CN112989069B - Traffic violation analysis method based on knowledge graph and block chain - Google Patents
Traffic violation analysis method based on knowledge graph and block chain Download PDFInfo
- Publication number
- CN112989069B CN112989069B CN202110505930.2A CN202110505930A CN112989069B CN 112989069 B CN112989069 B CN 112989069B CN 202110505930 A CN202110505930 A CN 202110505930A CN 112989069 B CN112989069 B CN 112989069B
- Authority
- CN
- China
- Prior art keywords
- violation
- driver
- vehicle
- behavior
- traffic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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]
-
- 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
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Animal Behavior & Ethology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
A traffic violation analysis method based on a knowledge graph and a block chain comprises the following steps: after the violation behaviors occur, vehicle information is obtained according to the violation license plate, a knowledge map is associated, and possible drivers of the vehicle are matched from the knowledge map; the driver who breaks rules and regulations goes to the traffic management department to accept the punishment, the suspected top-package behavior of the driver who breaks rules and regulations is judged, the information of the driver and the vehicle breaking rules and regulations is quickly inquired through the knowledge map, the occurrence prediction of the breaking rules and regulations is carried out, and the function of early warning the breaking rules and regulations is achieved; the personal knowledge map information of the driver is stored, sent and received through the block chain technology, data safety is improved, the establishment of an information storage center is omitted, the disaster recovery effect is achieved, the information in the block chain is made public and transparent, and illegal behaviors such as buying and selling scores and package pushing of the driver are reduced.
Description
Technical Field
The invention belongs to the field of artificial intelligence, and particularly relates to a traffic violation analysis method based on a knowledge graph and a block chain.
Background
With the rapid development of the modern transportation industry, more and more people choose to drive private cars for going out, but the violation behaviors of the vehicles are increased.
The current analysis method for the violation behaviors of the vehicle mainly depends on a video monitoring technology, the efficiency of the technology can be greatly improved by shooting monitoring equipment, a vehicle-mounted recorder, monitoring equipment in houses near the violation site and a witness at the accident, and after the violation behaviors occur, correct judgment on the violation behaviors can be easily obtained only by performing evidence analysis on collected various information.
However, the basic data layer of the traditional traffic violation processing system mainly depends on basic databases respectively established by different government departments such as traffic, public security and the like, in the violation event processing process, required related data need to be acquired from each department, the violation processing result is finally obtained through data center inspection and analysis, and after the violation result processing is completed, a violation driver needs to go to an appointed bank to pay a ticket.
Although the road monitoring system is increasingly perfected, the monitoring coverage area is gradually enlarged, and the image definition of monitoring equipment is also continuously improved, the situation that video monitoring cannot be solved is inevitable, namely, an area which cannot be installed or monitored in a small quantity due to remote or special geographic positions can be generated, and the monitoring definition is possibly insufficient, so that a monitoring terminal can only obtain photos of illegal vehicles but cannot obtain driver photos corresponding to the illegal behaviors, when the traffic is handled clearly and illegally, a driver can utilize bugs in the illegal processing process to avoid deduction and even escape from legal sanctions by purchasing and selling driver certificate scores, and the technology can only detect and analyze the generated traffic illegal behaviors, cannot predict the illegal behaviors, and plays a role in early warning for the driver.
The traditional traffic violation processing system has the disadvantages that the data acquisition approaches are limited, the sources are possibly unreliable, the data acquisition rate of a basic database is low, the database structures are not uniform, the data are difficult to verify and share mutually, and when a violation event is processed, all departments are required to cooperate with each other, so that the violation processing efficiency is greatly reduced; in addition, in the data transmission process, data is easily leaked or tampered, and the data security is insufficient.
Disclosure of Invention
The invention provides a traffic violation analysis method based on a knowledge graph and a block chain.
In order to solve the technical problems, the invention adopts the technical scheme that: a traffic violation analysis method based on a knowledge graph and a block chain comprises the following steps: s1, after the violation occurs, the vehicle information is obtained according to the violation license plate and the knowledge map is associated, the possible drivers of the vehicle are matched from the knowledge map, and the knowledge map mainly comprises three types of entities: the system comprises a driver entity, a vehicle entity and a violation recording entity, wherein the attributes of the driver entity comprise the name, the identity card, the age, the driving age, the relative of a driver with a driving license and the estimated time interval of possible violation; the vehicle entity attributes comprise license plate numbers, vehicle types, vehicle ages, drivers of the vehicles and available drivers of the vehicles; the violation record entity attributes comprise violation types, violation times, violation places and accident deduction conditions, and entity association is carried out according to the relationship between the driver and the vehicle, the relationship between the driver and the driver, violation records and information about the driver and the vehicle, so that a complete violation record knowledge map is finally obtained; s2, when the driver violating the regulations goes to the traffic control department to accept the penalty, if the driver violating the regulations does not belong to the driver list matched with the vehicle, the driver is suspected to have a top package behavior; s3, if the driver against the traffic regulations belongs to a driver list matched with the vehicle, the weight score comprises driving age weight division, accident frequently-occurring area weight division, violation type weight division, daily driving area weight division and threshold weight score, if the driving age weight division, the accident frequently-occurring area weight division, the violation type weight division and the daily driving area weight are added to exceed the set threshold weight score, the suspected driver is suspected to have a top-package behavior, a suspected driver top-package behavior is sent to a traffic police team through a block chain to carry out investigation request, traffic violation is carried out, violation information is uploaded to the block chain, the block chain is broadcasted, and the violation information is uploaded to a knowledge map; s4, if no top-packing behavior exists in the steps S1 to S3, analyzing the driving habit of the driver, analyzing the data of the violation behavior of the driver by using a Cox model, predicting the information of the next violation behavior, comparing the traffic violation condition of the violation behavior and the predicted violation behavior information when the driver goes to the traffic control department again to accept penalty, and if a large matching difference exists, determining that the top-packing behavior is suspected to appear.
In some embodiments, the Cox model is calculated by first passing throughEstablishing a knowledge map, extracting all violation records of the driver, acquiring violation time and times, and calculating the violation time interval of the driver
Wherein n represents the number of times of violation occurrence; the KM method is then used to take advantage of the driver's time interval for violations
To estimate the probability of occurrence
(ii) a Introducing a Cox proportional risk regression model to calculate the risk
Wherein
Is a vector formed by potential influence parameters of the ith violation behavior of the example, and t is given time; then, a partial likelilithood method is used for modeling to obtain the occurrence probability aiming at the single violation behaviors
Wherein
Is a parameter vector and estimates the parameters using maximum likelihood estimation; finally, calculating out the critical value of the violation risk
To the violation occurrence risk critical value
Substituting the latest violation occurrence time point
Thereby calculating the time interval of possible violation behaviors of the driver
And c represents the occurrence frequency of the latest violation behavior, and data is recorded into the knowledge graph to predict the violation behavior.
In some embodiments, the violation time interval is predicted by each driver
And sending a traffic safety prompt to the driver.
The scope of the present invention is not limited to the specific combinations of the above-described features, and other embodiments in which the above-described features or their equivalents are arbitrarily combined are also intended to be encompassed. For example, the above features and the technical features (but not limited to) having similar functions disclosed in the present application are mutually replaced to form the technical solution.
Due to the application of the technical scheme, compared with the prior art, the invention has the following advantages: the invention uses knowledge map to store relative attribute character of driver and vehicle, to express the relation between driver and vehicle, after the violation accident happens, it can inquire the knowledge map according to the vehicle information at the first time, to obtain the relative information of driver, to confirm the possible driver, when the violation driver goes to the traffic management department to receive the penalty, it can be used as the judgment base of whether the driver has top package behavior, and analyze the driving habit of driver, and it can be used as the secondary judgment base of whether the driver has top package behavior according to the daily driving route, general traffic violation form and judging whether it is the violation multiple road section, to consider the result of two methods by algorithm, when the probable top package behavior appears, it transfers all the relative information of accident to the traffic management department by block chain technology, the traffic control department is used for assisting the traffic control department in checking top package behaviors, and the Cox model can be used for carrying out data analysis on the violation occurrence intervals of the driver by combining with the characteristic information in the knowledge map, so that the time of the traffic violation possibly occurring to the driver is estimated, and the effect of predicting and early warning the violation behaviors of the driver is achieved.
Meanwhile, the block chain technology is utilized to disclose the information of all processed violation incidents, anyone can look up the related information and the processing result of the past violation incidents at any time, and when the violation incidents occur, the block chain can be utilized to broadcast the violation incidents in real time to prompt the drivers nearby to take caution and potentially cause potential safety hazards caused by the fact that the violation incidents continue to occur.
Drawings
FIG. 1 is a flow chart of violation processing;
FIG. 2 is a flow chart of a suspected top-pack analysis process;
FIG. 3 is a schematic view of a knowledge graph;
FIG. 4 is a block chain diagram.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
The specific implementation steps of the invention comprise: after the violation behaviors occur, acquiring vehicle information according to the violation license plate, associating a knowledge map, and inquiring all possible drivers of the vehicle from the knowledge map; when the driver violating the regulations goes to a traffic management department to accept the penalty, if the driver violating the regulations does not belong to a driver list matched with the vehicle, the driver violating the regulations is suspected to have a top package behavior; if the driver who breaks rules and regulations belongs to a driver list matched with the vehicle, analyzing and calculating the weight score according to the knowledge map, if the weight score exceeds a set threshold weight score, the behavior of package jacking is suspected to occur, the general block diagram of the system is shown in figure 1, analyzing and calculating the weight score according to the knowledge map is shown in figure 2, the parameters of the knowledge map are set, wherein the parameters comprise driving age weight, accident frequently-occurring section weight, violation type weight, daily driving area weight and threshold weight score, and the behavior of package jacking is determined when the accumulated weight scores exceed the threshold weight score.
TABLE 1 Driving age analysis situation table
| Age to drive/year | Weight of driving age |
| 0-2 | 0.5 |
| 3-5 | 0.3 |
| >6 | 0.1 |
TABLE 2 analysis of the frequently encountered areas
| Whether it is a section with multiple accidents | Weight distribution |
| Is that | 0.1 |
| Whether or not | 0.5 |
TABLE 3 violation type analysis situation table
| Whether it is a type of frequently occurring violation | Weight distribution |
| Is that | 0.5 |
| Whether or not | 0.1 |
Table 4 daily driving area analysis table
| Whether it is a daily driving area | Weight distribution |
| Is that | 0.6 |
| Whether or not | 0.1 |
Specifically judging suspected top-package behaviors under different conditions, and explaining by combining the following embodiments, the following embodiments perform suspected top-package calculation on all drivers through a suspected top-package score calculation formula, wherein the weight score is set as shown in tables 1-4, the suspected top-package score calculation formula = driving age weight + accident-prone zone weight + violation type weight + daily driving area weight, the threshold weight score is set as 1.2, the driver with the weight score >1.2 is a suspected top-package driver, and if the driver who goes to the traffic administration department and receives the penalty is not the suspected top-package driver, the suspected driver is judged to be the top-package behavior.
The first embodiment is as follows: and (3) if the violation behaviors occur, associating 3 drivers A, B and C from the knowledge graph according to the license plate number, directly judging that the driver D is suspected to be a top package if the driver D goes to the traffic management department to receive the penalty and the driver D is not associated with any one of the 3 drivers, and checking and confirming the driver D to the traffic management department.
Example two: the method comprises the following steps that (1) violation behaviors occur, 3 drivers A, B and C are associated from a knowledge map according to license plate numbers, the driver A goes to a traffic management department to receive punishment, the violation accident occurs and is a red light running, the violation place is A and is a section with multiple accidents, information of the driver A, the driver B and the driver C is analyzed respectively, the driving age of the driver A is higher by more than 6 years, the red light running occurs, and the daily driving area is B; the driver B is short in driving age, just takes the driving license, often drives nearby the area A and has red light running behaviors for many times; the third driving age of the driver is short, the driver often drives nearby the area C and rarely has violation behaviors, and suspected top package calculation is carried out on the three drivers through the knowledge map by combining the tables 1-4, wherein the suspected top package calculation comprises the following steps: first =0.1+0.1+0.5+0.1=0.8, second =0.5+0.1+0.5+0.6=1.7, third =0.5+0.1+0.1+0.1=0.8, and finally, the driver a is judged to be the driver second-top bag, and the inspection and confirmation are carried out to the traffic control department.
Example three: the method comprises the following steps that (1) violation behaviors occur, 3 drivers A, B and C are associated from a knowledge map according to license plate numbers, the driver A goes to a traffic management department to receive punishment, the violation accident is red light running, the violation place is A and is not a region with multiple accidents, after driver information is analyzed and discovered respectively, the driving age of the driver A is higher by more than 6 years, the daily driving area is B, and the type of the traffic violation which frequently occurs is overspeed; the driver B is short in driving age, just takes the driving license, often drives nearby the area A and has red light running behaviors for many times; the third driving age of the driver is shorter, the driver often drives nearby the area A, but the violation behaviors are less generated, and suspected top package calculation is carried out on the three drivers through the knowledge graph by combining the tables 1-4.
And (3) calculating a suspected top packet: first =0.1+0.5+0.1+0.1=0.8, second =0.5+0.5+ 0.6=2.1, third =0.5+0.5+0.1+0.1=1.2, and finally, it is judged that the driver a is suspected to be the driver second-top bag, and the inspection and confirmation needs to be performed to the traffic control department.
If the suspected top package calculation analysis shows that no top package behaviors exist, the driving habit of the driver is analyzed, a Cox model is used for analyzing data of violation occurrence of the driver, the next violation behavior information is predicted, when the violation behavior of the driver goes to a traffic management department again to accept penalty, the traffic violation condition of the occurrence and the predicted violation behavior information are compared, if a large matching difference exists, the top package behaviors are suspected to appear, and the method for predicting the next violation behavior information specifically comprises the following steps: firstly, calculating survival probability, namely violation occurrence probability:
，
the probability that the time T of the violation behavior is greater than the given time T is determined, firstly, all violation records of the driver are extracted through the established knowledge map, the violation time and times are obtained, and the violation behavior time interval of the driver is calculated
(ii) a The KM method is then used to estimate the probability of occurrence using the time interval of the driver's violation
The probability of occurrence can be calculated as:
wherein the content of the first and second substances,
meaning that the violation interval is less than
The occurrence probability of (2);
meaning at violation intervals equal to
Number of violation events;
means that the violation interval is not less than
The number of violation events is
，
。
Introducing a Cox proportional risk regression model to calculate the risk
The risk ratio formula is as follows:
，
wherein the content of the first and second substances,
is a baseline risk equation, canTo be any non-negative equation for time;
the feature vector of the ith violation behavior of the example is formed by potential influence parameters such as driver age, driving age, vehicle type, vehicle age and the like;
is a vector of parameters, which is obtained by maximizing the Cox partial likelihood;
representing variables
To pair
The cumulative survival rate for the driver violation interval function is as follows:
wherein the content of the first and second substances,
all potentially influencing parameters are ignored for the baseline survival function of the driver violation interval.
Then, a partial likelilehood method is used for modeling, and the interval time of the ith violation behavior is set as
According to the interval time
Finding all the interval time exceeds
Examples of (2)
，
Indicating the interval of the jth violation and
respectively calculate the interval time as
Then the probability of the violation occurring is:
to obtain the above likelihood probabilities, we only need to choose so that
To obtain a maximum value
The values are, i.e.:
use of
Survival function to time reference of violation interval
Performing estimation to obtainThe following equation:
finally, calculating out the critical value of the violation risk
From the midpoint density function, the following formula is obtained:
wherein
、
Calculating the risk value of each interval in the historical data by iteration of the historical data for the violation occurrence time interval in the historical data, and calculating the standard deviation to obtain the standard critical value
Bringing the latest violation occurrence time point
Thereby calculating the time when the driver is likely to have the next violation
The time interval in which the driver may have a violation:
As shown in fig. 4, the method sends a request for checking suspected driver bag-pushing behaviors to a traffic police team through a block chain, the traffic police team manually checks the driver bag-pushing behaviors after receiving a message to assist in violation processing, performs violation processing on traffic violations, uploads violation information to the block chain after processing, broadcasts the violation information in the area, and uploads the violation information to a knowledge map to serve as reference data for violation behavior prediction.
The block chain can also send traffic safety reminders to drivers according to the forecast violation time interval of each driver, and by utilizing the characteristics of distributed data storage and point-to-point transmission of the block chain technology, a violation information storage center is saved, so that data information required by violation forecasting departments, violation processing departments and traffic police teams is safer and cannot be falsified. Whether the information of the illegal vehicles and drivers from road monitoring, vehicle-mounted monitoring, indoor monitoring or witnesses meets the evidence rules set by the block chain, the information can be broadcast outwards, and redundant elimination can be carried out after one piece of the information which meets the condition is broadcast. If the identity of the driver with the violation is not proved by exact evidence, relevant information of the vehicle with the violation is extracted from the knowledge map by the appointed violation prediction department, possible relevant driver information is analyzed, violation prediction is carried out, and whether the violation possibly has the behavior of the driver in package overtaking is judged. And if the traffic information is possible, the violation vehicle information, the driver information and the prediction result are sent to a traffic police team, the traffic police is enabled to carry out further inspection, and after the inspection is successful, the violation related information is broadcasted in the block chain.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and the purpose thereof is 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 protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (3)
1. A traffic violation analysis method based on a knowledge graph and a block chain is characterized by comprising the following steps: the method comprises the following steps: s1, after the violation occurs, the vehicle information is obtained according to the violation license plate and the knowledge map is associated, the possible drivers of the vehicle are matched from the knowledge map, and the knowledge map mainly comprises three types of entities: the system comprises a driver entity, a vehicle entity and a violation recording entity, wherein the attributes of the driver entity comprise the name, the identity card, the age, the driving age, the relative of a driver with a driving license and the estimated time interval of possible violation; the vehicle entity attributes comprise license plate numbers, vehicle types, vehicle ages, drivers of the vehicles and available drivers of the vehicles; the violation record entity attributes comprise violation types, violation times, violation places and accident deduction conditions, and entity association is carried out according to the relationship between the driver and the vehicle, the relationship between the driver and the driver, violation records and information about the driver and the vehicle, so that a complete violation record knowledge map is finally obtained; s2, when the driver violating the regulations goes to the traffic control department to accept the penalty, if the driver violating the regulations does not belong to the driver list matched with the vehicle, the driver is suspected to have a top package behavior; s3, if the driver who violates the traffic rules belongs to a driver list matched with the vehicle, calculating a weight score according to knowledge map analysis, wherein the weight score comprises driving age weight distribution, accident-prone area weight distribution, violation type weight distribution, daily driving area weight distribution and a threshold weight score, if the driving age weight distribution, the accident-prone area weight distribution, the violation type weight distribution and the daily driving area weight distribution are added to exceed a set threshold weight score, a suspected top-package behavior occurs, sending a request for checking the suspected top-package behavior of the driver to a traffic police team through a block chain, carrying out violation processing on the traffic rules, uploading violation information to the block chain, broadcasting the block chain and uploading the violation information to the knowledge map; s4, if no top-packing behavior exists in the steps S1 to S3, analyzing the driving habit of the driver, analyzing the data of the violation behavior of the driver by using a Cox model, predicting the information of the next violation behavior, comparing the traffic violation condition of the violation behavior and the predicted violation behavior information when the driver goes to the traffic control department again to accept penalty, and if a large matching difference exists, determining that the top-packing behavior is suspected to appear.
2. The traffic violation analysis method based on knowledge-graph and blockchain of claim 1 wherein: the calculation method of the Cox model comprises the steps of firstly extracting all violation records of a driver through the established knowledge map, obtaining violation time and times, and calculating the violation time interval of the driver
Wherein n represents the number of times of violation occurrence; the KM method is then used to take advantage of the driver's time interval for violations
To estimate the probability of occurrence
(ii) a Introducing a Cox proportional risk regression model to calculate the risk
Wherein
Is a vector formed by potential influence parameters of the ith violation behavior of the example, and t is given time; then, a partial likelilithood method is used for modeling to obtain the occurrence probability aiming at the single violation behaviors
Wherein
Is a parameter vector and estimates the parameters using maximum likelihood estimation; finally, calculating out the critical value of the violation risk
To the violation occurrence risk critical value
Substituting the latest violation occurrence time point
Thereby calculating the time interval of possible violation behaviors of the driver
And c represents the occurrence frequency of the latest violation behavior, and data is recorded into the knowledge graph to predict the violation behavior.
3. The traffic violation analysis method based on knowledge-graph and blockchain of claim 2 wherein: based on the predicted time-to-violation interval for each driver
And sending a traffic safety prompt to the driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110505930.2A CN112989069B (en) | 2021-05-10 | 2021-05-10 | Traffic violation analysis method based on knowledge graph and block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110505930.2A CN112989069B (en) | 2021-05-10 | 2021-05-10 | Traffic violation analysis method based on knowledge graph and block chain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112989069A CN112989069A (en) | 2021-06-18 |
| CN112989069B true CN112989069B (en) | 2021-10-15 |
Family
ID=76337444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110505930.2A Active CN112989069B (en) | 2021-05-10 | 2021-05-10 | Traffic violation analysis method based on knowledge graph and block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112989069B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115440035B (en) * | 2022-08-25 | 2023-07-07 | 杭州海康威视系统技术有限公司 | Traffic event early warning method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110413695A (en) * | 2019-07-29 | 2019-11-05 | 北京百度网讯科技有限公司 | Police affair information management method, apparatus, equipment and medium based on block chain |
| CN112766115A (en) * | 2021-01-08 | 2021-05-07 | 广州紫为云科技有限公司 | Traffic travel scene violation intelligence based analysis method and system and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242227A (en) * | 2017-07-10 | 2019-01-18 | 卢照敢 | The driving risk and assessment models of car steering behavior |
| US10423726B2 (en) * | 2018-01-10 | 2019-09-24 | International Business Machines Corporation | Machine learning to integrate knowledge and natural language processing |
| CN108446626A (en) * | 2018-03-16 | 2018-08-24 | 佛山市洁宇信息科技有限公司 | A kind of intelligence is broken rules and regulations processing system and its method |
| CA3099659A1 (en) * | 2018-05-07 | 2019-11-14 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for analytics and maintenance using the industrial internet of things |
| CN108986479A (en) * | 2018-09-19 | 2018-12-11 | 浙江甬力区块链科技有限公司 | Break in traffic rules and regulations processing system and its processing method based on block chain technology |
| CN109658272A (en) * | 2018-12-26 | 2019-04-19 | 江苏数慧信息科技有限公司 | Driving behavior evaluation system and Insurance Pricing system based on driving behavior |
| CN110060484B (en) * | 2019-05-16 | 2021-10-22 | 武汉理工大学 | Road passenger traffic violation real-time early warning system and method based on block chain |
| CN111782823A (en) * | 2020-07-30 | 2020-10-16 | 国网江苏省电力有限公司南通供电分公司 | Application of knowledge graph in analysis of violation big data |
| CN111767440B (en) * | 2020-09-03 | 2021-01-05 | 平安国际智慧城市科技股份有限公司 | Vehicle portrayal method based on knowledge graph, computer equipment and storage medium |
-
2021
- 2021-05-10 CN CN202110505930.2A patent/CN112989069B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110413695A (en) * | 2019-07-29 | 2019-11-05 | 北京百度网讯科技有限公司 | Police affair information management method, apparatus, equipment and medium based on block chain |
| CN112766115A (en) * | 2021-01-08 | 2021-05-07 | 广州紫为云科技有限公司 | Traffic travel scene violation intelligence based analysis method and system and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| "Smart-Contract-Based Economical Platooning in Blockchain-Enabled Urban Internet of Vehicles";Chen Chen et al.;《IEEE TRANSACTIONS ON INDUSTRIAL INFOMATTICS》;20200630;第4122-4133页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112989069A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807930B (en) | Dangerous vehicle early warning method and device | |
| CN110060484B (en) | Road passenger traffic violation real-time early warning system and method based on block chain | |
| CN106971552B (en) | Fake plate phenomenon detection method and system | |
| CN104754011A (en) | Internet of Vehicles multi-party coordination control method and Internet of Vehicles coordination platform | |
| Ghosh et al. | Examination of factors affecting freeway incident clearance times: a comparison of the generalized F model and several alternative nested models | |
| CN112183245A (en) | Method and device for monitoring abnormal behaviors of taxi appointment driver of network and giving alarm and electronic equipment | |
| CN112447041B (en) | Method and device for identifying operation behavior of vehicle and computing equipment | |
| CN109166319A (en) | A kind of highway illegal activities recognition methods based on block chain technology | |
| CN206684779U (en) | A kind of vehicle insurance management service system based on ADAS intelligent vehicle mounted terminals | |
| CN108074400A (en) | A kind of emphasis vehicle analysis model based on mass data analysis | |
| CN109993098A (en) | City vehicle black smoke intelligent recognition big data analysis system and method | |
| CN112801541B (en) | Dangerous chemical road transportation risk dynamic assessment and risk navigation method | |
| CN113642893B (en) | New energy automobile operation risk assessment method | |
| CN112989069B (en) | Traffic violation analysis method based on knowledge graph and block chain | |
| Chen et al. | Lane-based Distance-Velocity model for evaluating pedestrian-vehicle interaction at non-signalized locations | |
| CN111899517A (en) | Expressway fatigue driving illegal behavior determination method | |
| CN114093143A (en) | Vehicle driving risk perception early warning method and device | |
| EP3774478A1 (en) | Vehicular motion assessment method | |
| CN116911610A (en) | Method and system for monitoring, evaluating and early warning of driving safety risk of transport vehicle | |
| CN114882448B (en) | Vehicle monitoring method and electronic equipment | |
| Pigman et al. | Identification of secondary crashes and recommended countermeasures | |
| Huang et al. | Jointly analyzing freeway primary and secondary crash severity using a copula-based approach | |
| Xu et al. | Evaluating the combined effects of weather and real-time traffic conditions on freeway crash risks | |
| CN114913398A (en) | Method for identifying real-time driving risk and judging risk level of passenger driver | |
| CN113919571A (en) | Dangerous chemical transportation premium estimation method based on edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |