CN112652168B - Major traffic accident early warning method, system and storage medium - Google Patents
Major traffic accident early warning method, system and storage medium Download PDFInfo
- Publication number
- CN112652168B CN112652168B CN202011473075.3A CN202011473075A CN112652168B CN 112652168 B CN112652168 B CN 112652168B CN 202011473075 A CN202011473075 A CN 202011473075A CN 112652168 B CN112652168 B CN 112652168B
- Authority
- CN
- China
- Prior art keywords
- data
- traffic accident
- early warning
- accident
- traffic
- 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
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
-
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a major traffic accident early warning method, a major traffic accident early warning system and a storage medium, and belongs to the technical field of traffic safety. The invention provides a major traffic accident early warning method, which comprises the steps that a data acquisition module acquires original sample data of a traffic accident and original sample data of traffic violation, a data processing module calculates the number of times of violation before the occurrence of the major traffic accident according to road attributes according to the data acquired by the data acquisition module, and calculates an estimated value of the data of the violation before the occurrence of the major traffic accident by using nuclear density estimation, and a data prediction module performs early warning by using the calculated estimated value as an early warning threshold value, reliably predicts the occurrence time interval of the major traffic accident and improves the safety of road traffic.
Description
Technical Field
The invention relates to the technical field of traffic safety, in particular to a major traffic accident early warning method, a major traffic accident early warning system and a storage medium.
Background
Automobiles are increasingly used in modern society, and the incidence of traffic accidents is also increasing year by year. Serious traffic accidents often cause serious personal and property losses, so that countless families are broken. The occurrence of serious traffic accidents is closely related to the violation of road traffic laws. Through quantitative analysis of the correlation between the major traffic accidents on different roads and the accumulated violation of the traffic laws by accident responsible parties, the accumulated quantity of the traffic violations between the major traffic accidents on the same road can be obtained. How to predict the traffic accident through the number of vehicle owners violating the traffic laws, and then prevent the accident, safe and reliable driving is a problem to be solved urgently.
The invention discloses a method and a device for identifying accident multi-occurrence points based on spatial autocorrelation, which are applied for a Chinese patent with the application number of CN201610890608.5, published 2017, 1 month and 25 days, and discloses the method and the device for identifying the accident multi-occurrence points based on the spatial autocorrelation, wherein from the geographical angle of accident distribution, the geographical distribution characteristics of road space units are described by combining the adjacent relation between the road space units, and the identification of the accident multi-occurrence points is carried out by adopting a nuclear density estimation and spatial autocorrelation method, thereby overcoming the defect that the identification process of the multi-occurrence points in the accident in the prior art adopts a classical mathematical statistical analysis method so as to cause poor visual expression capability of research data. The invention lays a foundation for the excavation of potential accident reasons, and the invention utilizes a nuclear density estimation method to research the multi-point distribution of traffic accidents in space, and solves the spatial correlation of the traffic accidents by the method, but cannot early warn the occurrence of future traffic accidents.
The Chinese patent application relates to a traffic road event early warning method based on graph embedding, application number CN202010623828.8, published on 2020, 10.13.A graph embedding model based on a GraphSAGE graph embedding algorithm is established for training to obtain an embedding vector of a road and reduce dimensions, the dimension-reduced data is used as a sample point to fit a probability density model, finally the speed data and the relevant attribute data of the road in the specified time period, which need to predict the traffic event, are normalized and fused, the embedding vector of the road is obtained through the trained graph embedding model and the dimensions are reduced, the dimension-reduced data is input into the fitted probability density model, and the probability value which needs to be predicted is obtained and visually displayed. The invention is beneficial to the management decision of urban managers on urban traffic, maintains the stable traffic operation order, relieves the urban traffic pressure and makes urban residents go out more conveniently. According to the method, the probability value of the occurrence of the traffic accident is predicted from a microscopic angle through the speed of the road before the historical traffic time occurs and accident-related attribute data, but the method only predicts on a microscopic level and cannot predict the time point of a serious traffic accident possibly occurring in the future from a macroscopic level.
Disclosure of Invention
1. Technical problem to be solved
The invention provides a major traffic accident early warning method, a system and a storage medium, aiming at the problems that the traffic accident prediction in the prior art is not accurate enough and cannot be carried out macroscopically, in particular to the occurrence of major traffic accidents.
2. Technical scheme
The purpose of the invention is realized by the following technical scheme.
A major traffic accident early warning method comprises the steps that a data acquisition module acquires original sample data of a traffic accident and original sample data of a traffic violation, wherein the original sample data of the traffic accident comprises road attributes, management attributes, number attributes, time attributes and accident attributes, and the original sample data of the traffic violation comprises the road attributes, the management attributes, the number attributes and the time attributes; the data processing module calculates the number of times of violation accumulated before the occurrence of the major traffic accident according to the road attributes and the data acquired by the data acquisition module, calculates an estimated value of the violation accumulated data before the occurrence of the major traffic accident by using a kernel density estimation algorithm, and the data prediction module performs early warning by using the calculated estimated value as an early warning threshold value.
Through the correlation analysis of historical road traffic violation and traffic accidents, the reason of each accident is associated with different types of violations. According to the invention, through the acquisition of original sample data, the quantitative correlation between major traffic accidents and law violation is quantitatively analyzed by using a formula, and the technical problems of early intervention and accurate early warning on the major traffic accidents are solved. From the relative distribution of the number of violations and the significant traffic accidents at the historical time, the best expected results in the test exist for the probability distribution fitted at the future time, rather than the density estimation of the parameters. Therefore, a univariate estimation method suitable for the road traffic accident risk is selected, a nonparametric density estimation function is determined by combining the number of the accumulated violations before the occurrence of the major traffic accident, and finally the number of the accumulated violations before each major traffic accident is predicted according to the estimation function.
Furthermore, when the kernel density estimation algorithm is applied, original sample data is divided into z groups according to road attributes and management attributes, wherein z is a natural number greater than zero, and the number of the accumulated illegal important traffic accidents of each group is recorded as
n represents the number of sample space samples of the packet z, variable XzDistribution-compliant kernel density estimation function f (X)z) The expression of (a) is:
in the above formula, K is a kernel function, and h is a bandwidth. Generally, the early warning and the processing of traffic accidents are divided and managed according to traffic management departments and roads, so the grouping of the original sample data is divided according to different roads or different areas of traffic management. The method combines the traffic accident data with the management department and the road information, and can directly further analyze the prediction content in the follow-up accident analysis aiming at the road, thereby greatly improving the accuracy and the calculation efficiency of the traffic accident prediction.
Further, by accumulating the number of violations x0Probability of occurrence of accident
Calculating the number of times of violation of the kernel density estimation function x0-1 and x0Estimate of (2) in between
And taking the minimum value of the absolute value sum of the difference values to calculate the bandwidth h.
Furthermore, the minimum value and the maximum value of the historical illegal times are respectively a and b, a and b are integers, a is smaller than b, the accumulated illegal number before each accident is distributed between a and b, and kernel density estimated values corresponding to all the integers in an array { a, a +1, a +2,. b-1, b } are calculated; and the numerical value corresponding to the maximum kernel density estimated value is an estimated value of accumulated illegal data before the major accident occurs on the road.
Furthermore, the data prediction module sets the estimation value of the accumulated illegal data as an early warning threshold value, and if the kernel density estimation value is greater than the early warning threshold value, the data prediction module carries out prompt troubleshooting according to the management attribute.
Furthermore, when the original sample data of the traffic accident and the original sample data of the traffic violation are grouped, the original sample data of the traffic accident and the original sample data of the traffic violation, which have the same management attribute and road attribute, form a group. The management attribute determines the management department of the road, and the data prediction module can send the prediction data to the road management department in time according to the management attribute. Due to the particularity of the traffic accidents, the accident occurrence frequency and the accident severity of each road are different, and the method and the system take the road attributes as the main classification basis for calculation when the major traffic accident early warning is carried out.
Furthermore, the time attributes in the original sample data of the traffic accident and the original sample data of the traffic violation are both represented by Unix timestamps, and the data processing module performs calculation processing on the data in the same time period. The Unix timestamp unifies different time expression modes, and facilitates data processing and calculation of a system.
Further, the original sample data accident attribute of the traffic accident is represented by the number of death people caused by the accident within a fixed time period. The invention relates to a major traffic accident, which refers to a traffic accident of a dead person and is an important research content in traffic safety technology.
The invention utilizes the relation between the road traffic accident and the law violation on the same traffic road structure to analyze the expected future occurrence time point of the major traffic accident, the road major traffic accident is a random event, no method which can be actually applied exists in the microscopic level, the invention carries out prediction from the macroscopic view, can carry out early warning on the major traffic accident in time according to the prediction result, and improves the prediction accuracy.
The early warning system comprises a data acquisition module, a data processing module and a prediction module, wherein the data acquisition module acquires original sample data of a traffic accident and original sample data of a traffic violation, the data processing module performs calculation processing on the original sample data acquired by the data acquisition module through a nuclear density estimation algorithm, and sends the processed data to the data prediction module for early warning of the major traffic accident.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs a method of providing a warning of a major traffic accident as described.
The invention scientifically predicts the quantity of traffic violations before major traffic accidents occur in each road through a nuclear density estimation method according to road traffic accidents and violation data. The traffic accident occurrence is predicted through univariate estimation, a scientific basis is provided for traffic accident prediction, and the prediction result is more accurate.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
according to the traffic accident early warning method and the traffic accident early warning system, correlation between illegal data and accident data is calculated according to historical traffic accident data and traffic violation data, the probability of a heavy traffic event is calculated and predicted, the danger development trend of a future heavy traffic accident is analyzed, and measures can be taken as early as possible to early warn and control the traffic accident in the traffic management process. The method provides data support for the management of major traffic events, reduces the occurrence frequency of the major traffic events, predicts the occurrence of traffic accidents by using nuclear density estimation, provides scientific basis for traffic accident prediction, enables the prediction result to be more accurate, associates the early warning of the traffic accidents with specific roads and management departments, can further analyze road conditions by combining the characteristics of the roads on the basis of the prediction data of the method, and is suitable for wide application.
Drawings
FIG. 1 is a schematic flow chart of a traffic accident warning method according to the present invention;
FIG. 2 is a block diagram of a traffic accident prediction system according to the present invention.
Detailed Description
The invention is described in detail below with reference to the drawings and specific examples.
Examples
The major traffic accident early warning system of the embodiment is shown in fig. 2, and the early warning system includes a data acquisition module, a data processing module and a prediction module, where the data acquisition module acquires original sample data of a traffic accident and original sample data of a traffic violation within a major traffic accident early warning range, the data processing includes data processing such as cleaning, converting, judging and calculating the acquired data, the data processing is performed by a kernel density estimation algorithm, and the processed data is sent to the data prediction module for performing major traffic accident early warning and prompting.
As shown in fig. 1, the major traffic accident early warning method firstly obtains historical traffic accident data through a data obtaining module, and a data processing module preprocesses the obtained data.
The important traffic accident early warning range is selected firstly, and due to the fact that the automobile running path has certain uncertainty, the early warning range of the traffic accident is determined according to the time range and the space range, and the important traffic accident is subjected to early warning macroscopically. The time range is a specific historical data range, and the embodiment acquires data of three years of history; the spatial range, i.e. the specific road code and the management department, is confirmed with the specific road.
And the data acquisition module is used for acquiring traffic accident data and traffic violation data of the traffic management department. The main fields of traffic accident data include road code (denoted as DLDM), management (denoted as GLBM), accident number (denoted as SGBH), time of accident occurrence (denoted as SGFSSJ), and 30-day number of deaths (denoted as SWRS 30). And (3) carrying out data processing on the acquired traffic accident data, and defining the traffic accident with the death number of more than 0 in 30 days as a major traffic accident. And taking the road code and the management department as units, acquiring the occurrence time of each major traffic accident and the occurrence time of the previous major accident, and recording the occurrence time of the previous major accident as pre _ sgfssj.
The traffic accident data acquired by the data acquisition module of the present embodiment is shown in table 1, wherein the format of the accident time uses Unix time stamps.
TABLE 1
| Major accident number | Management department | Road code | Time of occurrence of an accident | Time of previous major accident |
| xxxx0452018xxxxx | xxxxx9000xxx | XX001 | 1546299000 | 1545382620 |
| xxxx0442018xxxxx | xxxxx9000xxx | XX001 | 1548625500 | 1546299000 |
| xxxx0432018xxxxx | xxxxx9000xxx | XX001 | 1562347600 | 1558625500 |
| xxxx9942019xxxxx | xxxxx9000xxx | XX001 | 1569515200 | 1562347600 |
| ... | ... | ... | ... | ... |
| xxxx9942019xxxxx | xxxxx9000xxx | XX002 | 1572509080 | 1572234200 |
| xxxx9982019xxxxx | xxxxx9000xxx | XX002 | 1589103200 | 1582509080 |
| xxxx9992020xxxxx | xxxxx9000xxx | XX002 | 1596384800 | 1589103200 |
| xxxx9952020xxxxx | xxxxx9000xxx | XX002 | 1598929940 | 1596384800 |
The main fields of the traffic violation data acquired by the data acquisition module comprise a road code (recorded as DLDM), a management department (recorded as GLBM), an violation number (recorded as WFBH) and violation time (recorded as WFSJ). The traffic violation data acquired by the data acquisition module of the present embodiment is shown in table 2, wherein the format of the violation time is also the Unix timestamp.
TABLE 2
And for the data acquired by the data acquisition module, the data processing module calculates the accumulated illegal quantity before the occurrence of the major accident. And setting a time relation condition to be associated with the same road according to the road code and the field of a management department, and calculating the accumulated quantity of the traffic violations before each major accident. The set time relation conditions are as follows: the time of the previous major accident < the time of violation < the time of the accident.
For data of the same management department and road code, a data processing sample is determined, m different management departments and road codes are grouped, and different groups are distinguished by z (z is 0, 1, 2, m) marks. The number of violations accumulated for significant traffic accidents in different groups z is recorded
n represents the number of sample space samples of the packet z. Variable XzIs an independent and identically distributed sample, and the variable X of the independent and identically distributed fingerzSubject to the same distribution and independent of each other, variable XzDistribution-compliant density function f (X)z) The expression for estimating the nuclear density is as follows:
in the above formula, K is a kernel function, and h is a bandwidth.
The data processing module calculates the data acquired by the data acquisition module by using the formula to obtain the accumulated illegal times of the area before the major traffic incident occurs in the area after each group of management departments and the classification of the traffic codes, and calculates the accumulated illegal times of the area before the major traffic incident occurs according to the traffic accident data and the traffic illegal data acquired in the tables 1 and 2 to obtain the accumulated illegal times of the area before the major traffic incident occurs as shown in the table 3.
TABLE 3
| Major accident numbering | Management department | Road code | Time of occurrence of an accident | Accumulating number of violations |
| xxxx0452018xxxxx | xxxxx9000xxx | XX001 | 1546299000 | 80 |
| xxxx0442018xxxxx | xxxxx9000xxx | XX001 | 1548625500 | 192 |
| xxxx0432018xxxxx | xxxxx9000xxx | XX001 | 1562347600 | 101 |
| xxxx9942019xxxxx | xxxxx9000xxx | XX001 | 1569515200 | 115 |
| ... | ... | ... | ... | ... |
| xxxx9942019xxxxx | xxxxx9000xxx | XX002 | 1572509080 | 58 |
| xxxx9982019xxxxx | xxxxx9000xxx | XX002 | 1589103200 | 76 |
| xxxx9992020xxxxx | xxxxx9000xxx | XX002 | 1596384800 | 83 |
| xxxx9952020xxxxx | xxxxx9000xxx | XX002 | 1598929940 | 63 |
Comparing the estimation results of multiple kernel functions, the Gaussian kernel function based on Fourier transform has the optimal result, and the Gaussian function formula is
For the bandwidth of the kernel density function, each accumulated illegal quantity x in the history is used by combining the distribution characteristics of the traffic accidents and the illegal quantities on the random probability0Probability of occurrence of accident
(the value is between 0 and 1), and the number x of times of violation of the density estimation function is calculated0-1 and x0Estimate of (2) in between
The sum of the absolute values of the differences takes the minimum value. The specific formula of the bandwidth is as follows: when h is such that
When the minimum value is taken, h is the determined bandwidth value. In actual calculation, the bandwidth value h needs to be a certain value, which cannot be too large or too small, the bandwidth is too large and cannot meet the requirement, the point with too small bandwidth is too small, and the error is very large.
The minimum value and the maximum value of the historical illegal times are respectively a and b, a and b are integers, a is smaller than b, the step length is determined to be 1 according to the traffic illegal number as the integer, and the core density estimated values corresponding to all the integers in the array { a, a +1, a +2,. b-1, b } are calculated on the assumption that the accumulated illegal number is distributed between a and b before each accident to the same management department and road code; and the numerical value corresponding to the maximum kernel density estimation value is an estimation value of accumulated illegal data before the major accident occurs on the road, and the estimation value of the accumulated illegal data is an early warning threshold value before the major accident occurs on the road.
The present embodiment calculates the estimated value corresponding to the number of violations based on the above data as shown in table 4.
TABLE 4
As shown in table 4, the kernel density estimation values corresponding to different administrative departments and road codes are estimation values of the cumulative number of violations before a major accident occurs on the group of roads. The data prediction module can perform early warning on the occurrence of major accidents on the road according to the kernel density estimated value, if an early warning threshold value is set, if the kernel density estimated value of the road section exceeds the threshold value, the data prediction module indicates that the major traffic accidents can occur or the potential hazards of the major traffic accidents exist in the road section at a high probability, and the prediction system prompts a corresponding management department to investigate the accidents.
According to the embodiment, by utilizing the relation between the road traffic accidents and the illegal accidents on the same traffic road structure, the traffic illegal data accumulated on the road section before each major traffic accident occurs are calculated and analyzed, the time point of the expected future occurrence of the major traffic accident is scientifically predicted, and early warning and treatment are well performed. The embodiment overcomes the subjectivity of artificial prediction, provides data support for the treatment of major traffic events from a macroscopic perspective, and reduces the occurrence frequency of the major traffic events.
If the method for warning a major traffic accident is implemented in the form of a software functional unit and sold or used as an independent product, the method can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The invention and its embodiments have been described above schematically, without limitation, and the invention can be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The representation in the drawings is only one of the embodiments of the invention, the actual construction is not limited thereto, and any reference signs in the claims shall not limit the claims concerned. Therefore, if a person skilled in the art receives the teachings of the present invention, without inventive design, a similar structure and an embodiment to the above technical solution should be covered by the protection scope of the present patent. Furthermore, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Several of the elements recited in the product claims may also be implemented by one element in software or hardware. The terms first, second, etc. are used to denote names, but not to denote any particular order.
Claims (7)
1. A major traffic accident early warning method is characterized in that a data acquisition module acquires original sample data of a traffic accident and original sample data of a traffic violation, wherein the original sample data of the traffic accident comprises a road attribute, a management attribute, a serial number attribute, a time attribute and an accident attribute, and the original sample data of the traffic violation comprises the road attribute, the management attribute, the serial number attribute and the time attribute; the data processing module calculates the accumulated illegal times before the occurrence of the major traffic accident according to the road attributes according to the data acquired by the data acquisition module, calculates an estimated value of the accumulated illegal data before the occurrence of the major traffic accident by using a kernel density estimation algorithm, and the data prediction module performs early warning by using the calculated estimated value as an early warning threshold value;
nuclear density estimationWhen the algorithm is applied, original sample data is divided into z groups according to road attributes and management attributes, wherein z is a natural number greater than zero, and the number of the accumulated illegal important traffic accidents of each group is recorded as
n represents the number of sample space samples of the packet z, variable XzDistribution-compliant kernel density estimation function f (X)z) The expression of (a) is:
in the formula, K is a kernel function, and h is a bandwidth;
by accumulating the number of violations x0Probability of occurrence of accident
Calculating the number x of times of violation of a kernel density estimation function0-1 and x0Estimate of (2) in between
Calculating the bandwidth h by taking the minimum value of the absolute value sum of the difference values;
the minimum value and the maximum value of the historical illegal times are respectively a and b, a and b are integers, a is smaller than b, the accumulated illegal number before each accident is distributed between a and b, and the kernel density estimated values corresponding to all the integers in an array { a, a +1, a +2, … b-1, b } are calculated; and the numerical value corresponding to the maximum kernel density estimated value is an estimated value of accumulated illegal data before the major accident occurs on the road.
2. The major traffic accident early warning method according to claim 1, wherein the data prediction module sets an estimated value of the accumulated illegal data as an early warning threshold, and if the estimated value of the nuclear density is greater than the early warning threshold, the data prediction module performs prompt troubleshooting according to the management attribute.
3. The major traffic accident early warning method according to claim 1, wherein when the traffic accident original sample data and the traffic violation original sample data are grouped, the traffic accident original sample data and the traffic violation original sample data having the same management attribute and the same road attribute are grouped into one group.
4. The major traffic accident early warning method according to claim 3, wherein time attributes in the traffic accident original sample data and the traffic violation original sample data are both represented by Unix timestamps, and the data processing module performs calculation processing on data in the same time period.
5. The major traffic accident early warning method of claim 4, wherein the accident attribute of the original sample data of the traffic accident is represented by the number of death people caused by the accident within a fixed time period.
6. A major traffic accident early warning system is characterized in that the major traffic accident early warning method according to any one of claims 1 to 5 is used, the early warning system comprises a data acquisition module, a data processing module and a prediction module, the data acquisition module acquires original sample data of a traffic accident and original sample data of a traffic violation, the data processing module carries out calculation processing on the original sample data acquired by the data acquisition module through a nuclear density estimation algorithm, and the processed data are sent to the data prediction module to carry out major traffic accident early warning.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs a major traffic accident warning method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011473075.3A CN112652168B (en) | 2020-12-15 | 2020-12-15 | Major traffic accident early warning method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011473075.3A CN112652168B (en) | 2020-12-15 | 2020-12-15 | Major traffic accident early warning method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112652168A CN112652168A (en) | 2021-04-13 |
| CN112652168B true CN112652168B (en) | 2022-05-06 |
Family
ID=75353933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011473075.3A Active CN112652168B (en) | 2020-12-15 | 2020-12-15 | Major traffic accident early warning method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112652168B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177049A (en) * | 2021-05-13 | 2021-07-27 | 中移智行网络科技有限公司 | Data processing method, device and system |
| CN114564549A (en) * | 2022-02-14 | 2022-05-31 | 北京世纪高通科技有限公司 | Method, device, equipment and storage medium for generating thermodynamic diagram of region |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355881A (en) * | 2016-10-12 | 2017-01-25 | 同济大学 | Space-autocorrelation-based traffic accident blackspot identification method and device |
| CN106778866B (en) * | 2016-12-15 | 2020-06-05 | 东南大学 | Accident type and violation type corresponding analysis method in traffic accident |
| CN107845262A (en) * | 2017-11-09 | 2018-03-27 | 山东浪潮云服务信息科技有限公司 | A kind of Predictive Methods of Road Accidents and device |
| CN110766258B (en) * | 2018-07-25 | 2022-04-01 | 阿里巴巴（中国）有限公司 | Road risk assessment method and device |
| CN109584565A (en) * | 2018-12-25 | 2019-04-05 | 天津易华录信息技术有限公司 | A kind of Evaluation of Traffic Safety system and its evaluation number calculation method |
| JP7227577B2 (en) * | 2019-02-24 | 2023-02-22 | ジェネクスト株式会社 | Traffic risk information output system and traffic risk information output program |
| CN110648537B (en) * | 2019-09-28 | 2021-03-05 | 安徽百诚慧通科技有限公司 | Traffic accident correlation analysis method based on Haen's law |
-
2020
- 2020-12-15 CN CN202011473075.3A patent/CN112652168B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112652168A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107610469B (en) | Day-dimension area traffic index prediction method considering multi-factor influence | |
| Donovan et al. | Using coarse GPS data to quantify city-scale transportation system resilience to extreme events | |
| Zheng et al. | Freeway safety estimation using extreme value theory approaches: A comparative study | |
| CN112652168B (en) | Major traffic accident early warning method, system and storage medium | |
| Zou et al. | Jointly analyzing freeway traffic incident clearance and response time using a copula-based approach | |
| CN104750800A (en) | Motor vehicle clustering method based on travel time characteristic | |
| CN107766636A (en) | A kind of urban intersection safe evaluation method based on extreme value theory and microscopic simulation | |
| CN109767618B (en) | Comprehensive study and judgment method and system for abnormal data of public security traffic management service | |
| Chen et al. | Pattern recognition using clustering algorithm for scenario definition in traffic simulation-based decision support systems | |
| CN114596700A (en) | Real-time highway section flow estimation method based on portal data | |
| CN114418175A (en) | Personnel management method and device, electronic equipment and storage medium | |
| Sun et al. | Detecting Crime Types Using Classification Algorithms. | |
| CN116777124B (en) | Power stealing monitoring method based on user power consumption behavior | |
| Abdullah et al. | Exploring the factors influencing traffic accidents: an analysis of black spots and decision tree for injury severity | |
| CN111145535B (en) | Travel time reliability distribution prediction method under complex scene | |
| CN115545996B (en) | Similarity matrix-based subway abnormal historical passenger flow identification method and device | |
| Kumar et al. | Risk assessment of rear-end crashes by incorporating vehicular heterogeneity into Bayesian hierarchical extreme value models | |
| CN102157061A (en) | Keyword-statistic-based traffic event identifying method | |
| CN114708728B (en) | Method for identifying traffic peak period, electronic equipment and storage medium | |
| CN110188324B (en) | Traffic accident poisson regression analysis method based on feature vector space filtering value | |
| Fior et al. | Correlating extreme weather conditions with road traffic safety: A unified latent space model | |
| CN110866624A (en) | Chemical accident prediction method and system | |
| CN114518988A (en) | Resource capacity system, method of controlling the same, and computer-readable storage medium | |
| Yaghoubi et al. | Model-based clustering (MBC) for road data via multivariate mixture of normal distributions and factor analysis (FA) | |
| Yang et al. | Hybrid data-fusion model for short-term road hazardous segments identification based on the acceleration and deceleration information |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 707-710, 7th floor, building B3, innovation industrial park, No. 800, Wangjiang West Road, hi tech Zone, Hefei City, Anhui Province Applicant after: Anhui Baicheng Huitong Technology Co.,Ltd. Address before: Room 707-710, 7th floor, building B3, innovation industrial park, No. 800, Wangjiang West Road, hi tech Zone, Hefei City, Anhui Province Applicant before: ANHUI BAI CHENG HUI TONG TECHNOLOGY CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |