CN111858719A - Specific condition early warning method and system based on vehicle accident data mining analysis - Google Patents
Specific condition early warning method and system based on vehicle accident data mining analysis Download PDFInfo
- Publication number
- CN111858719A CN111858719A CN202010756437.3A CN202010756437A CN111858719A CN 111858719 A CN111858719 A CN 111858719A CN 202010756437 A CN202010756437 A CN 202010756437A CN 111858719 A CN111858719 A CN 111858719A
- Authority
- CN
- China
- Prior art keywords
- accident
- data
- vehicle
- added
- driving
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
A specific condition early warning method and a system based on vehicle accident data mining analysis comprise the following steps: mining vehicle accident data stored in the cloud database and storing the vehicle accident data in a local database; extracting accident reasons from the vehicle accident data, establishing a mapping relation according to the accident reasons and corresponding accident information, adding classification labels to the accident reasons, and respectively performing first clustering and second clustering on the accident reasons added with driving behavior labels and road environment labels and the corresponding accident information; analyzing accident reasons respectively, gathering mapping relations with the same accident reasons, arranging the mapping relations according to the gathering amount, acquiring driving data and driving road environment data of the current vehicle, judging whether the driving data and the driving road environment data respectively meet the generation conditions of the accident reasons which are arranged in the mapping relations in preset items and added with driving behavior labels and road environment labels, and triggering early warning behaviors of the current vehicle if the driving data and the driving road environment data meet the generation conditions.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a specific condition early warning method and system based on vehicle accident data mining analysis.
Background
Data mining, which is a nontrivial process that reveals implicit, previously unknown and potentially valuable information from a large amount of data in a database, is a hot problem for research in the fields of artificial intelligence and databases.
With the information technology stepping into the big data era, the road traffic accident data gradually presents big data characteristics of huge data volume, high updating speed, rich value and the like.
The conventional multi-injection method theoretical research for mining and analyzing accident data only stays at a macroscopic and single level for researching the traffic accident distribution rule, and the comprehensive consideration of the action of a plurality of factors is lacked.
Therefore, it is necessary to reasonably analyze the traffic accident, and particularly, to accurately grasp the characteristics and the trend of the traffic accident by using data mining and analyzing means, and to perform early warning on similar conditions, so as to reduce the occurrence of the road traffic accident.
Disclosure of Invention
The purpose of the invention is as follows:
in order to overcome the defects in the background art, the embodiment of the invention provides a specific condition early warning method and a specific condition early warning system based on vehicle accident data mining analysis, which can effectively solve the problems related to the background art.
The technical scheme is as follows:
a method for condition-specific early warning based on vehicle accident data mining analysis, the method comprising:
mining vehicle accident data stored in the cloud database and storing the mined vehicle accident data in a local database;
extracting accident reasons from the vehicle accident data, and establishing a mapping relation according to the accident reasons and corresponding accident information;
adding a classification label to the accident reason, wherein the classification label comprises a driving behavior label and a road environment label;
performing first clustering on the accident reason added with the driving behavior label and the corresponding accident information, and performing second clustering on the accident reason added with the road environment label and the corresponding accident information;
analyzing the accident reasons added with the driving behavior labels and the accident reasons added with the road environment labels respectively, converging the mapping relations with the same accident reasons, and arranging the items of the mapping relations according to the convergence quantity;
acquiring driving data and driving road environment data of a current vehicle;
judging whether the driving data of the current vehicle meets the generation condition of the accident reason added with the driving behavior label in the mapping relation arranged in the preset item, and/or judging whether the driving road environment data of the current vehicle meets the generation condition of the accident reason added with the road environment label in the mapping relation arranged in the preset item;
and if so, triggering the early warning behavior of the current vehicle.
As a preferable aspect of the present invention, acquiring driving data of a current vehicle includes:
acquiring the speed, the driving track and the driving time of the current vehicle;
acquiring driving road environment data of a current vehicle, comprising:
the method comprises the steps that environmental data outside a vehicle are obtained through a vehicle-mounted camera device, or positioning data where the current vehicle is located are obtained through a navigation terminal, and the environmental data of the corresponding position are obtained according to the positioning data.
As a preferred mode of the present invention, the method further includes:
dividing the first cluster and the second cluster according to the accident grade;
when judging that the driving data of the current vehicle meets the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the driving behavior labels, and/or when judging that the driving road environment data of the current vehicle meets the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the road environment labels, respectively obtaining the corresponding accident grades;
and triggering early warning behaviors of different levels of the current vehicle according to the accident level.
As a preferable mode of the present invention, the classification tag further includes a vehicle quality tag and a driver physical condition tag.
As a preferred mode of the present invention, the method further includes:
performing third clustering on the accident reasons added with the vehicle quality labels and the corresponding accident information, and performing fourth clustering on the accident reasons added with the driver physical condition labels and the corresponding accident information;
analyzing accident reasons added with the vehicle quality labels and accident reasons added with the body condition labels of the drivers respectively, converging the mapping relations with the same accident reasons, and arranging the items of the mapping relations according to the convergence quantity;
acquiring vehicle quality data and body condition data of a driver of a current vehicle;
judging whether the vehicle mass data of the current vehicle meets the generation condition of the accident reason added with the vehicle mass label in the mapping relation arranged in the preset item, and/or judging whether the driver physical condition data of the current vehicle meets the generation condition of the accident reason added with the driver physical condition label in the mapping relation arranged in the preset item;
and if so, triggering the early warning behavior of the current vehicle.
A condition-specific early warning system based on vehicle accident data mining analysis, comprising:
the vehicle accident data mining module is used for mining the vehicle accident data stored in the cloud database and storing the excavated vehicle accident data in the local database;
the accident reason extraction module is used for extracting accident reasons from the vehicle accident data;
the mapping relation establishing module is used for establishing a mapping relation according to the accident reason and the corresponding accident information;
the classification label adding module is used for adding a classification label on the accident reason, wherein the classification label comprises a driving behavior label and a road environment label;
the first clustering module is used for carrying out first clustering on the accident reasons added with the driving behavior labels and the corresponding accident information;
the second clustering module is used for carrying out second clustering on the accident reasons added with the road environment labels and the corresponding accident information;
the first accident reason processing module is used for analyzing the accident reasons added with the driving behavior labels and the accident reasons added with the road environment labels respectively, converging the mapping relations with the same accident reasons and arranging the items of the mapping relations according to the convergence quantity;
the driving data acquisition module is used for acquiring the driving data of the current vehicle;
the environment data acquisition module is used for acquiring driving road environment data of the current vehicle;
the driving data judging module is used for judging whether the driving data of the current vehicle meets the generation condition of the accident reason which is added with the driving behavior label and arranged in the mapping relation in the preset item;
the environment data judgment module is used for judging whether the driving road environment data of the current vehicle meets the generation condition of the accident reason which is arranged in the mapping relation in the preset item and added with the road environment label;
and the vehicle early warning module is used for triggering the early warning action on the current vehicle when the driving data of the current vehicle meets the generation condition of the accident reason added with the driving action label in the mapping relation arranged in the preset item and/or when the driving road environment data of the current vehicle meets the generation condition of the accident reason added with the road environment label in the mapping relation arranged in the preset item.
As a preferred mode of the present invention, the driving data obtaining module is further configured to obtain a speed, a trajectory, and a driving time of a current vehicle; the environment data acquisition module is further used for acquiring environment data outside the vehicle through the vehicle-mounted camera device, or acquiring positioning data of the current vehicle through the navigation terminal, and acquiring the environment data of the corresponding position according to the positioning data.
As a preferred embodiment of the present invention, the present invention further comprises:
the cluster division module is used for dividing the first cluster and the second cluster according to the accident grade;
the accident grade acquisition module is used for respectively acquiring corresponding accident grades when judging that the driving data of the current vehicle meets the generation conditions of the accident reasons which are added with the driving behavior labels in the mapping relation arranged in the preset item and/or when judging that the driving road environment data of the current vehicle meets the generation conditions of the accident reasons which are added with the road environment labels in the mapping relation arranged in the preset item;
and the vehicle grade early warning module is used for triggering early warning behaviors of different grades of the current vehicle according to the accident grade.
As a preferable mode of the present invention, the classification tag further includes a vehicle quality tag and a driver physical condition tag.
As a preferred embodiment of the present invention, the present invention further comprises:
the third clustering module is used for performing third clustering on the accident reasons added with the vehicle quality labels and the corresponding accident information;
the fourth clustering module is used for carrying out fourth clustering on the accident reasons added with the body condition labels of the drivers and the corresponding accident information;
the second accident reason processing module is used for analyzing the accident reasons added with the vehicle quality labels and the accident reasons added with the driver physical condition labels, gathering the mapping relations with the same accident reasons and arranging the items of the mapping relations according to the gathering quantity;
the vehicle quality data acquisition module is used for acquiring vehicle quality data of a current vehicle;
the physical condition data acquisition module is used for acquiring the physical condition data of a driver of the current vehicle;
the vehicle quality data judging module is used for judging whether the vehicle quality data of the current vehicle meets the generation condition of the accident reason which is added with the vehicle quality label and arranged in the mapping relation in the preset item;
the physical condition data judging module is used for judging whether the physical condition data of the driver of the current vehicle meets the generation condition of the accident reason which is added with the physical condition label of the driver and arranged in the mapping relation in the preset item;
the vehicle early warning module is further used for triggering early warning behaviors of the current vehicle when the vehicle quality data of the current vehicle meets the generation conditions of the accident reasons which are added with the vehicle quality labels in the mapping relations arranged in the preset items and/or when the body condition data of the driver of the current vehicle meets the generation conditions of the accident reasons which are added with the body condition labels of the driver in the mapping relations arranged in the preset items.
The invention realizes the following beneficial effects:
through the implementation of the invention, accident data is mined and analyzed to extract accident reasons, a mapping relation is established according to the accident reasons and corresponding accident information, the accident reasons added with driving behavior labels and road environment labels and the corresponding accident information are clustered respectively, the accident reasons added with the driving behavior labels and the accident reasons added with the road environment labels are analyzed respectively, the mapping relations with the same accident reasons are converged, the mapping relations are arranged according to the convergence quantity, and then early warning is triggered when the conditions are met by comparing the acquired driving data and driving road environment data of the current vehicle with the generation conditions of the accident reasons added with the driving behavior labels and the road environment labels in the mapping relations respectively arranged in preset items, so that the characteristics and the trends of traffic accidents can be accurately mastered by using data mining and analyzing means, early warning is carried out on similar conditions, so that the occurrence of road traffic accidents is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a clustering diagram of a specific condition early warning method based on vehicle accident data mining analysis according to an embodiment of the present invention;
fig. 2 is a clustering diagram of a specific condition early warning method based on vehicle accident data mining and analysis according to a second embodiment of the present invention;
fig. 3 is a schematic flowchart of a specific condition early warning method based on vehicle accident data mining analysis according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of a specific condition early warning method based on vehicle accident data mining analysis according to a second embodiment of the present invention;
fig. 5 is a schematic flowchart of a specific condition early warning method based on vehicle accident data mining analysis according to a third embodiment of the present invention;
fig. 6 is a first structural diagram of a specific condition early warning system based on vehicle accident data mining and analysis according to a third embodiment of the present invention;
fig. 7 is a second structural diagram of a specific condition early warning system based on vehicle accident data mining and analysis according to a third embodiment of the present invention;
fig. 8 is a third structural diagram of a special condition warning system based on vehicle accident data mining and analysis according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example one
Refer to fig. 1 and 3. The embodiment provides a specific condition early warning method based on vehicle accident data mining analysis, which comprises the following steps:
s101, mining vehicle accident data stored in a cloud database and storing the mined vehicle accident data in a local database;
s102, extracting accident reasons from the vehicle accident data, and establishing a mapping relation according to the accident reasons and corresponding accident information;
s103, adding a classification label to the accident reason, wherein the classification label comprises a driving behavior label and a road environment label;
s104, performing first clustering on the accident reason added with the driving behavior label and the corresponding accident information, and performing second clustering on the accident reason added with the road environment label and the corresponding accident information;
s105, analyzing the accident reason added with the driving behavior label and the accident reason added with the road environment label respectively, converging the mapping relations with the same accident reason, and arranging the items of the mapping relations according to the convergence quantity;
s106, acquiring driving data and driving road environment data of the current vehicle;
s107, judging whether the driving data of the current vehicle meets the generation condition of the accident reason which is arranged in the mapping relation in the preset item and added with the driving behavior label, and/or S108, judging whether the driving road environment data of the current vehicle meets the generation condition of the accident reason which is arranged in the mapping relation in the preset item and added with the road environment label;
and if so, executing S109 and triggering the early warning action of the current vehicle.
In S101, the vehicle accident data stored in the cloud database may be mined from the public traffic accident data on the network, or the recorded historical vehicle accident data may be uploaded by the traffic department.
In S102, accident reasons include overspeed, red light running, drunk driving, fatigue driving, random lane change, poor road conditions, more road obstacles, non-standard road buildings, poor weather conditions and the like. The accident information corresponding to the cause of the accident refers to the result of the accident, for example: resulting in collision of several vehicles, the degree of damage to each vehicle, the death or injury of a person, the degree of injury of an injured person, and the like.
In S103, the classification label is to classify the accident cause according to different attributes, that is, according to the driving behavior and the road environment behavior, so as to add different classification labels to different accident causes: the driving behavior tag means that the accident cause is caused by the driving behavior of the driver, and the road environment tag means that the accident cause is caused by the road environment.
For the accident reasons exemplified above, the classification results are: accident reasons of adding driving behavior labels: overspeed, running red light, drunk driving, fatigue driving and random lane change; accident reason of adding road environment label: poor road conditions, more road surface obstacles, non-standard road buildings and poor weather conditions.
In step S104, clustering is performed by identifying the classification label added to each accident cause, that is, performing first clustering on the accident cause added with the driving behavior label and the corresponding accident information, and performing second clustering on the accident cause added with the road environment label and the corresponding accident information, where only the accident cause added with the driving behavior label and the corresponding accident information exist in the first clustering, and only the accident cause added with the road environment label and the corresponding accident information exist in the second clustering.
In S105, the accident cause added with the driving behavior tag and the accident cause added with the road environment tag are analyzed, the same mapping relationships of the accident causes are aggregated, and for the accident causes of the above example, the mapping relationship of the accident cause "overspeed" (the accident cause and the corresponding accident information) is aggregated, the mapping relationship of the accident cause "running red light" (the accident cause and the corresponding accident information) is aggregated, and so on. The aggregation quantity is a mapping relation quantity corresponding to the same accident reason, and different items are arranged according to the size of the aggregation quantity.
For example, assuming that the accident cause corresponding to the mapping relationship with the highest aggregation amount in the first cluster is "overspeed", next to "running red light", and next to "drunk driving", the mapping relationship with the accident cause being "overspeed" is arranged in the first item, the mapping relationship with the accident cause being "running red light" is arranged in the second item, and the mapping relationship with the accident cause being "drunk driving" is arranged in the third item.
Assuming that the accident reason corresponding to the mapping relation with the highest aggregation amount in the second aggregation is 'poor road condition', the mapping relation with the accident reason being 'poor road condition' is arranged in the first item.
In S106, the acquiring of the driving data of the current vehicle specifically includes: and acquiring the speed, the driving track and the driving time of the current vehicle.
The driving data of the current vehicle can acquire the speed of the current vehicle through a speed sensor, acquire a driving track through GPS positioning equipment, judge driving time by acquiring starting time of an engine or a battery, and acquire the driving time through a navigation terminal.
It should be noted that the above driving data is only a part of the present application, and other driving data may be actually acquired, for example, by providing an alcohol detector in the vehicle to detect the alcohol content in the vehicle.
In S107, the specific value of the preset item may be set according to actual requirements, for example, set to 3.
When judging whether the driving data of the current vehicle meets the generation condition of the accident reason added with the driving behavior label in the mapping relation arranged in the previous item 3, firstly judging whether the driving data of the current vehicle meets the generation condition of 'overspeed', specifically judging whether the vehicle speed value of the current vehicle is overspeed, acquiring the current driving position through a GPS, then acquiring the speed limit value corresponding to the current driving position, then judging whether the vehicle speed value of the current vehicle exceeds the corresponding speed limit value, and if so, considering that the generation condition is met.
Judging whether the driving data of the current vehicle meets the generation condition of 'running red light', specifically acquiring a visual field image through a vehicle data recorder, and analyzing the acquired visual field image so as to judge whether the behavior of 'running red light' exists, wherein if the behavior of 'running red light' exists, the generation condition is considered to be met.
Judging whether the driving data of the current vehicle meets the generation condition of 'drunk driving', specifically, carrying out alcohol detection on the region where the driver is located by an alcohol detector arranged in the vehicle so as to judge whether the behavior of 'drinking' exists, and if so, considering that the generation condition is met.
The method for acquiring the driving road environment data of the current vehicle specifically comprises the following steps:
the method comprises the steps that environmental data outside a vehicle are obtained through a vehicle-mounted camera device, or positioning data where the current vehicle is located are obtained through a navigation terminal, and the environmental data of the corresponding position are obtained according to the positioning data.
In S108, the specific value of the preset item may be set according to actual requirements, for example, set to 1.
Judging whether the driving road environment data of the current vehicle meets the generation condition of the accident reason which is arranged in the mapping relation in item 1 and added with the road environment label, specifically, after the driving road environment data of the vehicle is obtained, analyzing the driving road environment data to judge whether the condition of the road condition difference exists, for example, the vehicle flow and the pedestrian flow can be analyzed to judge the road condition, and when the condition of the road condition difference exists, the generation condition is considered to be met.
And when the judgment result of S107 and/or S108 is that the generation condition is met, executing S109, and triggering the early warning behavior of the current vehicle so as to remind the driver of driving safety.
Example two
Refer to fig. 4. In this embodiment, the method further includes the steps of:
s201, dividing a first cluster and a second cluster according to accident grades;
s202, when judging that the driving data of the current vehicle meets the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the driving behavior labels, and/or when judging that the driving road environment data of the current vehicle meets the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the road environment labels, respectively obtaining corresponding accident grades;
and S203, triggering early warning behaviors of different levels of the current vehicle according to the accident level.
Wherein, the accident grade is respectively a light accident, a general accident, a major accident and a super major accident.
In S201, when the first cluster and the second cluster are respectively divided according to the accident level, the accident information in the mapping relationship is specifically analyzed, so as to determine the accident level to which the accident information belongs.
In S203, for different accident levels, different levels of early warning actions are taken, including but not limited to voice single prompt, voice loop prompt, vehicle flameout control and alarm.
EXAMPLE III
Refer to fig. 2 and 5. In this embodiment, the method comprises the steps of:
s301, mining vehicle accident data stored in a cloud database and storing the mined vehicle accident data in a local database;
s302, extracting accident reasons from the vehicle accident data, and establishing a mapping relation according to the accident reasons and corresponding accident information;
s303, adding a classification label to the accident reason, wherein the classification label comprises a vehicle quality label and a driver physical condition label;
s304, performing third clustering on the accident reasons added with the vehicle quality labels and the corresponding accident information, and performing fourth clustering on the accident reasons added with the driver physical condition labels and the corresponding accident information;
s305, analyzing the accident reason added with the vehicle quality label and the accident reason added with the driver physical condition label, converging the mapping relations with the same accident reason, and arranging the items of the mapping relations according to the convergence quantity;
s306, acquiring vehicle quality data and body condition data of a driver of the current vehicle;
s307, judging whether the vehicle mass data of the current vehicle meet the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the vehicle mass labels, and/or S308, judging whether the body condition data of the driver of the current vehicle meet the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the body condition labels of the driver;
and if so, executing S309 and triggering the early warning action of the current vehicle.
The implementation process of S301 is the same as S101, and the implementation process of S302 is the same as S102.
In S303, the vehicle quality label indicates that the accident cause is caused by the quality cause of the vehicle itself, and the driver physical status label indicates that the accident cause is caused by physical factors of the driver, such as diseases.
For the accident reasons exemplified above, the classification results are: accident reasons for adding vehicle quality labels: brake pedal failure, tire burst, constant speed failure, oil leakage, spontaneous combustion, steering failure and the like; accident reason of adding the driver physical condition label: various diseases such as heart disease, cerebral hemorrhage, etc.
In S304, the classification labels added for the accident reasons are identified for clustering, that is, the accident reasons added with the vehicle quality labels and the corresponding accident information are clustered into a third cluster, and the accident reasons added with the driver physical condition labels and the corresponding accident information are clustered into a fourth cluster, wherein only the accident reasons added with the vehicle quality labels and the corresponding accident information exist in the third cluster, and only the accident reasons added with the driver physical condition labels and the corresponding accident information exist in the fourth cluster.
In S305, the accident cause added with the vehicle quality label and the accident cause added with the driver physical condition label are analyzed, the mapping relationships with the same accident cause are aggregated, and for the accident causes mentioned above, the mapping relationship (accident cause and corresponding accident information) of the accident cause "brake pedal failure" is aggregated, the mapping relationship (accident cause and corresponding accident information) of the accident cause "constant speed failure" is aggregated, and so on. The aggregation quantity is a mapping relation quantity corresponding to the same accident reason, and different items are arranged according to the size of the aggregation quantity.
For example, assuming that the accident cause corresponding to the mapping relationship with the highest aggregation amount is "brake pedal failure" and "tire burst" next in the third category, the mapping relationship with the accident cause being "brake pedal failure" is arranged in the first item, and the mapping relationship with the accident cause being "tire burst" is arranged in the second item.
Assuming that the accident cause corresponding to the mapping relationship with the highest aggregation amount in the fourth cluster is "heart disease", the mapping relationship with the accident cause being "heart disease" is arranged in the first item.
In S306, the acquiring of the vehicle quality data of the current vehicle specifically includes performing quality detection on each part of the vehicle through a vehicle detection device, so as to obtain the vehicle quality data, where the vehicle detection device may be disposed in the vehicle itself or an external overhaul device.
The acquiring of the body condition data of the driver specifically includes analyzing and generating the body condition data through the intelligent wearable device, and the body condition data can also be read by acquiring personal information of the driver.
In S307, the specific value of the preset item may be set according to actual requirements, for example, set to 2.
When judging whether the vehicle mass data of the current vehicle meets the generation condition of the accident reason added with the vehicle mass label in the mapping relation arranged in the top item 2, firstly, judging whether the vehicle mass data of the current vehicle meets the generation condition of 'brake pedal failure', specifically judging whether the brake pedal of the current vehicle has a failure condition, and if so, considering that the generation condition is met.
Whether the vehicle quality data of the current vehicle meets the generation condition of 'tire burst' is judged, and the tire pressure value of the current vehicle tire is judged through the tire pressure detection equipment, so that whether the quality problem of 'tire burst' exists is judged, and if yes, the generation condition is considered to be met.
In S308, the specific value of the preset item may be set according to actual requirements, for example, set to 1.
Judging whether the body condition data of the driver meets the generation condition of the accident reason added with the body condition label of the driver in the mapping relation arranged in the item 1, specifically, after the body condition data of the driver is obtained, analyzing the body condition data of the driver to judge whether the heart disease exists or not, and if the heart disease exists, judging that the generation condition is met.
And when the judgment result of the S307 and/or the S308 is that the generation condition is met, executing S309, and triggering the early warning behavior of the current vehicle so as to remind the driver of driving safety.
Example four
Refer to fig. 6, 7, and 8. The embodiment provides a specific condition early warning system based on vehicle accident data mining analysis, which comprises:
and the vehicle accident data mining module 401 is configured to mine the vehicle accident data stored in the cloud database and store the mined vehicle accident data in the local database.
An accident cause extraction module 402, configured to extract an accident cause from the vehicle accident data.
A mapping relationship establishing module 403, configured to establish a mapping relationship according to the accident reason and the corresponding accident information.
A classification label adding module 404, configured to add a classification label to the accident cause, where the classification label includes a driving behavior label and a road environment label.
The first clustering module 405 is configured to perform first clustering on the accident reason to which the driving behavior tag is added and the corresponding accident information.
And a second clustering module 406, configured to perform second clustering on the accident reason with the road environment label added and the corresponding accident information.
The first accident reason processing module 407 is configured to analyze the accident reason added with the driving behavior tag and the accident reason added with the road environment tag, respectively, aggregate the mapping relationships with the same accident reason, and perform item arrangement on the mapping relationships according to the aggregation amount.
And a driving data obtaining module 408, configured to obtain driving data of the current vehicle.
And the environment data acquisition module 409 is used for acquiring driving road environment data of the current vehicle.
And the driving data judging module 410 is configured to judge whether the driving data of the current vehicle meets a generation condition of an accident cause added with a driving behavior tag in the mapping relationship arranged in the preset item.
The environmental data determining module 411 is configured to determine whether driving road environmental data of the current vehicle meets a condition for generating an accident cause with a road environmental label added in a mapping relationship arranged in a preset item.
The vehicle early warning module 412 is configured to trigger an early warning behavior for the current vehicle when the driving data of the current vehicle meets a generation condition of an accident reason added with a driving behavior tag in the mapping relationship arranged in the preset item, and/or when the driving road environment data of the current vehicle meets a generation condition of an accident reason added with a road environment tag in the mapping relationship arranged in the preset item.
Preferably, the driving data obtaining module 408 is further configured to obtain a vehicle speed, a driving track, and a driving time of the current vehicle; the environmental data obtaining module 409 is further configured to obtain environmental data outside the vehicle through the vehicle-mounted camera device, or obtain positioning data where the current vehicle is located through the navigation terminal, and obtain the environmental data of the corresponding position according to the positioning data.
Preferably, the early warning system further comprises:
and a cluster dividing module 413, configured to divide the first cluster and the second cluster according to the accident level.
The accident grade obtaining module 414 is configured to, when it is determined that the driving data of the current vehicle meets the generation condition of the accident reason with the driving behavior tag added in the mapping relationship arranged in the preset item, and/or when it is determined that the driving road environment data of the current vehicle meets the generation condition of the accident reason with the road environment tag added in the mapping relationship arranged in the preset item, respectively obtain corresponding accident grades thereof.
And a vehicle grade early warning module 415, configured to trigger early warning behaviors of different grades of the current vehicle according to the accident grade.
Preferably, the classification label further comprises a vehicle quality label and a driver physical condition label.
Preferably, the early warning system further comprises:
and a third clustering module 416, configured to perform a third clustering on the accident reason with the vehicle quality label and the corresponding accident information.
And a fourth clustering module 417, configured to perform fourth clustering on the accident reason to which the driver physical condition label is added and the corresponding accident information.
The second accident reason processing module 418 is configured to analyze the accident reason to which the vehicle quality label is added and the accident reason to which the driver physical status label is added, respectively, aggregate the mapping relationships with the same accident reason, and arrange items of the mapping relationships according to the aggregation amount.
And a vehicle mass data obtaining module 419 for obtaining vehicle mass data of the current vehicle.
And the physical condition data acquisition module 420 is used for acquiring the physical condition data of the driver of the current vehicle.
The vehicle quality data determining module 421 is configured to determine whether the vehicle quality data of the current vehicle meets a condition for generating an accident cause with a vehicle quality label added in the mapping relationship arranged in the preset item.
And the physical condition data judging module 422 is used for judging whether the physical condition data of the driver of the current vehicle meets the generation condition of the accident reason added with the physical condition label of the driver in the mapping relation arranged in the preset item.
The vehicle early warning module 412 is further configured to trigger an early warning action for the current vehicle when the vehicle quality data of the current vehicle meets the generation condition of the accident reason added with the vehicle quality tag in the mapping relationship arranged in the preset item, and/or when the driver physical condition data of the current vehicle meets the generation condition of the accident reason added with the driver physical condition tag in the mapping relationship arranged in the preset item.
The implementation process of this embodiment is the same as that of the first, second, and third embodiments, and specific reference is made to the above.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (10)
1. A specific condition early warning method based on vehicle accident data mining analysis is characterized by comprising the following steps:
mining vehicle accident data stored in the cloud database and storing the mined vehicle accident data in a local database;
extracting accident reasons from the vehicle accident data, and establishing a mapping relation according to the accident reasons and corresponding accident information;
adding a classification label to the accident reason, wherein the classification label comprises a driving behavior label and a road environment label;
performing first clustering on the accident reason added with the driving behavior label and the corresponding accident information, and performing second clustering on the accident reason added with the road environment label and the corresponding accident information;
analyzing the accident reasons added with the driving behavior labels and the accident reasons added with the road environment labels respectively, converging the mapping relations with the same accident reasons, and arranging the items of the mapping relations according to the convergence quantity;
acquiring driving data and driving road environment data of a current vehicle;
judging whether the driving data of the current vehicle meets the generation condition of the accident reason added with the driving behavior label in the mapping relation arranged in the preset item, and/or judging whether the driving road environment data of the current vehicle meets the generation condition of the accident reason added with the road environment label in the mapping relation arranged in the preset item;
and if so, triggering the early warning behavior of the current vehicle.
2. The special condition early warning method based on vehicle accident data mining analysis according to claim 1, wherein the obtaining of the driving data of the current vehicle comprises:
acquiring the speed, the driving track and the driving time of the current vehicle;
acquiring driving road environment data of a current vehicle, comprising:
the method comprises the steps that environmental data outside a vehicle are obtained through a vehicle-mounted camera device, or positioning data where the current vehicle is located are obtained through a navigation terminal, and the environmental data of the corresponding position are obtained according to the positioning data.
3. The method for condition-specific warning based on vehicle accident data mining analysis according to claim 1, wherein the method further comprises:
dividing the first cluster and the second cluster according to the accident grade;
when judging that the driving data of the current vehicle meets the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the driving behavior labels, and/or when judging that the driving road environment data of the current vehicle meets the generation conditions of the accident reasons which are arranged in the mapping relation in the preset item and added with the road environment labels, respectively obtaining the corresponding accident grades;
and triggering early warning behaviors of different levels of the current vehicle according to the accident level.
4. The condition-specific warning method based on vehicle accident data mining analysis according to claim 1, wherein the classification labels further comprise a vehicle quality label and a driver physical condition label.
5. The method for condition-specific warning based on vehicle accident data mining analysis according to claim 1, wherein the method further comprises:
performing third clustering on the accident reasons added with the vehicle quality labels and the corresponding accident information, and performing fourth clustering on the accident reasons added with the driver physical condition labels and the corresponding accident information;
analyzing accident reasons added with the vehicle quality labels and accident reasons added with the body condition labels of the drivers respectively, converging the mapping relations with the same accident reasons, and arranging the items of the mapping relations according to the convergence quantity;
acquiring vehicle quality data and body condition data of a driver of a current vehicle;
judging whether the vehicle mass data of the current vehicle meets the generation condition of the accident reason added with the vehicle mass label in the mapping relation arranged in the preset item, and/or judging whether the driver physical condition data of the current vehicle meets the generation condition of the accident reason added with the driver physical condition label in the mapping relation arranged in the preset item;
and if so, triggering the early warning behavior of the current vehicle.
6. A specific condition early warning system based on vehicle accident data mining analysis is characterized by comprising:
the vehicle accident data mining module is used for mining the vehicle accident data stored in the cloud database and storing the excavated vehicle accident data in the local database;
the accident reason extraction module is used for extracting accident reasons from the vehicle accident data;
the mapping relation establishing module is used for establishing a mapping relation according to the accident reason and the corresponding accident information;
the classification label adding module is used for adding a classification label on the accident reason, wherein the classification label comprises a driving behavior label and a road environment label;
the first clustering module is used for carrying out first clustering on the accident reasons added with the driving behavior labels and the corresponding accident information;
the second clustering module is used for carrying out second clustering on the accident reasons added with the road environment labels and the corresponding accident information;
the first accident reason processing module is used for analyzing the accident reasons added with the driving behavior labels and the accident reasons added with the road environment labels respectively, converging the mapping relations with the same accident reasons and arranging the items of the mapping relations according to the convergence quantity;
the driving data acquisition module is used for acquiring the driving data of the current vehicle;
the environment data acquisition module is used for acquiring driving road environment data of the current vehicle;
the driving data judging module is used for judging whether the driving data of the current vehicle meets the generation condition of the accident reason which is added with the driving behavior label and arranged in the mapping relation in the preset item;
the environment data judgment module is used for judging whether the driving road environment data of the current vehicle meets the generation condition of the accident reason which is arranged in the mapping relation in the preset item and added with the road environment label;
and the vehicle early warning module is used for triggering the early warning action on the current vehicle when the driving data of the current vehicle meets the generation condition of the accident reason added with the driving action label in the mapping relation arranged in the preset item and/or when the driving road environment data of the current vehicle meets the generation condition of the accident reason added with the road environment label in the mapping relation arranged in the preset item.
7. The specific condition early warning system based on vehicle accident data mining analysis of claim 6, wherein the driving data obtaining module is further used for obtaining the speed, the driving track and the driving time of the current vehicle; the environment data acquisition module is further used for acquiring environment data outside the vehicle through the vehicle-mounted camera device, or acquiring positioning data of the current vehicle through the navigation terminal, and acquiring the environment data of the corresponding position according to the positioning data.
8. The special condition warning system based on vehicle accident data mining analysis according to claim 6, further comprising:
the cluster division module is used for dividing the first cluster and the second cluster according to the accident grade;
the accident grade acquisition module is used for respectively acquiring corresponding accident grades when judging that the driving data of the current vehicle meets the generation conditions of the accident reasons which are added with the driving behavior labels in the mapping relation arranged in the preset item and/or when judging that the driving road environment data of the current vehicle meets the generation conditions of the accident reasons which are added with the road environment labels in the mapping relation arranged in the preset item;
and the vehicle grade early warning module is used for triggering early warning behaviors of different grades of the current vehicle according to the accident grade.
9. The condition-specific warning system based on vehicle accident data mining analysis according to claim 6, wherein the classification labels further comprise a vehicle quality label and a driver physical condition label.
10. The special condition warning system based on vehicle accident data mining analysis according to claim 9, further comprising:
the third clustering module is used for performing third clustering on the accident reasons added with the vehicle quality labels and the corresponding accident information;
the fourth clustering module is used for carrying out fourth clustering on the accident reasons added with the body condition labels of the drivers and the corresponding accident information;
the second accident reason processing module is used for analyzing the accident reasons added with the vehicle quality labels and the accident reasons added with the driver physical condition labels, gathering the mapping relations with the same accident reasons and arranging the items of the mapping relations according to the gathering quantity;
the vehicle quality data acquisition module is used for acquiring vehicle quality data of a current vehicle;
the physical condition data acquisition module is used for acquiring the physical condition data of a driver of the current vehicle;
the vehicle quality data judging module is used for judging whether the vehicle quality data of the current vehicle meets the generation condition of the accident reason which is added with the vehicle quality label and arranged in the mapping relation in the preset item;
the physical condition data judging module is used for judging whether the physical condition data of the driver of the current vehicle meets the generation condition of the accident reason which is added with the physical condition label of the driver and arranged in the mapping relation in the preset item;
the vehicle early warning module is further used for triggering early warning behaviors of the current vehicle when the vehicle quality data of the current vehicle meets the generation conditions of the accident reasons which are added with the vehicle quality labels in the mapping relations arranged in the preset items and/or when the body condition data of the driver of the current vehicle meets the generation conditions of the accident reasons which are added with the body condition labels of the driver in the mapping relations arranged in the preset items.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010756437.3A CN111858719A (en) | 2020-07-31 | 2020-07-31 | Specific condition early warning method and system based on vehicle accident data mining analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010756437.3A CN111858719A (en) | 2020-07-31 | 2020-07-31 | Specific condition early warning method and system based on vehicle accident data mining analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111858719A true CN111858719A (en) | 2020-10-30 |
Family
ID=72952541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010756437.3A Withdrawn CN111858719A (en) | 2020-07-31 | 2020-07-31 | Specific condition early warning method and system based on vehicle accident data mining analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111858719A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100855A (en) * | 2022-06-20 | 2022-09-23 | 公安部交通管理科学研究所 | Early warning method and system for hidden danger vehicles on highway |
| CN115830861A (en) * | 2022-11-17 | 2023-03-21 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Accident analysis and intelligent intervention method and system based on intelligent networked automobile |
| CN117194930A (en) * | 2023-11-07 | 2023-12-08 | 陕西交通电子工程科技有限公司 | Tunnel road section safety monitoring method based on vehicle driving data |
-
2020
- 2020-07-31 CN CN202010756437.3A patent/CN111858719A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100855A (en) * | 2022-06-20 | 2022-09-23 | 公安部交通管理科学研究所 | Early warning method and system for hidden danger vehicles on highway |
| CN115830861A (en) * | 2022-11-17 | 2023-03-21 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Accident analysis and intelligent intervention method and system based on intelligent networked automobile |
| CN115830861B (en) * | 2022-11-17 | 2023-09-05 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Accident analysis and intelligent intervention method and system based on intelligent network-connected automobile |
| CN117194930A (en) * | 2023-11-07 | 2023-12-08 | 陕西交通电子工程科技有限公司 | Tunnel road section safety monitoring method based on vehicle driving data |
| CN117194930B (en) * | 2023-11-07 | 2024-01-19 | 陕西交通电子工程科技有限公司 | Tunnel road section safety monitoring method based on vehicle driving data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784587B (en) | Driving behavior evaluation system | |
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN111858719A (en) | Specific condition early warning method and system based on vehicle accident data mining analysis | |
| CN113609016B (en) | Method, device, equipment and medium for constructing automatic driving test scene of vehicle | |
| CN107784251A (en) | The method evaluated based on image recognition technology driving behavior | |
| CN105045788A (en) | Method of processing and analysing vehicle driving big data and system thereof | |
| CN106448265A (en) | Collecting method and device of driver's driving behavior data | |
| CN107564280B (en) | Driving behavior data acquisition and analysis system and method based on environmental perception | |
| CN112950811B (en) | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety | |
| CN104092736A (en) | Vehicle networking device, server and system, scoring method and data collection method | |
| CN110304068B (en) | Method, device, equipment and storage medium for collecting automobile driving environment information | |
| CN111401414B (en) | Natural driving data-based dangerous scene extraction and classification method | |
| CN109278758B (en) | Intelligent vehicle personalized driving learning system based on intelligent mobile phone | |
| CN108492023A (en) | A kind of vehicle loan air control method based on trajectory analysis | |
| CN112466144A (en) | Road network traffic situation management and control system | |
| CN115279643A (en) | On-board active learning method and apparatus for training a perception network of an autonomous vehicle | |
| CN114446057A (en) | Accident high-incidence point identification early warning method and system based on intelligent network connection environment | |
| CN112070927A (en) | Highway vehicle microscopic driving behavior analysis system and analysis method | |
| CN116753938A (en) | Vehicle test scene generation method, device, storage medium and equipment | |
| CN108791300B (en) | Driving system with high intelligent degree | |
| CN111391859A (en) | Vehicle owner identification early warning method and system | |
| Sun et al. | Driving risk classification methodology for intelligent drive in real traffic event | |
| CN111341106A (en) | Traffic early warning method, device and equipment | |
| CN112686127A (en) | GM-HMM-based driver overtaking intention identification method | |
| Wang et al. | Evaluation of safe driving behavior of transport vehicles based on K-SVM-XGBoost |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201030 |
|
| WW01 | Invention patent application withdrawn after publication |