WO2023000548A1 - 交通拥堵事件的处理方法、设备、存储介质及程序产品 - Google Patents

交通拥堵事件的处理方法、设备、存储介质及程序产品 Download PDF

Info

Publication number
WO2023000548A1
WO2023000548A1 PCT/CN2021/129463 CN2021129463W WO2023000548A1 WO 2023000548 A1 WO2023000548 A1 WO 2023000548A1 CN 2021129463 W CN2021129463 W CN 2021129463W WO 2023000548 A1 WO2023000548 A1 WO 2023000548A1
Authority
WO
WIPO (PCT)
Prior art keywords
congestion
event
events
causative
correlation
Prior art date
Application number
PCT/CN2021/129463
Other languages
English (en)
French (fr)
Inventor
张军
史林涛
曲海龙
Original Assignee
阿波罗智联(北京)科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿波罗智联(北京)科技有限公司 filed Critical 阿波罗智联(北京)科技有限公司
Priority to KR1020227014625A priority Critical patent/KR20220063289A/ko
Publication of WO2023000548A1 publication Critical patent/WO2023000548A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation

Definitions

  • the present disclosure relates to fields such as intelligent transportation and automatic driving in computer technology, and in particular to a processing method, device, storage medium and program product for a traffic jam event.
  • the traditional method of determining the cause of traffic congestion is mainly based on the human judgment of the traffic police, which often fails to deal with it in time and cannot alleviate the traffic congestion in a timely manner, resulting in low efficiency of traffic congestion management.
  • the present disclosure provides a processing method, device, storage medium and program product of a traffic jam event.
  • a method for processing a traffic jam event including:
  • the causative event corresponding to the congestion event is determined according to the confidence degree of association between each causative event and the congestion event.
  • a processing device for a traffic jam event including:
  • the data synchronization module is used to obtain the data of the congestion event and the data of the cause event from the map data, wherein the cause event includes multiple types of events that occur on the road and cause traffic congestion;
  • An association confidence determination module for each of the congestion events, according to the data of the congestion event and the data of each of the causative events, determine the confidence of the association between each of the causative events and the congestion event;
  • the event correlation module is configured to determine the causal event corresponding to the congestion event according to the confidence degree of association between each causal event and the congestion event.
  • an electronic device including:
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the method described in the first aspect.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect.
  • a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device can read from the The computer program is read by reading the storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect.
  • the technology according to the present disclosure can timely and accurately determine the cause of traffic congestion, and improves the efficiency of traffic congestion control.
  • Fig. 1 is a scene diagram that can realize the traffic jam event processing of the embodiment of the present disclosure
  • FIG. 2 is a flow chart of a processing method for a traffic congestion event provided by the first embodiment of the present disclosure
  • FIG. 3 is a flow chart of a method for processing a traffic congestion event provided by the second embodiment of the present disclosure
  • Fig. 4 is an example diagram of a data query interface provided by the second embodiment of the present disclosure.
  • Fig. 5 is an example diagram of displaying congestion data query results provided by the second embodiment of the present disclosure.
  • FIG. 6 is an example diagram of the architecture of a method for processing a traffic jam event that can implement an embodiment of the present disclosure
  • FIG. 7 is a schematic diagram of a processing device for a traffic jam event provided by a third embodiment of the present disclosure.
  • FIG. 8 is a schematic diagram of a processing device for a traffic jam event provided by a fourth embodiment of the present disclosure.
  • Fig. 9 is a schematic block diagram of an electronic device that can implement the method for processing a traffic jam event according to an embodiment of the present disclosure.
  • the present disclosure provides a processing method, device, storage medium and program product for traffic congestion events, which relate to the fields of intelligent transportation and automatic driving in computer technology, to accurately determine the cause of traffic congestion events, and to alleviate traffic congestion in a timely manner. Provide data basis to improve the efficiency of traffic congestion management.
  • the method for processing traffic jam events provided by this disclosure can be specifically applied to the application scenario shown in Figure 1.
  • the map data provided by the map application 10 includes the data of traffic jam events that occur on the road, and the traffic jam events that may occur on the road that may cause Data on various causative events of traffic congestion.
  • the electronic device 11 for processing the traffic jam event can obtain the data of the congestion event and the data of the cause event from the map data, and perform analysis and processing of the cause of the congestion according to the data of the congestion event and the data of the cause event to determine the congestion The causal event corresponding to the event, so as to determine the cause of the congestion event (causal event).
  • the corresponding causative event of the congestion event can be displayed in the map application, and/or, according to the causative event corresponding to each congestion event, a congestion data report is generated and sent, so that Relevant personnel can avoid the congestion according to the causative event corresponding to the congestion event, or clear the congested road section in time to alleviate the traffic congestion, which can improve the efficiency of traffic congestion management.
  • Fig. 2 is a flowchart of a method for processing a traffic congestion event provided by the first embodiment of the present disclosure.
  • the traffic congestion event processing method provided in this embodiment may specifically be an electronic device for analyzing and processing the cause of the traffic congestion event, and may be a terminal device or a server running a map application. In other embodiments, the electronic device may also be implemented in other manners, which are not specifically limited in this embodiment.
  • Step S201 Obtain data of congestion events and data of causative events from map data, where causative events include various types of events that occur on roads and cause traffic jams.
  • the map data may be map data provided by a map application, including data of congestion events occurring on the road, and causative events occurring on the road that may cause traffic congestion.
  • Congestion events may include road congestion events and intersection congestion events.
  • the data of road congestion events may include: congestion start time, congestion end time, congestion source coordinates, and a set of congestion source coordinates.
  • the congestion source coordinates refer to the key coordinate points where the road congestion event occurs, and a road congestion event can include one or more congestion source coordinates.
  • the congestion source coordinate set includes many coordinate points where the road congestion event occurs. After being rendered on the map, a line segment is formed, that is, the congestion source coordinate connection line of the road congestion event is composed of coordinate points in the congestion source coordinate set.
  • the data of the road congestion event can also include: event identification (such as event number, etc.), congestion type, congestion location description, congestion duration, road number, road name, road type and road direction of the road where the congestion is located, congestion distance, Congestion index, average speed of vehicles on congested road sections, etc.
  • event identification such as event number, etc.
  • congestion type such as event number, etc.
  • congestion location description such as congestion location description
  • congestion duration such as road number, road name, road type and road direction of the road where the congestion is located
  • congestion distance such as Congestion index, average speed of vehicles on congested road sections, etc.
  • the congestion type of the road congestion event includes abnormal congestion or regular congestion
  • regular congestion refers to regular congestion
  • abnormal congestion refers to non-recurring congestion that bursts out relative to normal congestion. For example, when congestion occurs for the first time, it will be set as abnormal congestion. When the same congestion occurs for a certain number of times, it will be set as normal congestion.
  • the road type of the road where the congestion is located includes: expressway, ring road and expressway, trunk, secondary trunk, branch trunk, etc.
  • the road direction refers to the driving direction of the vehicle on the road.
  • the congestion index is used to measure whether the current congestion is serious.
  • the data of the intersection congestion event may include: congestion start time, congestion end time, congestion type, intersection number, intersection name and intersection coordinates of the intersection where the congestion is located.
  • the congestion type of the intersection congestion event includes an intersection deadlock event and an intersection overflow event.
  • the crossing deadlock event refers to that the entrance and exit roads of the crossing are all congested seriously.
  • the overflow event means that the congestion of the entrance road or the exit road of the intersection is not serious.
  • an intersection deadlock event means that the average vehicle speed of the entrance and exit roads at the intersection is less than the preset speed threshold
  • an overflow event means that the average vehicle speed of the intersection entrance or exit road is greater than or equal to the preset speed threshold.
  • the preset speed threshold can be set and adjusted according to the needs of actual application scenarios, and is not specifically limited here.
  • intersection coordinates of the intersection where the congestion is located may be the center point coordinates of the intersection, or the latitude and longitude coordinates.
  • the data of the intersection congestion event may also include: event identifier (such as event number), congestion duration, congestion distance, congestion index, average speed of vehicles on the congested section, and the like.
  • event identifier such as event number
  • congestion duration such as congestion duration
  • congestion distance such as congestion distance
  • congestion index such as average speed of vehicles on the congested section
  • the causative events include various types of events that occur on the road and cause traffic jams.
  • the data of the causative event may include: event identifier (eg, event number), event start time, event end time, coordinates of the causative event, description of the location of the causative event, type of the causative event, and the like.
  • the types of causative events include, but are not limited to: traffic accidents, faulty vehicles, water accumulation on roads, heavy fog, icy roads, snow accumulation on roads, road construction, traffic control, and dangerous road sections.
  • Step S202 for each congestion event, according to the data of the congestion event and the data of each causative event, determine the correlation confidence between each causative event and the congestion event.
  • each cause event is associated with each congestion event, and the confidence degree of association between each cause event and the congestion event is determined.
  • the confidence degree of the association between the causal event and the congestion event indicates the degree of association between the causal event and the congestion event.
  • the time and location of the congestion time and the time and location of each causal event can be used to determine the cause from the aspects of temporal correlation and spatial correlation. Analysis of the degree of association between events and congestion events, and determine the degree of confidence in the association between causative events and congestion events.
  • Step S203 according to the correlation confidence between each causative event and the congestion event, determine the causative event corresponding to the congestion event.
  • the causal event corresponding to the congestion event may be determined according to the correlation confidence between each causal event and the congestion event.
  • the causal event with the highest correlation confidence with the congestion event may be determined as the causal event corresponding to the congestion event.
  • the confidence threshold can be set and adjusted according to the needs of actual application scenarios, and is not specifically limited here.
  • Fig. 3 is a flowchart of a method for processing a traffic congestion event provided by the second embodiment of the present disclosure.
  • multiple causal analysis strategies and a confidence coefficient corresponding to each causal analysis strategy are preset.
  • determine the correlation confidence between each cause event and the congestion event including: for each congestion event, adopt at least one cause analysis strategy, according to According to the data of congestion events and the data of each causal event, determine the time correlation and spatial correlation between each causal event and the congestion event; according to the confidence coefficient corresponding to each causal analysis strategy, and the The time correlation and spatial correlation between each causative event and the congestion event determine the correlation confidence between each causal event and the congestion event.
  • Step S301 acquiring data of congestion events and data of causative events from the map data, wherein the causative events include various types of events that occur on roads and cause traffic jams.
  • the congestion event data and the causal event data in the previous period can be regularly obtained from the map data, and the congestion event corresponding to the congestion event can be determined in a timely manner according to the congestion event data and the causative event data in the previous period.
  • Causative events so that relevant personnel can formulate timely and effective control strategies according to the causative events corresponding to the congestion events in the previous period, so as to alleviate traffic congestion in a timely manner and improve the efficiency of traffic congestion management.
  • the map data may be map data provided by a map application, including data of congestion events occurring on the road, and causative events occurring on the road that may cause traffic congestion.
  • Congestion events may include road congestion events and intersection congestion events.
  • the data of road congestion events may include: congestion start time, congestion end time, congestion source coordinates, and a set of congestion source coordinates.
  • the congestion source coordinates refer to key coordinate points where road congestion events occur, and a road congestion event may include one or more congestion source coordinates.
  • the congestion source coordinate set includes many coordinate points where the road congestion event occurs. After being rendered on the map, a line segment is formed, that is, the congestion source coordinate connection line of the road congestion event is composed of coordinate points in the congestion source coordinate set.
  • the data of the road congestion event can also include: event identification (such as event number, etc.), congestion type, congestion location description, congestion duration, road number, road name, road type and road direction of the road where the congestion is located, congestion distance, Congestion index, average speed of vehicles on congested road sections, etc.
  • event identification such as event number, etc.
  • congestion type such as event number, etc.
  • congestion location description such as congestion location description
  • congestion duration such as road number, road name, road type and road direction of the road where the congestion is located
  • congestion distance such as Congestion index, average speed of vehicles on congested road sections, etc.
  • the congestion type of the road congestion event includes abnormal congestion or regular congestion
  • regular congestion refers to regular congestion
  • abnormal congestion refers to non-recurring congestion that bursts out relative to normal congestion. For example, when congestion occurs for the first time, it will be set as abnormal congestion. When the same congestion occurs for a certain number of times, it will be set as normal congestion.
  • the road type of the road where the congestion is located includes: expressway, ring road and expressway, trunk, secondary trunk, branch trunk, etc.
  • the road direction refers to the driving direction of the vehicle on the road.
  • the congestion index is used to measure whether the current congestion is serious.
  • the data of the intersection congestion event may include: congestion start time, congestion end time, congestion type, intersection number, intersection name and intersection coordinates of the intersection where the congestion is located.
  • the congestion type of the intersection congestion event includes an intersection deadlock event and an intersection overflow event.
  • the crossing deadlock event refers to that the entrance and exit roads of the crossing are all congested seriously.
  • the overflow event means that the congestion of the entrance road or the exit road of the intersection is not serious.
  • an intersection deadlock event means that the average vehicle speed of the entrance and exit roads at the intersection is less than the preset speed threshold
  • an overflow event means that the average vehicle speed of the intersection entrance or exit road is greater than or equal to the preset speed threshold.
  • the preset speed threshold can be set and adjusted according to the needs of actual application scenarios, and is not specifically limited here.
  • intersection coordinates of the intersection where the congestion is located may be the center point coordinates of the intersection, or the latitude and longitude coordinates.
  • the data of the intersection congestion event may also include: event identifier (such as event number), congestion duration, congestion distance, congestion index, average speed of vehicles on the congested section, and the like.
  • event identifier such as event number
  • congestion duration such as congestion duration
  • congestion distance such as congestion distance
  • congestion index such as average speed of vehicles on the congested section
  • the causative events include various types of events that occur on the road and cause traffic jams.
  • the data of the causative event may include: event identifier (eg, event number), event start time, event end time, coordinates of the causative event, description of the location of the causative event, type of the causative event, and the like.
  • the types of causative events include, but are not limited to: traffic accidents, faulty vehicles, water accumulation on roads, heavy fog, icy roads, snow accumulation on roads, road construction, traffic control, and dangerous road sections.
  • preprocessing such as data cleaning and data conversion may be performed on the data of the congestion event and the data of the cause event.
  • data cleaning includes removing duplicate data and invalid data.
  • Invalid data is data that lacks critical information needed.
  • Data conversion refers to converting data into a specified format, including deleting useless event information, data format conversion, etc.
  • useless event information refers to event information that will not be used in the process of determining the causative event corresponding to the congestion event, for example, the average speed and location description of the congestion event.
  • the data of the congestion event and the causative event after data preprocessing may be stored, and the original data of the congestion event and the causative event may be retained for subsequent query.
  • multiple causal analysis strategies and the confidence coefficient corresponding to each causal analysis strategy may be preset.
  • at least one cause analysis strategy is adopted, according to the data of the congestion event and the data of each causal event, Determine the time correlation and spatial correlation between each causal event and congestion event; according to the confidence coefficient corresponding to each causal analysis strategy, and the time correlation and spatial correlation between each causal event and congestion event determined by each causal analysis strategy Spatial correlation, to determine the correlation confidence between each causal event and congestion event, so, for any congestion event, using a variety of causal analysis strategies, from the time correlation and spatial correlation of the causal event and congestion event
  • associating causal events with congestion events can comprehensively and accurately determine the correlation confidence between each causal event and congestion event.
  • Step S302 for each congestion event, adopt at least one causal analysis strategy, and determine the time correlation and spatial correlation between each causative event and the congestion event according to the data of the congestion event and the data of each causative event.
  • At least one causal analysis strategy is used to screen out alternative causative events related to the congestion event in time and space according to the location where the congestion event occurred and the congestion start time, and determine the A time correlation degree and a spatial correlation degree between an alternative causative event and the congestion event, so as to realize an accurate analysis of the time correlation degree and the spatial correlation degree between each causative event and the congestion event.
  • congestion events can be divided into two categories: road congestion events and crossing congestion events.
  • the data of each congestion event includes which category the congestion event belongs to in the above two categories of congestion events, whether it is a road congestion event or a traffic congestion event. Intersection congestion incident.
  • road congestion cause analysis strategies For road congestion events, you can set a variety of road congestion cause analysis strategies. When associating road congestion events with cause events, you can use any one of the road congestion cause analysis strategies, or use multiple road congestion cause analysis strategies at the same time. The confidence degree of the association between the causal event and the road congestion event is calculated by the analysis strategy. The causal event with the highest correlation confidence is taken as the causal event corresponding to the road congestion event.
  • a road congestion cause analysis strategy is used to calculate the time correlation and spatial correlation between the cause event and the congestion event, and According to the confidence coefficient corresponding to the road congestion cause analysis strategy, the confidence degree of the correlation between each cause event and the road congestion event is determined, and the analysis result obtained by using this road congestion cause analysis strategy is obtained. Synthetically using the analysis results determined by each road congestion cause analysis strategy respectively, for each road congestion event, take the cause event with the highest degree of confidence associated with the road congestion event as the cause event corresponding to the road congestion event.
  • the first road congestion cause analysis strategy may be used to determine the degree of confidence associated with each cause event and the road congestion event.
  • the first road congestion cause analysis strategy is adopted, and the alternative cause events related to the congestion event in time and space are screened out according to the location of the congestion event and the start time of the congestion event. This is done as follows:
  • the congestion source coordinate point of the congestion event determine the first congestion buffer zone corresponding to the congestion event, the first congestion buffer zone includes the area within the first preset range centered on the congestion source coordinate point; according to the congestion start time of the congestion event , filter out the specified type of causal events that occurred in the first congestion buffer zone from the first moment to the current moment, and obtain the first candidate causal event, where the first moment is before the congestion start time and is the same as the congestion start time
  • the interval is a first preset time length.
  • the first preset range can be set and adjusted according to the needs of the actual application scenario, that is, the shape and size of the first congestion buffer can be set and adjusted according to the needs of the actual application scenario, which is not specifically limited here .
  • the first preset duration can be set and adjusted according to the needs of actual application scenarios.
  • the first preset duration can be 5 minutes, 10 minutes, 20 minutes, etc., which are not specifically limited here.
  • the first congestion buffer zone may include a circular area of a first preset range centered on the congestion source coordinate point, and the radius of the circular area is determined by the first preset range; or, the first congestion buffer zone It may include a rectangular area with the coordinate point of the congestion source as the center, and the distance between the sides of the rectangular area and the center is determined by the first preset range.
  • the first preset range can be set and adjusted according to the needs of the actual application scene, for example, the first preset range can be within a circle with a radius of 500 meters (or 2500, 3000 meters), etc.
  • the specific radius The value is not specifically limited.
  • determining the temporal correlation and spatial correlation between each alternative causal event and the congestion event can be achieved in the following manner:
  • the first pre-correlation degree can be set to the maximum value of the time correlation degree, for example, the first preset correlation degree can be 1, in addition, the first pre-correlation degree can be set and adjusted according to the needs of the actual application scene, here Not specifically limited.
  • the preset correlation degree corresponding to each distance range it is possible to determine the distance corresponding to the distance between the position where the first candidate causative event occurs and the congestion source coordinate point.
  • the preset correlation degree corresponding to the distance range is used as the spatial correlation degree between the first candidate causative event and the congestion event.
  • the set distance range and the preset correlation degree corresponding to the distance range can be set according to the needs of actual application scenarios, and are not specifically limited here.
  • a preset distance threshold if the distance between the position where the first candidate causative event occurs and the coordinate point of the congestion source is less than or equal to the first distance threshold, then it is determined that the first candidate causative event and The spatial correlation of the congestion event is the second preset correlation. If the distance between the position where the first candidate causative event occurs and the congestion source coordinate point is greater than the first distance threshold and less than or equal to the second distance threshold, then determine the spatial correlation between the first candidate causative event and the congestion event The degree is the third preset correlation degree. If the distance between the position where the first candidate causative event occurs and the coordinate point of the congestion source is greater than the second distance threshold, then determine the spatial correlation between the first candidate causative event and the congestion event as the fourth preset correlation.
  • the second preset correlation degree is the maximum value of the spatial correlation degree, and the second preset correlation degree can be set and adjusted according to the needs of actual application scenarios.
  • the second preset correlation degree can be 1, and no specific details are given here limited.
  • the third preset correlation degree is smaller than the second preset correlation degree
  • the fourth preset correlation degree is smaller than the third preset correlation degree
  • the values of the third preset correlation degree and the fourth preset correlation degree can be based on the needs of actual application scenarios
  • the third preset correlation degree may be 0.8
  • the fourth preset correlation degree may be 0.5, which are not specifically limited here.
  • the first distance threshold is less than the second distance threshold, the first distance threshold and the second distance threshold can be set and adjusted according to the needs of actual application scenarios, for example, the first distance threshold can be 0.8 kilometers (km), and the second distance threshold can be It is 1.5km, which is not specifically limited here.
  • the first congestion buffer zone includes a circular area centered on the coordinate point of the congestion source and a radius of 2.5km
  • the first distance threshold is 0.8km
  • the second distance threshold may be 1.5km
  • the second preset correlation It can be 1
  • the third preset correlation degree can be 0.8
  • the fourth preset correlation degree can be 0.5.
  • Use S to represent the distance between the position where the first candidate causative event occurs and the coordinate point of the congestion source
  • the first road congestion cause analysis strategy it is possible to set the first congestion buffer corresponding to the congestion event for the scope of influence of the specified type of cause event, and filter out the first preset time period before the congestion event starts to the current time , an alternative causal event of a specified type that occurs in the first congestion buffer zone of the congestion event (near where the congestion event occurs).
  • an alternative causal event of a specified type that occurs in the first congestion buffer zone of the congestion event (near where the congestion event occurs).
  • the alternative causative event occurs in the first congestion buffer zone of the congestion event, it can be determined that the alternative causative event is strongly correlated with the congestion event in time, then the first backup
  • the temporal correlation between the selected causal event and the congestion event is the first preset correlation.
  • the spatial correlation between each first candidate cause event and the congestion event is determined, and the specified type can be accurately determined.
  • the time correlation and spatial correlation between the causal event and the congestion event can be used to accurately determine the correlation confidence between the specified type of causal event and the congestion event.
  • the specified type includes at least one of the following: road construction, traffic control.
  • road construction e.g., road construction, traffic control.
  • the specified type of cause events that are strongly related to the road congestion event in time can be screened out, and the cause can be improved. Accuracy of temporal correlation and spatial correlation of events and road congestion events.
  • the specified type may also include other types of causal events.
  • the specific types of causative events included in the specified type can be set and adjusted according to the needs of actual application scenarios, and are not specifically limited here.
  • the congestion buffer zone corresponding to the congestion event before determining the first congestion buffer zone corresponding to the congestion event according to the congestion source coordinate point of the congestion event, it also includes: performing deduplication processing on the congestion source coordinate point of the congestion event, and for the congestion source retained after deduplication processing Subsequent processing of coordinate points can greatly reduce repeated data calculations, improve the calculation efficiency of the correlation confidence between causative events and congestion events, and improve the timeliness and efficiency of the method.
  • the first road congestion cause analysis strategy can be used for each piece of congestion data to determine the time correlation, Spatial correlation and association confidence.
  • multiple sets of time correlations and spatial correlations between the same cause event and the congestion event may be calculated, and multiple correlation confidence degrees between the same cause event and the congestion event can be determined. The maximum value of is used as the correlation confidence between the causative event and the congestion event.
  • a second road congestion cause analysis strategy may be used to determine the degree of confidence associated with each cause event and the road congestion event.
  • the second road congestion cause analysis strategy is adopted, and the alternative cause events related to the congestion event in time and space are screened out according to the location of the congestion event and the start time of the congestion event. This is done as follows:
  • the congestion event is a road congestion event.
  • the second congestion buffer zone corresponding to the congestion event is determined. All location points; according to the congestion start time of the congestion event, filter out the specific type of causal event that occurs in the second congestion buffer zone from the second moment to the current moment, and obtain the second alternative causal event, wherein the second moment Before the congestion start time and at a second preset time interval from the congestion start time.
  • the congestion source coordinate line is a line segment determined according to the congestion source coordinate set of the congestion event.
  • the shortest distance between any point and the line connecting the coordinates of the congestion source refers to the minimum value of the distance between the point and any point on the line connecting the coordinates of the congestion source.
  • the first preset distance can be set and adjusted according to the needs of actual application scenarios.
  • the first preset distance is 15 meters, 20 meters, 30 meters, etc., which are not specifically limited here.
  • the second preset duration can be set and adjusted according to the needs of the actual application scenario.
  • the second preset duration can be 5 minutes, 10 minutes, 20 minutes, etc., which is not specifically limited here.
  • determining the temporal correlation and spatial correlation between each alternative causal event and the congestion event can be achieved in the following manner:
  • each second alternative cause event determines the time correlation between each second alternative cause event and the congestion event; according to each second alternative cause The distance between the location where the event occurs and the line connecting the coordinates of the congestion source determines the spatial correlation between each second candidate cause event and the congestion event.
  • the distance between the position where the second candidate causative event occurs and the line of coordinates of the congestion source may be the vertical distance from the position where the second candidate causative event occurs to the straight line where the coordinate line of the congestion source is located.
  • the distance between the location where the second candidate causative event occurs and the line of the congestion source coordinates can be the distance from the location point where the second candidate causative event occurs to any point on the line of the congestion source coordinates the shortest distance.
  • the preset correlation degree corresponding to each time range determines the time interval corresponding to the time interval between the start time of the second candidate causative event and the congestion start time Time range, the preset correlation degree corresponding to the time range is used as the time correlation degree between the second candidate causative event and the congestion event.
  • the set time range and the preset correlation degree corresponding to the time range can be set according to actual application scenarios, and are not specifically limited here.
  • the preset correlation degree corresponding to each distance range it can be determined that the distance between the position where the second candidate causative event occurs and the line of the congestion source coordinates corresponds to distance range, and the preset correlation degree corresponding to the distance range is used as the spatial correlation degree between the second candidate causative event and the congestion event.
  • the set distance range and the preset correlation degree corresponding to the distance range can be set according to the needs of actual application scenarios, and are not specifically limited here.
  • the second road congestion cause analysis strategy it is possible to set the second congestion buffer corresponding to the congestion event for the scope of influence of a specific type of cause event, and filter out the second preset time period before the start of the congestion event to the current moment , an alternative causative event of a specific type that occurs in the second congestion buffer zone of the congestion event (near the location where the congestion event occurs).
  • the alternative causative events occur in the second congestion buffer zone of the congestion event, it can be determined that the alternative causative events and the congestion event have a certain correlation in time and space , according to the time interval between the start time of each second alternative cause event and the congestion start time, determine the time correlation between each second alternative cause event and the congestion event; Due to the distance between the location where the event occurred and the line connecting the coordinates of the congestion source, the spatial correlation between each second candidate causative event and the congestion event can be determined, and the time correlation between the specific type of causative event and the congestion event can be accurately determined degree and spatial correlation, so that the confidence degree of the association between a specific type of causative event and a congestion event can be accurately determined.
  • the specific type includes at least one of the following: traffic accidents, faulty vehicles, water accumulation on roads, icing on roads, and snow accumulation on roads.
  • traffic accidents faulty vehicles
  • water accumulation on roads icing on roads
  • snow accumulation on roads e.g., snow accumulation on roads.
  • specific types of causative events such as traffic accidents, faulty vehicles, road water, road icing, and road snow, which are related to road congestion events in time and space.
  • Specific types of causal events with strong correlation can improve the accuracy of temporal and spatial correlations between causative events and road congestion events.
  • the specific type may also include other types of causal events.
  • the specific types of causative events included in the specific type may be set and adjusted according to the needs of actual application scenarios, and are not specifically limited here.
  • the second congestion buffer corresponding to the congestion event before determining the second congestion buffer corresponding to the congestion event according to the congestion source coordinate connection of the congestion event, it also includes:
  • Deduplication processing is performed on the congestion source coordinate connection line of the congestion event. Subsequent processing of the congestion source coordinate lines retained after de-duplication processing can greatly reduce repeated data calculations, improve the calculation efficiency of the correlation confidence between causative events and congestion events, and improve the timeliness and efficiency of the method.
  • the second road congestion cause analysis strategy can be used for each piece of congestion data to determine the time correlation, Spatial correlation and association confidence.
  • multiple sets of time correlations and spatial correlations between the same cause event and the congestion event may be calculated, and multiple correlation confidence degrees between the same cause event and the congestion event can be determined. The maximum value of is used as the correlation confidence between the causative event and the congestion event.
  • a third road congestion cause analysis strategy may be used to determine the degree of confidence associated with each cause event and the road congestion event.
  • the third road congestion cause analysis strategy is adopted, and the candidate causal events related to the congestion event in time and space are screened out according to the location of the congestion event and the start time of the congestion event. This is done as follows:
  • the congestion event is a road congestion event.
  • the congestion source coordinate point of the congestion event determine the road section where the congestion source coordinate point is located and the downstream intersection, and use the road section and the downstream intersection where the congestion source coordinate point is located as the third congestion buffer zone corresponding to the congestion event;
  • the congestion start time of the congestion event the causal event that occurred in the third congestion buffer zone from the third moment to the current moment is screened out to obtain the third alternative causal event, wherein the third moment is before the congestion start time and is the same as
  • the congestion start time interval is a third preset duration.
  • the downstream intersection refers to the nearest next intersection on the road section where the congestion source coordinate point is located.
  • the third preset duration can be set and adjusted according to the needs of actual application scenarios.
  • the third preset duration can be 5 minutes, 10 minutes, 20 minutes, etc., which is not specifically limited here.
  • determining the temporal correlation and spatial correlation between each alternative causal event and the congestion event can be achieved in the following manner:
  • each third alternative cause event determines the time correlation between each third alternative cause event and the congestion event; determine each third alternative cause
  • the spatial correlation between the event and the congestion event is the second preset correlation.
  • the preset correlation degree corresponding to each time range determines the time interval corresponding to the time interval between the start time of the second candidate causative event and the congestion start time Time range, the preset correlation degree corresponding to the time range is used as the time correlation degree between the second candidate causative event and the congestion event.
  • the set time range and the preset correlation degree corresponding to the time range can be set according to actual application scenarios, and are not specifically limited here.
  • T3 to represent the time interval between the start time of the third alternative cause event and the congestion start time of the congestion event
  • TC3 use a time correlation between the third alternative cause event and the congestion event
  • the second pre-correlation degree can be set to the maximum value of the spatial correlation degree, for example, the second preset correlation degree can be 1, and in addition, the second pre-correlation degree can be set and adjusted according to the needs of the actual application scene, where Not specifically limited.
  • the road section and downstream intersection where the congestion source coordinate point of the congestion event is located can be set as the third congestion buffer zone corresponding to the congestion event, and filtered out.
  • the third alternative causative event occurs in the road section and downstream intersection where the congestion event is located, and it can be determined that the third alternative causative event is strongly correlated with the congestion event in space, then directly compare the third alternative causative event with the congestion event
  • the spatial correlation is set to the second preset correlation.
  • the time correlation between each third candidate causative event and the congestion event can be determined accurately to determine the third
  • the time correlation and spatial correlation between the causative event and the congestion event can be used to accurately determine the correlation confidence between the causative event and the congestion event.
  • the congestion source coordinate point of the congestion event determine the road section where the congestion source coordinate point is located and the downstream intersection, and use the road section where the congestion source coordinate point is located and the downstream intersection as the congestion event correspondence Before the third congestion buffer, also include:
  • Deduplication processing is performed on the congestion source coordinate points of the congestion event. Subsequent processing of the congestion source coordinate points retained after deduplication processing can greatly reduce repeated data calculations, improve the calculation efficiency of the correlation confidence between causative events and congestion events, and improve the timeliness and efficiency of the method.
  • a fourth road congestion cause analysis strategy may be used to determine the correlation confidence between each cause event and the road congestion event.
  • this step can be implemented in the following manner:
  • the congestion event is a road congestion event, and the user report event corresponding to the congestion event is obtained.
  • the user report event includes at least one fourth alternative cause event related to the congestion event; determine the time of at least one fourth alternative cause event and the congestion event correlation and spatial correlation.
  • the user-reported event includes a specific congestion event, and an indication of the congestion event is a related causal event.
  • At least one causative event related to the event of congestion in the event reported by the user is used as the fourth backup event of the event of congestion.
  • At least one intersection congestion cause analysis strategy can be used to calculate the time correlation and spatial correlation between the cause event and the congestion event, and according to the confidence coefficient corresponding to the intersection congestion cause analysis strategy , to determine the correlation confidence between each causative event and the intersection congestion event calculated by using each of the intersection congestion cause analysis strategies.
  • the causal event with the highest correlation confidence is taken as the causal event corresponding to the intersection congestion event.
  • intersection congestion analysis strategy For any intersection congestion event, one intersection congestion analysis strategy is used to calculate the temporal correlation and spatial correlation between the causal event and the congestion event, and According to the confidence coefficient corresponding to the intersection congestion cause analysis strategy, the correlation confidence between each cause event and the congestion event is determined, and the analysis result obtained by using this intersection congestion cause analysis strategy is obtained. Synthetically using the analysis results determined by each intersection congestion cause analysis strategy respectively, for each intersection congestion event, take the causal event with the highest degree of confidence associated with the intersection congestion event as the causal event corresponding to the intersection congestion event.
  • the first intersection congestion cause analysis strategy may be used to determine the correlation confidence between each cause event and the intersection congestion event.
  • each congestion event using the first intersection congestion cause analysis strategy, according to the data of the congestion event and the data of each cause event, determine the time correlation and spatial correlation between each cause event and the congestion event, which can be This is achieved in the following ways:
  • the congestion event is an intersection congestion event. According to the intersection coordinate point where the congestion event is located, the fourth congestion buffer zone corresponding to the congestion event is determined, and the fourth congestion buffer zone includes an area within the second preset range centered on the intersection coordinate point; according to The congestion start time of the congestion event, filter out the cause events that occurred in the fourth congestion buffer zone from the fourth moment to the current moment, and obtain the fifth alternative cause event, wherein, the fourth moment is before the congestion start time and is the same as the congestion
  • the start time interval is a fourth preset duration.
  • the second preset range can be set and adjusted according to the needs of the actual application scenario, that is, the shape and size of the fourth congestion buffer can be set and adjusted according to the needs of the actual application scenario, which is not specifically limited here .
  • the fourth preset duration can be set and adjusted according to the needs of actual application scenarios.
  • the fourth preset duration can be 5 minutes, 10 minutes, 20 minutes, etc., which are not specifically limited here.
  • the fourth congestion buffer zone may include a circular area of a second preset range centered on the intersection coordinate point, and the radius of the circular area is determined by the second preset range; or, the fourth congestion buffer zone may It includes a rectangular area with the intersection coordinate point as the center, and the distance between the sides of the rectangular area and the center is determined by the second preset range.
  • the second preset range can be set and adjusted according to the needs of the actual application scene, for example, the second preset range can be within a circle with a radius of 500 meters (or 400 meters, 800 meters), etc., where the radius The specific value is not specifically limited.
  • determining the temporal correlation and spatial correlation between each alternative causal event and the congestion event can be achieved in the following manner:
  • the alternative causal event includes the fifth alternative causal event, according to the start time of each alternative causal event and the congestion start time, determine the time correlation between each alternative causal event and the congestion event; Select the distance between the position where the causative event occurred and the coordinate point of the intersection, and determine the spatial correlation between each alternative causative event and the congestion event.
  • the start time of each fifth alternative cause event and the congestion start time if the start time of the fifth alternative cause event is earlier than the congestion start time of the congestion event, then determine the fifth alternative cause
  • the time correlation between the event and the congestion event is the first preset correlation.
  • the start time of the fifth alternative cause event is not earlier than the congestion start time of the congestion event, then according to the time interval between the start time of the fifth alternative cause event and the congestion start time, determine the fifth alternative cause event and Time correlation of congestion events. In this way, the temporal correlation between the candidate causative event and the congestion event can be accurately determined, thereby improving the accuracy of the confidence in the association between the causative event and the congestion event.
  • the start time of the fifth alternative causal event is not earlier than the congestion start time of the congestion event, then determine the time range corresponding to the time interval between the start time of the fifth candidate cause event and the congestion start time of the congestion event,
  • the preset correlation degree corresponding to the time range is used as the time correlation degree between the fifth candidate causative event and the congestion event.
  • the set time range and the preset correlation degree corresponding to the time range can be set according to actual application scenarios, and are not specifically limited here.
  • the distance corresponding to the distance between the position where the fifth candidate causative event occurs and the intersection coordinate point can be determined according to one or more preset distance ranges and the preset correlation degree corresponding to each distance range range, and the preset correlation degree corresponding to the distance range is used as the spatial correlation degree between the fifth candidate causative event and the congestion event.
  • the set distance range and the preset correlation degree corresponding to the distance range can be set according to the needs of actual application scenarios, and are not specifically limited here.
  • S5 to represent the distance between the position where the fifth alternative causal event occurs and the intersection coordinate point
  • the fourth congestion buffer zone corresponding to the intersection congestion event can be set for the intersection congestion event, and the fourth preset time period before the congestion event starts to the current moment.
  • the fifth alternative cause event occurs in the fourth congestion buffer zone (near the intersection where the congestion event occurs), and it can be determined that the fifth alternative cause event has a certain correlation with the congestion event in time and space.
  • the starting time of the five alternative causal events and the congestion start time determine the time correlation between each fifth alternative causative event and the congestion event; to determine the spatial correlation between each fifth alternative causal event and the congestion event, and to accurately determine the temporal correlation and spatial correlation between the causative event and the intersection congestion event, thereby accurately determining the causative event Confidence associated with intersection congestion events.
  • the second intersection congestion-causing analysis strategy can be used to determine the correlation confidence between each cause event and the intersection congestion event.
  • the second intersection congestion cause analysis strategy is used to determine the time correlation and spatial Relevance can be achieved in the following ways:
  • the congestion event is an intersection congestion event and the congestion event is an intersection deadlock event.
  • the causal event that occurs on the entrance section of the intersection where the congestion event is located from the fifth moment to the current moment is screened out, and the sixth backup is obtained. Select the causal event.
  • the fifth moment is before the congestion start time and is separated from the congestion start time by a fifth preset time period.
  • the fifth preset duration can be set and adjusted according to the needs of actual application scenarios.
  • the fifth preset duration can be 5 minutes, 10 minutes, 20 minutes, etc., which are not specifically limited here.
  • determining the temporal correlation and spatial correlation between each alternative causal event and the congestion event can be achieved in the following manner:
  • Alternative cause events include the sixth alternative cause events, according to the start time and congestion start time of each sixth alternative cause events, determine the time correlation between the sixth alternative cause events and congestion events;
  • the spatial correlation between the sixth candidate causative event and the congestion event is the second preset correlation.
  • the start time of each sixth alternative cause event and the congestion start time if the start time of the sixth alternative cause event is earlier than the congestion start time of the congestion event, then determine the sixth alternative cause
  • the time correlation between the event and the congestion event is the first preset correlation.
  • the start time of the sixth alternative cause event is not earlier than the congestion start time of the congestion event, then according to the time interval between the start time of the sixth alternative cause event and the congestion start time, determine the sixth alternative cause event and Time correlation of congestion events. In this way, the temporal correlation between the candidate causative event and the congestion event can be accurately determined, thereby improving the accuracy of the confidence in the association between the causative event and the congestion event.
  • the start time of the sixth alternative causal event is not earlier than the congestion start time of the congestion event, then determine the time range corresponding to the time interval between the start time of the sixth candidate cause event and the congestion start time of the congestion event,
  • the preset correlation degree corresponding to the time range is used as the time correlation degree between the sixth candidate causative event and the congestion event.
  • the set time range and the preset correlation degree corresponding to the time range can be set according to actual application scenarios, and are not specifically limited here.
  • the sixth alternative cause is obtained event, it can be determined that the sixth candidate causative event is strongly spatially correlated with the intersection deadlock event, then directly set the spatial correlation degree between the sixth candidate causative event and the intersection deadlock event as the second preset correlation degree. Further, according to the start time of the sixth alternative causative event and the congestion start time, the time correlation between the sixth alternative causative event and the intersection deadlock event can be determined accurately, and the relationship between the sixth causative event and the congestion event can be accurately determined. Time correlation and spatial correlation, so as to accurately determine the correlation confidence between the causative event and the congestion event.
  • a third intersection congestion cause analysis strategy may be used to determine the correlation confidence between each cause event and the intersection congestion event.
