include but are not limited to desert, mountainous area, marsh, grassland, city, and countryside, etc. After the positioning information and the map data are acquired, the host can determine the environment type of the current location of the vehicle from the map data according to the positioning information.

[0122] After the environment type is acquired, the host can determine the off-road level corresponding to the environment type of the external environment in which the front road is located from the multiple off-road levels available to the vehicle, i.e., the target off-road level. For example, it can be pre-set that the environment types corresponding to the off-road level 4 include sand, mountainous area, and marsh, the environment types corresponding to the off-road level 1 include city and countryside, and the environment types corresponding to the off-road level 3 include grassland. When it is determined that the environment type of the external environment in which the front road is located is one of sand, mountainous area, and marsh, the host can determine the target off-road level as the off-road level 4 based on the pre-stored correspondence relationship. Similarly, when it is determined that the environment type is one of city and countryside, the host can determine the target off-road level as the off-road level 1 based on the pre-stored correspondence relationship.

[0123] After the target off-road level is determined, the host detects the current off-road level of the vehicle, and if the target off-road level is higher than the current off-road level of the vehicle, the off-road level of the vehicle is re-set, and the off-road level of the vehicle is set to the target off-road level. For example, when the current off-road level configured for the vehicle is 1, and it is determined that the target off-road level is the off-road level 4, the off-road level of the vehicle can be set to the off-road level 4, i.e., the off-road level of the vehicle is adjusted from the off-road level 1 to the off-road level 4. When the off-road level of the vehicle is set to the off-road level 4, the crawling function, the steep slope slow descent function, the uphill assist function, the electronic limited slip function, and the part-time four-wheel drive function of the vehicle can all be controlled to be in an available state.

[0124] In the embodiments of the present application, the target off-road level matching the road ahead is determined from a plurality of off-road levels that the vehicle can reach, and when the off-road level currently set for the vehicle is lower than the target off-road level, the off-road level of the vehicle is set to the target off-road level, so that the off-road level of the vehicle can match the road ahead, thereby improving the adaptability of the vehicle to the road ahead, and further improving the safety of the vehicle when driving on the road ahead.

[0125] Optionally, the first reminding strategy is determined from a plurality of reminding strategies, comprising:

[0126] When the off-road level currently set for the vehicle is higher than the target off-road level, a first reminding strategy corresponding to the off-road level currently set for the vehicle and corresponding to the target danger level is determined from a plurality of reminding strategies.

[0127] In some cases, during driving of the vehicle, the user can manually adjust the off-road level of the vehicle, so that the off-road level set for the vehicle can be higher than the target off-road level matching the road ahead. When the off-road level currently set for the vehicle is higher than the target off-road level, it indicates that the user can need the vehicle to have better off-road performance when driving on the road ahead.

[0128] In an embodiment, after determining the target off-road level of the road ahead, when it is determined that the off-road level currently set for the vehicle is higher than the target off-road level, a first reminding strategy corresponding to the off-road level currently set for the vehicle and corresponding to the target danger level is determined from a plurality of reminding strategies. For example, when it is determined that the target off-road level is off-road level 3, and the off-road level currently set for the vehicle is 4, it can be determined that the off-road level currently set for the vehicle is higher than the target off-road level. At this time, a first reminding strategy corresponding to off-road level 4 (i.e. the off-road level currently set for the vehicle) and corresponding to the target danger level can be determined. In this way, the first reminding strategy can correspond to the actual off-road level of the vehicle.

[0129] In the embodiments of the present application, when the off-road level currently set for the vehicle is higher than the target off-road level matching the road ahead, a first reminding strategy corresponding to the off-road level currently set for the vehicle and corresponding to the target danger level is determined from a plurality of reminding strategies, so that the first reminding strategy can correspond to the actual off-road level of the vehicle, thereby making the danger reminding strategy correspond to the actual off-road performance of the vehicle.

[0130] Optionally, the step of executing the first reminding strategy can comprise:

[0131] When the driving speed of the vehicle is greater than a preset speed threshold, the first reminding strategy is executed;

[0132] After the first reminding strategy is executed, if it is determined that the decrease amplitude of the driving speed of the vehicle is less than the preset amplitude threshold, a second reminding strategy is executed; wherein the second reminding strategy is a reminding strategy corresponding to a higher dangerous level than the first reminding strategy among the plurality of reminding strategies.

[0133] In an embodiment, when the first reminding strategy is executed, the driving speed of the vehicle can be determined, and when the driving speed is greater than a preset speed threshold, the first reminding strategy is executed, and when the driving speed is less than or equal to the preset speed threshold, the first reminding strategy is not executed. The preset speed threshold can be a large value, and when the driving speed of the vehicle is greater than the preset speed threshold, the risk during the driving of the vehicle is greater, and when the driving speed is less than or equal to the speed threshold, the risk during the driving of the vehicle is smaller, and no reminding is needed.

[0134] Before the first reminding strategy is executed, the driving speed of the vehicle is detected to obtain a first driving speed, and after the first reminding strategy is executed, timing can be started, and when the timing duration reaches a preset duration (the preset duration is a shorter duration), the driving speed of the vehicle is detected to obtain a second driving speed, the difference between the first driving speed and the second driving speed is calculated to obtain the decrease amplitude of the driving speed, and when the decrease amplitude is greater than or equal to the preset amplitude threshold, it is determined that the first reminding strategy works. When the driving speed is less than the preset speed threshold, it is determined that the first reminding strategy does not work, and at this time, a second reminding strategy higher than the first reminding strategy can be determined from the plurality of reminding strategies, and then the second reminding strategy is executed. When the first reminding strategy is the highest reminding strategy among the plurality of reminding strategies, the first reminding strategy can be determined as the second reminding strategy, and the second reminding strategy is executed again.

[0135] Optionally, the host can execute the second reminding strategy when the driving speed of the vehicle is greater than the preset speed threshold and the first reminding strategy is a higher reminding strategy (such as the moderate reminding and the dangerous reminding in Table 2), and the decrease amplitude of the driving speed of the vehicle is less than the preset amplitude threshold after the first reminding strategy is executed.

[0136] In the embodiments of the present application, when the driving speed of the vehicle is greater than the preset speed threshold, the first reminding strategy is executed, and when the driving speed of the vehicle is low after the first reminding strategy is executed, a higher second reminding strategy is executed, which can improve the reminding intensity in time when the vehicle is driving at a high speed, thereby improving the safety of the vehicle.

[0137] Referring to Figure 2 , Figure 2 is a flowchart of a dangerous reminding method provided by the embodiments of the present application.

[0138] As Figure 2 shown, the method can include:

[0139] Step 201, acquiring a visible light image.

[0140] Step 202, determining whether the definition of the visible light image is less than a preset definition.

[0141] Exemplarily, during the driving of the vehicle, a front view image (i.e., a visible light image) can be acquired by a front view camera, and then the definition of the visible light image is determined to judge whether the definition of the visible light image is less than a preset definition. In the case that the definition is less than the preset definition, it is determined that the visibility of the front road is poor and does not meet the standard, and step 203 is executed. On the contrary, in the case that the definition is greater than or equal to the preset definition, it is determined that the visibility of the front road is good and meets the standard, and the process is ended. It should be understood that the method of determining whether the visibility of the front road meets the standard can also use other ways in the foregoing examples, and the present embodiment does not limit this.

[0142] Step 203, acquiring a thermal imaging image and / or radar data.

[0143] Step 204, determining a target danger level of the front road according to the thermal imaging image and / or the radar data.

[0144] Exemplarily, when the visibility of the front road is poor, a thermal imaging image can be acquired by a far-infrared system, and radar data can be acquired by a radar system. The thermal imaging image and the radar data are input into a multi-modal neural network model to obtain a target danger level determined by the neural network model based on the thermal imaging image and the radar data. The specific implementation manners of step 203 and step 204 can be referred to the foregoing examples, and the present embodiment does not make redundant description here.

[0145] Step 205, determining a first reminding strategy corresponding to the target danger level and corresponding to a target off-road level.

[0146] Step 206, executing the first reminding strategy.

[0147] Exemplarily, after the target danger level is determined, the target off-road level of the vehicle can be determined, and then the first reminding strategy corresponding to the target danger level and corresponding to the target off-road level is found from Table 2, and then the first reminding strategy is executed to remind the user. The specific process of determining the first reminding strategy corresponding to the target danger level and corresponding to the target off-road level, and executing the first reminding strategy can be referred to the foregoing examples, and the present embodiment does not make redundant description here.

[0148] The above describes the danger reminding method provided by the embodiments of the present application in detail; the following will combine Figures 1-2 and Figure 3 and Figure 4The device embodiments of the present application are described in detail. It should be understood that the device in the embodiments of the present application can perform the various methods of the foregoing embodiments of the present application, that is, the specific working processes of the following various products can refer to the corresponding processes in the foregoing method embodiments.

[0149] Referring to Figure 3 , Figure 3 is a structural schematic diagram of a danger reminding device provided by the embodiments of the present application.

[0150] As Figure 3 indicated, the danger reminding device 300 can include:

[0151] A determination module 301 is configured to determine a target danger level of a road ahead of a vehicle, and determine a first reminding strategy from a plurality of reminding strategies; wherein the plurality of reminding strategies correspond to different off-road levels and danger levels respectively, and the first reminding strategy corresponds to a target off-road level of the vehicle currently and corresponds to the target danger level.

[0152] An execution module 302 is configured to execute the first reminding strategy to remind a user.

[0153] Optionally, the determination module 301 is specifically configured to determine whether the visibility of the road ahead meets a standard; and if not, determine the target danger level of the road ahead.

[0154] Optionally, the determination module 301 is specifically configured to acquire a visible light image of the road ahead; and if the definition of the visible light image is less than a preset definition, determine that the visibility of the road ahead does not meet the standard.

[0155] Optionally, the determination module 301 is specifically configured to determine the target danger level according to a thermal imaging image and radar data of the road ahead when the visibility of the road ahead is less than a preset visibility threshold; and determine the target danger level according to the thermal imaging image or the radar data when the visibility of the road ahead is greater than or equal to the visibility threshold.

[0156] Optionally, the danger reminding device 300 further includes an output module configured to determine whether there is a movable target object on the road ahead when the visibility of the road ahead meets the standard; and if there is the movable target object, output prompt information to prompt the user.

[0157] Optionally, the output module is specifically configured to acquire a distance between the movable target object and the vehicle if there is the movable target object; and output the prompt information to prompt the user when the distance is less than or equal to a preset distance.

[0158] Optionally, the determination module 301 is further configured to determine the target off-road level that matches the road ahead from a plurality of off-road levels attainable by the vehicle; and when the off-road level currently set for the vehicle is lower than the target off-road level, the off-road level of the vehicle is set to the target off-road level.

[0159] Optionally, the determination module 301 is specifically used to determine the first reminder strategy corresponding to the off-road level currently set for the vehicle and the target danger level from the multiple reminder strategies when the off-road level currently set for the vehicle is higher than the target off-road level.

[0160] Optionally, the execution module 302 is specifically used to execute the first reminder strategy when the vehicle's driving speed is greater than a preset speed threshold; after executing the first reminder strategy, if it is determined that the decrease in the vehicle's driving speed is less than a preset amplitude threshold, execute the second reminder strategy; wherein, the second reminder strategy is a reminder strategy among the multiple reminder strategies whose corresponding danger level is higher than that of the first reminder strategy.

[0161] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of a device provided in an embodiment of the present application. Figure 4 As shown, the device 400 includes: a memory 401 and a processor 402, wherein the memory 401 stores an executable program code 4011, and the processor 402 is used to call and execute the executable program code 4011 to perform a danger reminder method.

[0162] In addition, an embodiment of the present application also protects a danger reminder device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a danger reminder method provided by an embodiment of the present application.

[0163] In this embodiment, the device can be divided into functional modules based on the above-described method examples. For example, each functional module can be mapped to a specific functional module, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0164] In the case of dividing each functional module into corresponding functional modules, the device may further include a determination module, a replacement module, a control module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0165] It should be understood that the device provided by the embodiment is used to execute the above-mentioned danger reminding method, and thus the same effects as the above-mentioned implementation method can be achieved.

