Road freezing early warning method, system, equipment and medium

Abstract

The invention provides a road freezing early warning method, system and device and a medium, and relates to the technical field of traffic safety, and the method comprises the steps: obtaining real-time multi-dimensional weather data; taking the multi-dimensional weather data as input, and utilizing a pre-trained Bayesian probability prediction model to output a road icing probability; and judging whether to carry out icing early warning according to the road icing probability. According to the method, the Bayesian discrimination theory is introduced, probability inference can be carried out based on multiple meteorological data, mutual influence among multiple factors is automatically considered, and uncertainty of meteorological changes can be better coped with, so that prediction accuracy is improved, and prediction errors can be effectively reduced especially under complex weather conditions.

Description

Technical Field

[0001] This application relates to the field of traffic safety technologies, and particularly to a road icing warning method, system, device and medium based on Bayesian discrimination theory. Background Art

[0002] In cold seasons, icing becomes an important hidden danger to traffic safety. Icing usually appears on the road surface. Especially when the temperature is close to zero degree, climatic factors such as moisture, precipitation or frost cause water to form ice layers on the road, greatly increasing the smoothness of the road surface. For drivers, icing is one of the main causes of traffic accidents. Therefore, it is particularly important to predict in advance whether the road will ice, and timely remind drivers and traffic management departments to take corresponding preventive measures before icing to reduce the safety risks brought by icing.

[0003] Current icing warning systems often rely on traditional meteorological prediction models. Due to the complexity of meteorological factors and the influence of local climate changes, there are defects in the low accuracy of icing prediction, especially under special climate conditions, the error of the prediction result is large. Summary of the Invention

[0004] The purpose of this application is to provide a road icing warning method, system, device and medium, which can improve the accuracy of icing prediction and warning.

[0005] To achieve the above purpose, the following solutions are provided in this application.

[0006] In the first aspect, this application provides a road icing warning method, including the following steps.

[0007] Obtain real-time weather data, where the multi-dimensional weather data includes ambient temperature, ambient humidity and ambient wind speed.

[0008] Use the multi-dimensional weather data as input, and output the road icing probability by using a pre-trained icing prediction model, where the icing prediction model is a Bayesian probability prediction model.

[0009] Judge whether to issue an icing warning according to the road icing probability.

[0010] In the second aspect, this application provides a road icing warning system, including the following functional modules.

[0011] An environmental data acquisition module, configured to obtain real-time weather data, where the multi-dimensional weather data includes ambient temperature, ambient humidity and ambient wind speed.

[0012] A prediction information processing module, configured to use the multi-dimensional weather data as input and output the road icing probability by using a pre-trained icing prediction model, where the icing prediction model is a Bayesian probability prediction model.

[0013] An early warning module, configured to determine whether to issue an icing early warning according to the road icing probability.

[0014] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the road icing early warning method described in the first aspect above.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the road icing early warning method described in the first aspect above is implemented.

[0016] According to the specific embodiments provided by the present application, the technical effects of the present application are as follows.

[0017] The present application provides a road icing early warning method, system, device and medium. The method includes: obtaining real-time multi-dimensional weather data; using the multi-dimensional weather data as input and outputting the road icing probability by using a pre-trained Bayesian probability prediction model; determining whether to issue an icing early warning according to the road icing probability. By introducing Bayesian discriminant theory, the present application can perform probability inference based on multiple meteorological data, automatically consider the mutual influence between various factors, better cope with the uncertainty of meteorological changes, thereby improving the prediction accuracy. Especially under complex weather conditions, the prediction error can be effectively reduced. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is an application environment diagram of a road icing early warning method in Embodiment 1 of the present application.

[0020] Figure 2 It is a flowchart of a road icing early warning method in Embodiment 1 of the present application.

[0021] Figure 3 It is a schematic diagram of the functional modules of a road icing early warning system provided in Embodiment 2 of the present application.

[0022] Figure 4 This is a schematic structural diagram of a computer device provided in Embodiment 3 of the present application. Specific embodiments

[0023] It has been found through research that the current icing warning technology has the following disadvantages.

[0024] 1. Insufficient prediction accuracy: Existing icing warning methods often rely on traditional meteorological prediction models. Due to the complexity of meteorological factors and the influence of local climate changes, the prediction accuracy may not be high, especially under special climate conditions, and the error of the prediction results is relatively large.

[0025] 2. Serious false alarm and missed alarm problems: In traditional icing warnings, single-climate factor data measured by environmental detectors are usually used for icing analysis, and the interaction relationship between multiple climate factors is not fully considered, resulting in relatively high false alarm rates and missed alarm rates. This situation is particularly likely to occur under complex weather conditions, affecting the timely response of traffic management.

[0026] 3. Poor adaptability: Existing icing warning systems are mostly applied in fixed local areas and are difficult to effectively handle icing problems in different geographical and climate environments. The occurrence of icing phenomena is difficult to accurately predict through a few simple parameters, affecting the universality and coverage of the warning.

[0027] In response to this, this embodiment provides a road icing warning method, system, device and medium to overcome the above technical defects.

[0028] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0029] To make the above objects, features and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] The road icing warning method provided in the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed on the cloud or other servers. The terminal 102 can send the acquired real-time multi-dimensional weather data to the server 104. After receiving the multi-dimensional weather data, the server 104 uses the multi-dimensional weather data as input and outputs the road icing probability by using a pre-trained icing prediction model. Among them, the icing prediction model is a Bayesian probability prediction model; whether to issue an icing warning is judged according to the road icing probability. When the server 104 judges that an icing warning needs to be issued, the obtained warning information can be fed back to the terminal 102. In addition, in some embodiments, the road icing warning method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly process the multi-dimensional weather data by using the road icing warning method, or the server 104 can obtain the multi-dimensional weather data from the data storage system and process it by using the road icing warning method.

[0031] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0032] In an exemplary embodiment, as Figure 2 shown, a road icing warning method is provided. This method is executed by a computer device, and can be specifically executed independently by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiment of the present application, taking this method applied to Figure 1 the server 104 in it as an example for illustration, it includes the following steps 201 to step 203.

[0033] Step 201, acquire real-time multi-dimensional weather data, where the multi-dimensional weather data includes ambient temperature, ambient humidity, and ambient wind speed.

[0034] Step 202, use the multi-dimensional weather data as input and output the road icing probability by using a pre-trained icing prediction model, where the icing prediction model is a Bayesian probability prediction model.

[0035] The discrimination principle of the Bayesian probability prediction model is: Given g p-dimensional populations , their prior probabilities are respectively , each population has a distinct p-dimensional density function (when it is a probability function in the discrete case), in the case of observing a sample , the posterior probability that it comes from the population (also called the posterior probability relative to the prior probability) can be calculated using Bayes' formula, and the expression is as follows.

[0036] , .

[0037] In the formula, represents the prior probability of the population, and the probability of different environmental states can be statistically obtained based on historical meteorological data and road icing conditions. represents the input quantity, including environmental temperature , environmental humidity , environmental wind speed ; represents the population; represents the value corresponding to the index in the population; represents the -dimensional density function under different environmental temperatures, environmental humidities, and environmental wind speeds.

[0038] And when , then it is judged that comes from the rd population.

[0039] In this embodiment, the input quantity is input into the trained Bayesian probability prediction model, and using Bayes discriminant analysis, its prior probability is (given by experience); then the -dimensional density function can be obtained, and its p-dimensional density functions are respectively , , , , and then according to , , the probability value of road icing can be obtained, and based on the magnitude of the probability value, it is judged whether ice warning needs to be carried out.

[0040] In this embodiment, the historical prediction data of the Bayesian probability prediction model and the actual icing conditions are regularly used to optimize the Bayesian probability prediction model. Using the prediction results of the Bayesian probability prediction model, the prediction error of the model is regularly analyzed, and the prior probabilities of different parameters are updated according to the detected historical meteorological data and icing conditions, and the model parameters are dynamically updated to continuously improve the model accuracy.

[0041] This embodiment uses a discriminant function based on minimizing the misclassification loss. At this time, misclassification belongs to the The expression of the overall average loss is as follows.

[0042] .

[0043] In the formula, is called the loss function, indicating the loss of misclassifying the sample of the th population as the th population. Obviously, the above formula is the weighted average of the loss function by probability or the average loss of misclassification. When , there is =0; when , there is >0. The discrimination criterion is established as: if , then judge that comes from the th population. In principle, considering the loss function is more reasonable, but in practical applications is not easy to determine. Therefore, it is often assumed in the mathematical model that the losses of various misclassifications are equal, that is: .

[0044] In this way, finding to maximize the posterior probability and minimize the average loss of misclassification is equivalent, that is: .

[0045] Introducing the misclassification loss can greatly improve the discrimination probability.

[0046] Step 203, determine whether to issue an icing warning according to the road icing probability.

[0047] Step 203 specifically includes: when the road icing probability is less than the lower limit of the first preset warning probability range, no icing warning is issued; when the road icing probability is within the first preset warning range, a medium and low-level warning is started; when the road icing probability is within the second preset warning range, a high-level warning is started, where the second preset warning range is greater than the first preset warning range; when the road icing probability is within the third preset warning range, an emergency warning is started, where the third preset warning range is greater than the second preset warning range.

[0048] Specifically, when the icing probability is between 50% and 69%, medium and low-level warnings can be initiated to alert relevant departments and drivers of possible risks and prepare corresponding preventive measures; when the icing probability reaches 70% - 89%, high-level warnings should be initiated, and at this time, emergency measures may need to be taken, including but not limited to restricting traffic on certain sections, strengthening road surface treatment measures, and issuing emergency warning information to drivers; when the icing probability reaches 90% - 100%, or icing has actually started, an emergency warning should be initiated. At this time, it is necessary to close the affected sections, conduct comprehensive de-icing operations, and ensure everyone's safety.

[0049] The road icing warning method provided by this embodiment has the following advantages.

[0050] 1. Improve prediction accuracy. By introducing a Bayesian probability prediction model based on Bayesian discriminant theory, this Bayesian probability prediction model can perform probability inference based on multiple meteorological data and automatically consider the mutual influence between various factors. Compared with traditional methods, Bayesian discriminant theory can better cope with the uncertainty of meteorological changes, thereby improving the accuracy of prediction. Especially under complex weather conditions, it can effectively reduce prediction errors.

[0051] 2. Significantly reduce false alarm and missed alarm rates. Through the training of the Bayesian probability prediction model, the probability of icing occurrence can be determined more accurately. Through in-depth analysis of historical data and updated inference of real-time data, dynamic adjustment can be achieved, thereby significantly reducing false alarm and missed alarm rates and reducing the probability of traffic accidents (before the experiment in this embodiment, interaction analysis between single factors and multiple factors has been carried out, and multiple index data has been used as the original index data for road icing warning analysis. It is concluded that the factors having a greater impact on road icing warning are ambient temperature, road surface temperature, and ambient humidity. Therefore, in this embodiment, three parameters, namely ambient temperature, ambient humidity, and ambient wind speed, are used as parameters for icing prediction, which can overcome the defect of poor accuracy in predicting icing using a single meteorological element).

[0052] 3. Enhance adaptability and universality. Since Bayesian discriminant theory has strong adaptability in dealing with multi-dimensional and incomplete data, this method can be customized according to different climate and geographical conditions. Considering the convenience of actual use, the system can make predictions through simple three parameters and can dynamically adjust the Bayesian probability prediction model based on historical warning data, improving the adaptability and universality of the warning method.

[0053] Therefore, a road icing warning method based on Bayesian discrimination theory provided in this embodiment significantly improves the prediction accuracy, reduces the false alarm and missed alarm rates, and enhances the adaptability and practicability for predicting different climate and geographical environments by introducing more accurate multi-variable probability inference. These advantages effectively solve the key problems existing in the prior art, such as insufficient prediction accuracy, false alarms and missed alarms, and weak response adaptability, and can effectively improve traffic safety.

[0054] Based on the same inventive concept, the embodiment of the present application also provides a road icing warning system for implementing the road icing warning method involved above. The implementation solution for solving problems provided by this system is similar to the implementation solution described in the above method. Therefore, the specific limitations in the embodiment of the road icing warning system provided below can refer to the limitations on the road icing warning method in this embodiment, and will not be elaborated here.

[0055] Embodiment 2 As Figure 3 shown, this embodiment provides a road icing warning system, including: An environmental data acquisition module, configured to acquire real-time multi-dimensional weather data, where the multi-dimensional weather data includes environmental temperature, environmental humidity, and environmental wind speed.

[0056] The environmental data acquisition module includes a weather data acquisition unit; the weather data acquisition unit is configured to acquire real-time multi-dimensional weather data and transmit it to the prediction information processing module.

[0057] The multi-dimensional weather data includes environmental temperature, environmental humidity, and environmental wind speed.

[0058] This embodiment uses an environmental temperature and humidity detector and an environmental wind speed detector to acquire multi-dimensional weather data.

[0059] Environmental temperature and humidity detector: Measure the temperature and humidity of the near-surface atmosphere; based on the principle of long-wave infrared radiation, select the net heat flux within a certain wavelength range for measurement to measure the temperature and humidity of the road surface.

[0060] Environmental wind speed detector: Detect the environmental wind speed; use the time difference of ultrasonic signals propagating in the air to measure the wind speed. The ultrasonic anemometer will emit and receive ultrasonic waves, and the wind speed can be calculated by calculating the time difference of ultrasonic waves propagating in the downwind and upwind directions.

[0061] A prediction information processing module, configured to use the multi-dimensional weather data as input and output the road icing probability by using a pre-trained icing prediction model, where the icing prediction model is a Bayesian probability prediction model.

[0062] An early warning module, configured to determine whether to issue an icing early warning to road administrators and drivers according to the road icing probability.

[0063] The early warning module includes: an early warning judgment sub-module, an information release module, a mobile terminal sub-module, and a voice notification sub-module.

[0064] The early warning judgment sub-module is configured to: when the road icing probability is within the first preset early warning range, initiate a medium and low-level early warning; when the road icing probability is within the second preset early warning range, initiate a high-level early warning, where the second preset early warning range is greater than the first preset early warning range; when the road icing probability is within the third preset early warning range, initiate an emergency early warning, where the third preset early warning range is greater than the second preset early warning range. The information release sub-module is configured to release real-time icing early warning information on the road in the form of a road information screen or warning lights, etc.

[0065] The mobile terminal sub-module is configured to send the icing early warning information to the mobile devices of road management personnel or relevant drivers.

[0066] The voice broadcast sub-module is configured to give voice prompts to drivers according to the icing early warning information through an in-vehicle system or other devices to improve the visibility and audibility of the early warning.

[0067] The early warning module also feeds back historical early warning data to the prediction information processing module for learning.

[0068] Embodiment 3 This embodiment provides a computer device, which can be a server or a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data in the road icing early warning method. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it realizes a road icing early warning method in Embodiment 1.

[0069] Those skilled in the art can understand that Figure 4 The structure shown in Figure 4 is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0070] Embodiment 4 This embodiment provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, a road icing warning method in Embodiment 1 above is implemented.

[0071] Embodiment 5 This embodiment provides a computer program product including a computer program, and when the computer program is executed by a processor, a road icing warning method in Embodiment 1 above is implemented.

[0072] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0073] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0074] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0075] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0076] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for warning of road icing, characterized in that, The road icing warning method includes: Obtain real-time multi-dimensional weather data, where the multi-dimensional weather data includes ambient temperature, ambient humidity, and ambient wind speed; Use the multi-dimensional weather data as input and utilize a pre-trained icing prediction model to output the road icing probability, where the icing prediction model is a Bayesian probability prediction model; Judge whether to issue an icing warning based on the road icing probability.

2. The road icing warning method according to claim 1, wherein The pre-trained icing prediction model is regularly optimized according to historical model prediction data and actual icing data.

3. The road icing warning method according to claim 1, wherein, The trained icing prediction model adopts a discriminant function based on minimizing the misjudgment loss during the discrimination process. The expression of the discriminant function is: ； ； ； ； Among them, represents finding the overall to maximize the posterior probability; represents finding the overall to minimize the average loss of misclassification; represents the average loss of misclassification; represents the overall; and both represent the dimensional probability density functions under different ambient temperatures, ambient humidities, and ambient wind speeds; represents the value corresponding to the index in the th overall; g represents the total number of the overall; and represent the prior probability of the th overall; represents the input quantity, including the ambient temperature , ambient humidity and ambient wind speed ; represents the loss of misclassifying the sample of the th overall as the th overall.

4. The road icing warning method according to claim 1, characterized in that Judging whether to issue an icing warning according to the road icing probability specifically includes: When the road icing probability is less than the lower limit of the first preset warning probability range, no icing warning is issued; When the road icing probability is within the first preset warning range, initiate a medium and low-level warning; When the road icing probability is within the second preset warning range, initiate a high-level warning, where the second preset warning range is larger than the first preset warning range; When the road icing probability is within the third preset warning range, initiate an emergency warning, where the third preset warning range is larger than the second preset warning range.

5. A road icing warning system, characterized in that, The road icing warning system includes: An environmental data acquisition module for obtaining real-time multi-dimensional weather data, where the multi-dimensional weather data includes ambient temperature, ambient humidity, and ambient wind speed; A prediction information processing module for using the multi-dimensional weather data as input and utilizing a pre-trained icing prediction model to output the road icing probability, where the icing prediction model is a Bayesian probability prediction model; A warning module for judging whether to issue an icing warning based on the road icing probability.

6. The road icing warning system according to claim 5, characterized in that, The environmental data acquisition module includes: an environmental temperature and humidity detector and an environmental wind speed detector; The environmental temperature and humidity detector is used to collect the atmospheric temperature and atmospheric humidity near the ground, where the atmospheric temperature is the ambient temperature and the atmospheric humidity is the ambient humidity; The environmental wind speed detector is used to collect the ambient wind speed.

7. The road icing warning system according to claim 5, wherein The warning module includes: a warning judgment sub-module, an information release module, a mobile terminal sub-module, and a voice announcement sub-module; The warning judgment sub-module is used for: When the road icing probability is within the first preset warning range, initiate a medium and low-level warning; When the road icing probability is within the second preset warning range, initiate a high-level warning, where the second preset warning range is larger than the first preset warning range; When the road icing probability is within the third preset warning range, initiate an emergency warning, where the third preset warning range is larger than the second preset warning range; The information release sub-module is used to release real-time icing warning information; The mobile terminal sub-module is used to send the icing warning information to the mobile devices of road management personnel or relevant drivers; The voice broadcast sub-module is used to give voice prompts according to the icing warning information.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the road icing warning method according to any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the road icing warning method according to any one of claims 1-4.

Images