CN-121982909-A - Traffic control method, device, equipment and medium based on multi-source data fusion

CN121982909ACN 121982909 ACN121982909 ACN 121982909ACN-121982909-A

Abstract

The embodiment of the invention discloses a traffic control method, a traffic control device, traffic control equipment and traffic control media based on multi-source data fusion. The method comprises the steps of obtaining internal traffic flow data and external linkage data in real time, fusing the obtained internal traffic flow data and the obtained external linkage data to obtain fused data flows, conducting flow prediction on the obtained fused data flows to obtain first prediction results, conducting risk prediction on the obtained fused data flows to obtain second prediction results, conducting collaborative decision on the basis of the obtained first prediction results and the second prediction results to obtain a structured strategy instruction set, conducting task decomposition on the obtained structured strategy instruction set to obtain task information, and controlling traffic control equipment on the basis of the obtained task information. The implementation mode provides a feasible core technical scheme for constructing a new generation of intelligent and cooperated urban traffic management system.

Inventors

SUI ZONGBIN
FAN WEI
YUAN WEN

Assignees

中关村科学城城市大脑股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260123

Claims (9)

1. A traffic control method based on multi-source data fusion comprises the following steps: acquiring internal traffic flow data and external linkage data in real time; fusing the acquired internal traffic flow data with external linkage data to obtain a fused data flow; carrying out flow prediction on the obtained fusion data flow to obtain a first prediction result, wherein the obtained first prediction result comprises traffic flow prediction values, speed prediction values and congestion probability prediction values of all nodes; carrying out risk prediction on the obtained fusion data stream to obtain a second prediction result, wherein the obtained second prediction result comprises accident risk probabilities of all road sections; Based on the obtained first prediction result and second prediction result, making a collaborative decision to obtain a structured policy instruction set; performing task decomposition on the obtained structured policy instruction set to obtain each task information; and controlling each traffic control device based on the obtained task information.
2. The method of claim 1, wherein the acquired internal traffic flow data includes traffic flow information, vehicle speed information, positioning information, and signal light status information, and the acquired external linkage data includes large activity information, planned events, and regulatory requirement information.
3. The method of claim 1, wherein the fusing the acquired internal traffic flow data with external linkage data to obtain a fused data flow comprises: carrying out standardized processing on the acquired internal traffic flow data to obtain standardized traffic data; carrying out structuring treatment on the obtained external linkage data to obtain structured event data; And carrying out space-time correlation processing on the obtained standardized traffic data and the structured event data to obtain a fusion data stream.
4. The method of claim 1, wherein the performing traffic prediction on the obtained merged data stream to obtain a first prediction result includes: extracting historical features of the obtained fusion data stream to obtain a historical traffic feature sequence; extracting real-time characteristics of the obtained fusion data stream to obtain a real-time traffic characteristic sequence; Extracting future event feature vectors from the obtained fusion data stream to obtain event feature vectors; carrying out space-time diagram convolution processing on the obtained historical traffic feature sequence, the real-time traffic feature sequence and the event feature vector to obtain space-time fusion features; forward prediction processing is carried out on the obtained space-time fusion characteristics, and a preliminary prediction result is obtained; and calibrating the obtained preliminary prediction result to obtain a first prediction result.
5. The method of claim 1, wherein the performing risk prediction on the obtained fused data stream to obtain a second prediction result includes: And extracting flow characteristics of the obtained fusion data stream to obtain a flow characteristic sequence. And extracting the speed characteristics of the obtained fusion data stream to obtain a speed characteristic sequence. And extracting the fluctuation characteristics of the obtained fusion data stream to obtain a fluctuation characteristic sequence. ; acquiring historical accident data; extracting environmental correlation features of the acquired historical accident data and the acquired fusion data stream to obtain environmental risk features, wherein the acquired environmental risk features comprise historical environmental risk features and real-time environmental risk features; carrying out risk reasoning on the obtained flow characteristic sequence, speed characteristic sequence, fluctuation characteristic sequence and environment risk characteristic to obtain initial risk probability; And carrying out time smoothing on the obtained initial risk probability to obtain a second prediction result.
6. The method of claim 1, wherein the collaborative decision-making based on the obtained first and second predictions results in a structured policy instruction set, comprising: carrying out weighted fusion processing on the obtained first prediction result and the second prediction result to obtain a comprehensive traffic situation map; Constructing a digital twin decision-making environment based on the obtained comprehensive traffic situation map; In the constructed digital twin decision environment, intelligent body modeling is carried out on each intersection signal lamp and each variable lane; performing collaborative strategy exploration on each modeled agent to obtain a candidate strategy set; performing microscopic traffic simulation processing on each candidate strategy in the obtained candidate strategy set to obtain a simulation result; extracting performance indexes from the obtained simulation results to obtain execution performance indexes; extracting risk indexes from the obtained simulation results to obtain execution risk indexes; performing multi-objective evaluation processing on each candidate strategy in the obtained candidate strategy set based on the obtained execution efficiency index and the execution risk index to obtain a strategy evaluation sequence; Sequencing the obtained strategy evaluation sequences to obtain target strategy sequences; And carrying out coding and packaging processing on the obtained target strategy sequence to obtain a structured strategy instruction set.
7. A traffic management and control device based on multi-source data fusion, comprising: An acquisition unit configured to acquire internal traffic flow data and external linkage data in real time; The fusion unit is configured to fuse the acquired internal traffic flow data with external linkage data to obtain a fusion data flow; The first prediction unit is configured to conduct flow prediction on the obtained fusion data flow to obtain a first prediction result, wherein the obtained first prediction result comprises traffic flow prediction values, speed prediction values and congestion probability prediction values of all nodes; The second prediction unit is configured to perform risk prediction on the obtained fusion data stream to obtain a second prediction result, wherein the obtained second prediction result comprises accident risk probabilities of all road sections; The decision unit is configured to carry out collaborative decision based on the obtained first prediction result and the second prediction result to obtain a structured strategy instruction set; the decomposition unit is configured to perform task decomposition on the obtained structured policy instruction set to obtain each task information; and the control unit is configured to control each traffic control device based on the obtained task information.
8. An electronic device, comprising: One or more processors; A storage device having one or more programs stored thereon; when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1 to 6.
9. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1 to 6.

Description

Traffic control method, device, equipment and medium based on multi-source data fusion Technical Field The embodiment of the disclosure relates to the technical field of computers, in particular to a traffic control method, a traffic control device, traffic control equipment and traffic control media based on multi-source data fusion. Background With the continuous rise of the intelligent demands of urban traffic management, traffic control systems have evolved from early fixed timing signal control to adaptive control based on real-time sensing (e.g., SCATS, SCOOT systems). The existing mainstream system collects real-time traffic flow data through deployment of detectors such as coils and radars, and dynamically optimizes signal timing of a single intersection or main road by using a mathematical model. Some advanced systems also attempt to access more data sources (e.g., GPS floating car, video surveillance) to enhance situational awareness. However, the prior art solutions still have fundamental limitations when dealing with complex, dynamic urban traffic challenges. Firstly, the system generally depends on historical and real-time traffic flow data, and event data reflecting future traffic demand rapid changes from external systems such as ticketing, police service and large-scale activity management are difficult to effectively fuse, so that decision making lacks predictability, and prospective resource allocation cannot be performed for known large-scale events (such as concert scattered fields). Secondly, most of optimization cores of the intelligent traffic control system are classical control models or simple prediction algorithms, two key targets of traffic efficiency (flow and congestion) and safety (accident risk) are difficult to process simultaneously and cooperatively, and collaborative strategies of crossing and crossing control means (signals, lanes and induction) cannot be simulated and optimized in a digital environment. Finally, a significant gap exists between the generation strategy and the actual change of the physical world state, namely the existing architecture lacks a standardized closed-loop execution mechanism for automatically analyzing, decomposing and driving heterogeneous traffic control equipment (such as signal lamps, variable lane marks and information boards) to cooperatively act, and the existing architecture seriously depends on manual intervention and multi-system manual operation, has slow response and poor synergy. The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country. Disclosure of Invention The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Some embodiments of the present disclosure propose traffic management methods, apparatus, electronic devices, and computer-readable media based on multi-source data fusion to address one or more of the technical problems mentioned in the background section above. In a first aspect, some embodiments of the present disclosure provide a traffic control method based on multi-source data fusion, which includes obtaining internal traffic flow data and external linkage data in real time, fusing the obtained internal traffic flow data and the obtained external linkage data to obtain a fused data flow, performing flow prediction on the obtained fused data flow to obtain a first prediction result, wherein the obtained first prediction result includes traffic flow prediction values, speed prediction values and congestion probability prediction values of all nodes, performing risk prediction on the obtained fused data flow to obtain a second prediction result, wherein the obtained second prediction result includes accident risk probability of all road segments, performing collaborative decision based on the obtained first prediction result and the obtained second prediction result to obtain a structured policy instruction set, performing task decomposition on the obtained structured policy instruction set to obtain all task information, and controlling all traffic control devices based on all obtained task information. In a second aspect, some embodiments of the present disclosure provide a traffic control device based on multi-source data fusion, which includes an acquisition unit configured to acquire internal traffic flow data and external linkage data in real time, a fusion unit configured to fuse the acquired internal traffic flow data and the external linkage data to obtain a fused data flow, a first prediction unit configured