[0166] In the case of using the integrated unit, the device can include a determination module and a control module. When the device is applied to the equipment, the processing module can be used to control and manage the action of the equipment. The storage module can be used to support the equipment to execute the related program code and the like.

[0167] The processing module can be a processor or a vehicle body setting module, which can realize or execute various exemplary logical blocks, modules and circuits shown in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as including one or more microprocessor combinations, a combination of digital signal processing (DSP) and microprocessor, and the like, and the storage module can be a memory.

[0168] The embodiment also provides a readable storage medium, which stores program code, and when the program code runs on the electronic device, the electronic device executes the above-mentioned related method steps to realize the danger reminding method provided by the above-mentioned embodiment.

[0169] The embodiment also provides a program product, which, when running on an electronic device, causes the electronic device to execute the above-mentioned related steps to realize the danger reminding method provided by the above-mentioned embodiment.

[0170] The device, readable storage medium, program product or chip provided by the embodiment are used to execute the corresponding method provided above, and thus the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding method provided above, which will not be described here.

[0171] Through the description of the above embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the above-mentioned division of functional modules is taken as an example for illustration, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0172] In the embodiments of the present disclosure, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, and the division of the modules or units is merely a logical function division. In actual implementation, another division manner can be adopted, for example, a plurality of units or components can be combined or integrated into another apparatus, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or in other forms.

[0173] The above merely describes specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present disclosure, which should be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.​

Claims

1. A danger reminder method, characterized in that: The method comprises: determining a target hazard level of the road ahead of the vehicle; Determining a first reminder strategy from a plurality of reminder strategies; wherein the plurality of reminder strategies correspond to different off-road levels and danger levels, respectively, and the first reminder strategy corresponds to a current target off-road level of the vehicle and to the target danger level; The first reminder strategy is executed to remind the user.

2. The method according to claim 1, wherein Determining the target danger level of the road ahead of the vehicle includes: determining whether visibility of the road ahead meets standards; If the target is not met, the target danger level of the road ahead is determined.

3. The method according to claim 2, wherein Determining whether the visibility of the road ahead meets the standard includes: Acquire a visible light image of the road ahead; When the clarity of the visible light image is less than a preset clarity, it is determined that the visibility of the road ahead does not meet the standard.

4. The method according to claim 2, wherein Determining the target danger level of the road ahead includes: When the visibility of the road ahead is less than a preset visibility threshold, determining the target danger level based on the thermal imaging image and radar data of the road ahead; When the visibility of the road ahead is greater than or equal to the visibility threshold, the target danger level is determined according to the thermal imaging image or the radar data.

5. The method according to claim 2, wherein The method further comprises: When the visibility of the road ahead meets the standard, determining whether there is a movable target object on the road ahead; If the movable target exists, prompt information is output to prompt the user.

6. The method according to claim 5, wherein If the movable target object exists, outputting prompt information to prompt the user includes: If the movable target object exists, obtaining the distance between the movable target object and the vehicle; When the distance is less than or equal to the preset distance, the prompt information is output to prompt the user.

7. The method according to claim 1, wherein The method further comprises: determining the target off-road level that matches the road ahead from a plurality of off-road levels attainable by the vehicle; When the off-road level currently set for the vehicle is lower than the target off-road level, the off-road level of the vehicle is set to the target off-road level.

8. The method according to claim 7, wherein The determining of the first reminder strategy from the plurality of reminder strategies includes: When the off-road level currently set for the vehicle is higher than the target off-road level, the first reminder strategy corresponding to the off-road level currently set for the vehicle and the target danger level is determined from the multiple reminder strategies.

9. A danger warning device, characterized in that: The device comprises: a determination module, configured to determine a target hazard level of a road ahead of the vehicle, and to determine a first reminder strategy from a plurality of reminder strategies, wherein the plurality of reminder strategies correspond to different off-road levels and hazard levels, respectively, and the first reminder strategy corresponds to the vehicle's current target off-road level and the target hazard level; An execution module is used to execute the first reminder strategy to remind the user.

10. A vehicle, characterized in that: The vehicle comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 8.

Images