Road icing prediction method, device, equipment and medium

Abstract

The invention provides a road icing prediction method and device, equipment and a medium. The road icing prediction method comprises the steps that weather information of a target time period of an area where a target road is located is acquired; the target time period comprises a time period from a target historical moment to a prediction moment; determining road icing prediction information of the target road at the prediction moment based on the weather information; and predicting the icing probability of the target road at the prediction time based on the road icing prediction information. Therefore, the road icing probability at the future moment can be accurately predicted.

Description

Technical Field

[0001] The present application relates to the technical field of road icing prediction, and particularly relates to a road icing prediction method, device, equipment and medium. Background Art

[0002] Road icing refers to the icing phenomenon that occurs when precipitation hits the ground with a temperature below 0°C. Road icing seriously threatens traffic safety and is likely to cause situations such as reducing vehicle adhesion and pedestrians falling. In order to effectively cope with the hazards brought by road icing, an accurate road icing prediction method is urgently needed so that the traffic management department can take necessary measures in advance to prevent the occurrence of road icing or reduce its impact, which is of great significance for ensuring traffic safety and reducing traffic accidents. Summary of the Invention

[0003] In view of this, the present application provides a road icing prediction method, device, equipment and computer-readable storage medium, which can accurately predict the road icing probability at a future moment.

[0004] According to the first aspect of the present application, a road icing prediction method is provided. The road icing prediction method includes: obtaining weather information of a target time period in the area where the target road is located; the target time period includes the time period between a target historical moment and a prediction moment; based on the weather information, determining road icing prediction information of the target road at the prediction moment; and predicting the icing probability of the target road at the prediction moment based on the road icing prediction information.

[0005] According to the second aspect of the present application, a road icing prediction device is provided. The road icing prediction device includes: a weather information obtaining module, configured to obtain weather information of a target time period in the area where the target road is located; the target time period includes the time period between a target historical moment and a prediction moment; a prediction information determining module, configured to determine road icing prediction information of the target road at the prediction moment based on the weather information; and a probability prediction module, configured to predict the icing probability of the target road at the prediction moment based on the road icing prediction information.

[0006] According to the third aspect of the present application, an electronic device is provided, including a processor, a memory, and a program stored on the memory and capable of running on the processor. When the program is executed by the processor, the steps of any one of the road icing prediction methods provided in the embodiments of the present application are implemented.

[0007] According to the fourth aspect of the present application, a computer-readable storage medium is provided. Instructions are stored on the computer-readable storage medium. When the instructions are executed by a processor, the steps of any one of the road icing prediction methods provided in the embodiments of the present application are implemented.

[0008] In summary, the road icing prediction method, device, electronic device, and computer-readable storage medium provided by the present application have the following beneficial effects: By obtaining the weather information of the target time period in the area where the target road is located, the weather data affecting road icing can be captured, and by analyzing and processing the weather information, the road icing prediction information of the target road at the prediction moment can be determined, and further the information affecting road icing can be extracted, providing strong support for subsequent icing probability prediction. Moreover, based on the road icing prediction information, the icing probability of the target road at the prediction moment can be comprehensively and accurately predicted, thereby improving the prediction accuracy and facilitating providing favorable support for subsequent early warning decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 The flowchart showing a road icing prediction method provided by an embodiment of the present application;

[0011] Figure 2 The structural diagram showing a road icing prediction model provided by an embodiment of the present application;

[0012] Figure 3 The structural diagram showing a road icing prediction device provided by an embodiment of the present application;

[0013] Figure 4 The structural diagram showing an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] In order to make the above and other features and advantages of the present application clearer, the present application will be further described below with reference to the drawings. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are merely exemplary, not restrictive.

[0015] In the following description, many specific details are set forth to provide a thorough understanding of the present application. However, it is obvious to those skilled in the art that the present application does not need to adopt specific details to be practiced. In other cases, well-known steps or operations are not described in detail to avoid obscuring the present application.

[0016] On the one hand, an embodiment of the present application provides a road icing prediction method, which can be applied to a road icing prediction device. Figure 1The flowchart of a road icing prediction method provided by an embodiment of the present application is shown, as Figure 1 shown. The road icing prediction method may include the following steps.

[0017] S11, Obtain the weather information of the target time period in the area where the target road is located.

[0018] The target time period involved in an embodiment of the present application includes the time period between the target historical moment and the prediction moment. The target historical moment can be a moment before the prediction moment, such as 48 hours before the prediction moment, etc. The weather information includes the predicted weather information at the prediction moment and the historical weather information at the target historical moment. The weather information can be obtained from a weather data service platform. The area where the target road is located can refer to the geographical scope where the target road is located.

[0019] In an embodiment of the present application, the road icing prediction device determines the geographical information of the target road, and quickly determines the area where the target road is located through an electronic map, so as to obtain the weather information of the target time period within the corresponding geographical scope from the weather data service platform according to the area where the target road is located.

[0020] S12, Based on the weather information, determine the road icing prediction information of the target road at the prediction moment.

[0021] The road icing prediction information involved in an embodiment of the present application includes at least one of the following: road surface temperature, air temperature, and the amount of water remaining on the road surface. Among them, the amount of water remaining on the road surface can be determined according to the precipitation. The road surface temperature can be determined according to the air temperature, or obtained by a road surface temperature sensor.

[0022] It should be noted that compared with the precipitation, using the amount of water remaining on the road surface as the road icing prediction information can more accurately predict the road icing probability.

[0023] In an embodiment of the present application, the road icing prediction device processes the weather information of the area where the target road is located based on a preset weather information processing model to obtain the road icing prediction information of the target road at the prediction moment. Among them, the weather information processing model can be composed of a variety of weather parameter processing models, and can include but is not limited to a road surface temperature processing model and a precipitation processing model, etc. The precipitation processing model is used to obtain the amount of water remaining on the road surface at the prediction moment based on the precipitation.

[0024] S13, Based on the road icing prediction information, predict the icing probability of the target road at the prediction moment.

[0025] In an embodiment of the present application, the road icing prediction device may process the road icing prediction information of the target road by using a road icing prediction model to obtain the icing probability of the predicted target road at the prediction moment. Among them, the road icing prediction model may be constructed based on a road icing prediction algorithm.

[0026] In the above embodiments, the weather information of the target time period in the area where the target road is located can be obtained, so that the weather data affecting road icing can be captured, and by analyzing and processing the weather information, the road icing prediction information of the target road at the prediction moment can be determined, and further the information affecting road icing can be extracted, providing strong support for subsequent icing probability prediction. And based on the road icing prediction information, the icing probability of the target road at the prediction moment can be comprehensively and accurately predicted, thereby improving the prediction accuracy and facilitating providing favorable support for subsequent early warning decisions.

[0027] In some embodiments, S13, predicting the icing probability of the target road based on the road icing prediction information includes: inputting the road icing prediction information into the road icing prediction model, and through the information conversion module of the road icing prediction model, obtaining a first probability parameter, a second probability parameter, and a third probability parameter corresponding to the road surface temperature, the air temperature, and the residual water volume on the road surface respectively; through the probability prediction module of the road icing prediction model, based on the first probability parameter, the second probability parameter, and the third probability parameter, obtaining the icing probability of the target road at the prediction moment.

[0028] Figure 2 The structural schematic diagram of a road icing prediction model provided by an embodiment of the present application is shown, as Figure 2 shown, the road icing prediction model 20 may include an information conversion module 21 and a probability prediction module 22. The information conversion module 21 is used to calculate the influence probability of the road icing prediction information on road icing. Each parameter in the road icing prediction information corresponds to an influence probability. For example, when the road icing prediction information includes the road surface temperature, the air temperature, and the residual water volume on the road surface, through the information conversion module 21, a first probability parameter corresponding to the road surface temperature, a second probability parameter corresponding to the air temperature, and a third probability parameter corresponding to the residual water volume on the road surface can be obtained.

[0029] The probability prediction module 22 may be used to fuse multiple influence probabilities to obtain the icing probability of the target road at the prediction moment.

[0030] In an embodiment of the present application, the information conversion module 21 may convert each parameter in the road icing prediction information into a corresponding influence probability based on a probability calculation rule. Among them, the probability calculation rule may include a probability calculation rule corresponding to the road surface temperature, a probability calculation rule corresponding to the air temperature, and a probability calculation rule corresponding to the residual water volume on the road surface.

[0031] In an embodiment of the present application, the probability calculation rule corresponding to the road surface temperature T1 may include that when the road surface temperature is lower than the first preset temperature, the first probability parameter ρ1 is 1; when the road surface temperature T1 is not lower than the first preset temperature and not higher than the second preset temperature, the first probability parameter ρ1 may be 1 / (1 + T1); when the road surface temperature T1 is higher than the second preset temperature, the first probability parameter ρ1 may be 0.

[0032] In an embodiment of the present application, the probability calculation rule corresponding to the air temperature T2 may include that when the air temperature T2 is lower than the third preset temperature, the second probability parameter ρ2 is 1; when the air temperature T2 is not lower than the third preset temperature and not higher than the fourth preset temperature, the second probability parameter ρ2 may be 1 / (6 + T2); when the air temperature T2 is higher than the fourth preset temperature, the second probability parameter ρ2 may be 0.

[0033] In an embodiment of the present application, the probability calculation rule corresponding to the road surface residual water volume W may include that when the road surface residual water volume W is lower than the first preset water volume, the third probability parameter ρ3 is 0; when the road surface residual water volume W is not lower than the first preset water volume and not higher than the second preset water volume, the third probability parameter ρ3 may be 1 / (6 - W); when the road surface residual water volume W is not lower than the second preset water volume, the third probability parameter ρ3 may be 1.

[0034] The probability prediction module 22 can be constructed by a probability fusion algorithm. In an embodiment of the present application, the probability fusion algorithm can be expressed by the following formula.

[0035] ρ = ρ1 * ρ2 * ρ3 (1)

[0036] Wherein, ρ may be the icing probability of the target road at the prediction moment.

[0037] It should be noted that the weight parameter, the first preset temperature, the second preset temperature, the third preset temperature, the fourth preset temperature, the first preset water volume, and the second preset water volume can be obtained by training with historical road icing data. That is to say, each parameter in the road icing prediction model 20 can be obtained by training with historical road icing data.

[0038] Optionally, the first preset temperature is 0 °C, the second preset temperature is 4 °C, the third preset temperature is -4 °C, the fourth preset temperature is 0 °C, the first preset water volume is 2 mm, and the second preset water volume is 5 mm.

[0039] In the above embodiments, the road icing prediction model can be used to calculate the influence degree of each icing influence factor on icing respectively, so as to comprehensively consider the influence degree of each icing influence factor, so as to more accurately predict the icing probability of the target road and improve the accuracy and reliability of the prediction result.

[0040] In some embodiments, the road icing prediction model 20 can also predict the icing probability of the target road at the prediction moment according to historical road weather data.

[0041] When the road icing prediction information does not include at least one of the road surface temperature, air temperature, and residual water volume on the road surface, the road icing prediction device obtains the historical specific moment weather information corresponding to the prediction moment, and processes the historical specific moment weather information to obtain the historical road icing information corresponding to each historical specific moment weather information. The historical road icing information may include, but is not limited to, the road surface temperature, air temperature, and residual water volume on the road surface.

[0042] The road icing prediction device filters the target historical road icing information that meets the road icing prediction information, and uses the road icing prediction model 20 to predict the icing probability of the target road at the prediction moment according to the target historical road icing information.

[0043] The historical specific moment weather data corresponding to the prediction moment involved in an embodiment of the present application may refer to the actual weather information recorded in the area where the target road is located at one or more time points in the past that are the same as the prediction moment, for example, the same moment on the same date. The target historical road icing information may refer to the historical moment weather information that matches each parameter in the road icing prediction information. For example, one or more historical road icing information with the road surface temperature of the target historical road icing information being close to the road surface temperature at the prediction moment.

[0044] In an embodiment of the present application, the road icing prediction device obtains the first probability parameter, the second probability parameter, and the third probability parameter corresponding to the target historical road icing information through the road icing prediction model 20, and obtains the icing probability of the target road at the prediction moment based on the first probability parameter, the second probability parameter, and the third probability parameter.

[0045] In this way, when the road icing prediction information does not meet the condition of not including at least one of the road surface temperature, air temperature, and residual water volume on the road surface, the icing probability of the target road at the prediction moment can be predicted through the target historical road icing information at the historical specific moment, so that the road icing situation can still be accurately predicted in the case of missing icing prediction parameters.

[0046] It should be noted that when the road icing prediction model 20 uses the target historical road icing information to predict the road icing probability, the probability fusion algorithm of the probability prediction module 22 can be expressed by the following formula.

[0047] ρ = K * ρ1 * ρ2 * ρ3 (2)

[0048] Among them, ρ can be the icing probability of the target road at the prediction moment, and K represents a weight parameter. The weight parameter can be obtained by training based on the weather information and icing conditions of the historical road.

[0049] Due to different road types, the road surface temperature is different under the same weather conditions. Therefore, in some embodiments, when the road icing prediction information includes the road surface temperature, in S12, based on the weather information, determining the road icing prediction information of the target road at the prediction moment may include: obtaining the road type of the target road; determining a target road surface temperature calculation model corresponding to the target road based on the road type of the target road; and determining the road surface temperature of the target road at the prediction moment by using the target road surface temperature calculation model based on the weather information.

[0050] In an embodiment of the present application, the weather information processing model may include a road surface temperature processing model. The road icing prediction device processes the weather information by using the road surface temperature processing model to obtain the road surface temperature of the target road at the prediction moment. Specifically, the road icing prediction device obtains the road type of the target road from the electronic map platform, selects a target road surface temperature calculation model matching the road type of the target road by using the road surface temperature processing model, and processes the weather information by using the target road surface temperature calculation model to obtain the road surface temperature of the target road at the prediction moment.

[0051] In the above embodiment, since it is considered that due to different road types, the road surface temperature is different under the same weather conditions. Therefore, it is proposed to select a corresponding target road surface temperature calculation model according to the road type and use the target road surface temperature calculation model to obtain the road surface temperature at the prediction moment, thereby improving the accuracy of calculating the road surface temperature.

[0052] In some embodiments, determining a target road surface temperature calculation model corresponding to the target road based on the road type of the target road includes: when the road type of the target road is a bridge deck, determining the first model as the target road surface temperature calculation model; when the road type of the target road is a non-bridge deck, determining the second model as the target road surface temperature calculation model.

[0053] Since the bottom of the bridge deck is in contact with the air and dissipates heat quickly. Therefore, the road surface temperature of the bridge deck is equal to the air temperature. That is, the first model can be expressed as the road surface temperature being equal to the air temperature.

[0054] Since the bottom of the non-bridge deck road is in contact with the soil and dissipates heat slowly. Therefore, the non-bridge deck road needs to consider the air temperature before the prediction moment. That is, the second model can take the air temperature data before the prediction moment and the predicted air temperature data at the prediction moment as inputs.

[0055] In the above embodiments, different pavement temperature calculation models need to be adopted for different types of roads, which can improve the accuracy of pavement temperature.

[0056] In some embodiments, when the target pavement temperature calculation model is the second model, the pavement temperature of the target road at the prediction moment is determined based on the weather information using the target pavement temperature calculation model, including: obtaining the air temperature at the prediction moment and the air temperatures at at least one historical moment before the prediction moment from the weather information; using the second model to obtain a pavement reference temperature based on the air temperatures at at least one historical moment, and determining the pavement temperature of the target road at the prediction moment according to the comparison result between the pavement reference temperature and the air temperature at the prediction moment.

[0057] In one embodiment of the present application, at least one historical moment involved may include moments at least one day before the prediction moment. Each historical moment is 24 hours apart.

[0058] In one embodiment of the present application, the second model may include a pavement reference temperature calculation module. The pavement reference temperature calculation module may be constructed based on the following formula.

[0059] C = C t-24*1 *a 1 + C t-24*2 *a 2 +...... + C t-24*N *a N (3)

[0060] Wherein, C represents the pavement reference temperature, t represents the prediction moment, C t-24*N represents the air temperature 24*N hours apart from the prediction moment, a 1 to a N represent weight parameters, and the sum of a 1 to a N is 1.

[0061] For example, at least one historical moment may include the moment 24 hours before, and may also include the moment 48 hours before the prediction moment. The pavement reference temperature may be C = C t-24 *60% + C t-48 *40%.

[0062] In an embodiment of the present application, the second model may further include a comparison module. The comparison module is configured to compare the road surface reference temperature with the air temperature at the prediction moment after obtaining the road surface reference temperature. And, when the road surface reference temperature is not lower than the air temperature at the prediction moment, the sum of the road surface temperature and the first threshold temperature is used as the road surface temperature at the prediction moment. When the road surface reference temperature is lower than the air temperature at the prediction moment, the sum of the road surface temperature and the second threshold temperature is used as the road surface temperature at the prediction moment. Wherein, the first threshold temperature is less than the second threshold temperature. Optionally, the first threshold temperature may be 2 and the second threshold temperature is 5.

[0063] In the above embodiment, by using the second model, the road surface temperature of the non-bridge road can be accurately obtained through the air temperature at one or more historical moments and the air temperature at the prediction moment, improving the accuracy of the road surface temperature of the non-bridge road.

[0064] In some embodiments, when the road icing prediction information includes the residual water amount on the road surface, S12, based on the weather information, determining the road icing prediction information of the target road at the prediction moment includes: obtaining the precipitation at the prediction moment and the precipitation at a plurality of historical moments before the prediction moment from the weather information; based on the precipitation at the prediction moment and the precipitation at a plurality of historical moments, obtaining the residual water amount on the road surface of the target road at the prediction moment.

[0065] The precipitation at the historical moment involved in an embodiment of the present application may refer to the precipitation that is 1 hour or several hours away from the prediction moment.

[0066] In an embodiment of the present application, the road icing prediction device may process the precipitation in the area where the target road is located based on the precipitation processing model to obtain the residual water amount on the road surface of the target road at the prediction moment. That is, the precipitation at the prediction moment and the precipitation at a plurality of historical moments are used as the input of the precipitation processing model and the residual water amount on the road surface of the target road at the prediction moment is used as the output.

[0067] Specifically, the precipitation processing model may be constructed according to a linear equation with multiple variables or according to a machine learning algorithm. Among them, the precipitation processing model constructed based on the linear equation with multiple variables can be expressed by the following formula.

[0068] W = W t *b 1 + W t-1*1 *b 2 +......+ W t-1*N *b N (4)

[0069] Wherein, W represents the residual water amount on the road surface at the prediction moment, t represents the prediction moment, W t-1*N represents the precipitation that is 1*N hours away from the prediction moment, and N is a positive integer less than 12. b1 to b N represents a weight parameter. Optionally, b 1 is 50%, b 2 is 10%, b 3 to b N is 5%.

[0070] In some embodiments, when the icing probability of the target road at the prediction moment exceeds the warning threshold, an icing warning message is sent to a third party. Among them, the third party can be a traffic management department or a map navigation platform. Optionally, the warning threshold is greater than 70%.

[0071] Another aspect of the embodiments of the present application provides a road icing prediction device. Figure 3 The structural schematic diagram of a road icing prediction device provided by an embodiment of the present application is shown, as Figure 3 shown, the road icing prediction device 30 may include the following modules.

[0072] A weather information acquisition module 31, configured to acquire weather information of a target time period in the area where the target road is located; the target time period includes the time period between the target historical moment and the prediction moment.

[0073] A prediction information determination module 32, configured to determine road icing prediction information of the target road at the prediction moment based on the weather information.

[0074] A probability prediction module 33, configured to predict the icing probability of the target road at the prediction moment based on the road icing prediction information.

[0075] In some embodiments, the probability prediction module 33 may specifically be configured to input the road icing prediction information into a road icing prediction model, and through the information conversion module of the road icing prediction model, obtain a first probability parameter, a second probability parameter, and a third probability parameter corresponding to the road surface temperature, the air temperature, and the residual water volume on the road surface respectively; through the probability prediction module of the road icing prediction model, based on the first probability parameter, the second probability parameter, and the third probability parameter, obtain the icing probability of the target road at the prediction moment.

[0076] In some embodiments, the prediction information determination module 32 is specifically configured to, when the road icing prediction information includes the road surface temperature, obtain the road type of the target road; determine a target road surface temperature calculation model corresponding to the target road based on the road type of the target road; and determine the road surface temperature of the target road at the prediction moment by using the target road surface temperature calculation model based on the weather information.

[0077] In some embodiments, the prediction information determination module 32 is specifically configured to determine the first model as the target road surface temperature calculation model when the road type of the target road is a bridge deck; and determine the second model as the target road surface temperature calculation model when the road type of the target road is not a bridge deck.

[0078] In some embodiments, when the target road surface temperature calculation model is the second model, the prediction information determination module 32 is specifically configured to obtain the air temperature at the prediction moment and the air temperatures at at least one historical moment before the prediction moment from the weather information; use the second model to obtain a road surface reference temperature based on the air temperatures at at least one historical moment, and determine the road surface temperature of the target road at the prediction moment according to the comparison result between the road surface reference temperature and the air temperature at the prediction moment.

[0079] In some embodiments, when the road icing prediction information includes the residual water amount on the road surface, the prediction information determination module 32 is specifically configured to obtain the precipitation amount at the prediction moment and the precipitation amounts at a plurality of historical moments before the prediction moment from the weather information; and obtain the residual water amount on the road surface of the target road at the prediction moment based on the precipitation amount at the prediction moment and the precipitation amounts at the plurality of historical moments.

[0080] It should be understood that the specific features, operations, and details described above regarding the method of the present application can be similarly applied to the devices and systems of the present application, or vice versa. Additionally, each step of the method of the present application described above can be executed by the corresponding components or units of the device or system of the present application.

[0081] It should be understood that each module / unit of the device of the present application can be implemented in whole or in part by software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the processor of the electronic device in the form of hardware or firmware, or independent of the processor, and can also be stored in the memory of the electronic device in the form of software for the processor to call to execute the operations of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0082] On the other hand, the present application provides an electronic device. Figure 4 The structural schematic diagram of an electronic device provided according to an embodiment of the present application is shown, as Figure 4 shown, the electronic device 40 includes a processor 41, a memory 42, and a program stored on the memory and capable of running on the processor. When the program is executed by the processor, it implements the steps of the road icing prediction method provided in any of the above embodiments.

[0083] In one embodiment, the electronic device 40 may include a processor, a memory, a network interface, a communication interface, etc., connected via a system bus. The processor of the electronic device 40 may be used to provide necessary computing, processing, and / or control capabilities. The memory of the electronic device 40 may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may store an operating system, a computer program, etc. The internal memory may provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the electronic device 40 may be used to connect and communicate with external devices via a network.

[0084] In another aspect of the present application, there is provided a computer-readable storage medium with instructions stored thereon. When the instructions are executed by a processor, the steps of the road icing prediction method provided in any of the above embodiments are implemented.

[0085] Those skilled in the art can understand that the method steps of the present application can be instructed by a computer program to complete relevant hardware such as an electronic device or a processor. The computer program can be stored in a non-transitory computer-readable storage medium. When the computer program is executed, the steps of the present application are caused to be executed. Depending on the situation, any reference to a memory, storage, or other medium herein may include non-volatile or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0086] The above-described technical features can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification as long as such a combination does not exist in contradiction.

[0087] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A road icing prediction method, characterized in that: include: Acquire weather information of a target time period in an area where a target road is located; the target time period includes a time period between a target historical moment and a predicted moment; Determining road icing prediction information of the target road at a prediction time based on the weather information; Based on the road icing prediction information, the icing probability of the target road at the prediction time is predicted.

2. The method according to claim 1, characterized in that The road icing prediction information includes at least one of the following: road surface temperature, air temperature, and residual water content on the road surface.

3. The method according to claim 2, characterized in that The predicting the icing probability of the target road based on the road icing prediction information includes: Inputting the road icing prediction information into a road icing prediction model, and obtaining a first probability parameter, a second probability parameter, and a third probability parameter corresponding to the road surface temperature, the air temperature, and the residual water content of the road surface, respectively, through an information conversion module of the road icing prediction model; The probability prediction module of the road icing prediction model is used to obtain the icing probability of the target road at the prediction time based on the first probability parameter, the second probability parameter and the third probability parameter.

4. The method according to claim 2, characterized in that: When the road icing prediction information includes road surface temperature, determining the road icing prediction information of the target road at the prediction time based on the weather information includes: Get the road type of the target road; Based on the road type of the target road, determining a target road surface temperature calculation model corresponding to the target road; The target road surface temperature calculation model is used based on the weather information to determine the road surface temperature of the target road at the predicted time.

5. The method according to claim 4, characterized in that The step of determining a target road surface temperature calculation model corresponding to the target road based on the road type of the target road includes: When the road type of the target road is a bridge deck, determining the first model as a target road surface temperature calculation model; When the road type of the target road is non-bridge surface, the second model is determined to be a target road surface temperature calculation model.

6. The method according to claim 5, characterized in that When the target road surface temperature calculation model is the second model, determining the road surface temperature of the target road at the prediction time by using the target road surface temperature calculation model based on the weather information includes: Acquire the temperature at the predicted time and the temperature at at least one historical time before the predicted time from the weather information; The second model is used to obtain a road surface reference temperature based on the air temperature at the at least one historical moment, and the road surface temperature of the target road at the predicted moment is determined based on a comparison result between the road surface reference temperature and the air temperature at the predicted moment.

7. The method according to claim 2, characterized in that: When the road icing prediction information includes the residual water amount on the road surface, determining the road icing prediction information of the target road at the prediction time based on the weather information includes: Acquire the precipitation at the predicted moment and the precipitation at multiple historical moments before the predicted moment from the weather information; Based on the precipitation at the predicted moment and the precipitation at the plurality of historical moments, the residual water volume on the road surface of the target road at the predicted moment is obtained.

8. A road icing prediction device, characterized in that: include: A weather information acquisition module is used to acquire weather information of a target time period in an area where a target road is located; The target time period includes the time period between the target historical moment and the predicted moment; A forecast information determination module, used to determine the road icing forecast information of the target road at the forecast time based on the weather information; A probability prediction module is used to predict the icing probability of the target road at a prediction time based on the road icing prediction information.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the road icing prediction method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, the steps of the road icing prediction method according to any one of claims 1 to 7 are implemented.

Images