CN113704317B - Accident black point prediction method based on traffic accident feature analysis - Google Patents
Accident black point prediction method based on traffic accident feature analysis Download PDFInfo
- Publication number
- CN113704317B CN113704317B CN202110785547.7A CN202110785547A CN113704317B CN 113704317 B CN113704317 B CN 113704317B CN 202110785547 A CN202110785547 A CN 202110785547A CN 113704317 B CN113704317 B CN 113704317B
- Authority
- CN
- China
- Prior art keywords
- accident
- data
- traffic
- maximum possible
- occurrence
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 40
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims abstract description 39
- 206010027146 Melanoderma Diseases 0.000 claims abstract description 34
- 230000002776 aggregation Effects 0.000 claims abstract description 8
- 238000004220 aggregation Methods 0.000 claims abstract description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 2
- 230000004927 fusion Effects 0.000 abstract description 3
- 238000007418 data mining Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
An accident black spot prediction method based on traffic accident feature analysis comprises the following steps: gridding a target area based on GIS; according to the position information of the accident, carrying out gridding aggregation on the accident data to obtain accident high-incidence distribution data; analyzing accident occurrence time, occurrence time meteorological conditions and vehicle speed threshold value data of an occurrence time period area to form a relation matrix of single grid accident occurrence frequency, time period, meteorological conditions and vehicle speed threshold values; merging traffic flow and traffic index road network data; the maximum possible accident black spot is determined through accident high incidence place analysis, the maximum possible accident black spot accident occurrence maximum possible time interval is determined through accident high incidence time period analysis, and the comprehensive characteristics of accidents at the historical accident high incidence spots under different time periods can be subjected to fusion analysis based on the maximum possible accident black spot, the maximum possible time interval, weather, traffic flow and traffic indexes, so that the prediction capability of the accident possible black spot is realized.
Description
Technical Field
The invention relates to the field of intelligent traffic and data mining, in particular to an accident black point prediction method based on traffic accident feature analysis.
Background
With the high-speed development of economy, the increase of population and the continuous promotion of the living standard of people, the annual increase of population density, the continuous improvement of travel traffic demand level, the annual increase of motor vehicle conservation, and the increasingly serious contradiction with the annual decrease of urban development available space, the annual increase of road network density and the increasingly serious road traffic pressure situation. Meanwhile, due to the continuous increase of the vehicle base number and the continuous increase of the traffic density, the pressure of traffic conditions is continuously increased, the accident occurrence frequency of motor vehicles is continuously increased, and the further deterioration of the traffic conditions is easily caused every time the accident occurs, so that vicious circulation is formed, the traffic safety risk of the accident road section is improved, the traffic control pressure is higher, and the larger property loss is easily caused.
In recent years, traffic management institutions continuously strengthen the investment of intelligent and informationized traffic management construction, and continuously construct rich outfield facility equipment, including video monitoring, high-definition bayonets, electronic police, flow detectors and the like, so that a more comprehensive channel is provided for information data acquisition of vehicles; meanwhile, with the continuous improvement of the AI processing capacity of big data, powerful capacity support guarantee is provided for the computing capacity; in addition, the analysis and prediction by utilizing the fusion analysis of the Internet plus data have more dimensionality data support, the result is more comprehensive and accurate, and the method has important significance and practical value requirements for the transition from post discovery, treatment to pre-warning, management and prevention of traffic management work.
Therefore, the accident black spot prediction based on the traffic accident feature analysis has important significance for accident occurrence, early warning and prevention and control, and by using the method, the traffic management department can not only precisely and quantitatively grasp the accident easy occurrence and high occurrence feature, but also can conduct preventive dispersion, management and control in advance by the early prediction discovery of the accident black spot, and command and guide preset police force, so that the accident occurrence possibility is controlled in a sprouting state, and possible accident occurrence is avoided.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an intelligent accident black spot prediction method based on traffic accident feature analysis based on data mining analysis of multiple places, high occurrence features, environmental factors and the like of road traffic accidents, which comprises the following specific scheme:
an accident black spot prediction method based on traffic accident feature analysis is characterized by comprising the following steps:
step 1, performing gridding division on a target area to be analyzed based on GIS (geographic information system Geographic Information System or Geo-Information system, hereinafter referred to as GIS);
step 2, accessing historical accident data, acquiring corresponding accident position information, and aggregating the historical accident data based on GIS grids based on the accident position information;
step 3, single grid analysis is carried out, and a relation matrix of occurrence frequency, time period, weather and high occurrence speed threshold of vehicle accidents of the single grid is obtained;
step 4, importing a frequency threshold value, removing data below the frequency threshold value through input setting control of the frequency threshold value, removing sporadic data, performing data cleaning on the relation matrix data, improving accuracy, and obtaining an available data sample matrix;
step 5, importing traffic flow data, taking a target grid as a range, and correlating the traffic flow data of the current grid and the adjacent grid in the available matrix when the accident occurs to obtain a single grid accident period, weather, a vehicle speed threshold value and a traffic flow relation matrix;
step 6, the traffic index data of the current grid when the accident occurs in the available matrix is associated by taking the target grid as a range, so as to obtain a single grid accident period, weather, a vehicle speed threshold value, traffic flow and a traffic index relation matrix;
and 7, analyzing and determining a maximum possible accident black point data set by accident high incidence places based on the single grid accident time period, the weather, the vehicle speed threshold, the traffic flow and the traffic index relation matrix, analyzing and determining a maximum possible accident black point accident time interval data set by accident high incidence time period, and providing accident black point prediction by fusing the weather, the traffic flow and the traffic index based on the maximum possible accident black point data set and the maximum possible time interval data set.
In step 2, the historical accident data is extracted and accessed by taking a day as a time period in units of time intervals.
Further, step 3 further includes: judging the number of the single-grid data to be analyzed, analyzing the sample data of the single grid if the number of the single-grid data to be analyzed meets the preset condition, and re-accessing the historical accident data by extending the time interval or the time period if the accident data to be analyzed does not meet the preset condition.
Further, the step 3 specifically includes:
extracting sample data time information, and analyzing to obtain accident high-incidence time period data sets in a data aggregation grouping mode;
the method comprises the steps of extracting weather environment information when sample data occur, and analyzing and obtaining accident high-incidence weather environment data sets in a data aggregation grouping mode;
according to accident occurrence time period data, extracting average speed information of vehicles in a sample data occurrence time period region, and obtaining a regional vehicle accident high-speed threshold value group through statistical analysis;
based on the obtained accident high incidence time period data set, the accident high incidence meteorological environment data set and the regional vehicle accident high incidence speed threshold value set, the time period is taken as an X axis, and data association combination is carried out through a time relationship, so that a relationship matrix of single grid accident occurrence frequency, time period, weather and vehicle accident high incidence speed threshold value is generated.
Further, step 4 further includes: if the data volume of the available data sample matrix after data cleaning does not meet the preset number, the historical accident data access is carried out again in a mode of prolonging the time interval or the time period.
Further, the accident high incidence place analysis to determine the most probable accident black point data set specifically includes:
combining the traffic accident data position information with the GIS road gateway and carrying out position grouping to obtain x 1 ,x 2 …x n ；
Frequency-aggregating the data in the same position to obtain n 1 ,n 2 …n n And carrying out frequency sequencing to obtain a black point data set Ar of the most probable accident, wherein the black point data set Ar is expressed as follows:
wherein x is i After point location information based on historical accident data is hidden in a GIS road network, logically gridding the road network to form an ith grid area, n i Accident data in a single logical grid is frequent.
Further, the maximum possible time interval data set for analyzing the accident high incidence period to determine the occurrence of the accident black spot accident with the maximum possible accident specifically includes:
removing the position data with low frequency in the black point data set Ar of the most probable accident to obtain high-frequency position point data x h1 ,x h2 …x hn As an association, accident occurrence time data is processedAssociating with the time interval segments, obtaining the maximum possible time interval data set At, expressed as follows:
further, in step 7, providing accident blackspot prediction based on the maximum possible accident blackspot and the maximum possible time interval by fusing weather, traffic flow and traffic index specifically includes:
taking high-frequency position point data in the data set of the maximum possible time interval as an association, taking the corresponding time interval as a time range, removing the sporadic special case data with too small and too large flow when single high-frequency position accidents happen, and then carrying out average value calculation to obtain the general flow value of the accident occurrence time interval;
taking high-frequency position point data in the data set of the maximum possible time interval as an association, taking the corresponding time interval as a time range, removing too small and too large sporadic special case data of the traffic index when single high-frequency position accidents happen, and then carrying out average value calculation to obtain a general traffic index value of the accident occurrence time interval;
the obtained general flow value of the accident occurrence period and the general traffic index value of the accident occurrence period are fused to form a comprehensive data characteristic matrix of the accident blackout points;
and finally, the accident black spot prediction based on the traffic accident feature analysis is realized by monitoring the accident multiple spots, time, weather, traffic flow, traffic index and average vehicle speed and analyzing and comparing the accident multiple spots, time, weather, traffic flow, traffic index and average vehicle speed with the comprehensive data feature matrix of the accident easy spot black spot.
The invention has the following beneficial effects:
firstly, in a selected area, a target analysis range based on GIS is specified, and is refined in a grid form, and historical accident data is extracted and accessed by dividing the target analysis range into time interval units and taking days as time periods; secondly, according to the position information of the accident, carrying out gridding aggregation on the accident data based on the GIS to obtain accident high-occurrence point distribution data; thirdly, analyzing the accident occurrence time, the occurrence time meteorological conditions and the vehicle speed threshold value data of the occurrence time period area to form a relation matrix of single grid accident occurrence frequency, time period, meteorological conditions and vehicle speed threshold values; finally merging traffic flow and traffic index road network data; based on the data support, the 'maximum possible accident black point' is determined through the 'accident high incidence place' analysis, the 'maximum possible accident black point' and the 'maximum possible accident time interval' are determined through the 'accident high incidence time period' analysis, and the comprehensive characteristics of accidents of the historical accident high incidence points under different time periods can be subjected to fusion analysis based on the 'maximum possible accident black point', 'maximum possible time interval', weather, traffic flow and traffic index, so that the prediction capability of the accident possible black point is realized.
Drawings
Fig. 1 is a schematic flow chart of an accident black spot prediction method based on traffic accident feature analysis according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the accident black spot prediction method based on the traffic accident feature analysis provided by the embodiment of the invention specifically includes:
step 1, meshing and dividing a target area to be analyzed based on GIS;
and carrying out GIS-based meshing division on the target area to be analyzed, wherein reasonable meshing division can effectively improve analysis accuracy.
And 2, accessing historical accident data, acquiring corresponding accident position information, and aggregating the historical accident data based on the GIS grids based on the accident position information.
Step 3, single grid analysis is carried out, and a relation matrix of occurrence frequency, time period, weather and high occurrence speed threshold of vehicle accidents of the single grid is obtained, wherein the relation matrix specifically comprises;
extracting sample data time information, and analyzing to obtain accident high-incidence time period data sets in a data aggregation grouping mode;
the method comprises the steps of extracting weather environment information when sample data occur, and analyzing and obtaining accident high-incidence weather environment data sets in a data aggregation grouping mode;
according to accident occurrence time period data, extracting average speed information of vehicles in a sample data occurrence time period region, and obtaining a regional vehicle accident high-speed threshold value group through statistical analysis;
based on the obtained accident high incidence time period data set, the accident high incidence meteorological environment data set and the regional vehicle accident high incidence speed threshold value set, the time period is taken as an X axis, and data association combination is carried out through a time relationship, so that a relationship matrix of single grid accident occurrence frequency, time period, weather and vehicle accident high incidence speed threshold value is generated.
Preferably, the method further comprises, before single-grid analysis, judging the number of data to be analyzed of the single grid, if the number of data to be analyzed of the single grid meets a preset condition, analyzing sample data of the single grid, and if the accident data to be analyzed does not meet the preset condition, re-accessing historical accident data by means of prolonging a time interval or a time period.
And 4, importing a frequency threshold, removing data below the frequency threshold through input setting control of the frequency threshold, removing sporadic data, cleaning the data of the relation matrix, improving accuracy, obtaining an available data sample matrix, and if the data quantity of the available data sample matrix after data cleaning does not meet the preset quantity, re-accessing the historical accident data in a mode of prolonging a time interval or a time period.
And step 5, importing traffic flow data, and correlating the traffic flow data of the current grid and the adjacent grid in the available matrix when the accident occurs by taking the target grid as a range to obtain a single grid accident period, weather, a vehicle speed threshold value and a traffic flow relation matrix.
And 6, associating the traffic index data of the current grid when the accident occurs in the available matrix by taking the target grid as a range to obtain a single grid accident period, weather, a vehicle speed threshold value, traffic flow and a traffic index relation matrix.
And 7, analyzing and determining a maximum possible accident black point data set by accident high incidence places based on the single grid accident time period, the weather, the vehicle speed threshold, the traffic flow and the traffic index relation matrix, analyzing and determining a maximum possible accident black point accident time interval data set by accident high incidence time period, and providing accident black point prediction by fusing the weather, the traffic flow and the traffic index based on the maximum possible accident black point data set and the maximum possible time interval data set.
The accident high incidence place analysis and determination of the maximum possible accident black point data set specifically comprises the following steps:
combining the traffic accident data position information with the GIS road gateway and carrying out position grouping to obtain x 1 ,x 2 …x n ；
Frequency-aggregating the data in the same position to obtain n 1 ,n 2 …n n And carrying out frequency sequencing to obtain a black point data set Ar of the most probable accident, wherein the black point data set Ar is expressed as follows:
wherein x is i After point location information based on historical accident data is hidden in a GIS road network, logically gridding the road network to form an ith grid area, n i Is the frequency of accident data in the ith logical grid.
The maximum possible time interval data set for analyzing the accident high incidence period to determine the occurrence of the accident black spot accident with the maximum possible comprises the following specific steps:
removing the position data with low frequency in the black point data set Ar of the most probable accident to obtain high-frequency position point data x h1 ,x h2 …x hn As an associationThe term, carrying out association and time interval segmentation on accident occurrence time data, obtaining a maximum possible time interval data set At, which is expressed as follows:
the method for providing the accident black spot prediction based on the maximum possible accident black spot and the maximum possible time interval by fusing weather, traffic flow and traffic index specifically comprises the following steps:
and taking high-frequency position point data in the maximum possible time interval data set At as an association, taking a corresponding time interval as a time range, and calculating an average value after eliminating the sporadic special case data with too small and too large flow rate when a single high-frequency position accident occurs, so as to obtain a general flow rate value f of the accident occurrence period.
f＝(f 1 +f 2 +f 3 +f 4 +…f n )/n；
Wherein f i Is the real-time traffic flow in the ith logic grid at the time of single accident occurrence.
And taking high-frequency position point data in the data set At of the 'maximum possible time interval' as an association and taking a corresponding time interval as a time range, removing too small and too large sporadic special case data of the traffic index when a single high-frequency position accident occurs, and then carrying out average value calculation to obtain a general traffic index value i of the accident occurrence period.
i＝(i 1 +i 2 +i 3 +i 4 +…i n )/n；
Wherein i is i Is the real-time traffic index in the ith logic grid at the time of single accident occurrence.
The above data are fused to form a comprehensive data feature matrix of accident-prone blackspots, as shown in the following table 1:
the accident black point prediction based on the traffic accident feature analysis is finally realized through monitoring the accident multiple points, time, weather, traffic flow, traffic index and average speed and analyzing and comparing the accident black point prediction with the comprehensive data feature matrix of the accident easy points to extract accident position information data, the accident data is aggregated based on grids of GIS, if the number of the data to be analyzed meets the preset number, the sample data analysis of single grids can be further carried out, and if the number of the accident data to be analyzed does not meet the preset number, such as the total number of the single grid data is less, the accident data distribution is scattered, and the like, the historical accident data access can be carried out again by prolonging the time interval or the time period.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. An accident black spot prediction method based on traffic accident feature analysis is characterized by comprising the following steps:
step 1, meshing and dividing a target area to be analyzed based on GIS;
step 2, accessing historical accident data, acquiring corresponding accident position information, and aggregating the historical accident data based on GIS grids based on the accident position information;
step 3, single grid analysis is carried out, and a relation matrix of occurrence frequency, time period, weather and high occurrence speed threshold of vehicle accidents of the single grid is obtained;
step 4, importing a frequency threshold value, removing data below the frequency threshold value through input setting control of the frequency threshold value, and performing data cleaning on the relational matrix data to obtain an available data sample matrix;
step 5, importing traffic flow data, taking a target grid as a range, and correlating the traffic flow data of the current grid and the adjacent grid in the available matrix when the accident occurs to obtain a single grid accident period, weather, a vehicle speed threshold value and a traffic flow relation matrix;
step 6, the traffic index data of the current grid when the accident occurs in the available matrix is associated by taking the target grid as a range, so as to obtain a single grid accident period, weather, a vehicle speed threshold value, traffic flow and a traffic index relation matrix;
and 7, analyzing and determining a maximum possible accident black point data set by accident high incidence places based on the single grid accident time period, the weather, the vehicle speed threshold, the traffic flow and the traffic index relation matrix, analyzing and determining a maximum possible accident black point accident time interval data set by accident high incidence time period, and providing accident black point prediction by fusing the weather, the traffic flow and the traffic index based on the maximum possible accident black point data set and the maximum possible time interval data set.
2. The traffic accident black spot prediction method based on the traffic accident feature analysis according to claim 1, wherein in the step 2, the historical accident data is extracted and accessed by dividing into time interval units and taking days as time periods.
3. The traffic accident black spot prediction method based on the traffic accident feature analysis according to claim 2, wherein the step 3 further comprises: judging the number of the single-grid data to be analyzed, analyzing the sample data of the single grid if the number of the single-grid data to be analyzed meets the preset condition, and re-accessing the historical accident data by extending the time interval or the time period if the accident data to be analyzed does not meet the preset condition.
4. The traffic accident black spot prediction method based on the traffic accident feature analysis according to claim 1, wherein the step 3 specifically comprises:
extracting sample data time information, and analyzing to obtain accident high-incidence time period data sets in a data aggregation grouping mode;
the method comprises the steps of extracting weather environment information when sample data occur, and analyzing and obtaining accident high-incidence weather environment data sets in a data aggregation grouping mode;
according to accident occurrence time period data, extracting average speed information of vehicles in a sample data occurrence time period region, and obtaining a regional vehicle accident high-speed threshold value group through statistical analysis;
based on the obtained accident high incidence time period data set, the accident high incidence meteorological environment data set and the regional vehicle accident high incidence speed threshold value set, the time period is taken as an X axis, and data association combination is carried out through a time relationship, so that a relationship matrix of single grid accident occurrence frequency, time period, weather and vehicle accident high incidence speed threshold value is generated.
5. The traffic accident black spot prediction method based on the traffic accident feature analysis according to claim 1, wherein the step 4 further comprises: if the data volume of the available data sample matrix after data cleaning does not meet the preset number, the historical accident data access is carried out again in a mode of prolonging the time interval or the time period.
6. The traffic accident feature analysis-based accident black spot prediction method according to claim 1, wherein the performing of the accident high-occurrence place analysis to determine the most probable accident black spot data set specifically comprises:
combining the traffic accident data position information with the GIS road gateway and carrying out position grouping to obtain x 1 ,x 2 …x n ；
Frequency-aggregating the data in the same position to obtain n 1 ,n 2 …n n And carrying out frequency sequencing to obtain a black point data set Ar of the most probable accident, wherein the black point data set Ar is expressed as follows:
wherein x is i After point location information based on historical accident data is hidden in a GIS road network, logically gridding the road network to form an ith grid area, n i Is the frequency of accident data in the ith logical grid.
7. The traffic accident black spot prediction method based on the traffic accident feature analysis according to claim 6, wherein the performing of the accident high occurrence period analysis to determine the maximum possible time interval data set of the maximum possible accident black spot accident occurrence specifically comprises:
removing the position data with low frequency in the black point data set Ar of the most probable accident to obtain high-frequency position point data x h1 ,x h2 …x hn As an association, accident occurrence time data is associated with time interval segmentation to obtain a maximum possible time interval data set At, which is expressed as follows:
8. the traffic accident feature analysis-based accident black spot prediction method according to claim 1, wherein in step 7, providing the accident black spot prediction based on the maximum possible accident black spot and the maximum possible time interval by fusing weather, traffic flow and traffic index specifically comprises:
taking high-frequency position point data in the data set of the maximum possible time interval as an association, taking the corresponding time interval as a time range, removing the sporadic special case data with too small and too large flow when single high-frequency position accidents happen, and then carrying out average value calculation to obtain the general flow value of the accident occurrence time interval;
taking high-frequency position point data in the data set of the maximum possible time interval as an association, taking the corresponding time interval as a time range, removing too small and too large sporadic special case data of the traffic index when single high-frequency position accidents happen, and then carrying out average value calculation to obtain a general traffic index value of the accident occurrence time interval;
the obtained general flow value of the accident occurrence period and the general traffic index value of the accident occurrence period are fused to form a comprehensive data characteristic matrix of the accident blackout points;
and finally, the accident black spot prediction based on the traffic accident feature analysis is realized by monitoring the accident multiple spots, time, weather, traffic flow, traffic index and average vehicle speed and analyzing and comparing the accident multiple spots, time, weather, traffic flow, traffic index and average vehicle speed with the comprehensive data feature matrix of the accident easy spot black spot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785547.7A CN113704317B (en) | 2021-07-12 | 2021-07-12 | Accident black point prediction method based on traffic accident feature analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785547.7A CN113704317B (en) | 2021-07-12 | 2021-07-12 | Accident black point prediction method based on traffic accident feature analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113704317A CN113704317A (en) | 2021-11-26 |
| CN113704317B true CN113704317B (en) | 2023-11-14 |
Family
ID=78648474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110785547.7A Active CN113704317B (en) | 2021-07-12 | 2021-07-12 | Accident black point prediction method based on traffic accident feature analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704317B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829613A (en) * | 2024-03-04 | 2024-04-05 | 深圳大学 | Marine accident influence factor analysis method, system, intelligent terminal and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017140175A1 (en) * | 2016-02-18 | 2017-08-24 | 华南理工大学 | Toll road network traffic information collection and guidance system based on route identification system |
| CN112837533A (en) * | 2021-01-08 | 2021-05-25 | 合肥工业大学 | Highway accident frequency prediction method considering risk factor time-varying characteristics |
| CN112966941A (en) * | 2021-03-09 | 2021-06-15 | 宁波工程学院 | Accident black spot identification method and system based on traffic accident big data |
| KR20210086381A (en) * | 2019-12-30 | 2021-07-08 | 계명대학교 산학협력단 | System and Method for Predicting Traffic Accident Risk |
-
2021
- 2021-07-12 CN CN202110785547.7A patent/CN113704317B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017140175A1 (en) * | 2016-02-18 | 2017-08-24 | 华南理工大学 | Toll road network traffic information collection and guidance system based on route identification system |
| KR20210086381A (en) * | 2019-12-30 | 2021-07-08 | 계명대학교 산학협력단 | System and Method for Predicting Traffic Accident Risk |
| CN112837533A (en) * | 2021-01-08 | 2021-05-25 | 合肥工业大学 | Highway accident frequency prediction method considering risk factor time-varying characteristics |
| CN112966941A (en) * | 2021-03-09 | 2021-06-15 | 宁波工程学院 | Accident black spot identification method and system based on traffic accident big data |
Non-Patent Citations (1)
| Title |
|---|
| 基于谱聚类的交通事故黑点鉴别及预测;孙晴晴;臧超;;工业控制计算机(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113704317A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107610469B (en) | Day-dimension area traffic index prediction method considering multi-factor influence | |
| CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
| CN109871876B (en) | Expressway road condition identification and prediction method based on floating car data | |
| CN110570664A (en) | automatic detection system for highway traffic incident | |
| CN110766258B (en) | Road risk assessment method and device | |
| CN109191283A (en) | Method for prewarning risk and system | |
| CN114596700B (en) | Real-time traffic estimation method for expressway section based on portal data | |
| CN110929939A (en) | Landslide hazard susceptibility spatial prediction method based on clustering-information coupling model | |
| CN113704317B (en) | Accident black point prediction method based on traffic accident feature analysis | |
| CN109379563B (en) | Method and system for monitoring video data storage management | |
| CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data | |
| CN112185108A (en) | Urban road network congestion mode identification method, equipment and medium based on space-time characteristics | |
| CN109272760B (en) | Online detection method for abnormal data value of SCATS system detector | |
| CN103093619A (en) | Traffic evaluation method and device based on intelligent traffic system | |
| CN108597224B (en) | Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data | |
| CN116524714A (en) | Method and device for predicting and determining parking saturation and trend of urban parking | |
| CN112488360B (en) | Distribution variation routine analysis early warning method based on artificial intelligence | |
| CN111710156B (en) | Road traffic flow prediction method, system, medium and equipment | |
| Fior et al. | Estimating the incidence of adverse weather effects on road traffic safety using time series embeddings | |
| CN106780245B (en) | Method and system for determining and forecasting dust haze probability of coastal region caused by tropical cyclone | |
| CN112416898A (en) | Intelligent water conservancy data center construction method | |
| CN112183597A (en) | Unbalanced traffic accident severity analysis method based on spectral clustering | |
| Lv et al. | A history data based traffic incident impact analyzing and predicting method | |
| CN113920723B (en) | Identification method for mountainous area expressway accident-prone road section | |
| CN115050181B (en) | Spatial hot spot of intersection traffic accident and traffic violation and influence factor identification method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |