CN-120220421-B - Traffic event dynamic risk prediction method, system, electronic equipment and storage medium

CN120220421BCN 120220421 BCN120220421 BCN 120220421BCN-120220421-B

Abstract

The embodiment of the application provides a traffic event dynamic risk prediction method, a system, electronic equipment and a storage medium, wherein the method comprises the steps of determining a vehicle running behavior and at least one event output type corresponding to the vehicle running behavior, wherein the vehicle running behavior is determined by a preset association relation among a plurality of vehicle running data; the method comprises the steps of obtaining first data, carrying out data fusion on the event output type and the first data to output a first result, and responding to the first result to output at least one traffic event dynamic risk prediction result corresponding to the first result. The embodiment of the application can realize comprehensive perception of traffic events, and remarkably enhances the intelligent reasoning capability of complex scenes, thereby ensuring that the dynamic risk prediction of the traffic events is more accurate and reliable.

Inventors

Cai Mouli
HAN KEWEI
XIE ZHIYU
SHEN FUMIN
SHEN HENGTAO

Assignees

南京码极客科技有限公司
成都考拉悠然科技有限公司

Dates

Publication Date: 20260512
Application Date: 20250507

Claims (7)

1. A method for traffic event dynamic risk prediction, the method comprising: determining a vehicle running behavior and at least one event output type corresponding to the vehicle running behavior, wherein the vehicle running behavior is determined by a preset association relationship among a plurality of vehicle running data; Acquiring first data; carrying out data fusion on the event output type and the first data to output a first result; outputting at least one traffic event dynamic risk prediction result corresponding to the first result in response to the first result; the traffic event dynamic risk prediction result is obtained through the following steps: editing each risk level pointed by the first result; Obtaining a risk level classification result based on the first result as the traffic event dynamic risk prediction result; The risk level is obtained by the following steps: The method comprises the steps of outputting a first response result in response to the relative distance between a target vehicle and a third-party vehicle in the first result, dividing the risk level into low risks when the relative distance between the target vehicle and the third-party vehicle in the first result is larger than the safety distance, dividing the risk level into medium risks when the relative distance between the target vehicle and the third-party vehicle in the first result is smaller than or equal to the safety distance, and dividing the risk level into high risks when the relative distance between the target vehicle and the third-party vehicle in the first result is equal to or smaller than the alarm distance; The second stage responds to a preset influence factor to output a second response result, compares the second response result based on the first response result and outputs a risk level with a higher level; Wherein the preset influence factor is obtained based on the first data.
2. The method of claim 1, wherein the vehicle travel behavior is determined by: Acquiring vehicle driving data; Editing corresponding preset association relations of the driving data of each vehicle; And determining the vehicle driving behavior based on a preset association relation between the vehicle driving data.
3. The method of claim 1, wherein the first data comprises vehicle travel speed data, vehicle travel lane flow data, vehicle travel lane density data, vehicle travel track data, weather data, and map information data.
4. The method of claim 1, wherein the data fusing the event output type with the first data outputs a first result, comprising: preprocessing the first data to obtain a first sub-processing result; and inputting the event output type and the first sub-processing result into a trained large model together to obtain a first data output result.
5. A traffic event dynamic risk prediction system for performing the method of any one of claims 1 to 4, comprising: The system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring vehicle running behaviors and at least one event output type corresponding to the vehicle running behaviors, wherein the vehicle running behaviors are determined by preset association relations among a plurality of vehicle running data; and is used for obtaining the first data; and the data processing module performs data fusion on the event output type and the first data to output a first result, and responds to the first result to output at least one traffic event dynamic risk prediction result corresponding to the first result.
6. An electronic device, comprising: a processor and a memory storing a program, Wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method of any of claims 1 to 4.
7. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to perform the method according to any of claims 1 to 4.

Description

Traffic event dynamic risk prediction method, system, electronic equipment and storage medium Technical Field The embodiment of the application relates to the technical field of intelligent traffic systems, in particular to a traffic event dynamic risk prediction method, a system, electronic equipment and a storage medium. Background In recent years, with the rapid expansion of expressway networks and the increase of the number of motor vehicles, traffic accidents, especially accidents caused by improper driving behaviors, are a serious threat to public safety. In order to reduce the loss caused by traffic accidents, intelligent traffic systems are becoming a research hotspot. CN115841252a discloses a "method for evaluating running risk of expressway based on predicted track", which obtains vehicle position information through networking platform, predicts movement track of vehicle based on the vehicle position information, so as to judge that there is no potential risk in interaction behavior between self vehicle and side vehicle, and then sends out risk early warning prompt according to risk level. However, the judgment of the prior art facing the complex scene is not accurate, and collision risk assessment cannot be performed, so that the judgment of the expressway traffic event lacks reliability. CN114267173a discloses a "multisource data fusion method, device and equipment for space-time characteristics of expressways", which realizes fusion of various multisource heterogeneous sensor data, retains special time and space characteristics of traffic data, constructs holographic traffic data into travel service oriented to safety and efficiency, determines risk level according to traffic flow state division standards according to various levels of service of expressways in China, but only considers traffic circulation state to make judgment standard single, and has no practicality in the face of more complex and changeable real running environments. Based on the above prior art, the risk level judgment standard of a single data source (such as a camera or a sensor) or a single traffic event is generally relied on, so that the understanding capability of a complex traffic scene is limited, and accurate research and judgment are difficult to realize. In addition, the high-efficiency reasoning capability is lacking, so that the multi-mode data cannot be subjected to deep fusion and comprehensive analysis, and only a single-mode or simple rule scene can be analyzed, so that the intelligent level is low and the precision is poor. The method has obvious defects in the aspects of joint reasoning of multi-source data and risk dynamic planning, and meanwhile, the prior art lacks comprehensive modeling of vehicle tracks, driving behaviors and environmental factors, and is difficult to recognize accident risks in advance and quantify risk grades. Under complex dynamic scenes (such as extreme weather, high-speed running and the like), the existing system is difficult to deal with vehicle track prediction and collision risk assessment, and cannot realize comprehensive perception of traffic events, so that the traffic event dynamic risk prediction has no reliability. Disclosure of Invention In view of the above, embodiments of the present application provide a traffic event dynamic risk prediction method, system, electronic device and storage medium, so as to at least partially solve the above problems. According to a first aspect of an embodiment of the application, a traffic event dynamic risk prediction method is provided, and the method comprises the steps of determining vehicle driving behaviors and at least one event output type corresponding to the vehicle driving behaviors, wherein the vehicle driving behaviors are determined by preset association relations among a plurality of vehicle driving data, acquiring first data, carrying out data fusion on the event output types and the first data to output a first result, and responding to the first result to output at least one traffic event dynamic risk prediction result corresponding to the first result. According to a second aspect of the embodiment of the application, a traffic event dynamic risk prediction system is provided, which comprises an acquisition module, a data processing module and a traffic event dynamic risk prediction module, wherein the acquisition module is used for acquiring vehicle driving behaviors and at least one event output type corresponding to the vehicle driving behaviors, the vehicle driving behaviors are determined by a preset association relation among a plurality of vehicle driving data, the data processing module is also used for acquiring first data, and the data processing module is used for carrying out data fusion on the basis of the event output types and the first data to output a first result, and outputting at least one traffic event dynamic risk prediction result corresponding to the first result in response to the first r