A method and system for identifying road traffic accident black spot areas

Abstract

The present invention discloses a method and system for identifying road traffic accident blackspot areas, relating to the field of data processing technology. The method comprises: collecting all historical road traffic accident data; performing first-order division of the target traffic area based on the nine-square correlation positioning method, and outputting a first-order spatial grid; encoding and mapping the full historical road traffic accident data according to the first-order spatial grid, and generating a road traffic accident coding mapping library; constructing an accident blackspot determiner, which calls the road traffic accident coding mapping library to identify the number of accidents and outputs a blackspot grid; performing a nine-square grid correlation merging analysis using the blackspot grid as the central grid, outputting a merged blackspot grid, and marking and visually displaying the merged blackspot grid. The method solves the technical problems of inaccurate and low efficiency in identifying traffic accident blackspot areas in the prior art, and achieves the technical effect of improving the accuracy and efficiency of identifying traffic accident blackspot areas.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for identifying black spot areas of road traffic accidents. Background Art

[0002] Existing methods for identifying accident blackspots generally suffer from the following problems: Traditional manual analysis methods are inefficient and easily influenced by subjective factors, resulting in inaccurate results. Furthermore, existing methods fail to adequately consider spatiotemporal clustering factors and cannot accurately reflect the distribution patterns of accidents within complex road networks. Furthermore, traditional methods exhibit low blackspot identification accuracy, often relying on crude data summaries and unable to pinpoint specific road sections or intersections. Furthermore, existing methods are often based on single-dimensional data and lack comprehensive analysis of multidimensional factors, making it difficult to delve into the root causes and regional characteristics of accidents. Finally, traditional methods experience low data update frequency, making it difficult to promptly identify new accident blackspots and ineffective in addressing traffic safety hazards. Summary of the Invention

[0003] The present application provides a method and system for identifying road traffic accident blackspot areas, which solves the technical problems of inaccurate and low efficiency in identifying traffic accident blackspot areas in the prior art.

[0004] In view of the above problems, the present application provides a method and system for identifying road traffic accident blackspot areas.

[0005] The first aspect of the present application provides a method for identifying road traffic accident black spot areas, the method comprising: collecting all historical road traffic accident data; performing a first-order division of the target traffic area based on the nine-square association positioning method, and outputting a first-order spatial grid, the first-order spatial grid including first-order setting parameters , and are the length and width of the first-order spatial grid; the full amount of historical road traffic accident data is coded and mapped according to the first-order spatial grid to generate a road traffic accident coding mapping library; an accident black spot determiner is constructed, the accident black spot determiner calls the road traffic accident coding mapping library to identify the number of accidents and outputs a black spot grid; a nine-square grid correlation merging analysis is performed with the black spot grid as the central grid, a merged black spot grid is output, and the merged black spot grid is marked and visualized.

[0006] The second aspect of the present application provides a road traffic accident black spot area identification system, the system comprising: a data acquisition module for collecting all historical road traffic accident data; an area division module for performing a first-order division of the target traffic area based on the nine-square correlation positioning method, and outputting a first-order spatial grid, the first-order spatial grid including first-order setting parameters , and is the length and width of the first-order spatial grid; a coding mapping module: performs coding mapping on the full amount of historical road traffic accident data according to the first-order spatial grid to generate a road traffic accident coding mapping library; an accident black spot determination module: constructs an accident black spot determiner, the accident black spot determiner calls the road traffic accident coding mapping library to identify the number of accidents, and outputs a black spot grid; a correlation analysis module: performs a nine-square grid correlation merging analysis with the black spot grid as the central grid, outputs a merged black spot grid, and marks and visualizes the merged black spot grid.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] First, collect all historical road traffic accident data. Then, perform first-order division of the target traffic area based on the Nine Palaces correlation positioning method and output the first-order spatial grid. The first-order spatial grid includes the first-order setting parameters. , and is the length and width of the first-order spatial grid. Furthermore, the entire amount of historical road traffic accident data is coded and mapped according to the first-order spatial grid to generate a road traffic accident coding mapping library. Then, an accident black spot determiner is constructed, which calls the road traffic accident coding mapping library to identify the number of accidents and outputs a black spot grid. Finally, a nine-square grid correlation merging analysis is performed using the black spot grid as the central grid, and a merged black spot grid is output, which is marked and visualized. This solves the technical problem of inaccurate and low efficiency in identifying traffic accident black spot areas in the prior art, and achieves the technical effect of improving the recognition accuracy and efficiency of traffic accident black spot areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic flow chart of a method for identifying black spot areas of road traffic accidents provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of the structure of a road traffic accident black spot area identification system provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: data collection module 11 , area division module 12 , coding mapping module 13 , accident black spot determination module 14 , correlation analysis module 15 . DETAILED DESCRIPTION

[0013] The present application solves the technical problems of inaccurate and low efficiency in identifying traffic accident black spot areas in the prior art by providing a method and system for identifying traffic accident black spot areas.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0016] Example 1, as Figure 1 As shown, the present application provides a method for identifying road traffic accident black spot areas, wherein the method includes:

[0017] Collect comprehensive historical road traffic accident data. This data covers every dimension from accident occurrence to handling outcome, including alarm sources (e.g., telephone alarms, automatic alarms from monitoring equipment), handling methods (online, offline), handling departments, management departments, weather conditions (e.g., sunny, rainy, foggy, snowy), location types (e.g., highways, urban arterial roads, rural roads), accident classifications (e.g., minor, general, major, catastrophic), accident types (e.g., rear-end collisions, side collisions, rollovers, crushing, pedestrian collisions, collisions with obstacles), handling outcomes, accident types (vehicle, pedestrian), accident violations (e.g., speeding, running red lights, drunk driving, fatigued driving, failure to yield to pedestrians, illegal lane changes), latitude and longitude location information (the latitude and longitude coordinates of the accident location), vehicle information (e.g., cars, trucks, buses, motorcycles), and personnel information (driver and passenger information). By collecting comprehensive historical road traffic accident data, a comprehensive data foundation is established to support subsequent spatial gridding, accident blackspot identification, and analysis.

[0018] Based on the nine-square correlation positioning method, the target traffic area is divided into the first order and the first order space grid is output. The first order space grid includes the first order setting parameters. , and are the length and width of the first-order spatial grid.

[0019] The Nine-Palace Correlation Positioning Method is a positioning method that divides a spatial area into nine small grids, similar to the layout of a nine-square grid. Each grid represents a smaller geographical area. Through the Nine-Palace Correlation Positioning Method, accurate spatial analysis can be performed within a larger area to identify clustered areas where accidents occur.

[0020] Based on the Nine-square correlation positioning method, the target traffic area (such as a city or road section) is preliminarily divided into nine-square grids, and multiple first-order spatial grids are output. Each grid represents a certain geographical area. Further, the first-order spatial grid refers to the first-level spatial unit after division. The length and width of the first-order spatial grid are set as and .

[0021] Furthermore, after outputting the first-order spatial grid, the method further includes: performing traffic feature analysis on the target traffic area to obtain the characteristic vector value corresponding to each grid area in the first-order spatial grid; judging according to the size of the characteristic vector value corresponding to each grid area, extracting N identification grids whose characteristic vector values are greater than the preset characteristic vector value; performing second-order division on the N identification grids based on the nine-square association positioning method, and outputting a second-order spatial grid, wherein the second-order spatial grid includes a second-order setting , and is the length and width of the second-order spatial grid, and ; Encode and map the full amount of historical road traffic accident data according to the second-order spatial grid, and update the road traffic accident coding mapping library.

[0022] After outputting the first-order spatial grid, the traffic characteristics are further analyzed in order to refine the spatial grid division and map the accident data to smaller areas, thereby more accurately identifying traffic accident black spots. Specifically, traffic characteristics analysis is performed on each first-order spatial grid in the target traffic area, including but not limited to accident frequency, traffic flow, road condition information, weather conditions, etc.; by analyzing historical traffic accident data, a feature vector value is generated for each first-order grid area. The feature vector value is usually a quantitative result calculated based on a series of traffic data (such as the number of accidents, traffic flow, etc.). This value represents the traffic conditions of the area. For example, areas where accidents frequently occur will have larger feature vector values. According to the size of the feature vector value corresponding to each grid area, N identification grids with feature vector values greater than the preset threshold are sorted and screened out. These grid areas are areas with a high frequency of accidents and represent key areas for traffic management. After identifying high-risk areas, these identification grids are divided into the second order based on the nine-square association positioning method, that is, the nine-square grid method is used to further subdivide these grids to improve the accuracy of accident-prone areas; unlike the first-order division, the size of the second-order spatial grid is smaller, with the length and width respectively being and Indicates that, and , meaning the second-order spatial grid is finer than the first-order spatial grid. Based on the division of the second-order spatial grid, all historical traffic accident data is mapped to the new second-order grid. That is, each accident data point is assigned to its corresponding second-order spatial grid. Simultaneously, the road traffic accident code mapping library is updated to store the mapping relationship between all accident data and the second-order spatial grid.

[0023] The full amount of historical road traffic accident data is coded and mapped according to the first-order spatial grid to generate a road traffic accident coding mapping library.

[0024] Historical traffic accident data is mapped onto a previously defined first-order spatial grid to generate a road traffic accident code mapping library. This library associates each accident with its corresponding spatial grid location, forming a database that facilitates subsequent retrieval and analysis. Specifically, the geographic coordinates (latitude and longitude) of each accident are converted into grid coordinates relative to the first-order spatial grid. This determines the grid within which the accident occurred, assigns a unique identifier (ID) to each grid, and, based on the specific time of the accident, generates a unique code for each accident, including the grid ID and a timestamp. The entire set of historical road traffic accident data is then traversed, and each accident is mapped onto the corresponding first-order spatial grid according to the code mapping rules. Its unique code is recorded and the mapping results are stored in the road traffic accident code mapping library.

[0025] Optionally, use the following formula to convert longitude and latitude information into grid numbers, thereby providing a gridded representation of the time-limited spatial area; longitude number = Earth's equatorial circumference * COS (the angle between the current latitude and the equator) * longitude value / (360 * grid length); latitude number = Earth's longitude circumference * current latitude / (360 * grid width); grid number = longitude number - latitude number.

[0026] Taking 50m x 50m as an example, the numbers of a grid and its eight surrounding grids are as follows:

[0027]

[0028] An accident black spot determiner is constructed, and the accident black spot determiner calls the road traffic accident code mapping library to identify the number of accidents and output a black spot grid.

[0029] The accident black spot determiner can call the road traffic accident code mapping library generated above, identify black spots according to the number of traffic accidents, and output a black spot grid, where black spots refer to areas with a higher frequency of traffic accidents.

[0030] Furthermore, the accident black spot determiner calls the road traffic accident code mapping library to identify the number of accidents and outputs a black spot grid, and the method includes:

[0031] The accident black spot determiner includes a first determination channel and a second determination channel, wherein the first determination channel is an absolute value method determination channel, and the second determination channel is a relative value method determination channel, and the first determination channel and the second determination channel are connected in sequence; based on the first determination channel, the number of accidents is calculated for the road traffic accident code mapping library to obtain an initial black spot grid that is greater than a first preset accident number threshold; based on the second determination channel, a black spot grid that is greater than a second preset accident number threshold is output from the initial black spot grid.

[0032] The accident blackspot detector consists of a first and second determination channel. The first channel uses the absolute value method, while the second uses the relative value method. The two channels are connected sequentially to process and filter traffic accident data. Based on the first determination channel (absolute value method), the accident blackspot detector calculates the number of accidents from the road accident code mapping database. By counting the total number of accidents within each grid area, if the number of accidents in a grid exceeds a first preset accident threshold, the grid is identified as an initial blackspot grid. The absolute value method directly counts the number of accidents and identifies areas with a high accident frequency. Based on the second determination channel (relative value method), grids that meet a second preset accident threshold are further filtered from the identified initial blackspot grids. Unlike the first determination channel, the second determination channel uses the relative value method, comparing the relative density of each grid against the second preset accident threshold to filter out grids with a high accident density. This eliminates occasional grids that are inconsistent with the overall traffic accident density, ensuring greater accuracy and reliability in the output blackspot grid. By sequentially processing these two determination channels, the accident blackspot detector first screens potential blackspot areas based on the number of accidents, and then further optimizes and accurately identifies them through a relative assessment of accident density. This dual screening mechanism effectively identifies areas with high accident frequency and density, ultimately outputting the final blackspot grid.

[0033] Furthermore, the second preset accident number threshold is the average network accident ratio of the dynamic grid area; the dynamic grid area is obtained by expanding the grid based on the first step length with the currently calculated initial black point grid as the center, and the first step length is the number of expanded grids.

[0034] The second preset incident threshold is not a fixed value but is dynamically calculated based on the average network incident ratio of the dynamic grid area. Specifically, the total number of incidents within each dynamic grid area is calculated, and then this total is compared with the number of grid cells within the area to obtain the average incident ratio for that area. This ratio serves as the criterion for determining whether the current blackspot area is serious. If the incident density (i.e., relative ratio) of a grid area exceeds this average incident ratio, the grid area will be marked as a final blackspot grid area.

[0035] After identifying the initial black spot grid, to more comprehensively assess the accident density in the black spot area, it's necessary to consider the grids surrounding the initial black spot grid. This area is called the dynamic grid area. The size of the dynamic grid area is controlled by the first step length, which determines the number of grids to be expanded. For example, if the first step length is set to 2, then starting from the initial black spot grid and expanding to the two surrounding grid layers, a larger grid area will be formed as the dynamic grid area.

[0036] The second preset incident threshold is not a fixed value but is dynamically calculated based on the average network incident ratio of the dynamic grid area. Specifically, the total number of incidents within each dynamic grid area is calculated, and then this total is compared with the number of grid cells within the area to obtain the average incident ratio for that area. This ratio serves as the criterion for determining whether the current blackspot area is serious. If the incident density (i.e., relative ratio) of a grid area exceeds this average incident ratio, the grid area will be marked as a final blackspot grid area.

[0037] Furthermore, the first preset accident number threshold and the second preset accident number threshold are dynamically updated by dynamically updating the network layer in a time series manner, and the method includes:

[0038] The training time series dynamic update network layer is obtained by training the ARIMA model until convergence, and the training data of the time series dynamic update network layer includes weather labels, holiday labels, traffic change indicators and historical random deviations; the accident trend of the full amount of historical road traffic accident data is predicted according to the time series dynamic update network layer, and the predicted accident growth rate is output; the first preset accident number threshold and the second preset accident number threshold are dynamically updated according to the predicted accident growth rate.

[0039] The first and second preset accident thresholds are dynamically updated via the time series dynamic update network layer. This dynamically adjusts the accident thresholds by training a time series model and using time series data to predict traffic accident trends. Specifically, the time series dynamic update network layer is trained using the ARIMA model to gain predictive capabilities for accident trends. The ARIMA (AutoRegressive Integrated Moving Average) model is a commonly used time series analysis model suitable for trend prediction of time series data. This model can model the temporal variations in traffic accident data and predict accident trends over a period of time. During training, the time series dynamic update network layer uses training data including weather labels (indicating the impact of different weather conditions on traffic accidents, such as rainy, snowy, and foggy weather), holiday labels (specific patterns of traffic flow and accidents during holidays or specific periods), traffic flow variation indicators (traffic flow trends, such as changes in traffic flow during the morning and evening rush hours), and historical random deviations (the random volatility in historical data, accounting for differences in volatility across years, months, or days). After the model converges and completes training, the time-series dynamic update network layer can predict accident trends for the entire historical road traffic accident data based on the training results and output the predicted accident growth rate. The accident growth rate represents the trend of accidents in the future, that is, the predicted rate of change in the number of traffic accidents.

[0040] Based on the predicted accident growth rate, the system will dynamically update the first preset accident number threshold and the second preset accident number threshold according to the following formula. The formula for updating the first preset accident number threshold is: ,in, is the initial accident number threshold, In order to control the impact coefficient of accident growth rate on threshold update, Represents the predicted accident growth rate. The second preset accident number threshold update formula is: , in, is the initial second preset accident number threshold, In order to control the influence coefficient of the accident growth rate on the update of the second threshold, Represents the accident growth rate.

[0041] Through the training of the ARIMA model, the time series dynamic update network layer can predict the accident growth trend in real time, and dynamically update the first preset accident number threshold and the second preset accident number threshold according to the predicted accident growth rate.

[0042] The black dot grid is used as the central grid to perform a nine-grid correlation merging analysis, a merged black dot grid is output, and the merged black dot grid is marked and visually displayed.

[0043] Taking the identified black spot grid as the center, the correlation merging analysis of the nine-square grid is performed. By analyzing the correlation of the grids around the central black spot, the scope of black spot identification is further expanded, and the merged black spot grid is obtained, which can more comprehensively reveal the concentrated areas of traffic accidents.

[0044] Furthermore, the black dot grid is used as the central grid to perform nine-grid correlation merging analysis, and the method includes:

[0045] According to the accident black spot determiner, grids whose number is greater than or equal to 1 / 2 of a first preset accident number threshold and less than the first preset accident number threshold are identified as buffer grids, and grids whose number is less than 1 / 2 of the first preset accident number threshold are identified as low-incidence grids; a first-order nine-square grid with the black spot grid as the center grid is obtained, and if the eight adjacent grids in the first-order nine-square grid include the black spot grid or the buffer grid, a first-order merging instruction is obtained, and the nine-square grids are associated and merged according to the first-order merging instruction, and a merged black spot grid is output.

[0046] Specifically, the accident blackspot determiner is used to analyze the number of accidents in each grid area and classify the grids according to the frequency of accidents. Grids with a number of accidents greater than or equal to 1 / 2 of the first preset accident number threshold and less than the first preset accident number threshold are identified as buffer grids. The accident frequency of these grids is close to that of blackspot grids, but has not yet reached the high-risk standard. Grids with a number of accidents less than 1 / 2 of the first preset accident number threshold are identified as low-incidence grids. These areas have a low frequency of accidents and a low risk, and are generally not considered blackspot areas. Using the black dot grid as the central grid, a nine-grid relevance merging analysis is performed. By obtaining a first-order nine-grid grid, consisting of the central black dot grid and its eight surrounding adjacent grids, the accident risk of these grids can be further analyzed. The relationship between the central grid's accident frequency and that of its surrounding grids will determine whether merging is necessary. For the eight adjacent grids in the first-order nine-grid grid, if at least one of them is a black dot grid or a buffer grid, these grids are considered closely related to the black dot area and have a certain degree of correlation. These areas have a high accident risk and meet the conditions for expanding the black dot area. In this case, the system will generate a first-order merging instruction to merge these grids. If the adjacent grids contain low-incidence grids, the merging conditions are not met and no merging is performed. Based on the generated first-order merging instructions, the system executes the nine-grid relevance merging, merging grids that meet the merging conditions and outputting a merged black dot grid. These merged grids represent a wider range of high-accident-incidence areas. These merged black dot grids are not necessarily regular rectangles; they may also be irregular shapes. This depends mainly on the density of accidents within the grid and their geographical proximity. The shape and size of the merged area will vary depending on the actual accident distribution. In addition, the number of grids merged in each merging operation is limited to less than or equal to 8. That is, in each round of merging, a maximum of 8 adjacent grids can be merged into the black spot area to ensure the accuracy and rationality of the merged area. By using the black spot grid as the central grid and utilizing the nine-square grid correlation merging analysis, the system can merge adjacent areas based on accident frequency to generate a new merged black spot grid. This method can identify high-risk areas over a larger area, helping traffic management departments to take targeted safety improvement measures and improve the accuracy and efficiency of traffic safety management.

[0047] Furthermore, after outputting the merged black point grid, the method further includes:

[0048] Obtain a second-order nine-square grid with the merged black dot grid as the center grid; if the eight adjacent grids in the second-order nine-square grid include the black dot grid or the buffer grid, obtain a second-order merging instruction, perform associative merging of the nine-square grids according to the second-order merging instruction, output a second-order merged black dot grid, and mark and visualize the second-order merged black dot grid.

[0049] After outputting the merged black spot grid, the system further analyzes the extended area of the merged black spot grid to identify a wider high-risk area. Specifically, the merged black spot grid is used as the central grid to generate a second-order nine-square grid. This second-order nine-square grid is a larger grid with the merged black spot grid as the core and encompasses eight adjacent grids. Next, the eight adjacent grids within the second-order nine-square grid are evaluated: if one or more grids within the second-order nine-square grid are black spot grids or buffer grids, the area is considered to have a high accident risk and meets the criteria for further merging. In this case, the system generates a second-order merge instruction, indicating that these grids can be merged to form a wider black spot area. By performing a nine-square grid associative merge, the system merges the grids that meet the criteria and outputs a second-order merged black spot grid. The resulting black spot grid may not be a regular rectangle but may exhibit an irregular shape, depending on the actual accident distribution and the grid morphology during the merging process. This merging process expands the scope of identifying high-accident-prone areas, helping traffic management departments accurately identify potential high-risk areas. Finally, the generated second-order merged black point grid will be displayed through a marker visualization display, using different colors or symbols to mark these high-risk areas on the map, making it easier for traffic management personnel to quickly identify and take corresponding safety improvement measures.

[0050] In summary, the embodiments of the present application have at least the following technical effects:

[0051] First, collect all historical road traffic accident data. Then, perform first-order division of the target traffic area based on the Nine Palaces correlation positioning method and output the first-order spatial grid. The first-order spatial grid includes the first-order setting parameters. , and is the length and width of the first-order spatial grid. Furthermore, the entire amount of historical road traffic accident data is coded and mapped according to the first-order spatial grid to generate a road traffic accident coding mapping library. Then, an accident black spot determiner is constructed, which calls the road traffic accident coding mapping library to identify the number of accidents and outputs a black spot grid. Finally, a nine-square grid correlation merging analysis is performed using the black spot grid as the central grid, and a merged black spot grid is output, which is marked and visualized. This solves the technical problem of inaccurate and low efficiency in identifying traffic accident black spot areas in the prior art, and achieves the technical effect of improving the recognition accuracy and efficiency of traffic accident black spot areas.

[0052] The second embodiment is based on the same inventive concept as the method for identifying a black spot area of a road traffic accident in the above embodiment. Figure 2 As shown, the present application provides a road traffic accident black spot area identification system, wherein the system includes:

[0053] Data collection module 11: collects all historical road traffic accident data; area division module 12: performs first-order division of the target traffic area based on the nine-square correlation positioning method, and outputs a first-order spatial grid, which includes first-order setting parameters , and is the length and width of the first-order spatial grid; a coding mapping module 13: performs coding mapping on the full amount of historical road traffic accident data according to the first-order spatial grid to generate a road traffic accident coding mapping library; an accident black spot determination module 14: constructs an accident black spot determiner, the accident black spot determiner calls the road traffic accident coding mapping library to identify the number of accidents, and outputs a black spot grid; a correlation analysis module 15: performs a nine-square grid correlation merging analysis with the black spot grid as the central grid, outputs a merged black spot grid, and marks and visualizes the merged black spot grid.

[0054] Furthermore, the region division module 12 is configured to perform the following method:

[0055] Perform traffic feature analysis on the target traffic area to obtain the eigenvector value corresponding to each grid area in the first-order spatial grid; judge according to the size of the eigenvector value corresponding to each grid area, and extract N identification grids whose eigenvector values are greater than the preset eigenvector value; perform second-order division on the N identification grids based on the nine-square association positioning method, and output a second-order spatial grid, which includes second-order setting parameters , and is the length and width of the second-order spatial grid, and ; Encode and map the full amount of historical road traffic accident data according to the second-order spatial grid, and update the road traffic accident coding mapping library.

[0056] Furthermore, the accident black spot determination module 14 is configured to execute the following method:

[0057] The accident black spot determiner includes a first determination channel and a second determination channel, wherein the first determination channel is an absolute value method determination channel, and the second determination channel is a relative value method determination channel, and the first determination channel and the second determination channel are connected in sequence; based on the first determination channel, the number of accidents is calculated for the road traffic accident code mapping library to obtain an initial black spot grid that is greater than a first preset accident number threshold; based on the second determination channel, a black spot grid that is greater than a second preset accident number threshold is output from the initial black spot grid.

[0058] Furthermore, the accident black spot determination module 14 is configured to execute the following method:

[0059] The second preset accident number threshold is the average network accident ratio of the dynamic grid area; the dynamic grid area is obtained by expanding the grid based on the first step length with the currently calculated initial black point grid as the center, and the first step length is the number of expanded grids.

[0060] Furthermore, the accident black spot determination module 14 is configured to execute the following method:

[0061] The training time series dynamic update network layer is obtained by training the ARIMA model until convergence, and the training data of the time series dynamic update network layer includes weather labels, holiday labels, traffic change indicators and historical random deviations; the accident trend of the full amount of historical road traffic accident data is predicted according to the time series dynamic update network layer, and the predicted accident growth rate is output; the first preset accident number threshold and the second preset accident number threshold are dynamically updated according to the predicted accident growth rate.

[0062] Furthermore, the correlation analysis module 15 is configured to perform the following method:

[0063] According to the accident black spot determiner, grids whose number is greater than or equal to 1 / 2 of a first preset accident number threshold and less than the first preset accident number threshold are identified as buffer grids, and grids whose number is less than 1 / 2 of the first preset accident number threshold are identified as low-incidence grids; a first-order nine-square grid with the black spot grid as the center grid is obtained, and if the eight adjacent grids in the first-order nine-square grid include the black spot grid or the buffer grid, a first-order merging instruction is obtained, and the nine-square grids are associated and merged according to the first-order merging instruction, and a merged black spot grid is output.

[0064] Furthermore, the correlation analysis module 15 is configured to perform the following method:

[0065] Obtain a second-order nine-square grid with the merged black dot grid as the center grid; if the eight adjacent grids in the second-order nine-square grid include the black dot grid or the buffer grid, obtain a second-order merging instruction, perform associative merging of the nine-square grids according to the second-order merging instruction, output a second-order merged black dot grid, and mark and visualize the second-order merged black dot grid.

[0066] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0068] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for identifying road traffic accident black spot areas, characterized in that: The method comprises: Collect all historical road traffic accident data; Based on the nine-square correlation positioning method, the target traffic area is divided into the first order and the first order space grid is output. The first order space grid includes the first order setting parameters. , and is the length and width of the first-order spatial grid; Performing code mapping on the entire amount of historical road traffic accident data according to the first-order spatial grid to generate a road traffic accident code mapping library; Constructing an accident black spot determiner, the accident black spot determiner calls the road traffic accident code mapping library to identify the number of accidents and output a black spot grid; Performing a nine-grid correlation merging analysis using the black dot grid as the central grid, outputting a merged black dot grid, and marking and visually displaying the merged black dot grid; The accident black spot determiner calls the road traffic accident code mapping library to identify the number of accidents and outputs a black spot grid, the method comprising: The accident black spot determiner includes a first determination channel and a second determination channel, the first determination channel is an absolute value method determination channel, the second determination channel is a relative value method determination channel, and the first determination channel and the second determination channel are connected in sequence; Calculating the number of accidents in the road traffic accident code mapping library based on the first determination channel to obtain an initial black dot grid with a number greater than a first preset accident number threshold; Outputting a black dot grid greater than a second preset accident number threshold from the initial black dot grid based on the second determination channel; The black dot grid is used as the central grid to perform nine-grid correlation merging analysis, and the method includes: According to the accident blackspot determiner, grids with a number of accidents greater than or equal to 1 / 2 of a first preset accident number threshold and less than the first preset accident number threshold are identified as buffer grids, and grids with a number of accidents less than 1 / 2 of the first preset accident number threshold are identified as low-incidence grids; Obtain a first-order nine-square grid with the black dot grid as the center grid. If the eight adjacent grids in the first-order nine-square grid include the black dot grid or the buffer grid, obtain a first-order merging instruction, perform associative merging of the nine-square grids according to the first-order merging instruction, and output a merged black dot grid.

2. The method for identifying a road traffic accident black spot area according to claim 1, wherein: After outputting the first-order spatial grid, the method further includes: Performing traffic characteristic analysis on the target traffic area to obtain characteristic vector values corresponding to each grid area in the first-order spatial grid; According to the size of the eigenvector value corresponding to each grid area, N identification grids with eigenvector values greater than the preset eigenvector value are extracted; Based on the nine-square correlation positioning method, the N identification grids are divided into second order, and a second order space grid is output. The second order space grid includes second order setting parameters , and is the length and width of the second-order spatial grid, and ; The full amount of historical road traffic accident data is coded and mapped according to the second-order spatial grid, and a road traffic accident coding mapping library is updated.

3. The method for identifying a road traffic accident black spot area according to claim 1, wherein: The second preset accident number threshold is the average network accident ratio of the dynamic grid area; The dynamic grid area is obtained by expanding the grid based on the first step length with the currently calculated initial black dot grid as the center, and the first step length is the number of expanded grids.

4. The method for identifying a road traffic accident black spot area according to claim 1, wherein: The first preset accident number threshold and the second preset accident number threshold are dynamically updated by dynamically updating the network layer in a time series manner, the method comprising: Training a time series dynamic update network layer, wherein the time series dynamic update network layer is obtained by training an ARIMA model until convergence, and the training data of the time series dynamic update network layer includes weather labels, holiday labels, traffic change indicators, and historical random deviations; Perform accident trend prediction on the entire amount of historical road traffic accident data according to the time series dynamic update network layer, and output the predicted accident growth rate; The first preset accident quantity threshold and the second preset accident quantity threshold are dynamically updated according to the predicted accident growth rate.

5. The method for identifying road traffic accident black spot areas according to claim 1, characterized in that: After outputting the merged black point grid, the method further includes: Obtain a second-order nine-square grid with the merged black dot grid as the center grid; If the eight adjacent grids in the second-order nine-square grid include the black dot grid or the buffer grid, obtain a second-order merging instruction, perform associative merging of the nine-square grids according to the second-order merging instruction, output a second-order merged black dot grid, and mark and visualize the second-order merged black dot grid.

6. A road traffic accident black spot area identification system, characterized in that: A method for identifying a road traffic accident blackspot area according to any one of claims 1 to 5, the system comprising: Data collection module: collects all historical road traffic accident data; Area division module: Based on the nine-square correlation positioning method, the target traffic area is divided into the first order and the first order space grid is output. The first order space grid includes the first order setting parameters. , and is the length and width of the first-order spatial grid; A coding mapping module: performing coding mapping on the full amount of historical road traffic accident data according to the first-order spatial grid to generate a road traffic accident coding mapping library; Accident black spot determination module: constructing an accident black spot determiner, the accident black spot determiner calls the road traffic accident code mapping library to identify the number of accidents and output a black spot grid; Correlation analysis module: using the black dot grid as the central grid to perform correlation merging analysis of the nine-square grid, outputting a merged black dot grid, and marking and visually displaying the merged black dot grid.

Images