  • the third intersection congestion cause analysis strategy is used to determine the temporal correlation and spatial Relevance can be achieved in the following ways:
  • the congestion event is an intersection congestion event and the congestion event is an intersection overflow event.
  • the congestion start time of the congestion event filter out the exit section of the intersection where the congestion event is located from the sixth moment to the current moment The resulting causal event occurs, and the seventh alternative causal event is obtained.
  • the sixth moment is before the congestion start time and is separated from the congestion start time by a sixth preset time period.
  • the sixth preset duration can be set and adjusted according to the needs of actual application scenarios.
  • the sixth preset duration can be 5 minutes, 10 minutes, 20 minutes, etc., which is not specifically limited here.
  • determining the temporal correlation and spatial correlation between each alternative causal event and the congestion event can be achieved in the following manner:
  • Alternative cause events include the seventh alternative cause events, according to the start time and congestion start time of each seventh alternative cause events, determine the time correlation between the seventh alternative cause events and congestion events;
  • the spatial correlation between the seventh candidate causative event and the congestion event is the second default correlation.
  • the start time of each seventh alternative cause event and the congestion start time if the start time of the seventh alternative cause event is earlier than the congestion start time of the congestion event, then determine the seventh alternative cause
  • the time correlation between the event and the congestion event is the first preset correlation.
  • the start time of the seventh alternative cause event is not earlier than the congestion start time of the congestion event, then according to the time interval between the start time of the seventh alternative cause event and the congestion start time, determine the seventh alternative cause event and Time correlation of congestion events. In this way, the temporal correlation between the candidate causative event and the congestion event can be accurately determined, thereby improving the accuracy of the confidence in the association between the causative event and the congestion event.
  • the start time of the seventh alternative causal event is not earlier than the congestion start time of the congestion event, then determine the time range corresponding to the time interval between the start time of the seventh candidate cause event and the congestion start time of the congestion event,
  • the preset correlation degree corresponding to the time range is used as the time correlation degree between the seventh candidate causative event and the congestion event.
  • the set time range and the preset correlation degree corresponding to the time range can be set according to actual application scenarios, and are not specifically limited here.
  • the causal event that occurred on the exit section of the intersection where the congestion event is located from the sixth moment to the current moment is screened out, and the seventh alternative cause is obtained event, it can be determined that the seventh candidate causative event is strongly correlated with the intersection overflow event in space, then directly set the spatial correlation degree between the seventh candidate causative event and the intersection overflow event as the second preset correlation degree. Further, according to the start time of the seventh alternative causative event and the congestion start time, the time correlation between the seventh alternative causative event and the intersection deadlock event can be determined accurately, and the relationship between the seventh causative event and the congestion event can be accurately determined. Time correlation and spatial correlation, so as to accurately determine the correlation confidence between the causative event and the congestion event.
  • Step S303 according to the confidence coefficient corresponding to each causal analysis strategy, and the time correlation and spatial correlation between each causative event and congestion event determined by each causal analysis strategy, determine the correlation between each causal event and congestion event Confidence.
  • the confidence coefficients corresponding to each road congestion cause analysis strategy can also be set.
  • the confidence coefficient corresponding to the fourth road congestion cause analysis strategy is greater than the confidence coefficient corresponding to the third road congestion cause analysis strategy, and the fourth road congestion cause analysis strategy corresponds to the confidence coefficient.
  • the confidence coefficient corresponding to the cause analysis strategy of the three road congestion is greater than the confidence coefficient corresponding to the cause analysis strategy of the first road congestion
  • the confidence coefficient corresponding to the cause analysis strategy of the third road congestion is greater than that corresponding to the cause analysis strategy of the second road congestion.
  • the confidence coefficient corresponding to the first road congestion cause analysis strategy may be the same as or different from the confidence coefficient corresponding to the second road congestion cause analysis strategy.
  • the confidence coefficients corresponding to the first and second road congestion cause analysis strategies can be 3, the confidence coefficients corresponding to the third road congestion cause analysis strategy can be 5, and the confidence coefficients corresponding to the fourth road congestion cause analysis strategy
  • the degree factor can be 10.
  • the confidence coefficient corresponding to the temporal correlation, spatial correlation and causal analysis strategy can be calculated The product of these three results in the correlation confidence between the causative event and the congestion event.
  • multiple sets of time correlations and spatial correlations between the same cause event and the congestion event may be calculated, and multiple association confidences between the same cause event and the congestion event may be determined. degrees, and take the maximum value as the confidence degree of the association between the causative event and the congestion event.
  • Step S304 according to the correlation confidence between each causative event and the congestion event, the causal event with the highest correlation confidence with the congestion event is taken as the causal event corresponding to the congestion event.
  • the causal event corresponding to the congestion event can be determined according to the correlation confidence between each causal event and the congestion event.
  • the causal event with the highest correlation confidence with the congestion event can be determined as the causal event corresponding to the congestion event, and the corresponding congestion event can be accurately determined. causative event.
  • the confidence threshold can be set and adjusted according to the needs of actual application scenarios, and is not specifically limited here.
  • the corresponding relationship between the congestion event and the causative event may be stored in a database, which is convenient for users to query.
  • Step S305 displaying the causative events corresponding to each congestion event.
  • the corresponding causative event of each congestion event can be displayed through the map application, so as to timely notify the driver to avoid the congested road section as needed.
  • the causative events corresponding to each congestion event may be displayed in a list form, so as to facilitate users to view.
  • Step S306 generating a congestion data report according to the causative events corresponding to each congestion event, and sending the congestion data report.
  • a congestion data report can also be generated and sent according to the causative events corresponding to each congestion event, so that relevant personnel can understand the causes of traffic congestion in a timely manner and take timely actions. Control measures should be taken to alleviate traffic congestion in a timely manner, thereby improving the efficiency of traffic congestion management.
  • the congestion data report may include the causal event corresponding to the congestion event and the statistical information of the congestion event, wherein the statistical information of the congestion event may be calculated according to information such as the congestion type and the road type of the congestion event.
  • all or part of the information of the congestion data report can also be displayed on the map application.
  • statistics on congestion events can be displayed in a map application.
  • a data query interface (as shown in FIG. 4 ) for analyzing the causes of road congestion may be provided, and users may query congestion events and corresponding causative events by setting filter conditions on the interface.
  • the filter conditions can include: date range, date type, time period range, congestion type, road type, etc., and you can also set "only view the congestion caused by the association", "only view the congestion that has not dissipated” and other conditions.
  • the road type supports multiple selections. Date types include weekdays, holidays, weekends, etc.
  • the time range includes: peak, morning peak, evening peak, etc., and supports user-selected time.
  • the congestion types include frequent congestion, abnormal congestion, etc., and may include one or more of the congestion types of the congestion event.
  • the road type is determined according to the road type of the congestion event, and may include one or more of the road types of the congestion event.
  • the congestion events satisfying the filtering conditions are queried, and the query results are displayed (as shown in FIG. 5 ).
  • avoidance routes can also be generated and displayed according to the causative events corresponding to each congestion event, so as to provide automatic driving vehicles or drivers with congestion avoidance routes, thereby alleviating traffic congestion and improving traffic congestion. governance efficiency.
  • the architecture shown in FIG. 6 may be used for implementation.
  • the architecture includes: a data synchronization module, a data transmission tool, a data preprocessing module, a data storage module, a causal analysis engine, and a database.
  • the data synchronization module is used to synchronize the data of the congestion event and the data of the cause event from the map application, and transmit the synchronized data of the congestion event and the data of the cause event to the data preprocessing module through the data transmission tool.
  • the data preprocessing module is used to perform data preprocessing on the data of the congestion event and the data of the causative event, and send the preprocessed data to the causal analysis engine and the data storage module.
  • the cause analysis engine is used to determine the cause event corresponding to the congestion event according to the received data of the congestion event and the data of the cause event, and send the corresponding relationship between the congestion event and the cause event to the data storage module.
  • the data storage module is used for storing the data of the congestion event, the data of the cause event, and the corresponding relationship between the congestion event and the cause event in the database.
  • the congestion-related data can be queried from the database, and the query results can be displayed at the application layer.
  • the data transmission tool can transmit data in the form of a message queue.
  • the data transmission tool can be implemented using kafka to ensure that data is not lost.
  • multiple causal analysis strategies and a confidence coefficient corresponding to each causal analysis strategy are preset.
  • For each congestion event adopt at least one cause analysis strategy, and determine the time correlation and spatial correlation between each cause event and the congestion event according to the data of the congestion event and the data of each cause event;
  • Fig. 7 is a schematic diagram of a processing device for a traffic congestion event provided by a third embodiment of the present disclosure.
  • the traffic congestion event processing device provided in the embodiments of the present disclosure may execute the processing procedure provided in the traffic congestion event processing method embodiment.
  • the processing device 70 of the traffic jam event includes: a data synchronization module 701 , an association confidence determination module 702 and an event association module 703 .
  • the data synchronization module 701 is configured to obtain data of congestion events and data of causative events from map data, wherein the causative events include multiple types of events that occur on roads and cause traffic jams.
  • the association confidence determining module 702 is configured to, for each congestion event, determine the association confidence between each causative event and the congestion event according to the data of the congestion event and the data of each causative event.
  • the event association module 703 is configured to determine the causal event corresponding to the congestion event according to the confidence degree of association between each causal event and the congestion event.
  • the device provided in the embodiments of the present disclosure may be specifically configured to execute the method embodiment provided in the above-mentioned first embodiment, and the specific functions will not be repeated here.
  • Fig. 8 is a schematic diagram of a processing device for a traffic congestion event provided by a fourth embodiment of the present disclosure.
  • the traffic congestion event processing device provided in the embodiments of the present disclosure may execute the processing procedure provided in the traffic congestion event processing method embodiment.
  • the processing equipment 80 of this traffic congestion event comprises: data synchronization module 801, association confidence degree determination module 802 and event association module 803.
  • the data synchronization module 801 is configured to acquire data of congestion events and data of causative events from the map data, wherein the causative events include various types of events that occur on roads and cause traffic jams.
  • the association confidence determination module 802 is configured to, for each congestion event, determine the association confidence between each causative event and the congestion event according to the data of the congestion event and the data of each causative event.
  • the event association module 803 is configured to determine the causal event corresponding to the congestion event according to the confidence degree of association between each causal event and the congestion event.
  • the association confidence determination module 802 includes:
  • the correlation determination unit 8021 is used for each congestion event, using at least one cause analysis strategy, according to the data of the congestion event and the data of each cause event, to determine the time correlation and spatial correlation between each cause event and the congestion event relativity.
  • Confidence determination unit 8022 configured to determine each causal event according to the confidence coefficient corresponding to each causal analysis strategy, and the time correlation and spatial correlation between each causal event and congestion event determined by each causal analysis strategy Confidence associated with congestion events.
  • the correlation determination unit includes:
  • the causal event screening sub-unit is used for each congestion event, using at least one causal analysis strategy, according to the location where the congestion event occurs and the congestion start time, to screen out alternative causal events related to the congestion event in time and space. Due to the event;
  • the correlation determination subunit is used to determine the time correlation and spatial correlation between each candidate cause event and the congestion event.
  • causal event screening subunit is also used to:
  • the congestion event is a road congestion event.
  • the first road congestion cause analysis strategy is adopted, and the first congestion buffer zone corresponding to the congestion event is determined according to the congestion source coordinate point of the congestion event.
  • the first congestion buffer zone includes the congestion source coordinate point as the center The area within the first preset range; according to the congestion start time of the congestion event, filter out the specified type of causal events that occurred in the first congestion buffer zone from the first moment to the current moment, and obtain the first alternative cause event, wherein the first moment is before the congestion start time and is separated from the congestion start time by a first preset duration.
  • the specified type includes at least one of the following:
  • the correlation determination subunit is also used for:
  • the correlation determination unit also includes:
  • the preprocessing subunit is configured to: deduplicate the congestion source coordinates of the congestion event before determining the first congestion buffer corresponding to the congestion event according to the congestion source coordinates of the congestion event.
  • causal event screening subunit is also used to:
  • the congestion event is a road congestion event.
  • the second road congestion cause analysis strategy is adopted, and the second congestion buffer zone corresponding to the congestion event is determined according to the congestion source coordinate connection line of the congestion event.
  • the second congestion buffer zone includes the connection line with the congestion source coordinates All location points whose shortest distance is less than the first preset distance; according to the congestion start time of the congestion event, filter out the specific type of causative events that occurred in the second congestion buffer zone from the second moment to the current moment, and obtain the second backup A causal event is selected, wherein the second moment is before the congestion start time and is separated from the congestion start time by a second preset duration.
  • the specific type includes at least one of the following:
  • the correlation determination subunit is also used for:
  • each second alternative cause event determines the time correlation between each second alternative cause event and the congestion event; according to each second alternative cause The distance between the location where the event occurs and the line connecting the coordinates of the congestion source determines the spatial correlation between each second candidate cause event and the congestion event.
  • the preprocessing subunit is further configured to: de-duplicate the congestion source coordinate connection of the congestion event before determining the second congestion buffer corresponding to the congestion event according to the congestion source coordinate connection of the congestion event.
  • causal event screening subunit is also used to:
  • the congestion event is a road congestion event.
  • the third road congestion cause analysis strategy is adopted. According to the congestion source coordinate point of the congestion event, the road section and the downstream intersection where the congestion source coordinate point is located are determined, and the road section and the downstream intersection where the congestion source coordinate point is located are taken as The third congestion buffer zone corresponding to the congestion event; according to the congestion start time of the congestion event, filter out the cause events that occurred in the third congestion buffer zone from the third moment to the current moment, and obtain the third alternative cause event, wherein, The third moment is before the congestion start time and is separated from the congestion start time by a third preset time period.
  • the correlation determination subunit is also used for:
  • each third alternative cause event determines the time correlation between each third alternative cause event and the congestion event; determine each third alternative cause
  • the spatial correlation between the event and the congestion event is the second preset correlation.
  • the preprocessing subunit is also used to: adopt the third road congestion cause analysis strategy, determine the road section and downstream intersection where the congestion source coordinate point is located according to the congestion source coordinate point of the congestion event, and convert the congestion source coordinate point to the Before the road section and the downstream intersection are used as the third congestion buffer corresponding to the congestion event, the congestion source coordinate points of the congestion event are deduplicated.
  • causal event screening subunit is also used to:
  • the congestion event is a road congestion event
  • the fourth road congestion cause analysis strategy is adopted to obtain user-reported events corresponding to the congestion event, and the user-reported event includes at least one fourth alternative cause event related to the congestion event.
  • the relevance determination subunit is also used for:
  • a temporal correlation and a spatial correlation between the at least one fourth candidate causative event and the congestion event are determined.
  • causal event screening subunit is also used to:
  • the congestion event is an intersection congestion event.
  • the first intersection congestion cause analysis strategy is adopted, and the fourth congestion buffer zone corresponding to the congestion event is determined according to the intersection coordinate point where the congestion event is located.
  • the fourth congestion buffer zone includes the intersection coordinate point as the center.
  • the area within the second preset range according to the congestion start time of the congestion event, filter out the cause events that occurred in the fourth congestion buffer zone from the fourth moment to the current moment, and obtain the fifth alternative cause event, wherein, the first The fourth moment is before the congestion start time and is separated from the congestion start time by a fourth preset duration.
  • the correlation determination subunit is also used for:
  • the alternative causal event includes the fifth alternative causal event, according to the start time of each alternative causal event and the congestion start time, determine the time correlation between each alternative causal event and the congestion event; Select the distance between the position where the causative event occurred and the coordinate point of the intersection, and determine the spatial correlation between each alternative causative event and the congestion event.
  • causal event screening subunit is also used to:
  • the congestion event is an intersection congestion event and the congestion event is an intersection deadlock event.
  • the congestion start time of the congestion event filter out the entry section of the intersection where the congestion event is located from the fifth moment to the current moment
  • the occurrence of the causal event the sixth alternative causal event is obtained; wherein, the fifth moment is before the congestion start time and is separated from the congestion start time by the fifth preset duration.
  • causal event screening subunit is also used to:
  • the congestion event is an intersection congestion event and the congestion event is an intersection overflow event.
  • the congestion start time of the congestion event filter out the exit section of the intersection where the congestion event is located from the sixth moment to the current moment
  • the occurrence of the causal event the seventh alternative causal event is obtained; wherein, the sixth moment is before the congestion start time and is separated from the congestion start time by a sixth preset time period.
  • the correlation determination subunit is also used for:
  • the alternative causal event includes the sixth alternative causal event or the seventh alternative causal event, and according to the start time of each alternative causal event and the congestion start time, it is determined that the alternative causal event is related to the time of the congestion event degree; determining the spatial correlation degree between each candidate cause event and the congestion event as the second preset correlation degree.
  • the correlation determination subunit is also used for:
  • the alternative causal event is the fifth alternative causal event, the sixth alternative causal event, or the seventh alternative causal event, if the start time of the alternative causal event is earlier than If the congestion start time is determined, the time correlation between the alternative cause event and the congestion event is determined as the first preset correlation degree; if the start time of the alternative cause event is not earlier than the congestion start time, then according to the alternative cause event The time interval between the start time and the congestion start time determines the time correlation between the alternative causal event and the congestion event.
  • the event correlation module is also used for:
  • the causal event with the largest correlation confidence degree with the congestion event is taken as the causal event corresponding to the congestion event.
  • the processing device 80 of the traffic jam event also includes:
  • a display module 804 configured to display the causative events corresponding to each congestion event
  • the congestion reporting module 805 is configured to generate a congestion data report according to the causative events corresponding to each congestion event, and send the congestion data report.
  • the data synchronization module is also used for:
  • the congestion event data and causal event data in the previous period are regularly obtained from the map data.
  • the device provided in the embodiment of the present disclosure may be specifically used to execute the method embodiment provided in the above-mentioned second embodiment, and specific functions will not be repeated here.
  • multiple causal analysis strategies and a confidence coefficient corresponding to each causal analysis strategy are preset.
  • For each congestion event adopt at least one cause analysis strategy, and determine the time correlation and spatial correlation between each cause event and the congestion event according to the data of the congestion event and the data of each cause event;
  • the acquisition, storage and application of the user's personal information involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • the present disclosure also provides a computer program product.
  • the computer program product includes: a computer program, the computer program is stored in a readable storage medium, and at least one processor of an electronic device can read the program from the readable storage medium. Taking a computer program, at least one processor executes the computer program so that the electronic device executes the solution provided by any one of the above embodiments.
  • FIG. 9 shows a schematic block diagram of an example electronic device 900 that may be used to implement embodiments of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 900 includes a computing unit 901 that can execute according to a computer program stored in a read-only memory (ROM) 902 or loaded from a storage unit 908 into a random-access memory (RAM) 903. Various appropriate actions and treatments. In the RAM 903, various programs and data necessary for the operation of the device 900 can also be stored.
  • the computing unit 901, ROM 902, and RAM 903 are connected to each other through a bus 904.
  • An input/output (I/O) interface 905 is also connected to the bus 904 .
  • the I/O interface 905 includes: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc. ; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 909 allows the device 900 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • the computing unit 901 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 901 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the calculation unit 901 executes various methods and processes described above, for example, a method for processing traffic jam events.
  • the method for handling a traffic jam event may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 908 .
  • part or all of the computer program may be loaded and/or installed on the device 900 via the ROM 902 and/or the communication unit 909.
  • the computer program When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the method for processing the traffic jam event described above can be performed.
  • the computing unit 901 may be configured in any other appropriate way (for example, by means of firmware) to execute a traffic jam event processing method.
  • Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system of systems
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problem of traditional physical host and VPS service ("Virtual Private Server", or "VPS”) Among them, there are defects such as difficult management and weak business scalability.
  • the server can also be a server of a distributed system, or a server combined with a blockchain.
  • steps may be reordered, added or deleted using the various forms of flow shown above.
  • each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

本公开提供了交通拥堵事件的处理方法、设备、存储介质及程序产品，涉及计算机技术领域，尤其涉及智能交通、自动驾驶等领域。具体实现方案为：通过从地图数据中获取拥堵事件的数据和致因事件的数据，对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度；根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件，能够全面、及时、准确地确定导致交通拥堵事件的原因，从而为及时地缓解交通拥堵提供依据，提高交通拥堵治理效率，减少交通拥堵造成的影响。

Description

交通拥堵事件的处理方法、设备、存储介质及程序产品
本公开要求于2021年07月21日提交中国专利局、申请号为202110823935.X、申请名称为“交通拥堵事件的处理方法、设备、存储介质及程序产品”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及计算机技术中的智能交通、自动驾驶等领域，尤其涉及一种交通拥堵事件的处理方法、设备、存储介质及程序产品。
背景技术
目前，城市交通压力越来越大、交通拥堵越来越频繁，快速、准确判断导致交通拥堵的原因，对准确制定合理处置策略降低拥堵造成的影响起到了决定性的作用。
传统交通拥堵原因的确定方法，主要是基于交警人为判断导致拥堵的原因，往往处理不及时，无法及时地缓解交通拥堵，导致交通拥堵治理效率低。
发明内容
本公开提供了一种交通拥堵事件的处理方法、设备、存储介质及程序产品。
根据本公开的第一方面，提供了一种交通拥堵事件的处理方法，包括：
从地图数据中获取拥堵事件的数据和致因事件的数据，其中所述致因事件包括道路上发生的会造成交通拥堵的多类事件；
对每一所述拥堵事件，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的关联置信度；
根据各所述致因事件与所述拥堵事件的关联置信度，确定所述拥堵事件对应的致因事件。
根据本公开的第二方面，提供了一种交通拥堵事件的处理设备，包括：
数据同步模块，用于从地图数据中获取拥堵事件的数据和致因事件的数据，其中所述致因事件包括道路上发生的会造成交通拥堵的多类事件；
关联置信度确定模块，用于对每一所述拥堵事件，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的关联置信度；
事件关联模块，用于根据各所述致因事件与所述拥堵事件的关联置信度，确定所述拥堵事件对应的致因事件。
根据本公开的第三方面，提供了一种电子设备，包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行第一方面所述的方法。
根据本公开的第四方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行第一方面所述的方法。
根据本公开的第五方面，提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序，所述计算机程序存储在可读存储介质中，电子设备的至少一个处理器可以从所述可读存储介质读取所述计算机程序，所述至少一个处理器执行所述计算机程序使得电子设备执行第一方面所述的方法。
根据本公开的技术能够及时地、准确地确定交通拥堵的原因，提高了交通拥堵治理效率。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
附图用于更好地理解本方案，不构成对本公开的限定。其中：
图1是可以实现本公开实施例的交通拥堵事件处理的场景图；
图2是本公开第一实施例提供的交通拥堵事件的处理方法流程图；
图3是本公开第二实施例提供的交通拥堵事件的处理方法流程图；
图4是本公开第二实施例提供的数据查询界面的示例图；
图5是本公开第二实施例提供的显示拥堵数据查询结果的示例图；
图6是可以实现本公开实施例的交通拥堵事件的处理方法架构示例图；
图7是本公开第三实施例提供的交通拥堵事件的处理设备示意图；
图8是本公开第四实施例提供的交通拥堵事件的处理设备示意图；
图9是可以实现本公开实施例的交通拥堵事件的处理方法的电子设备的示意性框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
本公开提供一种交通拥堵事件的处理方法、设备、存储介质及程序产品，涉及计算机技术中的智能交通、自动驾驶等领域，以精准地确定导致交通拥堵事件的原因，为及时地缓解交通拥堵提供数据基础，提高交通拥堵治理效率。
本公开提供的交通拥堵事件的处理方法，具体可以应用于如图1所示的应用场景，地图应用10提供的地图数据中包含道路上发生的拥堵事件的数据，以及道路上发生的可能会造成交通拥堵的各类致因事件的数据。用于进行交通拥堵事件的处理的电子设备11可以从地图数据中获取拥堵事件的数据和致因事件的数据，并根据拥堵事件的数据和致因事件的数据进行拥堵致因分析处理，确定拥堵事件对应的致因事件，从而确定导致拥堵事件发生的原因(致因事件)。在确定拥堵事件对应致因事件之后，可以在地图应用中显示拥堵事件对应的致因事件，和/或，根据各拥堵事件对应的致因事件，生成拥堵数据报告，并发送拥堵数据报告，使得相关人员可以根据拥堵事件对应的致因事件躲避拥堵，或者及时地疏通拥堵路段、缓解交通拥堵，能够提高交通拥堵的治理效率。
图2是本公开第一实施例提供的交通拥堵事件的处理方法流程图。本实施例提供的交通拥堵事件的处理方法具体可以为用于对交通拥堵事件进行致因分析处理的电子设备，可以是地图应用运行的终端设备或者服务器等。在其他实施例中，电子设备还可以采用其他方式实现，本实施例此处不做具体限定。
如图2所示，该方法具体步骤如下：
步骤S201、从地图数据中获取拥堵事件的数据和致因事件的数据，其中致因事件包括道路上发生的会造成交通拥堵的多类事件。
本实施例中，地图数据可以是地图应用提供的地图数据，包括道路上发生的拥堵事件的数据，以及道路上发生的可能会造成交通拥堵的致因事件。
拥堵事件可以包括道路拥堵事件和路口拥堵事件。
道路拥堵事件的数据可以包括：拥堵开始时间、拥堵结束时间、拥堵源坐标、拥堵源坐标集合。
其中，拥堵源坐标是指道路拥堵事件发生的关键坐标点，一个道路拥堵事件可以 包括一个或者多个拥堵源坐标。
拥堵源坐标集合包括道路拥堵事件发生的很多个坐标点，渲染到地图上之后形成一条线段，也即道路拥堵事件的拥堵源坐标连线，是由拥堵源坐标集合中的坐标点构成的。
另外，道路拥堵事件的数据还可以包括：事件标识(如事件编号等)，拥堵类型，拥堵位置描述，拥堵持续时间，拥堵所在道路的道路编号、道路名称、道路类型和道路方向，拥堵距离，拥堵指数，拥堵路段车辆的平均速度等。
其中，道路拥堵事件的拥堵类型包括异常拥堵或常规拥堵，常规拥堵是指经常性地拥堵，异常拥堵是相对于常规拥堵突发的非经常性地拥堵。例如，当拥堵第一次发生时，会被设置为异常拥堵。当同一拥堵发生达到一定次数时，会被设置为常规拥堵。
拥堵位置描述时道路拥堵事件发生的位置的文字描述，例如“东二环辅路附近”等。
拥堵所在道路的道路类型包括：高速、环路及快速路、主干、次干、支干等。道路方向是指道路上车辆的行驶方向。
拥堵指数用于衡量当前的拥堵情况是否严重。
路口拥堵事件的数据可以包括：拥堵开始时间，拥堵结束时间，拥堵类型，拥堵所在路口的路口编号、路口名称和路口坐标。
其中，路口拥堵事件的拥堵类型包括路口死锁事件和路口溢流事件。路口死锁事件是指路口进出口道路均拥堵严重。溢流事件是指路口进口道路或者出口道路的拥堵不严重。例如，路口死锁事件指路口进出口道路的平均车速均小于预设速度阈值，溢流事件是指路口进口道路或者出口道路的平均车速大于或等于预设速度阈值。其中预设速度阈值可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
拥堵所在路口的路口坐标可以是路口的中心点坐标，可以是经纬度坐标。
另外，路口拥堵事件的数据还可以包括：事件标识(如事件编号)、拥堵持续时间、拥堵距离、拥堵指数、拥堵路段车辆的平均速度等。其中，拥堵指数用于衡量当前的拥堵情况是否严重。
本实施例中，致因事件包括道路上发生的会造成交通拥堵的多类事件。致因事件的数据可以包括：事件标识(如事件编号)、事件开始时间、事件结束时间、致因事件坐标、致因事件位置描述、致因事件的类型等。
其中，致因事件的类型包括但不限于：交通事故、故障车、道路积水、大雾、道路结冰、道路积雪、道路施工、交通管制、危险路段。
步骤S202、对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度。
本实施例中，根据拥堵事件的数据和致因事件的数据，将各致因事件与每一拥堵事件进行关联，确定各致因事件与拥堵事件的关联置信度。致因事件与拥堵事件的关联置信度表示致因事件和拥堵事件之间的关联程度。
示例性地，将各致因事件与拥堵事件进行关联时，可以根据拥堵时间发生的时间和位置，以及各致因事件发生的时间和位置，从时间相关度和空间相关度等方面进行致因事件与拥堵事件关联程度的分析，并确定致因事件与拥堵事件的关联置信度。
步骤S203、根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件。
在确定各致因事件与拥堵事件的关联置信度之后，可以根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件。
示例性地，根据各致因事件与拥堵事件的关联置信度，可以将与拥堵事件的关联置信度最大的致因事件，确定为拥堵事件对应的致因事件。
示例性地，根据各致因事件与拥堵事件的关联置信度，可以将与拥堵事件的关联置信度大于置信度阈值的多个致因事件，确定为拥堵事件对应的致因事件。其中，置信度阈值可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
本实施例通过从地图数据中获取拥堵事件的数据和致因事件的数据，对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度；根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件，能够全面、及时、准确地确定导致交通拥堵事件的原因，从而为及时地缓解交通拥堵提供依据，提高交通拥堵治理效率，减少交通拥堵造成的影响。
图3是本公开第二实施例提供的交通拥堵事件的处理方法流程图。在上述第一实施例的基础上，本实施例中，预先设置多种致因分析策略，以及每一致因分析策略对应的置信度系数。对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度，包括：对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度；根据每一致因分析策略对应的置信度系数，以及采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度，确定各致因事件与拥堵事件的关联置信度。
如图3所示，该方法具体步骤如下：
步骤S301、从地图数据中获取拥堵事件的数据和致因事件的数据，其中致因事件包括道路上发生的会造成交通拥堵的多类事件。
本实施例中，可以定时地从地图数据中获取上一时段内的拥堵事件数据和致因事件数据，并根据上一时段内的拥堵事件数据和致因事件数据，及时地确定拥堵事件对应的致因事件，以便于相关人员根据上一时段内拥堵事件对应的致因事件，制定及时有效的调控策略，从而及时地缓解交通拥堵，提高交通拥堵的治理效率。
本实施例中，地图数据可以是地图应用提供的地图数据，包括道路上发生的拥堵事件的数据，以及道路上发生的可能会造成交通拥堵的致因事件。
拥堵事件可以包括道路拥堵事件和路口拥堵事件。
道路拥堵事件的数据可以包括：拥堵开始时间、拥堵结束时间、拥堵源坐标、拥堵源坐标集合。
其中，拥堵源坐标是指道路拥堵事件发生的关键坐标点，一个道路拥堵事件可以包括一个或者多个拥堵源坐标。
拥堵源坐标集合包括道路拥堵事件发生的很多个坐标点，渲染到地图上之后形成一条线段，也即道路拥堵事件的拥堵源坐标连线，是由拥堵源坐标集合中的坐标点构成的。
另外，道路拥堵事件的数据还可以包括：事件标识(如事件编号等)，拥堵类型，拥堵位置描述，拥堵持续时间，拥堵所在道路的道路编号、道路名称、道路类型和道路方向，拥堵距离，拥堵指数，拥堵路段车辆的平均速度等。
其中，道路拥堵事件的拥堵类型包括异常拥堵或常规拥堵，常规拥堵是指经常性地拥堵，异常拥堵是相对于常规拥堵突发的非经常性地拥堵。例如，当拥堵第一次发生时，会被设置为异常拥堵。当同一拥堵发生达到一定次数时，会被设置为常规拥堵。
拥堵位置描述时道路拥堵事件发生的位置的文字描述，例如“东二环辅路附近”等。
拥堵所在道路的道路类型包括：高速、环路及快速路、主干、次干、支干等。道路方向是指道路上车辆的行驶方向。
拥堵指数用于衡量当前的拥堵情况是否严重。
路口拥堵事件的数据可以包括：拥堵开始时间，拥堵结束时间，拥堵类型，拥堵所在路口的路口编号、路口名称和路口坐标。
其中，路口拥堵事件的拥堵类型包括路口死锁事件和路口溢流事件。路口死锁事 件是指路口进出口道路均拥堵严重。溢流事件是指路口进口道路或者出口道路的拥堵不严重。例如，路口死锁事件指路口进出口道路的平均车速均小于预设速度阈值，溢流事件是指路口进口道路或者出口道路的平均车速大于或等于预设速度阈值。其中预设速度阈值可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
拥堵所在路口的路口坐标可以是路口的中心点坐标，可以是经纬度坐标。
另外，路口拥堵事件的数据还可以包括：事件标识(如事件编号)、拥堵持续时间、拥堵距离、拥堵指数、拥堵路段车辆的平均速度等。其中，拥堵指数用于衡量当前的拥堵情况是否严重。
本实施例中，致因事件包括道路上发生的会造成交通拥堵的多类事件。致因事件的数据可以包括：事件标识(如事件编号)、事件开始时间、事件结束时间、致因事件坐标、致因事件位置描述、致因事件的类型等。
其中，致因事件的类型包括但不限于：交通事故、故障车、道路积水、大雾、道路结冰、道路积雪、道路施工、交通管制、危险路段。
可选地，在获取到拥堵事件的数据和致因事件的数据，可以对拥堵事件的数据和致因事件的数据进行数据清洗和数据转换等预处理。
其中，数据清洗包括去除重复数据和无效数据等。无效数据是指缺乏所需的关键信息的数据。
数据转换是指将数据转换为指定的格式，包括删减无用的事件信息、数据格式转换等。其中，无用的事件信息是指在确定拥堵事件对应的致因事件的过程中不会用到的事件信息，例如，拥堵事件的平均速度、位置描述等。
可选地，可以将数据预处理后的拥堵事件和致因事件的数据进行存储，保留拥堵事件和致因事件的原始数据，以便于后续查询。
本实施例中，可以预先设置多种致因分析策略，以及每一致因分析策略对应的置信度系数。在获取到拥堵事件的数据和致因事件的数据之后，通过以下步骤S302-S303，对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度；根据每一致因分析策略对应的置信度系数，以及采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度，确定各致因事件与拥堵事件的关联置信度，这样，对于任一拥堵事件，采用多种致因分析策略，从致因事件与拥堵事件的时间相关度和空间相关度这两方面，对致因事件与拥堵事件进行关联，能够全面地、精准地确定各致因事件与拥堵事件的关联置信度。
步骤S302、对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度。
具体地，对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与拥堵事件相关的备选致因事件，并确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，从而实现各致因事件与拥堵事件的时间相关度和空间相关度的精准分析。
本实施例中，可以将拥堵事件分为道路拥堵事件和路口拥堵事件两大类，每一拥堵事件的数据中包括拥堵事件属于上述两大类拥堵事件中的哪一类，是道路拥堵事件还是路口拥堵事件。
对于道路拥堵事件，可以设置多种道路拥堵致因分析策略，在将道路拥堵事件与致因事件进行关联时，可以采用其中任意一种道路拥堵致因分析策略、或者同时采用多种道路拥堵致因分析策略计算致因事件与道路拥堵事件的关联置信度。取关联置信度最大的致因事件，作为道路拥堵事件对应的致因事件。
具体地，若同时采用多种道路拥堵致因分析策略，则对于任一道路拥堵事件，分别采用一种道路拥堵致因分析策略计算致因事件与拥堵事件的时间相关度和空间相关度，并根据该道路拥堵致因分析策略对应的置信度系数，确定各致因事件与道路拥堵事件的关联置信度，得到使用该种道路拥堵致因分析策略得到的分析结果。综合分别使用每一道路拥堵致因分析策略确定的分析结果，对于每一道路拥堵事件，取与该道路拥堵事件的关联置信度最大的致因事件，作为道路拥堵事件对应的致因事件。
一种可选地实施方式中，对于任一道路拥堵事件，可以采用第一道路拥堵致因分析策略来确定各致因事件与该道路拥堵事件的关联置信度。
具体地，对每一拥堵事件，采用第一道路拥堵致因分析策略，根据拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与拥堵事件相关的备选致因事件，可以采用如下方式实现：
根据拥堵事件的拥堵源坐标点，确定拥堵事件对应的第一拥堵缓冲区，第一拥堵缓冲区包括以拥堵源坐标点为中心的第一预设范围内的区域；根据拥堵事件的拥堵开始时间，筛选出从第一时刻至当前时刻在第一拥堵缓冲区内发生的指定类型的致因事件，得到第一备选致因事件，其中，第一时刻在拥堵开始时间之前且与拥堵开始时间间隔第一预设时长。
其中，第一预设范围可以根据实际应用场景的需要进行设置和调整，也即是，第一拥堵缓冲区的形状和大小可以根据实际应用场景的需要进行设置和调整，此处不做 具体限定。
第一预设时长可以根据实际应用场景的需要进行设置和调整，例如第一预设时长可以是5分钟、10分钟、20分钟等，此处不做具体限定。
示例性地，第一拥堵缓冲区可以包括以拥堵源坐标点为中心的第一预设范围的圆形区域，该圆形区域的半径由第一预设范围确定；或者，第一拥堵缓冲区可以包括以拥堵源坐标点为中心的矩形区域，该矩形区域的边与中心的距离由第一预设范围确定。
其中，第一预设范围可以根据实际应用场景的需要进行设置和调整，例如，第一预设范围可以是半径为500米(或者2500、3000米)的圆内等，此处对于半径的具体数值不做具体限定。
进一步地，确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
确定每一第一备选致因事件与拥堵事件的时间相关度均为第一预设相关度；根据每一第一备选致因事件发生的位置与拥堵源坐标点之间的距离，确定每一第一备选致因事件与拥堵事件的空间相关度。
其中，第一预先相关度可以设置为时间相关度的最大值，例如，第一预设相关度可以为1，另外，第一预先相关度可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
可选地，可以根据预先设置的一个或者多个距离范围,以及每一距离范围对应的预设相关度，确定第一备选致因事件发生的位置与拥堵源坐标点之间的距离对应的距离范围,将该距离范围对应的预设相关度作为第一备选致因事件与拥堵事件的空间相关度。
其中，设置的距离范围以及距离范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
可选地，可以根据预先设置的距离阈值，若第一备选致因事件发生的位置与拥堵源坐标点之间的距离小于或等于第一距离阈值，则确定第一备选致因事件与拥堵事件的空间相关度为第二预设相关度。若第一备选致因事件发生的位置与拥堵源坐标点之间的距离大于第一距离阈值，且小于或等于第二距离阈值，则确定第一备选致因事件与拥堵事件的空间相关度为第三预设相关度。若第一备选致因事件发生的位置与拥堵源坐标点之间的距离大于第二距离阈值，则确定第一备选致因事件与拥堵事件的空间相关度为第四预设相关度。
其中，第二预设相关度为空间相关度的最大值，第二预设相关度可以根据实际应 用场景的需要进行设置和调整，例如第二预设相关度可以为1，此处不做具体限定。
第三预设相关度小于第二预设相关度，第四预设相关度小于第三预设相关度，第三预设相关度和第四预设相关度的值可以根据实际应用场景的需要进行设置和调整，例如第三预设相关度可以为0.8，第四预设相关度可以为0.5，此处不做具体限定。
第一距离阈值小于第二距离阈值，第一距离阈值和第二距离阈值可以根据实际应用场景的需要进行设置和调整，例如第一距离阈值可以为0.8千米(km)，第二距离阈值可以为1.5km，此处不做具体限定。
示例性地，第一拥堵缓冲区包括以拥堵源坐标点为中心、半径为2.5km的圆形区域，第一距离阈值为0.8km，第二距离阈值可以为1.5km，第二预设相关度可以为1，第三预设相关度可以为0.8，第四预设相关度可以为0.5，用S表示第一备选致因事件发生的位置与拥堵源坐标点之间的距离，用SC表示第一备选致因事件与拥堵事件的空间相关度，则有：若S<＝0.8km，则SC＝1；若0.8km<S<＝1.5km，则SC＝0.8；若1.5km<S<＝2.5km，则SC＝0.5。
通过第一道路拥堵致因分析策略，能够针对指定类型的致因事件的影响范围，设置拥堵事件对应的第一拥堵缓冲区，并筛选出在拥堵事件开始前第一预设时长至当前时刻内，在拥堵事件的第一拥堵缓冲区(拥堵事件发生位置附近)发生的指定类型的备选致因事件。对于这些类型的备选致因事件，如果备选致因事件发生在拥堵事件的第一拥堵缓冲区内，可以确定备选致因事件与拥堵事件在时间上强相关，那么直接将第一备选致因事件与拥堵事件的时间相关度均为第一预设相关度。进一步地，根据每一第一备选致因事件发生的位置与拥堵源坐标点之间的距离，确定每一第一备选致因事件与拥堵事件的空间相关度，能够精准地确定指定类型的致因事件与拥堵事件的时间相关度和空间相关度，从而能够精准地确定指定类型的致因事件与拥堵事件的关联置信度。
可选地，指定类型包括以下至少一种：道路施工、交通管制。这样，通过第一道路拥堵致因分析策略，能够针对道路施工、交通管制等指定类型的致因事件，筛选出与道路拥堵事件在时间上强相关的指定类型的致因事件，能够提高致因事件与道路拥堵事件的时间相关性和空间相关性的精准度。
另外，指定类型还可以包括其他致因事件的类型，指定类型具体包括哪些致因事件的类型，可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
可选地，根据拥堵事件的拥堵源坐标点，确定拥堵事件对应的第一拥堵缓冲区之前，还包括：对拥堵事件的拥堵源坐标点进行去重处理，针对去重处理后保留的拥堵 源坐标点进行后续处理，能够大大减少重复的数据计算，提高致因事件与拥堵事件的关联置信度的计算效率，提高方法的及时性和效率。
需要说明的是，如果同一道路拥堵事件包括多条拥堵数据，则可以分别针对每一条拥堵数据，采用第一道路拥堵致因分析策略，确定各致因事件与该道路拥堵事件的时间相关度、空间相关度和关联置信度。对于同一拥堵事件，可能计算得到了同一致因事件与该拥堵事件的多组时间相关度和空间相关度，也就可以确定同一致因事件与该拥堵事件的多个关联置信度，最终取其中的最大值作为该致因事件与该拥堵事件的关联置信度。
一种可选地实施方式中，对于任一道路拥堵事件，可以采用第二道路拥堵致因分析策略来确定各致因事件与该道路拥堵事件的关联置信度。
具体地，对每一拥堵事件，采用第二道路拥堵致因分析策略，根据拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与拥堵事件相关的备选致因事件，可以采用如下方式实现：
拥堵事件为道路拥堵事件，根据拥堵事件的拥堵源坐标连线，确定拥堵事件对应的第二拥堵缓冲区，第二拥堵缓冲区包括与拥堵源坐标连线的最短距离小于第一预设距离的所有位置点；根据拥堵事件的拥堵开始时间，筛选出第二时刻至当前时刻在第二拥堵缓冲区内发生的特定类型的致因事件，得到第二备选致因事件，其中，第二时刻在拥堵开始时间之前且与拥堵开始时间间隔第二预设时长。
其中，拥堵源坐标连线是根据拥堵事件的拥堵源坐标集合确定的一个线段。任一点与拥堵源坐标连线的最短距离是指：该点与拥堵源坐标连线上任意点的距离中的最小值。
第一预设距离可以根据实际应用场景的需要进行设置和调整，例如，第一预设距离为15米、20米、30米等，此处不做具体限定。
第二预设时长可以根据实际应用场景的需要进行设置和调整，例如第二预设时长可以是5分钟、10分钟、20分钟等，此处不做具体限定。
进一步地，确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
根据每一第二备选致因事件的开始时间与拥堵开始时间之间的时间间隔，确定每一第二备选致因事件与拥堵事件的时间相关度；根据每一第二备选致因事件发生的位置与拥堵源坐标连线之间的距离，确定每一第二备选致因事件与拥堵事件的空间相关度。
可选地，第二备选致因事件发生的位置与拥堵源坐标连线之间的距离，可以是第二备选致因事件发生的位置点到拥堵源坐标连线所在直线的垂直距离。
可选地，第二备选致因事件发生的位置与拥堵源坐标连线之间的距离，可以是第二备选致因事件发生的位置点到拥堵源坐标连线行任意点的距离中的最短距离。
示例性地，可以根据预先设置的一个或者多个时间范围,以及每一时间范围对应的预设相关度，确定第二备选致因事件的开始时间与拥堵开始时间之间的时间间隔对应的时间范围,将该时间范围对应的预设相关度作为第二备选致因事件与拥堵事件的时间相关度。
其中，设置的时间范围以及时间范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用T表示第二备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔，用TC表示第二备选致因事件与拥堵事件的时间相关度，若T<＝5分钟，则TC＝1；若5分钟<T<＝15分钟，则TC＝0.8；若15分钟<T<＝30分钟，则TC＝0.5；若T>30分钟，则TC＝0.1。
示例性地，可以根据预先设置的一个或者多个距离范围,以及每一距离范围对应的预设相关度，确定第二备选致因事件发生的位置与拥堵源坐标连线之间的距离对应的距离范围,将该距离范围对应的预设相关度作为第二备选致因事件与拥堵事件的空间相关度。
其中，设置的距离范围以及距离范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用S2表示第二备选致因事件发生的位置与拥堵源坐标连线之间的距离，用SC2表示第二备选致因事件与拥堵事件的空间相关度，若S2<＝5m，则SC2＝1；若5m<S2<＝10m，则SC2＝0.8；若10m<S2<＝20m，则SC2＝0.5。
通过第二道路拥堵致因分析策略，能够针对特定类型的致因事件的影响范围，设置拥堵事件对应的第二拥堵缓冲区，并筛选出在拥堵事件开始前第二预设时长至当前时刻内，在拥堵事件的第二拥堵缓冲区(拥堵事件发生位置附近)发生的特定类型的备选致因事件。对于这些特定类型的备选致因事件，如果备选致因事件发生在拥堵事件的第二拥堵缓冲区内，可以确定备选致因事件与拥堵事件在时间和空间上均具有一定的相关性，根据每一第二备选致因事件的开始时间与拥堵开始时间之间的时间间隔，确定每一第二备选致因事件与拥堵事件的时间相关度；根据每一第二备选致因事件发生的位置与拥堵源坐标连线之间的距离，确定每一第二备选致因事件与拥堵事件的空 间相关度，能够精准地确定特定类型的致因事件与拥堵事件的时间相关度和空间相关度，从而能够精准地确定特定类型的致因事件与拥堵事件的关联置信度。
可选地，特定类型包括以下至少一种：交通事故、故障车、道路积水、道路结冰、道路积雪。这样，通过第二道路拥堵致因分析策略，能够针对交通事故、故障车、道路积水、道路结冰、道路积雪等特定类型的致因事件，筛选出与道路拥堵事件在时间和空间上具有较强相关性的特定类型的致因事件，能够提高致因事件与道路拥堵事件的时间相关性和空间相关性的精准度。
另外，特定类型还可以包括其他致因事件的类型，特定类型具体包括哪些致因事件的类型，可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
可选地，根据拥堵事件的拥堵源坐标连线，确定拥堵事件对应的第二拥堵缓冲区之前，还包括：
对拥堵事件的拥堵源坐标连线进行去重处理。针对去重处理后保留的拥堵源坐标连线进行后续处理，能够大大减少重复的数据计算，提高致因事件与拥堵事件的关联置信度的计算效率，提高方法的及时性和效率。
需要说明的是，如果同一道路拥堵事件包括多条拥堵数据，则可以分别针对每一条拥堵数据，采用第二道路拥堵致因分析策略，确定各致因事件与该道路拥堵事件的时间相关度、空间相关度和关联置信度。对于同一拥堵事件，可能计算得到了同一致因事件与该拥堵事件的多组时间相关度和空间相关度，也就可以确定同一致因事件与该拥堵事件的多个关联置信度，最终取其中的最大值作为该致因事件与该拥堵事件的关联置信度。
一种可选地实施方式中，对于任一道路拥堵事件，可以采用第三道路拥堵致因分析策略来确定各致因事件与该道路拥堵事件的关联置信度。
具体地，对每一拥堵事件，采用第三道路拥堵致因分析策略，根据拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与拥堵事件相关的备选致因事件，可以采用如下方式实现：
拥堵事件为道路拥堵事件，根据拥堵事件的拥堵源坐标点，确定拥堵源坐标点所在的路段和下游路口，将拥堵源坐标点所在的路段和下游路口作为拥堵事件对应的第三拥堵缓冲区；根据拥堵事件的拥堵开始时间，筛选出第三时刻至当前时刻在第三拥堵缓冲区内发生的致因事件，得到第三备选致因事件，其中，第三时刻在拥堵开始时间之前且与拥堵开始时间间隔第三预设时长。
其中，下游路口是指拥堵源坐标点所在的路段最近的下一个路口。第三预设时长 可以根据实际应用场景的需要进行设置和调整，例如第三预设时长可以是5分钟、10分钟、20分钟等，此处不做具体限定。
进一步地，确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
根据每一第三备选致因事件的开始时间与拥堵开始时间之间的时间间隔，确定每一第三备选致因事件与拥堵事件的时间相关度；确定每一第三备选致因事件与拥堵事件的空间相关度均为第二预设相关度。
示例性地，可以根据预先设置的一个或者多个时间范围,以及每一时间范围对应的预设相关度，确定第二备选致因事件的开始时间与拥堵开始时间之间的时间间隔对应的时间范围,将该时间范围对应的预设相关度作为第二备选致因事件与拥堵事件的时间相关度。其中，设置的时间范围以及时间范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用T3表示第三备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔，用TC3表示第三备选致因事件与拥堵事件的时间相关度，若T3<＝5分钟，则TC3＝1；若5分钟<T3<＝15分钟，则TC3＝0.8；若15分钟<T3<＝30分钟，则TC3＝0.5；若T3>30分钟，则TC3＝0.1。
其中，第二预先相关度可以设置为空间相关度的最大值，例如，第二预设相关度可以为1，另外，第二预先相关度可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
通过第三道路拥堵致因分析策略，能够针对全部类型的致因事件，将拥堵事件的拥堵源坐标点所在的路段和下游路口，设置为拥堵事件对应的第三拥堵缓冲区，并筛选出在拥堵事件开始前第三预设时长至当前时刻内，在拥堵事件的第三拥堵缓冲区发生的第三备选致因事件。第三备选致因事件发生在拥堵事件所在的路段和下游路口，可以确定第三备选致因事件与拥堵事件在空间上强相关，那么直接将第三备选致因事件与拥堵事件的空间相关度设置为第二预设相关度。进一步地，根据每一第三备选致因事件的开始时间与拥堵开始时间之间的时间间隔，确定每一第三备选致因事件与拥堵事件的时间相关度，能够精准地确定第三致因事件与拥堵事件的时间相关度和空间相关度，从而能够精准地确定致因事件与拥堵事件的关联置信度。
可选地，采用第三道路拥堵致因分析策略，根据拥堵事件的拥堵源坐标点，确定拥堵源坐标点所在的路段和下游路口，将拥堵源坐标点所在的路段和下游路口作为拥堵事件对应的第三拥堵缓冲区之前，还包括：
对拥堵事件的拥堵源坐标点进行去重处理。针对去重处理后保留的拥堵源坐标点进行后续处理，能够大大减少重复的数据计算，提高致因事件与拥堵事件的关联置信度的计算效率，提高方法的及时性和效率。
一种可选地实施方式中，对于任一道路拥堵事件，可以采用第四道路拥堵致因分析策略来确定各致因事件与该道路拥堵事件的关联置信度。
具体地，该步骤可以采用如下方式实现：
拥堵事件为道路拥堵事件，获取拥堵事件对应的用户上报事件，用户上报事件包含至少一个与拥堵事件相关的第四备选致因事件；确定至少一个第四备选致因事件与拥堵事件的时间相关度和空间相关度。
在实际应用中，用户可以向地图应用提交用户上报事件。通常，用户上报事件包括针对的拥堵事件，以及该拥堵事件的指示一个相关的致因事件。
由于用户上报事件是根据道路实际情况进行上报的，具有很高的可信度，因此，该实施方式中，将用户上报事件中与拥堵事件相关的至少一个致因事件作为拥堵事件的第四备选致因事件，并将第四备选致因事件与拥堵事件的时间相关度设置为第一预设相关度，将第四备选致因事件与拥堵事件的空间相关度设置为第二预设相关度，能够准确地确定致因事件与拥堵事件的时间相关度和空间相关度，从而准确地确定致因事件与拥堵事件的关联之信息度。
本实施例中，对于路口拥堵事件，可以采用至少一种路口拥堵致因分析策略计算致因事件与拥堵事件的时间相关度和空间相关度，并根据路口拥堵致因分析策略对应的置信度系数，确定使用其中每一种路口拥堵致因分析策略计算得到的各致因事件与路口拥堵事件的关联置信度。取关联置信度最大的致因事件，作为路口拥堵事件对应的致因事件。
具体地，若同时采用多种路口拥堵致因分析策略，则对于任一路口拥堵事件，分别采用一种路口拥堵致因分析策略计算致因事件与拥堵事件的时间相关度和空间相关度，并根据该路口拥堵致因分析策略对应的置信度系数，确定各致因事件与拥堵事件的关联置信度，得到使用该种路口拥堵致因分析策略得到的分析结果。综合分别使用每一路口拥堵致因分析策略确定的分析结果，对于每一路口拥堵事件，取与该路口拥堵事件的关联置信度最大的致因事件，作为路口拥堵事件对应的致因事件。
一种可选的实施方式中，对于任一路口拥堵事件，可以采用第一路口拥堵致因分析策略来确定各致因事件与该路口拥堵事件的关联置信度。
具体地，对每一拥堵事件，采用第一路口拥堵致因分析策略，根据拥堵事件的数 据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
拥堵事件为路口拥堵事件，根据拥堵事件所在的路口坐标点，确定拥堵事件对应的第四拥堵缓冲区，第四拥堵缓冲区包括以路口坐标点为中心的第二预设范围内的区域；根据拥堵事件的拥堵开始时间，筛选出第四时刻至当前时刻在第四拥堵缓冲区内发生的致因事件，得到第五备选致因事件，其中，第四时刻在拥堵开始时间之前且与拥堵开始时间间隔第四预设时长。
其中，第二预设范围可以根据实际应用场景的需要进行设置和调整，也即是，第四拥堵缓冲区的形状和大小可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
第四预设时长可以根据实际应用场景的需要进行设置和调整，例如第四预设时长可以是5分钟、10分钟、20分钟等，此处不做具体限定。
示例性地，第四拥堵缓冲区可以包括以路口坐标点为中心的第二预设范围的圆形区域，该圆形区域的半径由第二预设范围确定；或者，第四拥堵缓冲区可以包括以路口坐标点为中心的矩形区域，该矩形区域的边与中心的距离由第二预设范围确定。
其中，第二预设范围可以根据实际应用场景的需要进行设置和调整，例如，第二预设范围可以是半径为500米(或者400米、800米)的圆内等，此处对于半径的具体数值不做具体限定。
进一步地，确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
备选致因事件包括第五备选致因事件，根据每一备选致因事件的开始时间与拥堵开始时间，确定每一备选致因事件与拥堵事件的时间相关度；根据每一备选致因事件发生的位置与路口坐标点之间的距离，确定每一备选致因事件与拥堵事件的空间相关度。
可选地，根据每一第五备选致因事件的开始时间与拥堵开始时间，若第五备选致因事件的开始时间早于拥堵事件的拥堵开始时间，则确定第五备选致因事件与拥堵事件的时间相关度为第一预设相关度。
若第五备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则根据第五备选致因事件的开始时间与拥堵开始时间的时间间隔，确定第五备选致因事件与拥堵事件的时间相关度。这样，能够精准地确定备选致因事件与拥堵事件的时间相关度，从而提高致因事件与拥堵事件的关联置信度的精准度。
进一步地，可以根据预先设置的一个或者多个时间范围,以及每一时间范围对应的预设相关度。若第五备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则确定第五备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔对应的时间范围,将该时间范围对应的预设相关度作为第五备选致因事件与拥堵事件的时间相关度。
其中，设置的时间范围以及时间范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用TC5表示第五备选致因事件与拥堵事件的时间相关度，若第五备选致因事件的开始时间早于拥堵事件的拥堵开始时间，则TC5＝1。若第五备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则用T5表示第五备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔，则有：若T5<＝5分钟，则TC5＝0.8；若5分钟<T5<＝15分钟，则TC5＝0.5；若15分钟<T5，则TC5＝0.1。
示例性地，可以根据预先设置的一个或者多个距离范围,以及每一距离范围对应的预设相关度，确定第五备选致因事件发生的位置与路口坐标点之间的距离对应的距离范围,将该距离范围对应的预设相关度作为第五备选致因事件与拥堵事件的空间相关度。
其中，设置的距离范围以及距离范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用S5表示第五备选致因事件发生的位置与路口坐标点之间的距离，用SC5表示第五备选致因事件与拥堵事件的空间相关度，若S5<＝0.2km，则SC5＝1；若0.2km<S5<＝0.5km，则SC5＝0.5。
通过第一路口拥堵致因分析策略，能够针对路口拥堵事件，设置路口拥堵事件对应的第四拥堵缓冲区，并筛选出在拥堵事件开始前第四预设时长至当前时刻内，在拥堵事件的第四拥堵缓冲区(拥堵事件发生的路口附近)发生第五备选致因事件，可以确定第五备选致因事件与拥堵事件在时间和空间上均具有一定的相关性，根据每一第五备选致因事件的开始时间与拥堵开始时间，确定每一第五备选致因事件与拥堵事件的时间相关度；根据每一第五备选致因事件发生的位置与路口坐标点之间的距离，确定每一第五备选致因事件与拥堵事件的空间相关度，能够精准地确定致因事件与路口拥堵事件的时间相关度和空间相关度，从而能够精准地确定致因事件与路口拥堵事件的关联置信度。
一种可选的实施方式中，对于任一路口拥堵事件，可以采用第二路口拥堵致因分 析策略来确定各致因事件与该路口拥堵事件的关联置信度。
具体地，对于属于路口死锁事件的拥堵事件，采用第二路口拥堵致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
拥堵事件为路口拥堵事件且拥堵事件为路口死锁事件，根据拥堵事件的拥堵开始时间，筛选出第五时刻至当前时刻在拥堵事件所在路口的进口路段上发生的致因事件，得到第六备选致因事件。
其中，第五时刻在拥堵开始时间之前且与拥堵开始时间间隔第五预设时长。
第五预设时长可以根据实际应用场景的需要进行设置和调整，例如第五预设时长可以是5分钟、10分钟、20分钟等，此处不做具体限定。
进一步地，确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
备选致因事件包括第六备选致因事件，根据每一第六备选致因事件的开始时间与拥堵开始时间，确定第六备选致因事件与拥堵事件的时间相关度；确定每一第六备选致因事件与拥堵事件的空间相关度为第二预设相关度。
可选地，根据每一第六备选致因事件的开始时间与拥堵开始时间，若第六备选致因事件的开始时间早于拥堵事件的拥堵开始时间，则确定第六备选致因事件与拥堵事件的时间相关度为第一预设相关度。
若第六备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则根据第六备选致因事件的开始时间与拥堵开始时间的时间间隔，确定第六备选致因事件与拥堵事件的时间相关度。这样，能够精准地确定备选致因事件与拥堵事件的时间相关度，从而提高致因事件与拥堵事件的关联置信度的精准度。
进一步地，可以根据预先设置的一个或者多个时间范围,以及每一时间范围对应的预设相关度。若第六备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则确定第六备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔对应的时间范围,将该时间范围对应的预设相关度作为第六备选致因事件与拥堵事件的时间相关度。
其中，设置的时间范围以及时间范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用TC6表示第六备选致因事件与拥堵事件的时间相关度，若第六备选致因事件的开始时间早于拥堵事件的拥堵开始时间，则TC6＝1。若第六备选致因事件的开 始时间不早于拥堵事件的拥堵开始时间，则用T6表示第六备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔，则有：若T6<＝5分钟，则TC6＝0.8；若5分钟<T6<＝15分钟，则TC6＝0.5；若15分钟<T6，则TC6＝0.1。
通过第二路口拥堵致因分析策略，针对属于路口死锁事件的拥堵事件，筛选出第五时刻至当前时刻在拥堵事件所在路口的进口路段上发生的致因事件，得到第六备选致因事件，可以确定第六备选致因事件与路口死锁事件在空间上强相关，那么直接将第六备选致因事件与路口死锁事件的空间相关度设置为第二预设相关度。进一步地，根据第六备选致因事件的开始时间与拥堵开始时间，确定第六备选致因事件与路口死锁事件的时间相关度，能够精准地确定第六致因事件与拥堵事件的时间相关度和空间相关度，从而能够精准地确定致因事件与拥堵事件的关联置信度。
一种可选的实施方式中，对于任一路口拥堵事件，可以采用第三路口拥堵致因分析策略来确定各致因事件与该路口拥堵事件的关联置信度。
具体地，对于属于路口溢流事件的拥堵事件，采用第三路口拥堵致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
拥堵事件为路口拥堵事件且拥堵事件为路口溢流事件，采用第三路口拥堵致因分析策略，根据拥堵事件的拥堵开始时间，筛选出第六时刻至当前时刻在拥堵事件所在路口的出口路段上发生的致因事件，得到第七备选致因事件。
其中，第六时刻在拥堵开始时间之前且与拥堵开始时间间隔第六预设时长。
第六预设时长可以根据实际应用场景的需要进行设置和调整，例如第六预设时长可以是5分钟、10分钟、20分钟等，此处不做具体限定。
进一步地，确定每一备选致因事件与拥堵事件的时间相关度和空间相关度，可以采用如下方式实现：
备选致因事件包括第七备选致因事件，根据每一第七备选致因事件的开始时间与拥堵开始时间，确定第七备选致因事件与拥堵事件的时间相关度；确定每一第七备选致因事件与拥堵事件的空间相关度为第二预设相关度。
可选地，根据每一第七备选致因事件的开始时间与拥堵开始时间，若第七备选致因事件的开始时间早于拥堵事件的拥堵开始时间，则确定第七备选致因事件与拥堵事件的时间相关度为第一预设相关度。
若第七备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则根据第七备选致因事件的开始时间与拥堵开始时间的时间间隔，确定第七备选致因事件与拥堵事 件的时间相关度。这样，能够精准地确定备选致因事件与拥堵事件的时间相关度，从而提高致因事件与拥堵事件的关联置信度的精准度。
进一步地，可以根据预先设置的一个或者多个时间范围,以及每一时间范围对应的预设相关度。若第七备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，则确定第七备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔对应的时间范围,将该时间范围对应的预设相关度作为第七备选致因事件与拥堵事件的时间相关度。
其中，设置的时间范围以及时间范围对应的预设相关度，可以根据实际应用场景的需要进行设置，此处不做具体限定。
例如，用TC7表示第七备选致因事件与拥堵事件的时间相关度，若第七备选致因事件的开始时间早于拥堵事件的拥堵开始时间，则TC7＝1。若第七备选致因事件的开始时间不早于拥堵事件的拥堵开始时间，用T7表示第七备选致因事件的开始时间与拥堵事件的拥堵开始时间之间的时间间隔，则有：若T7<＝5分钟，则TC7＝0.8；若5分钟<T7<＝15分钟，则TC7＝0.5；若15分钟<T7，则TC7＝0.1。
通过第三路口拥堵致因分析策略，针对属于路口溢流事件的拥堵事件，筛选出第六时刻至当前时刻在拥堵事件所在路口的出口路段上发生的致因事件，得到第七备选致因事件，可以确定第七备选致因事件与路口溢流事件在空间上强相关，那么直接将第七备选致因事件与路口溢流事件的空间相关度设置为第二预设相关度。进一步地，根据第七备选致因事件的开始时间与拥堵开始时间，确定第七备选致因事件与路口死锁事件的时间相关度，能够精准地确定第七致因事件与拥堵事件的时间相关度和空间相关度，从而能够精准地确定致因事件与拥堵事件的关联置信度。
步骤S303、根据每一致因分析策略对应的置信度系数，以及采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度，确定各致因事件与拥堵事件的关联置信度。
本实施例中，还可以设置各个道路拥堵致因分析策略对应的置信度系数，对应的置信度系数越大，则采用该道路拥堵致因分析策略确定的致因事件与拥堵事件的时间相关度和空间相关度的可靠性越高。
示例性地，上述步骤S302中给出的四个道路拥堵致因分析策略中，第四道路拥堵致因分析策略对应的置信度系数大于第三道路拥堵致因分析策略对应的置信度系数，第三道路拥堵致因分析策略对应的置信度系数大于第一道路拥堵致因分析策略对应的置信度系数，第三道路拥堵致因分析策略对应的置信度系数大于第二道路拥堵致因分 析策略对应的置信度系数。第一道路拥堵致因分析策略对应的置信度系数，与第二道路拥堵致因分析策略对应的置信度系数可以相同，也可以不同。
例如，第一和第二道路拥堵致因分析策略对应的置信度系数可以为3，第三道路拥堵致因分析策略对应的置信度系数可以为5，第四道路拥堵致因分析策略对应的置信度系数可以为10。
可选地，在采用采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度之后，可以计算时间相关度、空间相关度和致因分析策略对应的置信度系数这三者的乘积，得到致因事件与拥堵事件的关联置信度。
本实施例中，对于同一拥堵事件，可能计算得到了同一致因事件与该拥堵事件的多组时间相关度和空间相关度，也就可以确定同一致因事件与该拥堵事件的多个关联置信度，取其中的最大值作为该致因事件与该拥堵事件的关联置信度。
步骤S304、根据各致因事件与拥堵事件的关联置信度，将与拥堵事件的关联置信度最大的致因事件，作为拥堵事件对应的致因事件。
在计算得到各致因事件与拥堵事件的关联置信度之后，可以根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件。
示例性地，根据各致因事件与拥堵事件的关联置信度，可以将与拥堵事件的关联置信度最大的致因事件，确定为拥堵事件对应的致因事件，能够精准地确定拥堵事件对应的致因事件。
示例性地，根据各致因事件与拥堵事件的关联置信度，可以将与拥堵事件的关联置信度大于置信度阈值的多个致因事件，确定为拥堵事件对应的致因事件。其中，置信度阈值可以根据实际应用场景的需要进行设置和调整，此处不做具体限定。
可选地，在确定拥堵事件对应的致因事件之后，可以将拥堵事件与致因事件的对应关系存储到数据库中，便于用户查询。
步骤S305、显示各拥堵事件对应的致因事件。
在最终确定拥堵事件对应的致因事件之后，可以通过地图应用显示各拥堵事件对应的致因事件，以及时地通知驾驶员根据需要躲避拥堵路段。
可选地，可以以列表的形式显示各拥堵事件对应的致因事件，以便于用户查看。
步骤S306、根据各拥堵事件对应的致因事件，生成拥堵数据报告，并发送拥堵数据报告。
在最终确定拥堵事件对应的致因事件之后，还可以根据各拥堵事件对应的致因事件，生成拥堵数据报告，并发送拥堵数据报告，以便于相关人员及时了解导致交通拥 堵的原因，并及时做出调控措施，及时地缓解交通拥堵，从而提高交通拥堵的治理效率。
其中，拥堵数据报告可以包括拥堵事件对应的致因事件，以及拥堵事件的统计信息，其中，拥堵事件的统计信息可以依据拥堵事件的拥堵类型、道路类型等信息进行统计。
可选地，还可以在地图应用上显示拥堵数据报告的全部或部分信息。例如，可以在地图应用中显示拥堵事件的统计信息。
示例性地，可以提供道路拥堵致因分析的数据查询界面(如图4所示)，用户可以通过在该界面上设置筛选条件，来对拥堵事件及其对应的致因事件进行查询。
例如，如图4所示，筛选条件可以包括：日期范围、日期类型、时段范围、拥堵类型、道路类型等，还可以设置“仅查看关联致因的拥堵”、“仅查看尚未消散的拥堵”等其他条件。其中道路类型支持多选。日期类型包括工作日、节假日、周末等。时段范围包括：高峰、早高峰、晚高峰等，并支持用户自选时段。拥堵类型包括常发拥堵和异常拥堵等，可以包括拥堵事件的拥堵类型中的一种或多种。道路类型根据拥堵事件的道路类型确定，可以包括拥堵事件的道路类型中的一种或多种。
根据用户设置的筛选条件，查询满足筛选条件的拥堵事件，并显示查询结果(如图5所示)。
本实施例的其他实施方式中，还可以根据各拥堵事件对应的致因事件，生成并显示躲避路线，以向自动驾驶车辆或驾驶员提供拥堵的躲避路线，从而能够缓解交通拥堵，提高交通拥堵的治理效率。
本实施例的一种可选的实施方式中，可以采用如图6所示的架构实现。如图6所示，该架构包括：数据同步模块、数据传输工具、数据预处理模块、数据存储模块、致因分析引擎、数据库。其中，数据同步模块用于从地图应用同步拥堵事件的数据和致因事件的数据，并将同步到的拥堵事件的数据和致因事件的数据通过数据传输工具传输到数据预处理模块。数据预处理模块用于对拥堵事件的数据和致因事件的数据进行数据预处理，将预处理后的数据发送到致因分析引擎和数据存储模块。致因分析引擎用于根据接收到的拥堵事件的数据和致因事件的数据，确定拥堵事件对应的致因事件，并将拥堵事件与致因事件的对应关系发送到数据存储模块。数据存储模块用于将拥堵事件的数据、致因事件的数据、拥堵事件与致因事件的对应关系存储到数据库中。相应于应用层的查询请求，可以从数据库中查询拥堵相关数据，并在应用层展示查询结果。
可选地，数据传输工具可以采用消息队列的方式传输数据，例如数据传输工具可以使用kafka等实现，以保证数据不对丢失。
本实施例中，预先设置多种致因分析策略，以及每一致因分析策略对应的置信度系数。对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度；根据每一致因分析策略对应的置信度系数，以及采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度，确定各致因事件与拥堵事件的关联置信度，能够更加全面地、及时地、精准地确定导致交通拥堵事件的原因，从而为及时地缓解交通拥堵提供依据，提高交通拥堵治理效率，减少交通拥堵造成的影响。
图7是本公开第三实施例提供的交通拥堵事件的处理设备示意图。本公开实施例提供的交通拥堵事件的处理设备可以执行交通拥堵事件的处理方法实施例提供的处理流程。如图7所示，该交通拥堵事件的处理设备70包括：数据同步模块701，关联置信度确定模块702和事件关联模块703。
具体地，数据同步模块701，用于从地图数据中获取拥堵事件的数据和致因事件的数据，其中致因事件包括道路上发生的会造成交通拥堵的多类事件。
关联置信度确定模块702，用于对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度。
事件关联模块703，用于根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件。
本公开实施例提供的设备可以具体用于执行上述第一实施例提供的方法实施例，具体功能此处不再赘述。
本实施例通过从地图数据中获取拥堵事件的数据和致因事件的数据，对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度；根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件，能够全面、及时、准确地确定导致交通拥堵事件的原因，从而为及时地缓解交通拥堵提供依据，提高交通拥堵治理效率，减少交通拥堵造成的影响。
图8是本公开第四实施例提供的交通拥堵事件的处理设备示意图。本公开实施例提供的交通拥堵事件的处理设备可以执行交通拥堵事件的处理方法实施例提供的处理流程。如图8所示，该交通拥堵事件的处理设备80包括：数据同步模块801，关联置 信度确定模块802和事件关联模块803。
具体地，数据同步模块801，用于从地图数据中获取拥堵事件的数据和致因事件的数据，其中致因事件包括道路上发生的会造成交通拥堵的多类事件。
关联置信度确定模块802，用于对每一拥堵事件，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的关联置信度。
事件关联模块803，用于根据各致因事件与拥堵事件的关联置信度，确定拥堵事件对应的致因事件。
可选地，如图8所示，关联置信度确定模块802包括：
相关度确定单元8021，用于对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度。
置信度确定单元8022，用于根据每一致因分析策略对应的置信度系数，以及采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度，确定各致因事件与拥堵事件的关联置信度。
可选地，相关度确定单元包括：
致因事件筛选子单元，用于对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与拥堵事件相关的备选致因事件；
相关度确定子单元，用于确定每一备选致因事件与拥堵事件的时间相关度和空间相关度。
可选地，致因事件筛选子单元还用于：
拥堵事件为道路拥堵事件，采用第一道路拥堵致因分析策略，根据拥堵事件的拥堵源坐标点，确定拥堵事件对应的第一拥堵缓冲区，第一拥堵缓冲区包括以拥堵源坐标点为中心的第一预设范围内的区域；根据拥堵事件的拥堵开始时间，筛选出从第一时刻至当前时刻在第一拥堵缓冲区内发生的指定类型的致因事件，得到第一备选致因事件，其中，第一时刻在拥堵开始时间之前且与拥堵开始时间间隔第一预设时长。
可选地，指定类型包括以下至少一种：
道路施工、交通管制。
可选地，相关度确定子单元还用于：
确定每一第一备选致因事件与拥堵事件的时间相关度均为第一预设相关度；根据每一第一备选致因事件发生的位置与拥堵源坐标点之间的距离，确定每一第一备选致 因事件与拥堵事件的空间相关度。
可选地，相关度确定单元还包括：
预处理子单元，用于：根据拥堵事件的拥堵源坐标点，确定拥堵事件对应的第一拥堵缓冲区之前，对拥堵事件的拥堵源坐标点进行去重处理。
可选地，致因事件筛选子单元还用于：
拥堵事件为道路拥堵事件，采用第二道路拥堵致因分析策略，根据拥堵事件的拥堵源坐标连线，确定拥堵事件对应的第二拥堵缓冲区，第二拥堵缓冲区包括与拥堵源坐标连线的最短距离小于第一预设距离的所有位置点；根据拥堵事件的拥堵开始时间，筛选出第二时刻至当前时刻在第二拥堵缓冲区内发生的特定类型的致因事件，得到第二备选致因事件，其中，第二时刻在拥堵开始时间之前且与拥堵开始时间间隔第二预设时长。
可选地，特定类型包括以下至少一种：
交通事故、故障车、道路积水、道路结冰、道路积雪。
可选地，相关度确定子单元还用于：
根据每一第二备选致因事件的开始时间与拥堵开始时间之间的时间间隔，确定每一第二备选致因事件与拥堵事件的时间相关度；根据每一第二备选致因事件发生的位置与拥堵源坐标连线之间的距离，确定每一第二备选致因事件与拥堵事件的空间相关度。
可选地，预处理子单元还用于：根据拥堵事件的拥堵源坐标连线，确定拥堵事件对应的第二拥堵缓冲区之前，对拥堵事件的拥堵源坐标连线进行去重处理。
可选地，致因事件筛选子单元还用于：
拥堵事件为道路拥堵事件，采用第三道路拥堵致因分析策略，根据拥堵事件的拥堵源坐标点，确定拥堵源坐标点所在的路段和下游路口，将拥堵源坐标点所在的路段和下游路口作为拥堵事件对应的第三拥堵缓冲区；根据拥堵事件的拥堵开始时间，筛选出第三时刻至当前时刻在第三拥堵缓冲区内发生的致因事件，得到第三备选致因事件，其中，第三时刻在拥堵开始时间之前且与拥堵开始时间间隔第三预设时长。
可选地，相关度确定子单元还用于：
根据每一第三备选致因事件的开始时间与拥堵开始时间之间的时间间隔，确定每一第三备选致因事件与拥堵事件的时间相关度；确定每一第三备选致因事件与拥堵事件的空间相关度均为第二预设相关度。
可选地，预处理子单元还用于：采用第三道路拥堵致因分析策略，根据拥堵事件 的拥堵源坐标点，确定拥堵源坐标点所在的路段和下游路口，将拥堵源坐标点所在的路段和下游路口作为拥堵事件对应的第三拥堵缓冲区之前，对拥堵事件的拥堵源坐标点进行去重处理。
可选地，致因事件筛选子单元还用于：
拥堵事件为道路拥堵事件，采用第四道路拥堵致因分析策略，获取拥堵事件对应的用户上报事件，用户上报事件包含至少一个与拥堵事件相关的第四备选致因事件。
相关度确定子单元还用于：
确定至少一个第四备选致因事件与拥堵事件的时间相关度和空间相关度。
可选地，致因事件筛选子单元还用于：
拥堵事件为路口拥堵事件，采用第一路口拥堵致因分析策略，根据拥堵事件所在的路口坐标点，确定拥堵事件对应的第四拥堵缓冲区，第四拥堵缓冲区包括以路口坐标点为中心的第二预设范围内的区域；根据拥堵事件的拥堵开始时间，筛选出第四时刻至当前时刻在第四拥堵缓冲区内发生的致因事件，得到第五备选致因事件，其中，第四时刻在拥堵开始时间之前且与拥堵开始时间间隔第四预设时长。
可选地，相关度确定子单元还用于：
备选致因事件包括第五备选致因事件，根据每一备选致因事件的开始时间与拥堵开始时间，确定每一备选致因事件与拥堵事件的时间相关度；根据每一备选致因事件发生的位置与路口坐标点之间的距离，确定每一备选致因事件与拥堵事件的空间相关度。
可选地，致因事件筛选子单元还用于：
拥堵事件为路口拥堵事件且拥堵事件为路口死锁事件，采用第二路口拥堵致因分析策略，根据拥堵事件的拥堵开始时间，筛选出第五时刻至当前时刻在拥堵事件所在路口的进口路段上发生的致因事件，得到第六备选致因事件；其中，第五时刻在拥堵开始时间之前且与拥堵开始时间间隔第五预设时长。
可选地，致因事件筛选子单元还用于：
拥堵事件为路口拥堵事件且拥堵事件为路口溢流事件，采用第三路口拥堵致因分析策略，根据拥堵事件的拥堵开始时间，筛选出第六时刻至当前时刻在拥堵事件所在路口的出口路段上发生的致因事件，得到第七备选致因事件；其中，第六时刻在拥堵开始时间之前且与拥堵开始时间间隔第六预设时长。
可选地，相关度确定子单元还用于：
备选致因事件包括第六备选致因事件或第七备选致因事件，根据每一备选致因事 件的开始时间与拥堵开始时间，确定备选致因事件与拥堵事件的时间相关度；确定每一备选致因事件与拥堵事件的空间相关度为第二预设相关度。
可选地，相关度确定子单元还用于：
对于每一备选致因事件，备选致因事件为第五备选致因事件、第六备选致因事件或者第七备选致因事件，若备选致因事件的开始时间早于拥堵开始时间，则确定备选致因事件与拥堵事件的时间相关度为第一预设相关度；若备选致因事件的开始时间不早于拥堵开始时间，则根据备选致因事件的开始时间与拥堵开始时间的时间间隔，确定备选致因事件与拥堵事件的时间相关度。
可选地，事件关联模块还用于：
根据各致因事件与拥堵事件的关联置信度，将与拥堵事件的关联置信度最大的致因事件，作为拥堵事件对应的致因事件。
可选地，如图8所示，该交通拥堵事件的处理设备80还包括：
显示模块804，用于显示各拥堵事件对应的致因事件；
和/或，
拥堵报告模块805，用于根据各拥堵事件对应的致因事件，生成拥堵数据报告，并发送拥堵数据报告。
可选地，数据同步模块还用于：
定时地从地图数据中获取上一时段内的拥堵事件数据和致因事件数据。
本公开实施例提供的设备可以具体用于执行上述第二实施例提供的方法实施例，具体功能此处不再赘述。
本实施例中，预先设置多种致因分析策略，以及每一致因分析策略对应的置信度系数。对每一拥堵事件，采用至少一种致因分析策略，根据拥堵事件的数据和各致因事件的数据，确定各致因事件与拥堵事件的时间相关度和空间相关度；根据每一致因分析策略对应的置信度系数，以及采用每一致因分析策略确定的各致因事件与拥堵事件的时间相关度和空间相关度，确定各致因事件与拥堵事件的关联置信度，能够更加全面地、及时地、精准地确定导致交通拥堵事件的原因，从而为及时地缓解交通拥堵提供依据，提高交通拥堵治理效率，减少交通拥堵造成的影响。
本公开的技术方案中，所涉及的用户个人信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
根据本公开的实施例，本公开还提供了一种计算机程序产品，计算机程序产品包括：计算机程序，计算机程序存储在可读存储介质中，电子设备的至少一个处理器可以从可读存储介质读取计算机程序，至少一个处理器执行计算机程序使得电子设备执行上述任一实施例提供的方案。
图9示出了可以用来实施本公开的实施例的示例电子设备900的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图9所示，设备900包括计算单元901，其可以根据存储在只读存储器(ROM)902中的计算机程序或者从存储单元908加载到随机访问存储器(RAM)903中的计算机程序，来执行各种适当的动作和处理。在RAM 903中，还可存储设备900操作所需的各种程序和数据。计算单元901、ROM 902以及RAM 903通过总线904彼此相连。输入/输出(I/O)接口905也连接至总线904。
设备900中的多个部件连接至I/O接口905，包括：输入单元906，例如键盘、鼠标等；输出单元907，例如各种类型的显示器、扬声器等；存储单元908，例如磁盘、光盘等；以及通信单元909，例如网卡、调制解调器、无线通信收发机等。通信单元909允许设备900通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元901可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元901的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元901执行上文所描述的各个方法和处理，例如交通拥堵事件的处理方法。例如，在一些实施例中，交通拥堵事件的处理方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元908。在一些实施例中，计算机程序的部分或者全部可以经由ROM 902和/或通信单元909而被载入和/或安装到设备900上。当计算机程序加载到RAM 903并由计算单元901执行时，可以执行上文描述的交通拥堵事件的处理方法的一个或多个步骤。备选地，在其他实施例中，计算单元901可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行交通拥堵事件的处理方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部 件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决了传统物理主机与VPS服务("Virtual Private Server"，或简称"VPS")中，存在的管理难度大，业务扩展性弱的缺陷。服务器也可以为分布式系统的服务器，或者是结合了区块链的服务器。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (51)

  1. 一种交通拥堵事件的处理方法，包括：
    从地图数据中获取拥堵事件的数据和致因事件的数据，其中所述致因事件包括道路上发生的会造成交通拥堵的多类事件；
    对每一所述拥堵事件，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的关联置信度；
    根据各所述致因事件与所述拥堵事件的关联置信度，确定所述拥堵事件对应的致因事件。
  2. 根据权利要求1所述的方法，其中，所述对每一所述拥堵事件，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的关联置信度，包括：
    对每一所述拥堵事件，采用至少一种致因分析策略，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的时间相关度和空间相关度；
    根据每一所述致因分析策略对应的置信度系数，以及采用每一所述致因分析策略确定的各所述致因事件与所述拥堵事件的时间相关度和空间相关度，确定各所述致因事件与所述拥堵事件的关联置信度。
  3. 根据权利要求2所述的方法，其中，所述对每一所述拥堵事件，采用至少一种致因分析策略，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的时间相关度和空间相关度，包括：
    对每一所述拥堵事件，采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件；
    确定每一所述备选致因事件与所述拥堵事件的时间相关度和空间相关度。
  4. 根据权利要求3所述的方法，其中，所述采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件，包括：
    所述拥堵事件为道路拥堵事件，采用第一道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标点，确定所述拥堵事件对应的第一拥堵缓冲区，所述第一拥堵缓冲区包括以所述拥堵源坐标点为中心的第一预设范围内的区域；
    根据所述拥堵事件的拥堵开始时间，筛选出从第一时刻至当前时刻在所述第一拥 堵缓冲区内发生的指定类型的致因事件，得到第一备选致因事件，其中，所述第一时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第一预设时长。
  5. 根据权利要求4所述的方法，其中，所述指定类型包括以下至少一种：
    道路施工、交通管制。
  6. 根据权利要求4所述的方法，其中，所述确定每一所述备选致因事件与所述拥堵事件的时间相关度和空间相关度，包括：
    确定每一所述第一备选致因事件与所述拥堵事件的时间相关度均为第一预设相关度；
    根据每一所述第一备选致因事件发生的位置与所述拥堵源坐标点之间的距离，确定每一所述第一备选致因事件与所述拥堵事件的空间相关度。
  7. 根据权利要求4所述的方法，其中，所述根据所述拥堵事件的拥堵源坐标点，确定所述拥堵事件对应的第一拥堵缓冲区之前，还包括：
    对所述拥堵事件的拥堵源坐标点进行去重处理。
  8. 根据权利要求3-7中任一项所述的方法，其中，所述采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件，包括：
    所述拥堵事件为道路拥堵事件，采用第二道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标连线，确定所述拥堵事件对应的第二拥堵缓冲区，所述第二拥堵缓冲区包括与所述拥堵源坐标连线的最短距离小于第一预设距离的所有位置点；
    根据所述拥堵事件的拥堵开始时间，筛选出第二时刻至当前时刻在所述第二拥堵缓冲区内发生的特定类型的致因事件，得到第二备选致因事件，其中，所述第二时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第二预设时长。
  9. 根据权利要求8所述的方法，其中，所述特定类型包括以下至少一种：
    交通事故、故障车、道路积水、道路结冰、道路积雪。
  10. 根据权利要求8所述的方法，其中，所述确定每一所述备选致因事件与所述拥堵事件的时间相关度和空间相关度，包括：
    根据每一所述第二备选致因事件的开始时间与所述拥堵开始时间之间的时间间隔，确定每一所述第二备选致因事件与所述拥堵事件的时间相关度；
    根据每一所述第二备选致因事件发生的位置与所述拥堵源坐标连线之间的距离，确定每一所述第二备选致因事件与所述拥堵事件的空间相关度。
  11. 根据权利要求8所述的方法，其中，所述根据所述拥堵事件的拥堵源坐标连 线，确定所述拥堵事件对应的第二拥堵缓冲区之前，还包括：
    对所述拥堵事件的拥堵源坐标连线进行去重处理。
  12. 根据权利要求3-11中任一项所述的方法，其中，所述采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件，包括：
    所述拥堵事件为道路拥堵事件，采用第三道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标点，确定所述拥堵源坐标点所在的路段和下游路口，将所述拥堵源坐标点所在的路段和下游路口作为所述拥堵事件对应的第三拥堵缓冲区；
    根据所述拥堵事件的拥堵开始时间，筛选出第三时刻至当前时刻在所述第三拥堵缓冲区内发生的致因事件，得到第三备选致因事件，其中，所述第三时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第三预设时长。
  13. 根据权利要求12所述的方法，其中，所述确定每一所述备选致因事件与所述拥堵事件的时间相关度和空间相关度，包括：
    根据每一所述第三备选致因事件的开始时间与所述拥堵开始时间之间的时间间隔，确定每一所述第三备选致因事件与所述拥堵事件的时间相关度；
    确定每一所述第三备选致因事件与所述拥堵事件的空间相关度均为第二预设相关度。
  14. 根据权利要求12所述的方法，其中，所述采用第三道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标点，确定所述拥堵源坐标点所在的路段和下游路口，将所述拥堵源坐标点所在的路段和下游路口作为所述拥堵事件对应的第三拥堵缓冲区之前，还包括：
    对所述拥堵事件的拥堵源坐标点进行去重处理。
  15. 根据权利要求3-14中任一项所述的方法，其中，所述对每一所述拥堵事件，采用至少一种致因分析策略，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的时间相关度和空间相关度，包括：
    所述拥堵事件为道路拥堵事件，采用第四道路拥堵致因分析策略，获取所述拥堵事件对应的用户上报事件，所述用户上报事件包含至少一个与所述拥堵事件相关的第四备选致因事件；
    确定至少一个所述第四备选致因事件与所述拥堵事件的时间相关度和空间相关度。
  16. 根据权利要求3-15中任一项所述的方法，其中，所述采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述 拥堵事件相关的备选致因事件，包括：
    所述拥堵事件为路口拥堵事件，采用第一路口拥堵致因分析策略，根据所述拥堵事件所在的路口坐标点，确定所述拥堵事件对应的第四拥堵缓冲区，所述第四拥堵缓冲区包括以所述路口坐标点为中心的第二预设范围内的区域；
    根据所述拥堵事件的拥堵开始时间，筛选出第四时刻至当前时刻在所述第四拥堵缓冲区内发生的致因事件，得到第五备选致因事件，其中，所述第四时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第四预设时长。
  17. 根据权利要求16所述的方法，其中，所述确定每一所述备选致因事件与所述拥堵事件的时间相关度和空间相关度，包括：
    所述备选致因事件包括所述第五备选致因事件，根据每一所述备选致因事件的开始时间与所述拥堵开始时间，确定每一所述备选致因事件与所述拥堵事件的时间相关度；
    根据每一所述备选致因事件发生的位置与所述路口坐标点之间的距离，确定每一所述备选致因事件与所述拥堵事件的空间相关度。
  18. 根据权利要求3-17中任一项所述的方法，其中，所述采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件，包括：
    所述拥堵事件为路口拥堵事件且所述拥堵事件为路口死锁事件，采用第二路口拥堵致因分析策略，根据所述拥堵事件的拥堵开始时间，筛选出第五时刻至当前时刻在所述拥堵事件所在路口的进口路段上发生的致因事件，得到第六备选致因事件；
    其中，所述第五时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第五预设时长。
  19. 根据权利要求3-17中任一项所述的方法，其中，所述采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件，包括：
    所述拥堵事件为路口拥堵事件且所述拥堵事件为路口溢流事件，采用第三路口拥堵致因分析策略，根据所述拥堵事件的拥堵开始时间，筛选出第六时刻至当前时刻在所述拥堵事件所在路口的出口路段上发生的致因事件，得到第七备选致因事件；
    其中，所述第六时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第六预设时长。
  20. 根据权利要求18或19所述的方法，其中，所述确定每一所述备选致因事件 与所述拥堵事件的时间相关度和空间相关度，包括：
    所述备选致因事件包括第六备选致因事件或第七备选致因事件，根据每一所述备选致因事件的开始时间与所述拥堵开始时间，确定备选致因事件与所述拥堵事件的时间相关度；
    确定每一所述备选致因事件与所述拥堵事件的空间相关度为第二预设相关度。
  21. 根据权利要求17或20所述的方法，其中，所述根据每一所述备选致因事件的开始时间与所述拥堵开始时间，确定每一所述备选致因事件与所述拥堵事件的时间相关度，包括：
    对于每一所述备选致因事件，所述备选致因事件为第五备选致因事件、第六备选致因事件或者第七备选致因事件，若所述备选致因事件的开始时间早于所述拥堵开始时间，则确定所述备选致因事件与所述拥堵事件的时间相关度为第一预设相关度；
    若所述备选致因事件的开始时间不早于所述拥堵开始时间，则根据所述备选致因事件的开始时间与所述拥堵开始时间的时间间隔，确定所述备选致因事件与所述拥堵事件的时间相关度。
  22. 根据权利要求1-21中任一项所述的方法，其中，所述根据各所述致因事件与所述拥堵事件的关联置信度，确定所述拥堵事件对应的致因事件，包括：
    根据各所述致因事件与所述拥堵事件的关联置信度，将与所述拥堵事件的关联置信度最大的致因事件，作为所述拥堵事件对应的致因事件。
  23. 根据权利要求1-22中任一项所述的方法，其中，所述根据各所述致因事件与所述拥堵事件的关联置信度，确定所述拥堵事件对应的致因事件之后，还包括：
    显示各所述拥堵事件对应的致因事件；
    和/或，
    根据各所述拥堵事件对应的致因事件，生成拥堵数据报告，并发送所述拥堵数据报告。
  24. 根据权利要求1所述的方法，其中，所述从地图数据中获取拥堵事件数据和致因事件数据，包括：
    定时地从地图数据中获取上一时段内的拥堵事件数据和致因事件数据。
  25. 一种交通拥堵事件的处理设备，包括：
    数据同步模块，用于从地图数据中获取拥堵事件的数据和致因事件的数据，其中所述致因事件包括道路上发生的会造成交通拥堵的多类事件；
    关联置信度确定模块，用于对每一所述拥堵事件，根据所述拥堵事件的数据和各 所述致因事件的数据，确定各所述致因事件与所述拥堵事件的关联置信度；
    事件关联模块，用于根据各所述致因事件与所述拥堵事件的关联置信度，确定所述拥堵事件对应的致因事件。
  26. 根据权利要求25所述的设备，其中，所述关联置信度确定模块包括：
    相关度确定单元，用于对每一所述拥堵事件，采用至少一种致因分析策略，根据所述拥堵事件的数据和各所述致因事件的数据，确定各所述致因事件与所述拥堵事件的时间相关度和空间相关度；
    置信度确定单元，用于根据每一所述致因分析策略对应的置信度系数，以及采用每一所述致因分析策略确定的各所述致因事件与所述拥堵事件的时间相关度和空间相关度，确定各所述致因事件与所述拥堵事件的关联置信度。
  27. 根据权利要求26所述的设备，其中，所述相关度确定单元包括：
    致因事件筛选子单元，用于对每一所述拥堵事件，采用至少一种致因分析策略，根据所述拥堵事件发生的位置和拥堵开始时间，筛选出在时间和空间上与所述拥堵事件相关的备选致因事件；
    相关度确定子单元，用于确定每一所述备选致因事件与所述拥堵事件的时间相关度和空间相关度。
  28. 根据权利要求27所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为道路拥堵事件，采用第一道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标点，确定所述拥堵事件对应的第一拥堵缓冲区，所述第一拥堵缓冲区包括以所述拥堵源坐标点为中心的第一预设范围内的区域；
    根据所述拥堵事件的拥堵开始时间，筛选出从第一时刻至当前时刻在所述第一拥堵缓冲区内发生的指定类型的致因事件，得到第一备选致因事件，其中，所述第一时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第一预设时长。
  29. 根据权利要求28所述的设备，其中，所述指定类型包括以下至少一种：
    道路施工、交通管制。
  30. 根据权利要求29所述的设备，其中，所述相关度确定子单元还用于：
    确定每一所述第一备选致因事件与所述拥堵事件的时间相关度均为第一预设相关度；
    根据每一所述第一备选致因事件发生的位置与所述拥堵源坐标点之间的距离，确定每一所述第一备选致因事件与所述拥堵事件的空间相关度。
  31. 根据权利要求28所述的设备，其中，所述相关度确定单元还包括：
    预处理子单元，用于：所述根据所述拥堵事件的拥堵源坐标点，确定所述拥堵事件对应的第一拥堵缓冲区之前，对所述拥堵事件的拥堵源坐标点进行去重处理。
  32. 根据权利要求27-31中任一项所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为道路拥堵事件，采用第二道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标连线，确定所述拥堵事件对应的第二拥堵缓冲区，所述第二拥堵缓冲区包括与所述拥堵源坐标连线的最短距离小于第一预设距离的所有位置点；
    根据所述拥堵事件的拥堵开始时间，筛选出第二时刻至当前时刻在所述第二拥堵缓冲区内发生的特定类型的致因事件，得到第二备选致因事件，其中，所述第二时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第二预设时长。
  33. 根据权利要求32所述的设备，其中，所述特定类型包括以下至少一种：
    交通事故、故障车、道路积水、道路结冰、道路积雪。
  34. 根据权利要求32所述的设备，其中，所述相关度确定子单元还用于：
    根据每一所述第二备选致因事件的开始时间与所述拥堵开始时间之间的时间间隔，确定每一所述第二备选致因事件与所述拥堵事件的时间相关度；
    根据每一所述第二备选致因事件发生的位置与所述拥堵源坐标连线之间的距离，确定每一所述第二备选致因事件与所述拥堵事件的空间相关度。
  35. 根据权利要求32所述的设备，其中，所述相关度确定单元还包括：
    预处理子单元，用于：所述根据所述拥堵事件的拥堵源坐标连线，确定所述拥堵事件对应的第二拥堵缓冲区之前，对所述拥堵事件的拥堵源坐标连线进行去重处理。
  36. 根据权利要求27-35中任一项所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为道路拥堵事件，采用第三道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标点，确定所述拥堵源坐标点所在的路段和下游路口，将所述拥堵源坐标点所在的路段和下游路口作为所述拥堵事件对应的第三拥堵缓冲区；
    根据所述拥堵事件的拥堵开始时间，筛选出第三时刻至当前时刻在所述第三拥堵缓冲区内发生的致因事件，得到第三备选致因事件，其中，所述第三时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第三预设时长。
  37. 根据权利要求36所述的设备，其中，所述相关度确定子单元还用于：
    根据每一所述第三备选致因事件的开始时间与所述拥堵开始时间之间的时间间隔，确定每一所述第三备选致因事件与所述拥堵事件的时间相关度；
    确定每一所述第三备选致因事件与所述拥堵事件的空间相关度均为第二预设相关度。
  38. 根据权利要求36所述的设备，其中，所述相关度确定单元还包括：
    预处理子单元，用于：所述采用第三道路拥堵致因分析策略，根据所述拥堵事件的拥堵源坐标点，确定所述拥堵源坐标点所在的路段和下游路口，将所述拥堵源坐标点所在的路段和下游路口作为所述拥堵事件对应的第三拥堵缓冲区之前，对所述拥堵事件的拥堵源坐标点进行去重处理。
  39. 根据权利要求27-38中任一项所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为道路拥堵事件，采用第四道路拥堵致因分析策略，获取所述拥堵事件对应的用户上报事件，所述用户上报事件包含至少一个与所述拥堵事件相关的第四备选致因事件；
    所述相关度确定子单元还用于：
    确定至少一个所述第四备选致因事件与所述拥堵事件的时间相关度和空间相关度。
  40. 根据权利要求27-39中任一项所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为路口拥堵事件，采用第一路口拥堵致因分析策略，根据所述拥堵事件所在的路口坐标点，确定所述拥堵事件对应的第四拥堵缓冲区，所述第四拥堵缓冲区包括以所述路口坐标点为中心的第二预设范围内的区域；
    根据所述拥堵事件的拥堵开始时间，筛选出第四时刻至当前时刻在所述第四拥堵缓冲区内发生的致因事件，得到第五备选致因事件，其中，所述第四时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第四预设时长。
  41. 根据权利要求40所述的设备，其中，所述相关度确定子单元还用于：
    所述备选致因事件包括所述第五备选致因事件，根据每一所述备选致因事件的开始时间与所述拥堵开始时间，确定每一所述备选致因事件与所述拥堵事件的时间相关度；
    根据每一所述备选致因事件发生的位置与所述路口坐标点之间的距离，确定每一所述备选致因事件与所述拥堵事件的空间相关度。
  42. 根据权利要求27-41中任一项所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为路口拥堵事件且所述拥堵事件为路口死锁事件，采用第二路口拥 堵致因分析策略，根据所述拥堵事件的拥堵开始时间，筛选出第五时刻至当前时刻在所述拥堵事件所在路口的进口路段上发生的致因事件，得到第六备选致因事件；
    其中，所述第五时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第五预设时长。
  43. 根据权利要求27-42中任一项所述的设备，其中，所述致因事件筛选子单元还用于：
    所述拥堵事件为路口拥堵事件且所述拥堵事件为路口溢流事件，采用第三路口拥堵致因分析策略，根据所述拥堵事件的拥堵开始时间，筛选出第六时刻至当前时刻在所述拥堵事件所在路口的出口路段上发生的致因事件，得到第七备选致因事件；
    其中，所述第六时刻在所述拥堵开始时间之前且与所述拥堵开始时间间隔第六预设时长。
  44. 根据权利要求42或43所述的设备，其中，所述相关度确定子单元还用于：
    所述备选致因事件包括第六备选致因事件或第七备选致因事件，根据每一所述备选致因事件的开始时间与所述拥堵开始时间，确定备选致因事件与所述拥堵事件的时间相关度；
    确定每一所述备选致因事件与所述拥堵事件的空间相关度为第二预设相关度。
  45. 根据权利要求41或44所述的设备，其中，所述相关度确定子单元还用于：
    对于每一所述备选致因事件，所述备选致因事件为第五备选致因事件、第六备选致因事件或者第七备选致因事件，若所述备选致因事件的开始时间早于所述拥堵开始时间，则确定所述备选致因事件与所述拥堵事件的时间相关度为第一预设相关度；
    若所述备选致因事件的开始时间不早于所述拥堵开始时间，则根据所述备选致因事件的开始时间与所述拥堵开始时间的时间间隔，确定所述备选致因事件与所述拥堵事件的时间相关度。
  46. 根据权利要求25-45中任一项所述的设备，其中，所述事件关联模块还用于：
    根据各所述致因事件与所述拥堵事件的关联置信度，将与所述拥堵事件的关联置信度最大的致因事件，作为所述拥堵事件对应的致因事件。
  47. 根据权利要求25-46中任一项所述的设备，还包括：
    显示模块，用于显示各所述拥堵事件对应的致因事件；
    和/或，
    拥堵报告模块，用于根据各所述拥堵事件对应的致因事件，生成拥堵数据报告，并发送所述拥堵数据报告。
  48. 根据权利要求25所述的设备，其中，所述数据同步模块还用于：
    定时地从地图数据中获取上一时段内的拥堵事件数据和致因事件数据。
  49. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-24中任一项所述的方法。
  50. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行根据权利要求1-24中任一项所述的方法。
  51. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-24中任一项所述的方法。
PCT/CN2021/129463 2021-07-21 2021-11-09 交通拥堵事件的处理方法、设备、存储介质及程序产品 WO2023000548A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020227014625A KR20220063289A (ko) 2021-07-21 2021-11-09 교통 체증 사건의 처리 방법, 기기, 저장매체 및 프로그램 제품

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110823935.X 2021-07-21
CN202110823935.XA CN113538915B (zh) 2021-07-21 2021-07-21 交通拥堵事件的处理方法、设备、存储介质及程序产品

Publications (1)

Publication Number Publication Date
WO2023000548A1 true WO2023000548A1 (zh) 2023-01-26

Family

ID=78100642

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/129463 WO2023000548A1 (zh) 2021-07-21 2021-11-09 交通拥堵事件的处理方法、设备、存储介质及程序产品

Country Status (2)

Country Link
CN (1) CN113538915B (zh)
WO (1) WO2023000548A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113538915B (zh) * 2021-07-21 2023-02-28 阿波罗智联(北京)科技有限公司 交通拥堵事件的处理方法、设备、存储介质及程序产品
CN114067565B (zh) * 2021-11-16 2022-08-30 北京百度网讯科技有限公司 确定拥堵识别精度的方法及装置
CN117079467B (zh) * 2023-10-12 2024-01-02 成都通广网联科技有限公司 一种基于感知融合技术缓解道路拥堵的方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160247397A1 (en) * 2015-02-24 2016-08-25 Here Global B.V. Method and apparatus for providing traffic jam detection and prediction
CN106997669A (zh) * 2017-05-31 2017-08-01 青岛大学 一种基于特征重要性的判断交通拥堵成因的方法
CN110473396A (zh) * 2019-06-27 2019-11-19 安徽科力信息产业有限责任公司 交通拥堵数据分析方法、装置、电子设备及存储介质
CN111028507A (zh) * 2019-12-16 2020-04-17 北京百度网讯科技有限公司 交通拥堵致因确定方法及装置
CN111785031A (zh) * 2020-09-07 2020-10-16 深圳市城市交通规划设计研究中心股份有限公司 一种基于速度时空图的交通拥堵成因智能识别算法
CN113538915A (zh) * 2021-07-21 2021-10-22 阿波罗智联(北京)科技有限公司 交通拥堵事件的处理方法、设备、存储介质及程序产品

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140278032A1 (en) * 2013-03-15 2014-09-18 Inrix, Inc. Traffic causality
CN106991818B (zh) * 2017-05-23 2020-06-09 安徽科力信息产业有限责任公司 一种有效缓解城市交通拥堵的方法、存储介质和系统
CN109035778B (zh) * 2018-08-29 2021-11-30 深圳市赛为智能股份有限公司 拥堵成因分析方法、装置、计算机设备及存储介质
CN111091715A (zh) * 2020-03-20 2020-05-01 北京交研智慧科技有限公司 一种基于历史重现率的道路偶发拥堵识别方法及装置
CN112489433B (zh) * 2020-12-17 2022-11-04 华为技术有限公司 交通拥堵分析方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160247397A1 (en) * 2015-02-24 2016-08-25 Here Global B.V. Method and apparatus for providing traffic jam detection and prediction
CN106997669A (zh) * 2017-05-31 2017-08-01 青岛大学 一种基于特征重要性的判断交通拥堵成因的方法
CN110473396A (zh) * 2019-06-27 2019-11-19 安徽科力信息产业有限责任公司 交通拥堵数据分析方法、装置、电子设备及存储介质
CN111028507A (zh) * 2019-12-16 2020-04-17 北京百度网讯科技有限公司 交通拥堵致因确定方法及装置
CN111785031A (zh) * 2020-09-07 2020-10-16 深圳市城市交通规划设计研究中心股份有限公司 一种基于速度时空图的交通拥堵成因智能识别算法
CN113538915A (zh) * 2021-07-21 2021-10-22 阿波罗智联(北京)科技有限公司 交通拥堵事件的处理方法、设备、存储介质及程序产品

Also Published As

Publication number Publication date
CN113538915B (zh) 2023-02-28
CN113538915A (zh) 2021-10-22

Similar Documents

Publication Publication Date Title
WO2023000548A1 (zh) 交通拥堵事件的处理方法、设备、存储介质及程序产品
JP7366094B2 (ja) 信号灯データ表示方法、装置、サーバ、端末、システムと媒体
US11798408B2 (en) Green wave speed determination method, electronic device and storage medium
CN111613053B (zh) 一种交通扰动的检测分析方法、装置、存储介质及终端
US20230091252A1 (en) Method for processing high-definition map data, electronic device and medium
WO2023279603A1 (zh) 路网交通瓶颈的识别方法、装置及电子设备
US20220254253A1 (en) Method and apparatus of failure monitoring for signal lights and storage medium
CN114120650A (zh) 用于生成测试结果的方法、装置
EP4012344A2 (en) Method and apparatus for generating route information, device, medium and product
KR20220063289A (ko) 교통 체증 사건의 처리 방법, 기기, 저장매체 및 프로그램 제품
WO2023236522A1 (zh) 夜间步行导航方法、装置、设备、存储介质及程序产品
EP4141386A1 (en) Road data monitoring method and apparatus, electronic device and storage medium
CN115936522A (zh) 一种车辆停靠站点的评估方法、装置、设备以及存储介质
EP4174847B1 (en) Navigation broadcast detection method and apparatus, and electronic device and medium
CN115481170A (zh) 一种车辆轨迹的处理方法、装置、电子设备及存储介质
CN112836626B (zh) 事故确定方法及装置、模型训练方法及装置、电子设备
CN113869439A (zh) 一种数据融合方法、装置及电子设备
CN114419883A (zh) 识别路口缺失交通限制信息的方法、装置和电子设备
WO2023045062A1 (zh) 划分时段的方法、装置、电子设备和存储介质
US20240273113A1 (en) Method of importing data to database, electronic device, and storage medium
Leshchik et al. Applying of combined algorithm for prediction urban road traffic based on fuzzy search theory
CN114185908B (zh) 一种地图数据处理方法、装置、电子设备及存储介质
CN114970949B (zh) 行驶速度预测方法、装置、电子设备及存储介质
CN114863285B (zh) 识别目标道路的方法、装置、设备以及存储介质
CN114363207A (zh) 云控平台的测试方法、装置、设备、存储介质及程序

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 20227014625

Country of ref document: KR

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21950786

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE