Safe driving early warning system based on big data and machine learning

Abstract

The invention discloses a safe driving early warning system based on big data and machine learning, and the system comprises the following steps: S1, data collection: collecting the vehicle position, parking time, vehicle door state, vehicle type and other data in real time through a roadside sensing device, and obtaining environment context information, such as road type, traffic flow, weather condition and other data; s2, data processing and fusion: matching and associating the real-time data acquired in S1 with historical data by using a multi-source data fusion technology, and constructing a complete vehicle behavior data set; s3, establishing a risk assessment model: inputting model related data based on a machine learning algorithm, constructing a door opening risk prediction model, and obtaining a probability value Pdoopen that the model output is a door opening behavior; s4, early warning: when a model early warning value is set to be Pthreshold and a probability value is greater than or equal to the early warning value, early warning about the door opening condition of a front parked vehicle is given to a rear vehicle through a vehicle-road cooperation system; the early warning system can effectively reduce the occurrence of traffic accidents.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle-road cooperative systems, and specifically relates to a safe driving warning system based on big data and machine learning. Background Art

[0002] Vehicle-road collaboration uses advanced wireless communications and new-generation Internet technologies to implement all-round dynamic real-time information interaction between vehicles and roads, and carries out vehicle active safety control and road collaborative management based on the collection and integration of dynamic traffic information in all time and space. The road test perception equipment and perception methods of the vehicle-road collaboration system require the conversion of various road environment information for vehicles installed with the vehicle-road collaboration system in advance.

[0003] The traffic risk warnings of existing roadside sensing equipment mostly focus on predicting collision risks when the vehicle is in motion, but lack an effective reminder mechanism for the risk of opening doors when the vehicle is parked. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, a safe driving warning system based on big data and machine learning is proposed. The present invention uses real-time data from roadside sensing equipment and historical vehicle data to predict door opening risks, reminding vehicles behind to avoid, thereby reducing the occurrence of traffic accidents.

[0005] The technical solution adopted by the present invention is to provide a safe driving warning system based on big data and machine learning, including the following steps: S1 Data Collection: Roadside sensing equipment collects real-time data such as vehicle location, parking time, door status, vehicle type, and environmental context information such as road type, traffic flow, and weather conditions. S2, data processing and fusion: Using multi-source data fusion technology, the real-time data collected by S1 is matched and correlated with historical data to build a complete vehicle behavior dataset; S3, establish a risk assessment model: Based on the machine learning algorithm, input the model-related data, build a door opening risk prediction model, and obtain the model output as the probability value of the door opening behavior P door_open ; S4, warning: set the model warning value to P threshold When the probability value is greater than or equal to the warning value, the vehicle-road cooperative system will issue a warning to the rear vehicle that the door of the parked vehicle in front is open.

[0006] Preferably, the vehicle position in step S1 is the precise position of the vehicle in the parking space; the parking time is the real-time accumulated parking time; the door status is determined by image processing technology to determine whether the door is open; and the vehicle type is AI-based vehicle type recognition.

[0007] Preferably, the historical data in step S2 is derived from a historical database; the historical data is the vehicle's previous parking behavior data, including statistical information such as parking time distribution and probability of door opening behavior.

[0008] Preferably, the machine learning algorithm in step S3 may adopt a supervised learning algorithm of random forest or XGBoost; the model-related data is the data set of step S2; the data set includes parking time, door opening history probability, vehicle type, road type and traffic flow.

[0009] Preferably, the probability value of the door opening behavior in step S4 is P door_open The calculation formula is as follows: P door_open =f(parking time, door opening history probability, vehicle type, road type, traffic flow), where f is the machine learning model; based on the real-time data updated by the roadside perception equipment, calculate the current vehicle's P door_open , when P door_open ≥P threshold , a warning message is generated and sent to the vehicle behind, suggesting slowing down or changing lanes.

[0010] Preferably, the warning value in step S4 is set based on historical data analysis.

[0011] The beneficial effects of the present invention are:

[0012] The present invention uses roadside sensing equipment to collect data in real time, combines it with historical behavior data, and constructs a door opening risk assessment model based on big data and machine learning. It can predict the probability of door opening of the vehicle parked in front. When the predicted door opening probability is greater than or equal to the warning value, the roadside sensing equipment generates a warning message and sends it to the vehicle behind through the vehicle-road cooperative system to remind the driver to slow down or change lanes. The use of this warning system can effectively reduce traffic accidents with parked vehicles on the roadside. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a flow chart of a safe driving warning system based on big data and machine learning as described in the present invention. DETAILED DESCRIPTION

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. The components of the embodiments of the present invention generally described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0015] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0016] Unless otherwise defined, technical or scientific terms used in this patent document shall have the ordinary meanings understood by persons of ordinary skill in the art to which this invention belongs. The terms "first," "second," and similar expressions used in the specification and claims of this invention do not denote any order, quantity, or importance, but are merely used to distinguish one component from another. Similarly, terms such as "a," "an," or "the" do not denote a limitation of quantity, but rather denote the presence of at least one. Terms such as "include" or "comprising" mean that the elements or objects preceding the phrase "include" or "comprising" include the elements or objects listed after the phrase and their equivalents, and do not exclude other elements or objects. Terms such as "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" are used solely to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. These terms are used solely to facilitate the description of the invention and to simplify the description. They are not intended to indicate or imply that the device or component referred to must have, be constructed, or operate in a specific orientation, and are not to be construed as limitations on the invention.

[0017] The following describes some embodiments of the present invention in detail with reference to the accompanying drawings. In the absence of conflict, the features of the following embodiments can be combined with each other.

[0018] Specifically, such as Figure 1 As shown, a safe driving warning system based on big data and machine learning is provided, including the following steps: S1 Data Collection: Roadside sensing equipment collects real-time data such as vehicle location, parking time, door status, vehicle type, and environmental context information, such as road type, traffic flow, and weather conditions. The vehicle location is the precise location of the vehicle in the parking space; the parking time is the real-time accumulated parking time; the door status is determined by image processing technology to determine whether the door is open; and the vehicle type is AI-based vehicle type recognition. S2, Data Processing and Fusion: Using multi-source data fusion technology, the real-time data collected in S1 is matched and correlated with historical data to construct a complete vehicle behavior dataset. The historical data comes from a historical database and contains the vehicle's past parking behavior data, including statistical information such as parking time distribution and door opening probability. S3, establish a risk assessment model: Based on the machine learning algorithm, input the model-related data, build a door opening risk prediction model, and obtain the model output as the probability value of the door opening behavior P door_open The machine learning algorithm may adopt a supervised learning algorithm such as random forest or XGBoost; the model-related data is the data set of step S2; the data set mainly includes parking time, door opening history probability, vehicle type, road type and traffic flow; S4, warning: set the model warning value to P threshold When the probability value is greater than or equal to the warning value, the vehicle-road cooperative system will issue a warning to the rear vehicle that the door of the parked vehicle in front is open; the probability value P of the door opening behavior door_open The calculation formula is as follows: door_open =f(parking time, door opening history probability, vehicle type, road type, traffic flow), where f is the machine learning model; based on the real-time data updated by the roadside perception equipment, calculate the current vehicle's P door_open , when P door_open ≥P threshold , a warning message is generated and sent to the vehicle behind, suggesting slowing down or changing lanes; the warning value is set based on historical data analysis.

[0019] The data set of step S2 includes real-time data and historical data; the real-time data includes parking time, vehicle type, door status, vehicle type, roadside environment, etc.; the historical data includes vehicle parking time distribution, door opening probability distribution, driver behavior habits, etc.; according to the supervised learning algorithm of random forest or XGBoost, model-related data selects several main parameters from the data set and imports them into the model. The main parameters include parking time, door opening history probability, vehicle type, road type and traffic flow.

[0020] In step S4, when the probability value is greater than or equal to the warning value, the roadside sensing device generates a warning message and sends it to the vehicle behind through the vehicle-road cooperative system to remind the owner to slow down or change lanes; when the probability value is less than the warning value, the roadside sensing device does not generate a warning message, and returns to step S3 to continue monitoring the door opening of the vehicle in front.

[0021] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from all perspectives, the embodiments should be regarded as illustrative and non-restrictive. The scope of the present invention is defined by the appended claims rather than the foregoing description, and it is intended that all changes that come within the meaning and range of equivalents of the claims be included in the present invention. Any reference signs in the claims should not be construed as limiting the claim to which they relate.

Claims

1. A safe driving warning system based on big data and machine learning, characterized by: The following steps are included: S1 Data Collection: Roadside sensing equipment collects real-time data such as vehicle location, parking time, door status, vehicle type, and environmental context information such as road type, traffic flow, and weather conditions. S2, data processing and fusion: Using multi-source data fusion technology, the real-time data collected by S1 is matched and correlated with historical data to build a complete vehicle behavior dataset; S3, establish a risk assessment model: Based on the machine learning algorithm, input the model-related data, build a door opening risk prediction model, and obtain the model output as the probability value of the door opening behavior P door_open ; S4, warning: set the model warning value to P threshold When the probability value is greater than or equal to the warning value, the vehicle-road cooperative system will issue a warning to the rear vehicle that the door of the parked vehicle in front is open.

2. The safe driving warning system based on big data and machine learning according to claim 1, characterized in that: The vehicle position in step S1 is the precise position of the vehicle in the parking space; the parking time is the real-time accumulated parking time; The door status is determined by image processing technology to determine whether the door is open; the vehicle type is identified based on AI.

3. The safe driving warning system based on big data and machine learning according to claim 1, characterized in that: The historical data in step S2 is derived from a historical database; the historical data is the vehicle's previous parking behavior data, including statistical information such as parking time distribution and door opening behavior probability.

4. The safe driving warning system based on big data and machine learning according to claim 1, characterized in that: The machine learning algorithm in step S3 may adopt a supervised learning algorithm such as random forest or XGBoost; the model-related data is the data set of step S2; the data set includes parking time, door opening history probability, vehicle type, road type and traffic flow.

5. The safe driving warning system based on big data and machine learning according to claim 1, characterized in that: The probability value of the door opening behavior in step S4 is P door_open The calculation formula is as follows: P door_open =f(parking time, door opening history probability, vehicle type, road type, traffic flow), where f is the machine learning model; based on the real-time data updated by the roadside perception equipment, calculate the current vehicle's P door_open , when P door_open ≥P threshold , a warning message is generated and sent to the vehicle behind, suggesting slowing down or changing lanes.

6. The safe driving warning system based on big data and machine learning according to claim 5, characterized in that: The warning value in step S4 is set based on historical data analysis.

Images