CN109816975A - Traffic accident based reminding method - Google Patents
Traffic accident based reminding method Download PDFInfo
- Publication number
- CN109816975A CN109816975A CN201811200977.2A CN201811200977A CN109816975A CN 109816975 A CN109816975 A CN 109816975A CN 201811200977 A CN201811200977 A CN 201811200977A CN 109816975 A CN109816975 A CN 109816975A
- Authority
- CN
- China
- Prior art keywords
- analysis
- trend
- accident
- data
- value
- 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.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present invention discloses a kind of traffic accident based reminding method, obtain in target time section in car accident amount and target time section car accident time of origin every time, crash analysis is carried out according to car accident time of origin each in car accident amount in target time section and target time section, it is analyzed as a result, generating the prompt information reminded for traffic accident based on the analysis results.The traffic accident based reminding method of the embodiment of the present invention, obtain in target time section in car accident amount and target time section car accident time of origin every time, crash analysis is carried out according to car accident time of origin each in car accident amount in target time section and target time section, obtain analysis result, the prompt information reminded for traffic accident is generated based on the analysis results, to carry out traffic accident prompting based on historical traffic accident.
Description
Technical field
The present invention relates to automotive field more particularly to a kind of traffic accident based reminding methods.
Background technique
With the increase year by year of car ownership, the probability and absolute quantity that vehicle traffic accident occurs also gradually are increasing
Add, in order to promote individual client to the user experience of vehicle, improves degree of recognition, loyalty of the client to vehicle brand, automobile factory
Family, navigation Service quotient etc. usually carry out traffic accident prompt to driver.
Summary of the invention
The embodiment of the present invention provides a kind of traffic accident based reminding method, can carry out traffic accident based on historical traffic accident
It reminds.
The technical solution of the embodiment of the present invention is as follows:
A kind of traffic accident based reminding method, comprising:
Obtain in target time section in car accident amount and the target time section car accident time of origin every time；
According to car accident time of origin each in car accident amount in the target time section and the target time section
Crash analysis is carried out, analysis result is obtained；
The prompt information reminded for traffic accident is generated according to the analysis result.
Traffic accident based reminding method based on the above-mentioned technical proposal obtains in target time section car accident amount and when target
Between car accident time of origin every time in section, according to vehicle thing each in car accident amount in target time section and target time section
Therefore time of origin carries out crash analysis, is analyzed as a result, generating the prompt letter reminded for traffic accident based on the analysis results
Breath, to carry out traffic accident prompting based on historical traffic accident.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is the flow chart of the traffic accident based reminding method shown in the embodiment of the present invention.
Fig. 2 is one of the crash analysis schematic diagram shown in the embodiment of the present invention.
Fig. 3 is two of the crash analysis schematic diagram shown in the embodiment of the present invention.
Fig. 4 is three of the crash analysis schematic diagram shown in the embodiment of the present invention.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistented with the present invention.On the contrary, they be only with it is such as appended
The example of device and method being described in detail in claims, some aspects of the invention are consistent.
As shown in Figure 1, method, which buys that embodiment, provides a kind of traffic accident based reminding method, comprising:
11, car accident time of origin every time is obtained in target time section in car accident amount and the target time section；
12, when being occurred according to each car accident in car accident amount in the target time section and the target time section
Between carry out crash analysis, obtain analysis result；
13, the prompt information reminded for traffic accident is generated according to the analysis result.
In one embodiment, vehicle thing every time in car accident amount and the target time section in the target time section
Therefore time of origin progress crash analysis includes:
Car accident amount is analyzed in the target time section；
And/or
Car accident colliding part and air bag flick state analysis.
In one embodiment, the analysis of car accident amount includes: in the target time section
Accident amount overall trend analytical calculation:
Compare section with calendar year for one, three months (first quarter) is granularity, using rolling average comparison algorithm, is eliminated single
A extreme value influences
Calculation formula is described as follows:
Bmax represents stationarity worst error
V(y)(m)Y m-th month accident amount is represented, wherein V represents accident amount, and y represents y, and m represents m month
Season trend stability sex factor calculates:
S(y-1, y) (m+1, m+3)=| ((V(y)(m+1)+V(y)(m+2)+V(y)(m+3))÷3-(V(y-1)(m+1)+V(y-1)(m+2)+
V(y-1)(m+3))÷ 3)|-Bmax
If S(y-1, y) (m+1, m+3)Value be less than or equal to 0, then season data trend is steady, if S(y-1, y) (m+1, m+3)
Value be greater than 0, then season data trend；
Wherein, Bmax represents stationarity worst error, V(y)(m)Y m-th month accident amount is represented, wherein V represents thing
Therefore measure, y represents y, and m represents m month；
Y-1 to y annual trend calculates:
V(y-1, y)=(S(y-1, y) (1,3)÷|S(y-1, y) (1,3)|)X 0.25+ (S(y-1, y) (4,6)÷|S(y-1, y) (4,6)|)X
0.25+ (S(y-1, y) (7,9)÷|S(y-1, y) (7,9)|)X 0.25+ (S(y-1, y) (10,12)÷|S(y-1, y) (10,12)|)X 0.25
Wherein, S(y-1, y) (1,3)For first quarter trend stability sex factor, S(y-1, y) (4,6)For second quarter trend stability
The factor, S(y-1, y) (7,9)For third season trend stability sex factor, S(y-1, y) (10,12)For fourth quarter trend stability sex factor；
If V(y-1, y)Value be less than or equal to 0, then illustrate that the annual data trend comparison is steady, if V(y-1, y)Value it is big
In 0, then illustrate that the annual data trend is unstable, trend trend is rising or decline；
Season trend directional factors calculate:
D(y-1, y) (m+1, m+3)=((V(y)(m+1)+V(y)(m+2)+V(y)(m+3))-(V(y-1)(m+1)+V(y-1)(m+2)+V(y-1)(m+3)))
÷ |((V(y)(m+1)+V(y)(m+2)+V(y)(m+3))-(V(y-1)(m+1)+V(y-1)(m+2)+V(y-1)(m+3)))|
Wherein, V(y)(m+1)Represent 1st month accident amount of y, V(y-1)(m+2)2nd month accident amount of y-1 is represented,
And so on.
Annual trend directionality calculates:
D(y-1, y)=D(y-1, y) (1,3)X 0.25+D(y-1, y) (4,6)X 0.25+D(y-1, y) (7,9)X 0.25+ D(y-1, y) (10,12)X
0.25
Wherein D(y-1, y) (1,3)For y-1 to y first quarter trend directional factors, D(y-1, y) (4,6)For y-1
To y second quarter trend directional factors, and so on.
Work as V(y-1, y)Greater than 0, and D(y-1, y)When greater than 0, annual data trend is ascendant trend, works as V(y-1, y)Greater than 0, and
D(y-1, y)When less than 0, annual data trend is downward trend, works as V(y-1, y)When less than or equal to 0, annual data trend is steadily to become
Gesture, without apparent raising and lowering sign.
In one embodiment, the analysis of car accident amount includes: in the target time section
Accident amount fluctuation pattern amplitude calculates analysis:
For fluction analysis with year for an analystal section, monthly is analysis time granularity；
Fluctuating range minimum value W is defined firstmin, when fluctuating range value exceeds WminWhen, assert that there are a fluctuations, such as schemes
Shown in 2, when the difference for the accident numerical quantity that three circles mark exceeds fluctuating range minimum value 10, it can be assumed that belong to
One fluctuation section.
It is carried out since the initial data of data sequence, with WminCalculate current time segment data first for criterion
Belong to and rise or fall section, if belonging to ascendant trend, the maximum value of first transition section, i.e. wave are relatively found out by numerical value
The minimum value and trough of last transition section are relatively found out by numerical value, finally calculates one if belonging to downward trend in peak
A wave crest and the staggered data sequence of trough, as shown in Figure 3.
According to calculated Wave crest and wave trough sequence, how many fluctuation section can be calculated, according to each adjacent wave spike
The timestamp of paddy, the time span that can calculate each fluctuation section can according to the accident numerical quantity of each adjacent peaks trough
To calculate, accidents happened measures the oscillation amplitude fluctuated.
In one embodiment, the analysis of car accident amount includes: in the target time section
Maximum accident amount mutation calculates analysis
Definition Δ V is accident amount mutation value Δ V=Vn-Vn-1
Every month, accident amount was respectively V0, V1, V2, V3..., Vn-1, Vn, calculate the accident amount mutation value of corresponding every month:
Δ V1=V1-V0；
Δ V2=V2-V1；
Δ V3=V3-V2；
Δ Vn=Vn-Vn-1；
Obtain mutation value sequence Δ V1, Δ V2, a Δ V3 ... Δ Vn, with Bubble Sort Algorithm to mutation value sequence into
Row sequence obtains adjacent month period and specific mutation value that maximum sudden change value occurs.
In one embodiment, the car accident colliding part flicks state analysis bag with air bag and includes:
All kinds of Other Concomitant Factors data when accident occurs are analyzed, and the relevance between each Other Concomitant Factors is analyzed, under
Face carries out ECALL accident by taking the association analysis method of " accident amount, air bag state, crash type, impact velocity " as an example
It is associated with the method explanation automatically analyzed.
The data definition of each factor is described as follows:
Air bag state: it flicks, flick；
Crash type: it is preceding hit, after hit, side crash, rollover；
Impact velocity: n km/h；
Because this association analysis main purpose is that analysis auto vendor provides vehicle safety when encountering collision accident
The pop-up situation of air bag, thus the emphasis of Main Analysis factor preceding hit, speed per hour 40KM/H or more, according to the class of all kinds of factors
Type number can produce 16 kinds of following factor pattern combinations, as shown in Figure 4.
As shown in Figure 4, each factorial arrangement combination shares 16 kinds, and it is for statistical analysis that we choose following two combination:
It flicks -- preceding to hit -- more than or equal to 40km/h
It does not flick -- preceding to hit -- more than or equal to 40km/h
The respective quantity of both above combination namely accident amount are counted from data set, to calculate collision
Under the conditions of air bag pop-up and do not pop up shared percent data.
In one embodiment, described that the prompt information packet reminded for traffic accident is generated according to the analysis result
It includes:
The result data obtained according to automated analysis automatically generates character property according to the dictionary of different analysis scenes
Crash analysis conclusion.
In one embodiment, the result data obtained according to automated analysis, the word according to different analysis scenes
Library, the crash analysis conclusion for automatically generating character property include:
According to the various different business scenes that eCALL is analyzed, different Scene Semantics templates is defined, in the association of scene template
Different types of semanteme dictionary；
The data that analysis generates are transmitted to automatic conclusion as input and generate engine, engine switches not according to data source
Same analysis scene analyzes scene according to different semantic templates and wins corresponding word or sentence from dictionary, final and analysis
Data combine the analysis conclusion for forming character property together.
In one embodiment, further includes: carry out traffic accident prompting according to template, specifically include:
Define semantic template:
Template 1: from the point of view of prediction result data, the following xx accident per year is in xx trend, annual xx month to xx month
Obvious fluctuating change trend can be presented, maximum fluctuation amplitude reaches xx
Tag entry is calculated currently to calculate data:
Automatic conclusion engine calculates data label item by following steps, according to V(y-1, y)And D(y-1, y)Value, determine whole
Then trend stamps corresponding label for up and down or steadily, according to volatility series data value, determine whether there is fluctuation,
If it is present stamping fluctuation label；
Semantic template is selected, dictionary is called, generates textual conclusion:
Automatic conclusion engine is first according to data source, and selecting analysis scene is forecast analysis scene, then according to second
Calculated tag entry is walked, corresponding suitable semantic template is selected in scene analyzing, is chosen in conjunction with calculating data, and from dictionary
Corresponding word, such as " increase, promoted, decline, being reduced, oscillation, fluctuation " etc., according to semantic template, it is clear and coherent to be combined into comparison
Character analysis summarize；
Generate analysis conclusion:
For the data with fluctuation label, automatic conclusion engine can do the further analysis of causes, according to Wave crest and wave trough
Time point, affiliated date property is calculated, than such as whether having festivals or holidays attribute, bad weather attribute etc., according to semantic mould
The analysis description of plate Crack cause, replenishes in final analysis conclusion.
The traffic accident based reminding method of the embodiment of the present invention obtains car accident amount and target time section in target time section
Interior each car accident time of origin is sent out according to car accident each in car accident amount in target time section and target time section
The raw time carries out crash analysis, is analyzed as a result, generating based on the analysis results and is used for the prompt information that traffic accident is reminded, from
And traffic accident prompting is carried out based on historical traffic accident.
Various embodiments of the present invention are described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In the principle, practical application or improvement to the technology in market for best explaining each embodiment, or make the art
Other those of ordinary skill can understand each embodiment disclosed herein.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (9)
1. a kind of traffic accident based reminding method characterized by comprising
Obtain in target time section in car accident amount and the target time section car accident time of origin every time；
It is carried out according to car accident time of origin each in car accident amount in the target time section and the target time section
Crash analysis obtains analysis result；
The prompt information reminded for traffic accident is generated according to the analysis result.
2. the method according to claim 1, wherein car accident amount and the target in the target time section
Each car accident time of origin carries out crash analysis and includes: in period
Car accident amount is analyzed in the target time section；
And/or
Car accident colliding part and air bag flick state analysis.
3. according to the method described in claim 2, it is characterized in that, in the target time section car accident amount analysis include:
Accident amount overall trend analytical calculation:
Season trend stability sex factor calculates:
S(y-1, y) (m+1, m+3)=
|((V(y)(m+1)+V(y)(m+2)+V(y)(m+3))÷3-(V(y-1)(m+1)+V(y-1)(m+2)+V(y-1)(m+3))÷3)|-Bmax
If S(y-1, y) (m+1, m+3)Value be less than or equal to 0, then season data trend is steady, if S(y-1, y) (m+1, m+3)Value
Greater than 0, then season data trend；
Wherein, Bmax represents stationarity worst error, V(y)(m)Y m-th month accident amount is represented, wherein V represents accident
Amount, y represent y, and m represents m month；
Y-1 to y annual trend calculates:
V(y-1, y)=(S(y-1, y) (1,3)÷|S(y-1, y) (1,3)|)X0.25+
(S(y-1, y) (4,6)÷|S(y-1, y) (4,6)|)X0.25+
(S(y-1, y) (7,9)÷|S(y-1, y) (7,9)|)X0.25+
(S(y-1, y) (10,12)÷|S(y-1, y) (10,12)|)X0.25
Wherein, S(y-1, y) (1,3)For first quarter trend stability sex factor, S(y-1, y) (4,6)For second quarter trend stability sex factor,
S(y-1, y) (7,9)For third season trend stability sex factor, S(y-1, y) (10,12)For fourth quarter trend stability sex factor；
If V(y-1, y)Value be less than or equal to 0, then illustrate that the annual data trend comparison is steady, if V(y-1, y) value be greater than 0,
Then illustrate that the annual data trend is unstable, trend trend is rising or decline；
Season trend directional factors calculate:
D(y-1, y) (m+1, m+3)=
((V(y)(m+1)+V(y)(m+2)+V(y)(m+3))-(V(y-1)(m+1)+V(y-1)(m+2)+V(y-1)(m+3)))÷
|((V(y)(m+1)+V(y)(m+2)+V(y)(m+3))-(V(y-1)(m+1)+V(y-1)(m+2)+V(y-1)(m+3)))|
Wherein, V(y)(m+1)Represent 1st month accident amount of y, V(y-1)(m+2)Represent 2nd month accident amount of y-1；
Annual trend directionality calculates:
D(y-1, y)=D(y-1, y) (1,3)X0.25+D(y-1, y) (4,6)X0.25+D(y-1, y) (7,9)X0.25+D(y-1, y) (10,12)X0.25
Wherein D(y-1, y) (1,3)For y-1 to y first quarter trend directional factors, D(y-1, y) (4,6)For y-1 to y
Second quarter trend directional factors；
Work as V(y-1, y)Greater than 0, and D(y-1, y)When greater than 0, annual data trend is ascendant trend, works as V(y-1, y)Greater than 0, and D(y-1, y)
When less than 0, annual data trend is downward trend, works as V(y-1, y)When less than or equal to 0, annual data trend is moderate tone, is not had
There is apparent raising and lowering sign.
4. according to the method described in claim 2, it is characterized in that, in the target time section car accident amount analysis include:
Accident amount fluctuation pattern amplitude calculates analysis:
For fluction analysis with year for an analystal section, monthly is analysis time granularity；
Fluctuating range minimum value W is defined firstmin, when fluctuating range value exceeds WminWhen, assert that there are a fluctuations；
It is carried out since the initial data of data sequence, with WminCurrent time segment data is calculated first for criterion to belong to
Section is risen or fallen, if belonging to ascendant trend, the maximum value of first transition section, i.e. wave crest are relatively found out by numerical value,
If belonging to downward trend, the minimum value and trough of last transition section are relatively found out by numerical value, finally calculates a wave
Peak and the staggered data sequence of trough；
According to calculated Wave crest and wave trough sequence, how many fluctuation section can be calculated, according to each adjacent peaks trough
Timestamp can calculate the time span of each fluctuation section, according to the accident numerical quantity of each adjacent peaks trough, Ke Yiji
The oscillation amplitude of calculating accident amount fluctuation.
5. according to the method described in claim 2, it is characterized in that, in the target time section car accident amount analysis include:
Maximum accident amount mutation calculates analysis
Definition Δ V is accident amount mutation value Δ V=Vn-Vn-1
Every month, accident amount was respectively V0, V1, V2, V3..., Vn-1, Vn, calculate the accident amount mutation value of corresponding every month:
Δ V1=V1-V0；
Δ V2=V2-V1；
Δ V3=V3-V2；
Δ Vn=Vn-Vn-1；
Obtain mutation value sequence Δ V1, Δ V2, a Δ V3 ... Δ Vn arranges mutation value sequence with Bubble Sort Algorithm
Sequence obtains adjacent month period and specific mutation value that maximum sudden change value occurs.
6. the method according to any one of claim 2 to 5, which is characterized in that the car accident colliding part and gas
Capsule flicks state analysis bag and includes:
All kinds of Other Concomitant Factors data when accident occurs are analyzed, and the relevance between each Other Concomitant Factors is analyzed；
The data definition of each factor is described as follows:
Air bag state: it flicks, flick；
Crash type: it is preceding hit, after hit, side crash, rollover；
Impact velocity: n km/h；
It calculates the air bag pop-up under impact conditions and does not pop up shared percent data.
7. method according to any one of claim 1 to 6, which is characterized in that described to be generated according to the analysis result
For traffic accident remind prompt information include:
The result data obtained according to automated analysis automatically generates the accident of character property according to the dictionary of different analysis scenes
Analyze conclusion.
8. the method according to the description of claim 7 is characterized in that the result data obtained according to automated analysis, according to
According to the dictionary of different analysis scenes, the crash analysis conclusion for automatically generating character property includes:
According to various different business scenes, different Scene Semantics templates is defined, scene template is associated with upper different types of semanteme
Dictionary；
The data that analysis generates are transmitted to automatic conclusion as input and generate engine, engine switches different according to data source
Scene is analyzed, scene is analyzed according to different semantic templates and wins corresponding word or sentence from dictionary, final and analysis data
Combination forms the analysis conclusion of character property together.
9. according to the method described in claim 8, it is characterized by further comprising: carrying out traffic accident prompting according to template, specifically
Include:
Define semantic template:
Template 1: from the point of view of prediction result data, the following xx accident per year can be in xx trend, annual xx month to xx month
Existing obvious fluctuating change trend, maximum fluctuation amplitude reach xx
Tag entry is calculated currently to calculate data:
Automatic conclusion engine calculates data label item by following steps, according to V(y-1, y)And D(y-1, y)Value, determine overall trend
For up and down or steadily, corresponding label is then stamped, according to volatility series data value, determines whether there is fluctuation, if
In the presence of then stamping fluctuation label；
Semantic template is selected, dictionary is called, generates textual conclusion:
Automatic conclusion engine is first according to data source, and selecting analysis scene is forecast analysis scene, then according to second step meter
The tag entry of calculating selects corresponding suitable semantic template analyzing, chooses accordingly in conjunction with calculating data, and from dictionary in scene
Word, such as " increase, promoted, decline, reduce, oscillation, fluctuation " etc., according to semantic template, be combined into the clear and coherent text of comparison
Word analysis is summarized；
Generate analysis conclusion:
For the data with fluctuation label, automatic conclusion engine can do the further analysis of causes, according to Wave crest and wave trough when
Between point, affiliated date property is calculated, than such as whether having festivals or holidays attribute, bad weather attribute etc., according to semantic template shape
It describes, is replenished in final analysis conclusion at the analysis of causes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811200977.2A CN109816975A (en) | 2018-10-11 | 2018-10-11 | Traffic accident based reminding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811200977.2A CN109816975A (en) | 2018-10-11 | 2018-10-11 | Traffic accident based reminding method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109816975A true CN109816975A (en) | 2019-05-28 |
Family
ID=66601866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811200977.2A Pending CN109816975A (en) | 2018-10-11 | 2018-10-11 | Traffic accident based reminding method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816975A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111599171A (en) * | 2020-04-24 | 2020-08-28 | 重庆科技学院 | Intelligent control system, method and storage medium for applying big data to traffic |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236171A (en) * | 2013-04-28 | 2013-08-07 | 李庆忠 | Traffic early-warning method, information transmitter, information receiver and traffic early-warning system |
| CN105678588A (en) * | 2016-01-13 | 2016-06-15 | 焦点科技股份有限公司 | Product sales volume fluctuation assessment method based on e-commerce platform |
| CN107430006A (en) * | 2014-12-02 | 2017-12-01 | 凯文·孙林·王 | Avoid the method and system of accident |
| KR20180078029A (en) * | 2016-12-29 | 2018-07-09 | (주) 더아이엠씨 | Analysis Method for Risk of Traffic Accident and Storage Medium Having the Same |
| CN108491418A (en) * | 2018-02-06 | 2018-09-04 | 西南交通大学 | A kind of acquisition of traffic accident data informationization, management and analysis system and method |
-
2018
- 2018-10-11 CN CN201811200977.2A patent/CN109816975A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236171A (en) * | 2013-04-28 | 2013-08-07 | 李庆忠 | Traffic early-warning method, information transmitter, information receiver and traffic early-warning system |
| CN107430006A (en) * | 2014-12-02 | 2017-12-01 | 凯文·孙林·王 | Avoid the method and system of accident |
| CN105678588A (en) * | 2016-01-13 | 2016-06-15 | 焦点科技股份有限公司 | Product sales volume fluctuation assessment method based on e-commerce platform |
| KR20180078029A (en) * | 2016-12-29 | 2018-07-09 | (주) 더아이엠씨 | Analysis Method for Risk of Traffic Accident and Storage Medium Having the Same |
| CN108491418A (en) * | 2018-02-06 | 2018-09-04 | 西南交通大学 | A kind of acquisition of traffic accident data informationization, management and analysis system and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111599171A (en) * | 2020-04-24 | 2020-08-28 | 重庆科技学院 | Intelligent control system, method and storage medium for applying big data to traffic |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109801491B (en) | Intelligent navigation method, device and equipment based on risk assessment and storage medium | |
| Yi et al. | A machine learning based personalized system for driving state recognition | |
| Yao et al. | Clustering driver behavior using dynamic time warping and hidden Markov model | |
| Xu et al. | Evaluation of the impacts of traffic states on crash risks on freeways | |
| CN108072381B (en) | Path planning method and device | |
| EP3457378A1 (en) | Speed prediction method and apparatus | |
| Llopis-Castelló et al. | Speed prediction models for trucks on horizontal curves of two-lane rural roads | |
| EP3483801A1 (en) | Methods and apparatuses for fuel consumption prediction | |
| CN104834977A (en) | Traffic alarm condition level predication method based on distance metric learning | |
| CN107438547B (en) | Method for predicting the speed of a driver driving a vehicle | |
| CN105354638A (en) | Prediction method and system for repair and maintenance costs of automobile | |
| Kwigizile et al. | Inconsistencies of ordered and unordered probability models for pedestrian injury severity | |
| CN111091215B (en) | Vehicle identification method, device, computer equipment and storage medium | |
| Mahmoudzadeh et al. | Studying crash avoidance maneuvers prior to an impact considering different types of driver’s distractions | |
| CN109816975A (en) | Traffic accident based reminding method | |
| Chen et al. | Driver behavior formulation in intersection dilemma zones with phone use distraction via a logit-Bayesian network hybrid approach | |
| Zou et al. | Multivariate analysis of car-following behavior data using a coupled hidden Markov model | |
| Shangguan et al. | An empirical investigation of driver car-following risk evolution using naturistic driving data and random parameters multinomial logit model with heterogeneity in means and variances | |
| CN113095713B (en) | Driver space risk early warning method based on public transport history alarm data | |
| Wang et al. | Characterizing behavioral differences of autonomous vehicles and human-driven vehicles at signalized intersections based on Waymo Open Dataset | |
| Shiomi et al. | Analysis of stochasticity and heterogeneity of car-following behavior based on data-driven modeling | |
| CN109636053A (en) | A kind of car accident solution optimization system | |
| CN116091254B (en) | Commercial vehicle risk analysis method | |
| CN112035644A (en) | Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium | |
| TWI586571B (en) | Driving behavior analysis method and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |