CN109145954A - A kind of net based on multisource spatio-temporal data about vehicle safety evaluation method and system - Google Patents
A kind of net based on multisource spatio-temporal data about vehicle safety evaluation method and system Download PDFInfo
- Publication number
- CN109145954A CN109145954A CN201810821097.0A CN201810821097A CN109145954A CN 109145954 A CN109145954 A CN 109145954A CN 201810821097 A CN201810821097 A CN 201810821097A CN 109145954 A CN109145954 A CN 109145954A
- Authority
- CN
- China
- Prior art keywords
- data
- safety
- road
- net
- driver
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 33
- 238000007405 data analysis Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013501 data transformation Methods 0.000 claims description 3
- 238000012732 spatial analysis Methods 0.000 claims description 3
- 238000013278 delphi method Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims 1
- 230000003068 static effect Effects 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000011002 quantification Methods 0.000 abstract description 2
- 238000009412 basement excavation Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 11
- 230000006399 behavior Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000013144 data compression Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of net based on multisource spatio-temporal data about vehicle safety evaluation method and system, the method for the present invention is the following steps are included: data acquisition is calculated with pretreatment, section division, map match, various dimensions safety index；Present system includes multisource spatio-temporal data analysis platform, geolocation server, government's terminal, enterprise terminal, driver terminal and passenger terminal.Compared with the static supervisory systems of existing identity-based attribute, the present invention is based on multisource spatio-temporal data excavations, analyze to various dimensions each section of each time road safety and each driver each section driver safety, and then more accurately evaluate net about vehicle safety grade, and by safety index by net about vehicle go on a journey risk quantification, Supervision is innovated, it is the important embodiment of improvement system and Governance Ability modernization, governability efficiency can be improved, realize enterprise dynamic supervision, specification driver driving behavior, Assisted Passenger trip decision-making.
Description
Technical field
The present invention relates to online order taxi technical field, more particularly, to a kind of based on multisource spatio-temporal data
Net about vehicle safety evaluation method and system.
Background technique
Net about vehicle safety evaluation becomes current hot spot and difficulties urgently to be resolved with supervision.It makes a general survey of both at home and abroad
Existing the relevant technologies and method are the qualitative research based on static data mostly, lack quantifying based on multisource spatio-temporal data
Change research.And already present supervisory systems is made of Report on Network, aptitude checking and condition monitoring mostly at present, mainly
The static supervisory systems of identity-based attribute, lacks the dynamic supervision system based on driving behavior.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind to be based on multi-source space-time
The net of data about vehicle safety evaluation method and system.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of net based on multisource spatio-temporal data about vehicle safety evaluation method, comprising the following steps:
S1: multisource spatio-temporal data data acquisition；
Acquire and merge net about wheel paths data, order data, road accident data, camera position data, crime and
Responding data, urban highway traffic index, road equipment data, bridge facility data, mobile data, base station location number
According to multisource spatio-temporal datas such as, meteorological datas.
S2: data prediction；
Big data distributed variable-frequencypump frame based on Hadoop and Spark, counts magnanimity multisource spatio-temporal data
According to cleaning (denoising with extraneous data), data integration (data in multiple data sources are combined be stored in one it is consistent
Data storage in), data transformation (initial data being converted into the form of suitable data mining), hough transformation (return by dimension
About, data compression, numerical value reduction, discretization) etc. pretreatment.
S3: section divides；
Section division is carried out to surface road using intersection as node, is node to city expressway using ring road entrance
Section division is carried out, by urban road network's discretization and assigns unique number.
S4: map match；
Based on GIS-Geographic Information System spatial analysis, by different types of multisource spatio-temporal data, (point data, line number are according to, face number
According to) it is matched to above-mentioned corresponding section, the reference frame as safety index evaluation.
S5: safety index calculates；
The relevant characteristic parameter of safety evaluation is extracted to the step S4 multisource spatio-temporal data for being matched to respective stretch, is gone forward side by side
The standardization of row characteristic parameter, the safety index based on machine learning calculate.
Security feature extracts: calculating the relevant feature of safety evaluation based on the above-mentioned multisource spatio-temporal data for being matched to section
Parameter, being specifically divided into road safety characteristic parameter (includes: different sections of highway in the road accident parameter of different periods, congestion in road
Parameter, road equipment parameter, camera parameter, crowd massing parameter, crime parameter, weather parameters etc.) and driver safety feature
Parameter (includes: different drivers in the average speed parameter of different sections of highway, average acceleration parameter, the number parameter, flat of averagely braking
Equal drift angle parameter etc.).
Characteristic parameter standardization: percentile conversion is carried out to above-mentioned all parameters respectively, obtains standardized parameter, just
In comparative analysis and mode input.
Safety index based on machine learning calculates:
(1) above-mentioned standard characteristic parameter is utilized, using Naive Bayes model respectively to road safety level and department
Machine security level carries out classification prediction and calculates with safety index.
Wherein, the specific steps that each safety index calculates are as follows:
(1) frequency of occurrences P (y of each classification in training sample is obtainedi)；
(2) each characteristic parameter a under acquisition is of all categoriesjConditional probability P (aj|yi)；
(3) it is based on Bayesian model, calculates each classification grade yiConditional probability:
Wherein:
(4) it based on the model evaluation of cross validation, is required if meeting verifying, exports optimum classifier model, if discontented
Foot verifying requires, then modifies model parameter, and return step (1)；
(5) sample x={ a to be sorted is inputted1, a2..., am, it is based on optimum classifier model, calculates item category to be sorted
In the probability P (y of each security leveli| x), the security level of output condition maximum probability is as prediction security level:
Max{P(y1| x), P (y2| x) ..., P (yn|x)}
(6) conditional probability based on each security level calculates safety index Kx:
Kx=∑ P (yi|x)×bi
Wherein: biFor security level yiCorresponding standard security index weight (bA=100, bB=75, bC=50, bD=
25)。
(2) according to the calculation method of above-mentioned safety index, comprehensive driver's safety index and road safety index, according to out
The safety index K for the road section length weighted calculation net about vehicle trip route that walking along the street diameter is passed through:
Wherein, lnFor the length of section n,WithRespectively driver safety index and the road peace in the section
Total index number.
A kind of about vehicle safety evaluation system, system of the net based on multisource spatio-temporal data include:
Multisource spatio-temporal data analysis platform: for acquiring, storing, calculating the multi-source sky data of real-time and history；When multi-source
Empty Data Analysis Platform is integrated with the above-mentioned net based on multisource spatio-temporal data about vehicle safety evaluation method, and uses Spark
The technology of Streaming Stream Processing is analyzed and is calculated with history space-time data in real time to above-mentioned, and database is regularly updated
In safety index result.
Geolocation server: for analyzing, generating, issue safety index visualized map；
Background data base: for storing the safety index data of output, and data are regularly updated；
Web server: for connecting database and geolocation server, visual query terminal is built；
Government's terminal: checking the road safety level visualized map of arbitrary region for government customer, and inquires any
The road safety exponential number in period any section, to assist government to carry out safety management to urban road, to potential danger road
Duan Jinhang is built and perfect；Meanwhile the comprehensive safety of Wang Yue vehicle enterprise that government customer can also supervise it in the terminal refers to
Number (weighted average of all nets of the enterprise about vehicle driver safety index and accident number) carries out real-time dynamic ranking, assists government
To Wang Yue vehicle, enterprise is evaluated and is examined, and promotes benign competition between enterprise.
Enterprise terminal: for net about vehicle enterprise customer inquire respective enterprise it is all net Yue Che drivers safety index and its
Ranking, and any driver is checked in the driver safety grade visualized map of different sections of highway, auxiliary enterprises are to net Yue Chesi
Machine driving behavior safety is evaluated and is examined；Meanwhile net about vehicle enterprise customer can also check any driver's in the terminal
Real-time running state (position, speed, acceleration etc.), facilitates enterprise to make emergency processing to emergency case
Driver terminal: the driver safety grade of each comfortable different sections of highway is checked visually for netting Yue Che driver user
Figure, and the driver safety index in any section of search inquiry, are ranked up the driver safety index in all sections, facilitate department
Alert cautious dangerous driving section, improves driving behavior, promotes service level.
Passenger terminal: for being embedded in net about vehicle app by way of api interface, to net, about vehicle passenger pushes safety index
Data realize the function of trip route safety index prediction and the monitoring that detours, and Assisted Passenger is to net Yue Che driver and trip route
It is selected, passenger is allowed to control the trip risk of oneself in real time.
Compared with prior art, the invention has the following advantages that
One, the static supervisory systems of identity-based attribute different from the past, the present invention is based on multisource spatio-temporal data diggings
Pick, analyze to various dimensions each section of each time road safety and each driver each section driver safety,
And then net about vehicle safety grade is more accurately evaluated, and net about vehicle trip risk quantification is innovated by safety index
Net about vehicle Supervision is the important embodiment of improvement system and Governance Ability modernization, governability efficiency can be improved, real
Existing enterprise dynamic supervision, specification driver driving behavior, Assisted Passenger trip decision-making；
Two, the present invention can satisfy the demand of different levels object: Government is provided under day part different weather
Road safety index assessment function and enterprise security index dynamic supervision function；Towards enterprise, each driver is provided in each section
Safety index Function of Evaluation and vehicle operation state monitoring function；Towards driver, the driver safety index in each section is provided
Ranking query function；Towards passenger, trip route safety index Function of Evaluation is provided.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of net based on multisource spatio-temporal data of the present invention about vehicle safety evaluation method；
Fig. 2 is the flow diagram that safety index calculates；
Fig. 3 is Naive Bayes model algorithm flow chart used by calculating safety index；
Fig. 4 is a kind of system architecture diagram of net based on multisource spatio-temporal data of the present invention about vehicle safety evaluation system.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
The present invention relates to a kind of net based on multisource spatio-temporal data about vehicle safety evaluation methods, as shown in Figure 1, packet
Include following steps:
Step 1: multisource spatio-temporal data acquires:
By the data open platform of relevant departments and project cooperation, respectively from Wang Yue vehicle enterprise, traffic department, public affairs
Peace department, urban construction department, Office of the Telecommunications Authority, meteorological department acquire space-time data relevant to net about vehicle safety evaluation, including
But it is not limited to following data type and data field:
(1) net about vehicle track of vehicle data (point data): driver ID, vehicle ID, time, longitude, latitude, speed, brake
Vehicle, direction, empty wagons, it is overhead ...
(2) net about vehicle order data (point data): order ID, driver ID, vehicle ID, order starting point longitude and latitude, order
Terminal longitude and latitude, order start time, the order end time, stroke ID ...
(3) road traffic index (line number evidence): road section ID, state, region, current time index, benchmark index, index difference
Value ...
(4) road accident data (point data): accident ID, accident pattern, accident spot, time of casualty ...
(5) camera position data (point data): number ID, title, infield, longitude, latitude ...
(6) crime data (face data): region, murder number injure number, rob inexorable doom, rape number, swindle number, theft
Number ...
(7) responding data (face data): branch office's title, the time of receiving a crime report, the responding time, the responding origin of an incident ...
(8) road equipment data (line number evidence): when road ID, start-stop place, road width, the road gross area, transformation
Between ...
(9) bridge facility data (line number evidence): bridge ID, bridge title, length, width, transformation the age ...
(10) mobile data (point data): mobile phone ID, the time, base station cell ID, event id ...
(11) base station position data (point data): base station cell ID, longitude, latitude ...
(12) weather data (face data): the time, region, temperature, wind speed, wind direction, precipitation ...
Step 2: multisource spatio-temporal data pre-processes:
Big data distributed variable-frequencypump frame based on Hadoop and Spark, counts above-mentioned multisource spatio-temporal data
According to cleaning (denoising with extraneous data), data integration (data in multiple data sources are combined be stored in one it is consistent
Data storage in), data transformation (initial data being converted into the form of suitable data mining), hough transformation (return by dimension
About, data compression, numerical value reduction, discretization) etc. pretreatment.
Step 3: section divides:
It is node to ground road using intersection based on Open Street Map service acquisition urban road network vector data
Road carries out section division, section division is carried out to city expressway using ring road entrance as node, by urban road network's discretization
And assign unique number.Different direction of traffic are considered for two-way section, 2 different numbers can be subdivided into.
Step 4: map match:
It based on GIS-Geographic Information System spatial analysis and calculates, by above-mentioned different types of space-time data (point data, line number
According to, face data) it is matched to corresponding section, the reference frame as safety index evaluation.
Step 5: various dimensions safety index calculates:
It is divided into the calculating of driver safety index, road safety index calculates and trip route safety index calculates, detailed process
As shown in Figure 2.
Firstly, calculating the relevant characteristic parameter of safety evaluation based on the above-mentioned multisource spatio-temporal data for being matched to section, specifically
Being divided into road safety characteristic parameter (includes: road accident parameter, congestion in road parameter, road of the different sections of highway in different periods
Facility parameters, camera parameter, crowd massing parameter, crime parameter, weather parameters) with driver safety characteristic parameter (include:
Different drivers are in the average speed parameter of different sections of highway, average acceleration parameter, averagely brake number parameter, average drift angle parameter
Deng).
For the ease of comparative analysis and mode input, above-mentioned each characteristic parameter is pressed into Route Grouped, percentile is carried out and turns
It changes, obtains standardized parameter: x={ a1, a2..., am, wherein ajFor the percentile conversion value of security feature parameter.
Then, parameters weighting is determined using Delphi method, and manual grading skill is carried out to a part of characteristic parameter data, beaten
Upper security level label (tetra- grades of A, B, C, D), i.e. label={ y1, y2..., yn, obtain the data of training sample: x0
={ a1, a2..., am, yi, wherein yiFor classification, security level is represented.
Secondly, being trained based on Naive Bayes model to marked characteristic parameter, obtained by cross validation
Optimal classification device model, carries out classification prediction to road safety level and driver safety grade respectively, according to the prediction of each grade
Probability calculation safety index, as shown in figure 3, specifically includes the following steps:
(1) frequency of occurrences P (y of each classification in training sample is calculatedi)；
(2) each characteristic parameter a under calculating is of all categoriesjConditional probability P (aj|yi)；
(3) it is based on Bayesian model, calculates each classification grade yiConditional probability:
Wherein:
(4) based on the model evaluation of cross validation, optimum classifier model is exported if meeting verifying and requiring, it is such as discontented
Foot verifying requires then to modify model parameter, and return step (1)；
(5) sample x={ a to be sorted is inputted1, a2..., am, it is based on optimum classifier model, calculates item category to be sorted
In the probability P (y of each security leveli| x), the security level of output condition maximum probability is as prediction security level:
Max{P(y1| x), P (y2| x) ..., P (yn|x)}
(6) conditional probability based on each security level calculates safety index Kx:
Kx=∑ P (yi|x)×bi
Wherein: biFor security level yiCorresponding standard security index weight (bA=100, bB=75, bC=50, bD=
25)。
Finally, comprehensive network about vehicle trip route passes through the driver safety index of each section nRefer to road safety
NumberThe safety index of net about vehicle trip route is weighted according to road section length.
Wherein: lnFor the length of section n.
The invention further relates to a kind of net based on multisource spatio-temporal data about vehicle safety evaluation system, which includes:
Multisource spatio-temporal data analysis platform, geographical background server, government's terminal, enterprise terminal, driver terminal, passenger terminal.This is
Framework unite as shown in figure 4, implementation steps are as follows:
Step 1: multisource spatio-temporal data analysis platform is built:
It, should based on Spark+Hadoop big data distributed variable-frequencypump framework establishment multisource spatio-temporal data analysis platform
The platform intergration above-mentioned net based on multisource spatio-temporal data about vehicle safety evaluation method, and apply Spark Streaming
The technology of Stream Processing is analyzed and is calculated to real-time and history multi-source sky data, and driver and the road of various dimensions are exported
Safety index.
Step 2: geolocation server is built with background data base:
The safety index that multisource spatio-temporal data analysis platform calculates output is stored in MySQL database, and periodically more
Safety index result in new database.Meanwhile based on GIS-Geographic Information System ArcGIS Desktop to the safety of above-mentioned calculating
Index carries out map visualization, and issues safety index Map Services by geolocation server ArcGIS Server.
Step 3: visualization terminal development:
The safety index map of safety index data and geolocation server publication based on background data base storage, and face
To different object-oriented requirements, including government's terminal, enterprise terminal, driver terminal, passenger terminal, develops respectively: serving government
Webpage terminal, function includes road safety index visual query, dynamic ranking and enterprise security index dynamic ranking
Deng；Serve the webpage terminal of Wang Yue vehicle enterprise, function include each driver safety index visual query, dynamic ranking with
And vehicle dynamic supervision etc.；The mobile terminal of driver is served, function includes inherently safe index visual query and safety
Trip route navigation etc.；The mobile terminal of passenger is served, function includes the prediction of trip route safety index and the monitoring that detours
Deng.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, appoints
The staff what is familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications
Or replacement, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention is answered
It is subject to the protection scope in claims.
Claims (7)
1. a kind of net based on multisource spatio-temporal data about vehicle safety evaluation method, which is characterized in that this method includes following
Step:
1) multisource spatio-temporal data is acquired；
2) the big data distributed variable-frequencypump frame based on Hadoop and Spark carries out data to multisource spatio-temporal data and locates in advance
Reason；
3) section division is carried out to urban road, and the section of division is numbered；
4) be based on GIS-Geographic Information System spatial analysis, by step 2) treated multisource spatio-temporal data is matched to divide after correspondence
Section；
5) multisource spatio-temporal data for being matched to respective stretch based on step 4) obtains the relevant characteristic parameter of safety evaluation, uses
Naive Bayes model carries out security level classification prediction and safety index to road related data and driver's related data respectively
It calculates, and then pre- survey grid about vehicle trip route safety index.
2. a kind of net based on multisource spatio-temporal data according to claim 1 about vehicle safety evaluation method, feature
It is, multisource spatio-temporal data described in step 1) includes but is not limited to net about wheel paths data, order data, road accident number
According to, camera position data, crime and responding data, urban highway traffic index, road equipment data, bridge facility data,
Mobile data, base station position data and meteorological data.
3. a kind of net based on multisource spatio-temporal data according to claim 1 about vehicle safety evaluation method, feature
It is, in step 2), data prediction includes data cleansing, data transformation and hough transformation.
4. a kind of net based on multisource spatio-temporal data according to claim 1 about vehicle safety evaluation method, feature
It is, the particular content of step 3) are as follows:
Section division is carried out to surface road using intersection as node, road is carried out to city expressway using ring road entrance as node
Section divides, and by urban road network's discretization and assigns unique number.
5. a kind of net based on multisource spatio-temporal data according to claim 1 about vehicle safety evaluation method, feature
Be, step 5) specifically includes the following steps:
501) multisource spatio-temporal data that will match to respective stretch is divided into road safety characteristic parameter and driver safety characteristic parameter；
502) road safety characteristic parameter and driver safety characteristic parameter are pressed into Route Grouped, and carries out percentile conversion, obtained
Standardized characteristic parameter；
503) characteristic parameter weight is determined by Delphi method, and manual grading skill, label is carried out to a part of characteristic parameter data
Security level label obtains training sample data；
504) it is trained based on characteristic parameter of the Naive Bayes model to marked security level label, is tested by intersecting
After card obtains optimal classification device model, classification prediction carried out to road safety level and driver safety grade respectively, and according to point
Class probability calculation road safety index and driver safety index；
505) road safety index and driver safety index, overall merit net about vehicle trip route safety index are combined.
6. a kind of realize the net as described in any one in claim 1-5 based on multisource spatio-temporal data about vehicle safety evaluation side
The evaluation system of method, which is characterized in that the system includes:
Multisource spatio-temporal data analysis platform: for acquiring, storing, calculating the multi-source sky data of real-time and history；
Geolocation server: for analyzing, generating, issue safety index visualized map；
Background data base: for storing the safety index data of output, and data are regularly updated；
Web server: for connecting database and geolocation server, visual query terminal is built；
Government's terminal: the road safety level visualized map of arbitrary region is checked for government customer, and inquires arbitrary period
The road safety exponential number in any section；
Enterprise terminal: the safety index and its ranking feelings of all net Yue Che drivers of respective enterprise are checked for net about vehicle enterprise customer
Condition, and check any driver in the security level visualized map of different sections of highway；
Driver terminal: checking the driver safety grade visualized map of each comfortable different sections of highway for netting Yue Che driver user, and
The driver safety index in any section of search inquiry is ranked up the driver safety index in all sections；
Passenger terminal: app is serviced for being embedded in net about vehicle by way of api interface, about vehicle passenger pushes safety index to net
Data.
7. a kind of evaluation system according to claim 6, which is characterized in that the multisource spatio-temporal data analysis platform is adopted
Real-time and history multi-source sky data are analyzed and calculated with Spark Streaming Stream Processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810821097.0A CN109145954B (en) | 2018-07-24 | 2018-07-24 | Network taxi appointment travel safety evaluation method and system based on multi-source time-space data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810821097.0A CN109145954B (en) | 2018-07-24 | 2018-07-24 | Network taxi appointment travel safety evaluation method and system based on multi-source time-space data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109145954A true CN109145954A (en) | 2019-01-04 |
| CN109145954B CN109145954B (en) | 2021-11-09 |
Family
ID=64797713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810821097.0A Active CN109145954B (en) | 2018-07-24 | 2018-07-24 | Network taxi appointment travel safety evaluation method and system based on multi-source time-space data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145954B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726942A (en) * | 2019-03-01 | 2019-05-07 | 北京汽车研究总院有限公司 | A kind of driving environment methods of risk assessment and system |
| CN110162702A (en) * | 2019-05-11 | 2019-08-23 | 任明和 | The method that safety label is carried out to road based on big data |
| CN110555536A (en) * | 2019-09-06 | 2019-12-10 | 南京领行科技股份有限公司 | security prediction method, device, equipment and storage medium for network taxi appointment orders |
| CN110716935A (en) * | 2019-10-09 | 2020-01-21 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Track data analysis and visualization method and system based on online taxi appointment travel |
| CN110992119A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Method and system for sequencing risk orders |
| CN111145542A (en) * | 2019-12-23 | 2020-05-12 | 北京高诚科技发展有限公司 | Operation property monitoring system and method based on vehicle behaviors |
| CN111612200A (en) * | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Order security prediction method, device, server and storage medium |
| CN111612197A (en) * | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Security event order detection method and device and electronic equipment |
| CN111932046A (en) * | 2019-05-13 | 2020-11-13 | 阿里巴巴集团控股有限公司 | Method for processing risk in service scene, computer equipment and storage medium |
| CN112017463A (en) * | 2020-07-17 | 2020-12-01 | 盛威时代科技集团有限公司 | Intelligent network car booking management method |
| CN112052972A (en) * | 2020-09-11 | 2020-12-08 | 广州宸祺出行科技有限公司 | Method and system for visualizing behavior of taxi booking driver |
| CN112188438A (en) * | 2020-09-22 | 2021-01-05 | 广州宸祺出行科技有限公司 | Method and system for exchanging data between network booking APP and vehicle machine |
| CN113379233A (en) * | 2021-06-08 | 2021-09-10 | 重庆大学 | Travel time reliability estimation method and device based on high-order moment |
| CN114386737A (en) * | 2021-10-09 | 2022-04-22 | 浙江警察学院 | Method for monitoring safety of passengers on network appointment in mobile internet era |
| WO2022142922A1 (en) * | 2020-12-29 | 2022-07-07 | 中兴通讯股份有限公司 | Road safety assessment method, video processing center, and storage medium |
| CN114756975A (en) * | 2022-06-15 | 2022-07-15 | 江苏新晖测控科技有限公司 | Dynamic liquid level wireless monitoring system and method based on double channels |
| CN114997527A (en) * | 2022-07-18 | 2022-09-02 | 苏州智能交通信息科技股份有限公司 | Enterprise assessment and evaluation method, system and terminal based on road transportation dynamic data |
| CN117014473A (en) * | 2023-09-28 | 2023-11-07 | 东莞中科智城软件有限公司 | Intelligent networking automobile monitoring system based on end cloud fusion technology |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855756A (en) * | 2012-09-28 | 2013-01-02 | 深圳华宏联创科技有限公司 | Intelligent method, server and system for calling taxi |
| CN103531025A (en) * | 2013-11-08 | 2014-01-22 | 宁波市康惠网络科技有限公司 | Carpooling system for matching information through route segmenting method |
| US20140372351A1 (en) * | 2013-03-28 | 2014-12-18 | Wal-Mart Stores, Inc. | Rule-based item classification |
| CN104978853A (en) * | 2014-04-01 | 2015-10-14 | 中国移动通信集团公司 | Road traffic safety evaluating method and system |
| CN105844384A (en) * | 2016-03-14 | 2016-08-10 | 北京工业大学 | Road safety evaluation method and apparatus |
| CN107679636A (en) * | 2017-08-29 | 2018-02-09 | 明光泰源安防科技有限公司 | A kind of driver safety appraisal procedure based on net about car |
-
2018
- 2018-07-24 CN CN201810821097.0A patent/CN109145954B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855756A (en) * | 2012-09-28 | 2013-01-02 | 深圳华宏联创科技有限公司 | Intelligent method, server and system for calling taxi |
| US20140372351A1 (en) * | 2013-03-28 | 2014-12-18 | Wal-Mart Stores, Inc. | Rule-based item classification |
| CN103531025A (en) * | 2013-11-08 | 2014-01-22 | 宁波市康惠网络科技有限公司 | Carpooling system for matching information through route segmenting method |
| CN104978853A (en) * | 2014-04-01 | 2015-10-14 | 中国移动通信集团公司 | Road traffic safety evaluating method and system |
| CN105844384A (en) * | 2016-03-14 | 2016-08-10 | 北京工业大学 | Road safety evaluation method and apparatus |
| CN107679636A (en) * | 2017-08-29 | 2018-02-09 | 明光泰源安防科技有限公司 | A kind of driver safety appraisal procedure based on net about car |
Non-Patent Citations (1)
| Title |
|---|
| 王中锋: "基于动态朴素贝叶斯分类器的明渠水华风险评估模型", 《南水北调与水利科技》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992119A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Method and system for sequencing risk orders |
| CN111612200A (en) * | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Order security prediction method, device, server and storage medium |
| CN111612197A (en) * | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Security event order detection method and device and electronic equipment |
| CN111612200B (en) * | 2019-02-25 | 2023-07-14 | 北京嘀嘀无限科技发展有限公司 | Order security prediction method, device, server and storage medium |
| CN109726942A (en) * | 2019-03-01 | 2019-05-07 | 北京汽车研究总院有限公司 | A kind of driving environment methods of risk assessment and system |
| CN110162702A (en) * | 2019-05-11 | 2019-08-23 | 任明和 | The method that safety label is carried out to road based on big data |
| CN111932046A (en) * | 2019-05-13 | 2020-11-13 | 阿里巴巴集团控股有限公司 | Method for processing risk in service scene, computer equipment and storage medium |
| CN110555536A (en) * | 2019-09-06 | 2019-12-10 | 南京领行科技股份有限公司 | security prediction method, device, equipment and storage medium for network taxi appointment orders |
| CN110716935A (en) * | 2019-10-09 | 2020-01-21 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Track data analysis and visualization method and system based on online taxi appointment travel |
| CN111145542A (en) * | 2019-12-23 | 2020-05-12 | 北京高诚科技发展有限公司 | Operation property monitoring system and method based on vehicle behaviors |
| CN112017463A (en) * | 2020-07-17 | 2020-12-01 | 盛威时代科技集团有限公司 | Intelligent network car booking management method |
| CN112017463B (en) * | 2020-07-17 | 2021-11-12 | 盛威时代科技集团有限公司 | Intelligent network car booking management method |
| CN112052972B (en) * | 2020-09-11 | 2021-05-18 | 广州宸祺出行科技有限公司 | Method and system for visualizing behavior of taxi booking driver |
| CN112052972A (en) * | 2020-09-11 | 2020-12-08 | 广州宸祺出行科技有限公司 | Method and system for visualizing behavior of taxi booking driver |
| CN112188438A (en) * | 2020-09-22 | 2021-01-05 | 广州宸祺出行科技有限公司 | Method and system for exchanging data between network booking APP and vehicle machine |
| WO2022142922A1 (en) * | 2020-12-29 | 2022-07-07 | 中兴通讯股份有限公司 | Road safety assessment method, video processing center, and storage medium |
| CN113379233A (en) * | 2021-06-08 | 2021-09-10 | 重庆大学 | Travel time reliability estimation method and device based on high-order moment |
| CN113379233B (en) * | 2021-06-08 | 2023-02-28 | 重庆大学 | Travel time reliability estimation method and device based on high-order moment |
| CN114386737A (en) * | 2021-10-09 | 2022-04-22 | 浙江警察学院 | Method for monitoring safety of passengers on network appointment in mobile internet era |
| CN114386737B (en) * | 2021-10-09 | 2023-10-13 | 浙江警察学院 | Method for monitoring safety of passengers on internet about car in mobile interconnection era |
| CN114756975A (en) * | 2022-06-15 | 2022-07-15 | 江苏新晖测控科技有限公司 | Dynamic liquid level wireless monitoring system and method based on double channels |
| CN114756975B (en) * | 2022-06-15 | 2022-09-02 | 江苏新晖测控科技有限公司 | Dynamic liquid level wireless monitoring system and method based on double channels |
| CN114997527A (en) * | 2022-07-18 | 2022-09-02 | 苏州智能交通信息科技股份有限公司 | Enterprise assessment and evaluation method, system and terminal based on road transportation dynamic data |
| CN117014473A (en) * | 2023-09-28 | 2023-11-07 | 东莞中科智城软件有限公司 | Intelligent networking automobile monitoring system based on end cloud fusion technology |
| CN117014473B (en) * | 2023-09-28 | 2023-12-19 | 东莞中科智城软件有限公司 | Intelligent networking automobile monitoring system based on end cloud fusion technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145954B (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145954A (en) | A kind of net based on multisource spatio-temporal data about vehicle safety evaluation method and system | |
| CN109923575B (en) | Device and method for measuring absolute and/or relative risk potential of vehicle accident | |
| De Oña et al. | Key factors affecting rail service quality in the Northern Italy: a decision tree approach | |
| Torbaghan et al. | Understanding the potential of emerging digital technologies for improving road safety | |
| CN112749825B (en) | Method and device for predicting destination of vehicle | |
| KR20140128063A (en) | Traffic prediction system | |
| CN111653096A (en) | Urban trip mode identification method based on mobile phone signaling data | |
| Pauer | Development potentials and strategic objectives of intelligent transport systems improving road safety | |
| CN113988476A (en) | Dynamic assessment prediction method for road transportation safety risk | |
| CN111291916A (en) | Driving behavior safety prediction method and device, electronic equipment and storage medium | |
| Chepuri et al. | Travel time reliability analysis on selected bus route of mysore using GPS data | |
| CN113868492A (en) | Visual OD (origin-destination) analysis method based on electric police and checkpoint data and application | |
| Alrassy et al. | Driver behavior indices from large-scale fleet telematics data as surrogate safety measures | |
| Chand et al. | Examining the macro-level factors affecting vehicle breakdown duration | |
| Růžička et al. | Big data application for urban transport solutions | |
| D'Andrea et al. | A functional road classification with data mining techniques | |
| CN113538907B (en) | Traffic flow classification-based driving time estimation system | |
| Cohen et al. | Travel time estimation between loop detectors and FCD: A compatibility study on the Lille network, France | |
| CN114298493A (en) | Road operation monitoring system, method, terminal and storage medium | |
| Lian et al. | Advances in estimating pedestrian measures through artificial intelligence: From data sources, computer vision, video analytics to the prediction of crash frequency | |
| Khabiri et al. | Application of data mining algorithm to investigate the effect of intelligent transportation systems on road accidents reduction by decision tree | |
| Causevic et al. | Potentials and advantages of applying geographic information systems in various fields of traffic engineering | |
| Wang | Real‐Time Evaluation Method of Vehicle Conflict Risk on Urban Expressway Based on Smartphone GPS Data | |
| Babu et al. | Smart transport system for passenger comfort using IoT | |
| Farajollahi et al. | Assessing accident hotspots by using volunteered geographic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |