Road agglomerate fog prediction method, device, equipment and medium

Abstract

The invention provides a road agglomerate fog prediction method and device, equipment and a medium. The road agglomerate fog prediction method comprises the following steps: acquiring weather information and traffic information of a target road in a target time period; the target time period comprises a time period from a target historical moment to a prediction moment; processing the weather information and the traffic information to obtain agglomerate fog prediction information; and based on the agglomerate fog prediction information, obtaining the agglomerate fog occurrence probability of the target road at the prediction moment.

Description

Technical Field

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

[0002] Patchy fog refers to a small-scale thick fog formed under the influence of the local microclimate environment. When patchy fog appears, the visibility of the air significantly decreases, and the road surface becomes slippery, seriously affecting the driver's line of sight and easily leading to traffic accidents. Therefore, it is particularly important to give early warnings for the areas where patchy fog occurs. Early warnings can enable users to make preparations in advance, such as reducing the vehicle speed, maintaining a safe distance, turning on the fog lights, etc., to cope with the line-of-sight obstacles and road surface slipperiness problems brought by patchy fog, thereby significantly reducing the incidence of traffic accidents and protecting the lives and property safety of drivers and passengers.

[0003] When using meteorological monitoring equipment to give early warnings for patchy fog areas currently, false alarms are likely to occur. Therefore, how to improve the accuracy of predicting the occurrence of patchy fog and reduce the false alarm rate has become an urgent task. Summary of the Invention

[0004] In view of this, the present application provides a road patchy fog prediction method, device, equipment, and computer-readable storage medium, which can accurately predict the occurrence probability of road patchy fog at a future moment.

[0005] According to the first aspect of the present application, a road patchy fog prediction method is provided. The method may include: obtaining weather information and traffic information of a target road for a target time period; the target time period includes the time period between a target historical moment and a prediction moment; processing the weather information and the traffic information to obtain patchy fog prediction information; and obtaining the occurrence probability of patchy fog on the target road at the prediction moment based on the patchy fog prediction information.

[0006] According to the second aspect of the present application, a road patchy fog prediction device is provided. The road patchy fog prediction device includes: an information acquisition module, configured to obtain weather information and traffic information of a target road for a target time period; the target time period includes the time period between a target historical moment and a prediction moment; a prediction information obtaining module, configured to process the weather information and the traffic information to obtain patchy fog prediction information; and a probability obtaining module, configured to obtain the occurrence probability of patchy fog on the target road at the prediction moment based on the patchy fog prediction information.

[0007] According to the third aspect of the present application, an electronic device is provided, including a processor, a memory, and a program stored in the memory and capable of running on the processor, where the program, when executed by the processor, implements the steps of any one of the road patchy fog prediction methods provided in the embodiments of the present application.

[0008] According to a fourth aspect of the present application, a computer-readable storage medium is provided. Instructions are stored on the computer-readable storage medium, and when the instructions are executed by a processor, the steps of any one of the road patchy fog prediction methods provided in the embodiments of the present application are implemented.

[0009] In summary, the road patchy fog 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 and traffic information of a target road during a target time period, the weather data and traffic data affecting the occurrence of road patchy fog can be captured, and by analyzing and processing the weather information and traffic information, the road patchy fog prediction information of the target road at the prediction moment can be determined, and further the characteristic data affecting road patchy fog can be extracted, providing strong support for the subsequent prediction of the probability of patchy fog occurrence. And, based on the road patchy fog prediction information, the probability of patchy fog occurrence on 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

[0010] 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, other drawings can be obtained based on these drawings without creative efforts.

[0011] Figure 1 A flowchart showing a road patchy fog prediction method provided by an embodiment of the present application;

[0012] Figure 2 A structural diagram showing a road patchy fog prediction model provided by an embodiment of the present application;

[0013] Figure 3 A structural diagram showing a road patchy fog prediction device provided by an embodiment of the present application;

[0014] Figure 4 A structural diagram showing an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] 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.

[0016] In the following description, numerous specific details are set forth to provide a thorough understanding of the present application. However, it is apparent to those skilled in the art that the present application may be practiced without these specific details. In other instances, well-known steps or operations have not been described in detail to avoid obscuring the present application.

[0017] An embodiment of the present application provides a method for predicting road patchy fog, which is applied to a road patchy fog prediction device. Figure 1 The flowchart showing a method for predicting road patchy fog provided by an embodiment of the present application is as Figure 1 shown, and the method for predicting road patchy fog may include the following steps.

[0018] S11, Obtain the weather information and traffic information of a target road for a target time period.

[0019] The target time period involved in an embodiment of the present application includes the time period between a target historical moment and a prediction moment. Among them, the target historical moment refers to the moment before the prediction moment. The weather information may include the weather information at the prediction moment and the historical weather information at the historical moment before the prediction moment. The traffic information may include the traffic flow data of the road. Among them, the traffic information can be obtained from a traffic platform. The target road can be a certain section of any road on an electronic map.

[0020] In an embodiment of the present application, the road patchy fog prediction device may obtain the weather information of the target time period from a weather data service platform according to the geographical information of the target road, and obtain the traffic information of the target road from a traffic platform.

[0021] S12, Process the weather information and traffic information to obtain patchy fog prediction information.

[0022] The patchy fog prediction information involved in an embodiment of the present application includes at least one of the following: the cooling amplitude value, humidity, wind speed, and traffic flow. Among them, the cooling amplitude value can be used to indicate the cooling amplitude from the historical moment to the prediction moment. The traffic flow can be the total traffic volume from at least two hours before the prediction moment to the prediction moment. The wind speed can refer to the wind speed at the prediction moment.

[0023] In an embodiment of the present application, the road patchy fog prediction device may perform data preprocessing and extract feature data on the weather information and traffic information, so as to obtain patchy fog prediction information.

[0024] S13, Based on the patchy fog prediction information, obtain the probability of patchy fog occurrence on the target road at the prediction moment.

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

[0026] In each of the above embodiments, the weather information and traffic information of the target time period of the target road can be obtained, so that the weather data and traffic data affecting the occurrence of road patchy fog can be captured, and by analyzing and processing the weather information and traffic information, the road patchy fog prediction information of the target road at the prediction moment can be determined, and further the characteristic data affecting road patchy fog can be extracted to provide strong support for the subsequent prediction of the probability of patchy fog occurrence. Moreover, based on the road patchy fog prediction information, the probability of patchy fog occurrence on 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, when the patchy fog prediction information includes the cooling amplitude value, S12, processing the weather information and traffic information to obtain the patchy fog prediction information may include: determining the initial temperature at the initial cooling moment and the predicted temperature at the prediction moment based on the temperature information in the weather information; subtracting the predicted temperature from the initial temperature to obtain the cooling amplitude value of the target road.

[0028] The initial cooling moment involved in an embodiment of the present application may refer to the historical moment when the temperature starts to drop before the prediction moment. The cooling amplitude value reflects the degree of temperature drop from the initial cooling moment to the prediction moment.

[0029] In an embodiment of the present application, the road patchy fog prediction device performs data preprocessing on the weather information, extracts the temperature information from the processed weather information, analyzes the initial temperature at the initial cooling moment and the predicted temperature at the prediction moment from the temperature information, and then subtracts the predicted temperature from the initial temperature to obtain the cooling amplitude value of the target road.

[0030] In the above embodiments, the temperature information can be extracted from the weather information, the initial temperature at the initial cooling moment and the predicted temperature at the prediction moment can be analyzed, and based on the difference between the two, the cooling amplitude value of the target road at the prediction moment can be accurately obtained, providing a reliable basis for subsequent patchy fog prediction.

[0031] In some embodiments, based on the temperature information in the weather information, determining the initial temperature at the initial moment of temperature drop and the predicted temperature at the predicted moment includes: based on the temperature information in the weather information, determining whether there is at least one temperature rise period within a specific period from a historical specific moment to the predicted moment; if so, taking the temperature at the last moment corresponding to the last temperature rise period as the initial temperature at the initial moment of temperature drop; if not, taking the temperature corresponding to the historical specific moment as the initial temperature at the initial moment of temperature drop.

[0032] In an embodiment of the present application, the historical specific moment involved is a moment at least 2 hours before the predicted moment. In an embodiment of the present application, the road fog prediction device extracts the temperature data from the historical specific moment to the predicted moment from the temperature information, traverses the temperature data within the specific period, and analyzes whether there is one or more temperature rise periods within the specific period.

[0033] If there is at least one temperature rise period, the road fog prediction device finds the last temperature rise period from all the temperature rise periods, determines the end moment of the temperature rise period, that is, the last moment, and takes the last moment as the initial temperature at the initial moment of temperature drop.

[0034] If there is no temperature rise period, it has been in the temperature drop stage from the historical specific moment to the predicted moment, and the road fog prediction device takes the temperature corresponding to the historical specific moment as the initial temperature at the initial moment of temperature drop.

[0035] It should be noted that the last temperature rise period is the temperature rise period with the closest last moment to the predicted moment.

[0036] In this way, by analyzing the temperature information to determine whether there is a temperature rise stage, the initial temperature of the temperature drop process within the period from the historical specific moment to the predicted moment can be reasonably and accurately determined through the analysis result, thereby ensuring the accuracy of the temperature drop amplitude value at the predicted moment.

[0037] In some embodiments, based on the temperature information in the weather information, determining whether there is at least one temperature rise period within a specific period from a historical specific moment to the predicted moment includes: obtaining the temperatures of two adjacent specific moments within the specific period from the historical specific moment to the predicted moment from the temperature information in the weather information, where the two adjacent specific moments include a first specific moment and a second specific moment earlier than the first specific moment; comparing the magnitudes of the temperatures of the first specific moment and the second specific moment; when the temperature of the first specific moment is greater than the temperature of the second specific moment, determining that the period from the second specific moment to the first specific moment is a temperature rise period.

[0038] In an embodiment of the present application, the road patchy fog prediction device selects the temperatures at two adjacent specific moments within a specific time period from the temperature information, compares their magnitudes, and determines whether the time period between the two adjacent specific moments is a temperature-rising time period according to the comparison result.

[0039] If the temperature at the first specific moment is greater than the temperature at the second specific moment, it is determined that the time period from the second specific moment to the first specific moment is a temperature-rising time period. If the temperature at the first specific moment is not greater than the temperature at the second specific moment, it is determined that the time period from the second specific moment to the first specific moment is not a temperature-rising time period.

[0040] It should be noted that the first specific moment and the second specific moment are at least half an hour apart. The first specific moment and the second specific moment are any two adjacent specific moments within the specific time period.

[0041] The road patchy fog prediction device repeats the above steps, traverses the temperatures at two adjacent specific moments throughout the specific time period, determines all the temperature-rising time periods within the specific time period, and records the relevant information of the temperature-rising time periods, such as the start time, the end time, and the corresponding temperatures.

[0042] In the above embodiment, by comparing the magnitudes of the temperatures at two adjacent specific moments, it is determined whether the time period between the two adjacent specific moments is a temperature-rising time period, so that all the temperature-rising stages within the specific time period can be accurately determined.

[0043] In an example, there are the temperatures at 7 specific moments within the specific time period, such as the temperature C at the prediction moment t , the temperature C at the first specific moment earlier than the prediction moment t-1 , the temperature C at the second specific moment earlier than the first specific moment t-2 , the temperature C at the third specific moment earlier than the second specific moment t-3 , the temperature C at the fourth specific moment earlier than the third specific moment t-4 , the temperature C at the fifth specific moment earlier than the fourth specific moment t-5 , the temperature C at the sixth specific moment earlier than the fifth specific moment t-6 , the temperature C at the seventh specific moment earlier than the sixth specific moment t-7 .

[0044] The road patchy fog prediction device traverses the temperatures at 7 specific moments and compares the magnitudes of the temperatures at two adjacent specific moments in turn.

[0045] First, compare the magnitudes of C t-1 and Ct. If C t-1 is less than C t , then the end time of the last temperature-rising stage coincides with the prediction moment, and it can be determined that the temperature drop amplitude value at the prediction moment is 0.

[0046] If C t-1 is not less than C t , then continue to compare C t-2 with C t-1 . If C t-2 is less than C t-1 , then it can be determined that the last moment of the last heating stage is C t-1 , and the temperature drop amplitude value at the prediction moment is C t-1 - C t . If C t-2 is not less than C t-1 , then continue to compare C t-3 with C t-2 .

[0047] If C t-3 is less than C t-2 , then it can be determined that the last moment of the last heating stage is C t-2 , and the temperature drop amplitude value at the prediction moment is C t-2 - C t . If C t-3 is not less than C t-2 , then continue to compare C t-4 with C t-3 .

[0048] If C t-4 is less than C t-3 , then it can be determined that the last moment of the last heating stage is C t-3 , and the temperature drop amplitude value at the prediction moment is C t-3 - C t . If C t-4 is not less than C t-3 , then continue to compare C t-5 with C t-4 .

[0049] If C t-5 is less than C t-4 , then it can be determined that the last moment of the last heating stage is C t-4 , and the temperature drop amplitude value at the prediction moment is C t-4 - C t . If C t-5 is not less than C t-4 , then continue to compare C t-6 with C t-5 .

[0050] If C t-6 is less than C t-5 , then it can be determined that the last moment of the last heating stage is C t-5 , and the temperature drop amplitude value at the prediction moment is Ct-5 -C t If C t-6 is not less than C t-5 , then the comparison between C t-7 and C t-6 can be continued.

[0051] If C t-7 is less than C t-6 , then it can be determined that the last moment of the last temperature increase stage is C t-6 , and the temperature decrease amplitude value at the prediction moment is C t-6 -C t If C t-7 is not less than C t-6 , then it can be determined that the last moment of the last temperature increase stage is C t-7 , and the temperature decrease amplitude value at the prediction moment is C t-7 -C t .

[0052] Since the formation of patchy fog is a long-term cumulative process, in some embodiments of the present application, the humidity may refer to the air humidity value one hour before the prediction moment. In this way, the trend of the recent environment can be better reflected, thereby improving the accuracy of patchy fog generation prediction. It should be noted that the humidity is expressed as a percentage.

[0053] In some embodiments, when the patchy fog prediction information includes traffic flow, in S12, the weather information and traffic information are processed to obtain the patchy fog prediction information, including: estimating the traffic flow passing through the target road during a specific traffic time period based on the traffic information.

[0054] A specific traffic time period involved in an embodiment of the present application is a time period from the historical traffic moment at least 2 hours before the prediction moment to the prediction moment. The traffic flow can represent the number of vehicles passing through a road within a period of time.

[0055] In an embodiment of the present application, the road patchy fog prediction device can obtain the traffic information of the target road and the adjacent roads connected to the target road during the historical time period within the specific traffic time period from the traffic information platform, where the traffic information generally includes information such as the number of vehicles, average vehicle speed, and vehicle distance.

[0056] Since the specific traffic time period includes the prediction time period and the historical time period. Therefore, in an embodiment of the present application, the road patchy fog prediction device can estimate the traffic flow of the target road during the prediction time period according to the traffic information of the adjacent roads during the historical time period, and add the traffic flow of the historical time period and the traffic flow of the prediction time period to obtain the traffic flow passing through the target road during the specific traffic time period. In this way, a reliable basis can be provided for accurately estimating the probability of patchy fog occurrence.

[0057] In some embodiments, S13, obtaining the probability of the occurrence of patchy fog on the target road at the prediction moment based on the patchy fog prediction information includes: inputting the patchy fog prediction information into the road patchy fog prediction model, and through the information conversion module of the road patchy fog prediction model, performing probability conversion on the temperature drop value, humidity, wind speed, and traffic flow to obtain a first probability parameter, a second probability parameter, a third probability parameter, and a fourth probability parameter; through the probability prediction module of the road patchy fog prediction model, based on the first probability parameter, the second probability parameter, the third probability parameter, and the fourth probability parameter, obtaining the probability of the occurrence of patchy fog on the target road at the prediction moment.

[0058] Figure 2 The structural schematic diagram of a road patchy fog prediction model provided by an embodiment of the present application is shown, as Figure 2 shown, the road patchy fog 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 patchy fog prediction information on the occurrence of road patchy fog. Each parameter in the road patchy fog prediction information corresponds to an influence probability. For example, when the road patchy fog prediction information includes the temperature drop value, humidity, wind speed, and traffic flow, through the information conversion module 21, a first probability parameter corresponding to the temperature drop value, a second probability parameter corresponding to the humidity, a third probability parameter corresponding to the wind speed, and a fourth probability parameter corresponding to the traffic flow can be obtained.

[0059] The probability prediction module 22 can be used to fuse multiple influence probabilities to obtain the probability of the occurrence of patchy fog on the target road at the prediction moment.

[0060] In an embodiment of the present application, the information conversion module 21 can convert each parameter in the road patchy fog prediction information into a corresponding influence probability based on a probability calculation rule. The probability calculation rule may include a probability calculation rule corresponding to the temperature drop value, a probability calculation rule corresponding to the humidity, a probability calculation rule corresponding to the wind speed, and a probability calculation rule corresponding to the traffic flow.

[0061] In an embodiment of the present application, for the temperature drop value C 降 the corresponding probability calculation rule may include that when C 降 is not greater than the first temperature difference, the first probability parameter ρ1 is 0.8; when C 降 is not greater than the second temperature difference, the first probability parameter ρ1 is 0.85; when C 降 is not greater than the third temperature difference, the first probability parameter ρ1 is 0.9; when C 降When it is not greater than the fourth temperature difference, the first probability parameter ρ1 is 0.95; when C drop is greater than the fourth temperature difference, the first probability parameter ρ1 is 1. Among them, the first temperature difference is less than the second temperature difference, the second temperature difference is less than the third temperature difference, and the third temperature difference is less than the fourth temperature difference. Optionally, the first temperature difference is 1, the second temperature difference is 2, the third temperature difference is 3, and the fourth temperature difference is 4.

[0062] In an embodiment of the present application, the probability calculation rule corresponding to the humidity H may include that when H is not lower than the first threshold, the second probability parameter ρ2 is H; when H is lower than the first threshold, the second probability parameter ρ2 is 0. Optionally, the first threshold is not lower than 80%.

[0063] In an embodiment of the present application, the probability calculation rule corresponding to the wind speed V may include that when V is lower than the first preset speed or higher than the second preset speed, the third probability parameter ρ3 is 0; when V is not lower than the first preset speed and not higher than the second preset speed, the third probability parameter ρ3 may be V*(6-V) / 9. Optionally, the first preset speed is 0 and the second preset speed is 6.

[0064] In an embodiment of the present application, the probability calculation rule corresponding to the traffic flow S may include that when S is not lower than the first flow rate S1, the fourth probability parameter ρ4 may be 1; when S is lower than S1, the fourth probability parameter ρ4 may be S / S1. Optionally, the first flow rate is not lower than 500.

[0065] 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.

[0066] ρ = ρ1 * ρ2 * ρ3 * ρ4 (1)

[0067] Among them, ρ can be the probability of the occurrence of a frontal fog on the target road at the prediction moment.

[0068] It should be noted that the temperature difference, the first threshold, the preset speed, and the first flow rate can be obtained by training based on historical road frontal fog data. That is to say, the parameters in the road frontal fog prediction model 20 can be obtained by training based on historical road frontal fog data.

[0069] In the above embodiments, the influence degree of each frontal fog influence factor on the occurrence of frontal fog can be calculated respectively by using the road frontal fog prediction model, so as to comprehensively consider the influence degree of each frontal fog influence factor, so as to be able to more accurately predict the probability of the occurrence of frontal fog on the target road and improve the accuracy and reliability of the prediction result.

[0070] In some embodiments, the road frontal fog prediction model 20 can also predict the probability of the occurrence of frontal fog on the target road at the prediction moment according to historical road weather data and historical traffic information.

[0071] When the road fog prediction information does not include at least one of the temperature drop value, humidity, wind speed, and traffic flow, the road prediction device obtains the weather information and historical traffic flow of a historical specific period corresponding to the prediction moment, and processes the weather information and traffic flow of the historical specific period to obtain the historical road fog information corresponding to each piece of weather information of the historical specific period. Among them, the historical road fog information may include, but is not limited to, the temperature drop value, humidity, wind speed, and traffic flow.

[0072] The road fog prediction device screens the target historical road fog information that meets the road fog prediction information, and uses the road fog prediction model 20 to predict the fog occurrence probability of the target road at the prediction moment according to the target historical road fog information.

[0073] The weather information and historical traffic flow of the historical specific period involved in an embodiment of the present application refer to the actual weather information and traffic flow of the target road recorded in a specific period that is the same as or similar to the target time period in the past one year or several years. The target historical road fog information may refer to the weather information and traffic flow at the historical moment that match each parameter in the road fog prediction information. For example, the humidity of the target historical road fog information is close to the humidity of the fog prediction information at the preset moment.

[0074] In an embodiment of the present application, the road fog prediction device obtains the probability parameter corresponding to the road fog prediction information and the probability parameter of the target historical road fog information, and obtains the fog occurrence probability of the target road at the prediction moment based on the probability parameters of the two. That is to say, when the road fog prediction information lacks at least one of the temperature drop value, humidity, wind speed, and traffic flow, it is supplemented by the target historical road fog information at the historical specific moment, so that the road fog prediction device uses the road fog prediction model 20 based on the temperature drop value, humidity, wind speed, and traffic flow to obtain the fog occurrence probability of the target road at the prediction moment.

[0075] For example, when the road fog prediction information does not include traffic flow, the target historical road fog information includes traffic flow. The road fog prediction device inputs the temperature drop value, humidity, and wind speed in the road fog prediction information, and the traffic flow in the target historical road fog information into the road fog prediction model 20, so as to obtain the fog occurrence probability of the target road at the prediction moment.

[0076] In this way, when the road fog prediction information does not include at least one of the temperature drop value, humidity, wind speed, and traffic flow, the fog occurrence probability of the target road at the prediction moment can be predicted through the target historical road fog information at the historical specific moment, so that the road fog situation can still be accurately predicted in the case of missing fog prediction parameters.

[0077] It should be noted that when the road fog prediction model 20 uses the target historical road fog information to predict the probability of road fog occurrence, the probability fusion algorithm of the probability prediction module 22 can be expressed by the following formula.

[0078] ρ = K * ρ1 * ρ2 * ρ3 * ρ4 (2)

[0079] Among them, ρ can be the probability of fog occurrence on the target road at the prediction moment, and K represents the weight parameter. The weight parameter can be obtained by training based on the historical weather information, historical traffic information, and fog occurrence situation of the road.

[0080] In some embodiments, when the probability of fog occurrence on the target road at the prediction moment exceeds the warning threshold, a fog 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%.

[0081] Another aspect of the embodiments of the present application provides a road fog prediction device. Figure 3 The structural schematic diagram of a road fog prediction device provided by an embodiment of the present application is shown, as Figure 3 shown, the road fog prediction device 30 may include the following modules.

[0082] An information acquisition module 31, configured to acquire the weather information and traffic information of the target road in the target time period; the target time period includes the time period between the target historical moment and the prediction moment.

[0083] A prediction information obtaining module 32, configured to process the weather information and traffic information to obtain fog prediction information.

[0084] A probability obtaining module 33, configured to obtain the probability of fog occurrence on the target road at the prediction moment based on the fog prediction information.

[0085] In some embodiments, when the fog prediction information obtained by the prediction information obtaining module 32 includes the cooling amplitude value, based on the temperature information in the weather information, the initial temperature at the initial cooling moment and the predicted temperature at the prediction moment are determined; the initial temperature is subtracted from the predicted temperature to obtain the cooling amplitude value of the target road.

[0086] In some embodiments, the prediction information obtaining module 32 is specifically configured to determine whether there is at least one temperature increase time period within a specific time period from the historical specific moment to the prediction moment based on the temperature information in the weather information, where the historical specific moment is the moment at least 2 hours before the prediction moment; if so, the temperature at the last moment corresponding to the last temperature increase time period is used as the initial temperature at the initial cooling moment; if not, the temperature corresponding to the historical specific moment is used as the initial temperature at the initial cooling moment.

[0087] In some embodiments, the prediction information obtaining module 32 may specifically be configured to obtain the temperatures at two adjacent specific moments within a specific time period from the historical specific moment to the prediction moment from the temperature information in the weather information, where the two adjacent specific moments include a first specific moment and a second specific moment earlier than the first specific moment; compare the temperature at the first specific moment with the temperature at the second specific moment; and when the temperature at the first specific moment is greater than the temperature at the second specific moment, determine the time period from the second specific moment to the first specific moment as the temperature rising time period.

[0088] In some embodiments, when the fog prediction information obtained by the prediction information obtaining module 32 includes traffic flow, based on the traffic information, the traffic flow passing through the target road within a specific traffic time period is estimated, and the specific traffic time period is the time period from the historical traffic moment at least 2 hours before the prediction moment to the prediction moment.

[0089] In some embodiments, the probability obtaining module 33 is configured to input the fog prediction information into the road fog prediction model, and through the information conversion module of the road fog prediction model, perform probability conversion on the temperature drop value, humidity, wind speed, and traffic flow to obtain a first probability parameter, a second probability parameter, a third probability parameter, and a fourth probability parameter; and through the probability prediction module of the road fog prediction model, based on the first probability parameter, the second probability parameter, the third probability parameter, and the fourth probability parameter, obtain the fog occurrence probability of the target road at the prediction moment.

[0090] 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 apparatus and system 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 apparatus or system of the present application.

[0091] It should be understood that each module / unit of the apparatus 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, or 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.

[0092] 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 4As 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, the steps of the road fog prediction method provided in any of the above embodiments are implemented.

[0093] In one embodiment, the electronic device 40 may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the electronic device 40 can 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 can 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 can be used to connect and communicate with external devices through a network.

[0094] On the other hand, the present application provides a computer-readable storage medium with instructions stored thereon. When the instructions are executed by a processor, the steps of the road fog prediction method provided in any of the above embodiments are implemented.

[0095] 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, and when the computer program is executed, the steps of the present application are executed. Depending on the situation, any reference to a memory, storage, or other medium in this document 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.

[0096] 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.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit 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 cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A road fog prediction method, characterized in that: include: Obtain weather information and traffic information for a target road during a target period of time; The target time period includes the time period between the target historical moment and the predicted moment; Processing the weather information and traffic information to obtain fog forecast information; Based on the fog group prediction information, the probability of fog group occurrence on the target road at the prediction time is obtained.

2. The method according to claim 1, characterized in that The fog cluster prediction information includes at least one of the following: temperature drop amplitude value, humidity, wind speed and traffic flow.

3. The method according to claim 2, characterized in that When the fog group prediction information includes a temperature drop amplitude value, the weather information and traffic information are processed to obtain the fog group prediction information, including: Based on the temperature information in the weather information, determining the initial temperature at the initial time of cooling and the predicted temperature at the predicted time; The predicted temperature is subtracted from the initial temperature to obtain a temperature drop value for the target road.

4. The method according to claim 3, characterized in that: The determining, based on the temperature information in the weather information, the initial temperature at the initial time of cooling and the predicted temperature at the predicted time, comprises: Based on the temperature information in the weather information, determine whether there is a temperature rise period in a specific time period from a specific historical moment to a predicted moment, wherein the specific historical moment is a moment at least 2 hours before the predicted moment; If it exists, the temperature at the last moment of the heating period is used as the initial temperature at the initial moment of cooling; If it does not exist, the temperature corresponding to the specific historical moment will be used as the initial temperature at the initial moment of cooling.

5. The method according to claim 4, characterized in that The determining, based on the temperature information in the weather information, whether there is a temperature rise period in a specific time period from a specific historical moment to a predicted moment includes: Acquire the temperatures of two adjacent specific moments within a specific time period from the historical specific moment to the predicted moment from the temperature information in the weather information, wherein the two adjacent specific moments include a first specific moment and a second specific moment earlier than the first specific moment; Comparing the temperature at the first specific moment with the temperature at the second specific moment; When the temperature at the first specific moment is greater than the temperature at the second specific moment, it is determined that the period from the second specific moment to the first specific moment is a temperature rising period.

6. The method according to claim 2, characterized in that When the fog group prediction information includes traffic flow, the weather information and traffic information are processed to obtain the fog group prediction information, including: Based on the traffic information, the traffic flow through the target road within a specific time period is estimated, and the specific time period is a time period from a time at least 2 hours before the predicted time to the predicted time.

7. The method according to claim 2, characterized in that: The step of obtaining the probability of occurrence of fog clusters on the target road at the prediction time based on the fog cluster prediction information includes: The fog group prediction information is input into the road fog group prediction model, and the temperature drop amplitude value, the humidity, the wind speed and the traffic flow are probability converted through the information conversion module of the road fog group prediction model to obtain a first probability parameter, a second probability parameter, a third probability parameter and a fourth probability parameter; Through the probability prediction module of the road fog prediction model, based on the first probability parameter, the second probability parameter, the third probability parameter and the fourth probability parameter, the probability of fog occurrence on the target road at the prediction time is obtained.

8. A road fog prediction device, characterized in that: include: An information acquisition module, used to acquire weather information and traffic information of a target road during a target period of time; The target time period includes the time period between the target historical moment and the predicted moment; A forecast information obtaining module, used for processing the weather information and traffic information to obtain fog forecast information; The probability obtaining module is used to obtain the probability of occurrence of fog clusters on the target road at the predicted time based on the fog cluster 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 fog 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 fog prediction method according to any one of claims 1 to 7 are implemented.

Images