CN111698305A - Method for determining confidence and/or priority of vehicle reported event data - Google Patents
Method for determining confidence and/or priority of vehicle reported event data Download PDFInfo
- Publication number
- CN111698305A CN111698305A CN202010488828.1A CN202010488828A CN111698305A CN 111698305 A CN111698305 A CN 111698305A CN 202010488828 A CN202010488828 A CN 202010488828A CN 111698305 A CN111698305 A CN 111698305A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- event
- reporting
- priority
- reported
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 230000006855 networking Effects 0.000 claims abstract description 33
- 238000009826 distribution Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 17
- 238000004891 communication Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 231100001261 hazardous Toxicity 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of vehicle networking, in particular to a vehicle rear end data monitoring platform for a vehicle networking system. A method for determining confidence and/or priority of reported event data reported by vehicles in an internet of vehicles system (1) is provided, comprising at least: acquiring an event risk degree parameter corresponding to a reported event type, acquiring historical traffic flow speed at a corresponding geographical position based on the reported geographical position, and then acquiring a speed deviation parameter based on the deviation of the vehicle speed at the reporting moment and the historical traffic flow speed; a confidence and/or priority of reporting event data is determined based at least on the event risk parameter and the speed deviation parameter. The method may further comprise: the frequency parameter is determined based at least on the same or similar event reporting frequencies at the respective geographic locations and is also considered in determining a confidence and/or priority of reporting event data. The confidence level and/or the calculation reliability of the priority of the vehicle reported event can be improved.
Description
Technical Field
The invention relates to a method for determining a confidence and/or priority of event data reported by vehicles in a vehicle networking system, a vehicle back-end data monitoring platform for a vehicle networking system, and a computer readable program carrier for a vehicle back-end data monitoring platform and/or a networked vehicle of a vehicle networking system.
Background
The car networking industry relies on an information communication technology, comprehensive information service is provided through all-round connection and data interaction of in-car, car-to-road, car-to-person, car-to-service platform, and a novel industry form (national car networking industry standard system construction guideline) with deep integration of industries such as automobile, electronics, information communication, road transportation and the like is formed. The car networking system senses roads and traffic by using an advanced sensing technology, a network technology, a computing technology, a control technology and an intelligent technology, and realizes interaction of large-range and large-capacity data among a plurality of systems. For example, the car networking system can perform traffic control on corresponding cars and perform traffic control on corresponding roads, so as to provide networks and applications mainly based on traffic efficiency and traffic safety.
The Vehicle networking wireless communication technology V2X (Vehicle to evolution) includes Vehicle-to-Vehicle (V2V), Vehicle-to-infrastructure (V2I), Vehicle-to-network (V2N), Vehicle-to-peer (V2P), and the like, and there are C2X, Car2X, and the like that have been commercialized or are about to be commercialized. The cloud interactive system is, for example, Car2X, and the interactive system distributes information passively and actively reported from other cars with Car2X through a cloud platform, so that real-time information interaction between cars is realized. More specifically, the cloud platform aggregates the data, checks its rationality, and forwards to the relevant, nearby, other vehicles that carry the Car2X system. The detection range limitation of vehicle-mounted sensors, communication equipment and systems in the traditional sense, such as cameras and radars, is widened, and therefore early warning of dangerous events is achieved. The future of this system also envisages connections to traffic lights, on-board diagnostics, road forewarning, and other emergency and commercial services.
Throughout the development of the whole industry, the future trend is to apply the information of the internet of vehicles to the field of automatic driving through vehicle-to-vehicle communication technology, wireless communication and remote sensing technology. The advent of autonomous driving has brought about a rapidly growing new demand and challenge for C-V2X. In short, the vehicle type equipped with the system can directly read and monitor the key data predefined by the system, and the data can be transmitted to the data center closest to the vehicle through a secure communication network (such as 5G and eLTE), so that the data can be spread all over the world. Therefore, the automatic driving system can receive related information through the C-V2X, and synchronously process the information in the automatic driving mode to adjust the path planning of the automatic driving vehicle and the output result of vehicle control in real time.
However, if the events reported by the vehicles in the vehicle networking system are used for planning and controlling the automatic driving system without screening, the problem that the vehicles are excessively interfered is caused. How the data center or the vehicle receiving the information confirms the data confidence and/or priority is a key difficulty for the technology to be generally applied.
For example, there is a problem of abuse of a hazard warning flash (double flash) in the urban environment of china. The danger alarm flash lamp is a signal lamp for reminding other vehicles and pedestrians of paying attention to special conditions of the vehicle. The fifty-second road traffic safety law of the people's republic of china describes one of the applications of a danger warning flash lamp as follows: when the motor vehicle breaks down on the road and needs to be parked to remove the fault, the driver should immediately turn on the hazard warning flash lamp to move the motor vehicle to a place where the traffic is not obstructed to park; the dangerous alarm flash lamp is difficult to move, the warning distance is enlarged by measures such as continuously turning on the dangerous alarm flash lamp, setting a warning sign in the coming direction and the like, and the vehicle can rapidly give an alarm when necessary. The danger alarm flash lamp should be turned on when a fault occurs on a highway, when the vehicle runs at a high speed, when the vehicle temporarily stops on a road, when a fault motor vehicle is pulled, an emergency fault occurs during running, when the vehicle has a traffic accident, and a special task is being executed. However, due to geographical and cultural reasons, it is difficult to set up a certain fixed and quantitative standard for the application of the hazard warning flash lamp. Many drivers turn on the hazard flashlights at times that are not critical.
The information of the vehicle networking system such as a danger alarm flash lamp is defined as high-risk warning information which should be communicated to the affected vehicles in the periphery. For a driver, if the frequently popped warning information does not substantially influence driving, the driver can have a certain degree of bored emotion on the information, so that the trust degree and the good sensitivity of the system are influenced; for a vehicle with an automatic driving system, the safety of the vehicle is always the greatest importance of the system design, if such information is received in a short distance, the system should re-plan a path and even stop an automatic driving mode, and if the automatic driving system frequently receives warning information on a preset driving path, the system is difficult to provide reasonable and comfortable planning and control.
Some methods have been proposed in the prior art to verify the reliability and/or priority of data and perform some subsequent processing according to the verification result.
For example, CN107959943A discloses a V2X communication apparatus and system and a method of verifying the reliability of V2X data, in which a reliability verification parameter for verifying the reliability of V2X data is calculated by a parameter calculator, and a reliability level is determined by comparing the reliability verification parameter with a predetermined reference value, and then V2X data including the determined reliability level is generated. Some specific calculation and determination methods are also given in detail herein, for example, the reliability level determiner may set the first to third reference values based on the speed of the vehicle and the distance between the vehicle and the surrounding vehicle, and may set the first to third reference values to become smaller as the speed of the vehicle decreases and the distance between the vehicle and the surrounding vehicle becomes farther, and the reliability levels may include a first reliability level corresponding to the guidance level, a second reliability level corresponding to the warning level, and a third reliability level corresponding to the control level.
Determination of the reliability of information received by a vehicle is also discussed in CN103918242A, e.g. signal strength based on received peer-to-peer transmissions, comparison of signal strength with distance to the sender based on message content, age of received messages, signal quality of received messages and other parameters, etc.
CN109672628A, also related to the field of car networking, discloses determining the priority of V2X data packets according to a filtering rule comprising, for example, a correspondence of attribute information and priority of different V2X data packets, wherein the priority of V2X data packets is related to data reception frequency.
CN105684397A also relates to the field of car networking and discloses how messages can be filtered, for example, according to parameters such as type of vehicle-to-X message, sender's direction, etc.
CN101916514A discloses a method for supporting road hazard condition warning using an in-network message protocol based on V2X and providing a message indicating a potentially hazardous road condition using a wireless communication network, wherein sensors of vehicles are able to detect various potentially hazardous road conditions, such as rain, fog, icy road conditions, traffic congestion, etc., a plurality of vehicles detecting a particular road condition provide confidence values that the condition exists, which are then aggregated by the vehicles with confidence values of detected conditions from other vehicles to provide an aggregated result identifying the probability that the detected road condition occurred. The aggregated results may then be transmitted in a multi-hop fashion to other vehicles approaching the road condition. Alternatively, the confidence values from all vehicles that detected the condition may be transmitted to approaching vehicles that will provide an aggregate result identifying the likelihood that the condition exists.
CN109756897A discloses a certification authority mechanism and system for internet of vehicles, which describes how to certify the credibility of V2X information.
However, the prior art still has many defects, especially, the confidence and/or priority of the data are related to many factors, wherein the relevance of some factors to the confidence and/or priority of the data and how to specifically influence the confidence and/or priority are not discussed in the prior art, which also influences the application of the car networking.
Disclosure of Invention
It is an object of the present invention to provide an improved method for determining confidence and/or priority of reported event data reported by vehicles in an internet of vehicles system, an improved vehicle back-end data monitoring platform for an internet of vehicles system, and an improved computer readable program carrier for a vehicle back-end data monitoring platform and/or an internet connected vehicle for an internet of vehicles system, to solve at least some of the problems of the prior art.
According to a first aspect of the present invention, there is provided a method for determining confidence and/or priority of reported event data reported by vehicles in an internet of vehicles system, the method comprising at least the steps of: acquiring an event risk parameter corresponding to an event type based on the event type reported by the vehicle, acquiring a historical traffic flow speed at a corresponding geographic position based on the reported geographic position, and then acquiring a speed deviation parameter based on the deviation between the vehicle speed of the vehicle at the reporting moment and the historical traffic flow speed; and determining the confidence and/or priority of the reported event data at least based on the event risk parameter and the speed deviation parameter.
According to an alternative embodiment of the invention, the method further comprises: and receiving event data reported by the vehicles, wherein the reported event data comprises the type of a reported event, the running speed of the vehicle reporting the event at the moment of reporting the event and the geographical position information of the event.
According to an alternative embodiment of the invention, the method further comprises the steps of: determining a frequency parameter based at least on a reporting frequency of the same or similar events at the corresponding geographical location within a predetermined time period; and additionally based on the frequency parameter when determining the confidence and/or priority of reporting event data.
According to an alternative embodiment of the invention, the confidence and/or priority is determined by the following function:
wherein C represents confidence and/or priority;
e is an event risk degree parameter corresponding to the event type;
f is a frequency parameter; and
v is a velocity deviation parameter.
According to an optional embodiment of the invention, the data center fits the historical traffic flow speed of each regional block into normal distribution, stores the position parameter and the scale parameter of the traffic flow speed normal distribution curve of each regional block after statistics, and determines the speed deviation parameter based on the relation between the difference value between the vehicle speed of the vehicle at the reporting moment and the average value of the historical traffic flow speed and the scale parameter of the historical traffic flow speed; and/or the historical traffic flow speed comprises the historical traffic flow speed at a time period near the reporting time and at a corresponding geographic position within a past period of time relative to the reporting time; and/or the historical traffic flow speed also comprises the reported historical traffic flow speed of vehicles in a preset area near the geographic position.
According to an optional embodiment of the present invention, the historical traffic flow speed and the normal distribution curve thereof are obtained by integrating the vehicle rear-end data monitoring platform of the car networking system according to the historical traffic flow speed of the vehicle monitored by the vehicle rear-end data monitoring platform; or the historical traffic flow speed and the normal distribution curve thereof are determined by the cooperation of the vehicle rear-end data monitoring platform of the vehicle networking system and other monitoring platforms different from the vehicle rear-end data monitoring platform.
According to an optional embodiment of the present invention, the frequency parameter is determined based on a reporting frequency of the vehicle reporting event within a certain period of time; or the frequency parameter is determined based on the reporting frequency of the vehicle reporting event and the total number of vehicles passing through the corresponding geographic position; and/or the predetermined reference value range of the frequency parameter is (0,1 ].
According to an optional embodiment of the invention, the confidence and/or priority is determined based on a big data machine learning method; and/or according to the determined confidence coefficient and/or priority, dividing the reported event data into three categories: invalid information, prompt information, warning information.
According to an optional embodiment of the invention, when the warning information is sent, the corresponding information is sent to the relevant vehicle for corresponding operation, the corresponding operation displays an icon on a screen of the relevant vehicle and/or sends out voice, and the corresponding information is used for controlling the relevant vehicle in the case that the sent vehicle is an automatic driving vehicle with a network safety interface; and/or confidence and/or priority, as data for insurance and/or accident and/or municipal uses.
According to a second aspect of the present invention, a vehicle back end data monitoring platform for a vehicle networking system is provided, wherein the vehicle back end data monitoring platform is configured to be able to perform the above method.
According to a third aspect of the present invention, there is provided a computer readable program carrier for a vehicle backend data monitoring platform of a vehicle networking system, the computer readable program carrier storing program instructions which, when executed by a processor, are capable of performing the above method.
The method can improve the confidence coefficient and/or the calculation reliability of the priority of the vehicle reported event.
Drawings
The principles, features and advantages of the present invention may be better understood by describing the invention in more detail below with reference to the accompanying drawings. The drawings comprise:
FIG. 1 illustrates an application scenario diagram of a vehicle networking system, according to an exemplary embodiment of the present invention; and
fig. 2 illustrates a method of calculating confidence and/or priority of reporting event data.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and exemplary embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
The invention generally relates to a technical scheme that a vehicle rear-end data monitoring platform analyzes and determines the confidence coefficient and/or priority of reported event data at least based on an event risk degree parameter corresponding to the type of a reported event, the deviation between the vehicle speed of a vehicle reporting the event and the historical traffic flow speed at the moment and/or the reporting frequency of the same or similar events, so as to further improve the reliability and user friendliness of the practical application of the Internet of vehicles. The reporting event data may be V2X, C2X, or Car2X data.
Fig. 1 shows an application scenario diagram of a car networking system according to an exemplary embodiment of the present invention.
As shown in fig. 1, the exemplary internet of vehicles system 1 includes: the system comprises an on-board vehicle networking module 11 installed on a vehicle, a Road Side device (Road Side Unit)12, and a vehicle back-end data monitoring platform 13 capable of communicating with the on-board vehicle networking module 11 and the Road Side device 12. The vehicle rear-end data monitoring platform 13 may be a cloud server, the networked vehicle may report event information and/or vehicle self status sensed by the vehicle or the drive test equipment to the vehicle rear-end data monitoring platform 13 in a wireless communication manner (e.g., through a 5G, eLTE network, etc.) through the vehicle-mounted internet of vehicles module 11 and the roadside equipment 12, and store and/or analyze the event information and/or the vehicle self status, and the vehicle rear-end data monitoring platform 13 may also transmit the stored information or the analyzed result to a related vehicle (e.g., another vehicle near the location of the traffic event), so as to provide information to the related vehicle and/or control the driving of the related vehicle.
The cloud server may be a server provided by a third party, or may be a server provided by a vehicle manufacturing enterprise itself.
As can also be seen from fig. 1, in the car networking system 1, besides that the vehicles can report information to the Vehicle rear-end data monitoring platform 13, the vehicles can also perform direct information transmission (for example, V2V-Vehicle to Vehicle) through the car networking module 11, as shown by reference numeral 14. In addition, the Vehicle may also communicate information with the roadside apparatus 12 (e.g., V2I-Vehicle to Infrastructure), as indicated by reference numeral 15; the vehicle may also communicate information with other facilities, such as buildings, for example, as shown at 16; the vehicle may also provide information to the pedestrian as indicated by reference numeral 17.
According to an exemplary embodiment of the present invention, the reported event data received by the vehicle backend data monitoring platform 13 from the vehicle may include at least a specific event, a running speed of the event reporting vehicle at the reporting time, and geographic location information of the event occurrence. For example, for a collision accident at a certain road location, reporting event data may include: the method comprises the following steps of (1) reporting a collision event, wherein the collision event reports the running speed of a vehicle when the collision accident event is reported and the geographical position information of the road position; for the condition that the vehicle detects and reports that the vehicle turns on the hazard warning flash lamp at a certain road position on the road, reporting the event data may include: and the dangerous alarm flash lamp warns the event, and the event reports the running speed of the vehicle when the dangerous alarm flash lamp is detected and the geographical position information of the road position. The vehicle rear-end data monitoring platform 13 processes and analyzes the received reported event data, and provides early warning information to related vehicles (for example, vehicles traveling towards the road position) according to the processing result, and even changes an automatic driving mode or parameters if the related vehicles are in an automatic driving state.
According to one embodiment of the present invention, the reliability and/or priority of the reported event data needs to be ensured before more reasonable and effective pre-warning and/or control adjustments can be subsequently made. For this reason, confidence and/or priority analysis of the reported event data is required.
The confidence level can be used to characterize the reliability of the reported event data. The priority may be used to characterize the importance, risk level, and/or urgency of reporting event data. According to an exemplary embodiment of the present invention, the confidence level and/or priority level may be calculated based at least on the specific type of event reported and/or the deviation (which may be expressed directly as an absolute difference, or may be expressed in a relative difference, or in some other form) between the travel speed of the reporting vehicle at the time of the event reported and the historical traffic flow speed at the corresponding geographic location. It can be understood that the greater the deviation between the travel speed of the event reporting vehicle at the time of the event reporting and the historical traffic flow speed at the corresponding geographical location, the greater the deviation between the travel state of the vehicle of the currently reported event and the regular travel state at the geographical location, and therefore, the greater the possibility of the occurrence of the traffic event and the greater the influence of the traffic event on the traffic and surrounding vehicles, and accordingly, the higher the confidence and/or priority of the reported event data.
According to a further exemplary embodiment of the present invention, the calculation of the confidence level and/or priority level may additionally also take into account the reporting frequency of the same or similar events at the respective geographical location within a predetermined time period. It will be appreciated by those skilled in the art that if an event is likely to occur at a particular geographic location, other vehicles will be in the same driving environment without a change in the basic external driving environment, for example, over a period of time, and that other vehicles will have a greater likelihood of the same or similar event occurring or being detected at that geographic location if other factors are not considered. According to the embodiment of the invention, when the reliability and/or the priority of the reported event data are calculated, the three parameters of the specific event type, the deviation between the running speed of the event reporting vehicle at the event reporting time and the historical traffic flow speed at the corresponding geographical position, and the reporting frequency of the same or similar events at the geographical position in a preset time period can be used singly or in combination (including two-by-two combination or all combination) to better reflect the reliability and/or the priority of the reported event data.
There is a high probability that a surrounding predetermined area of the geographic location will also have a similar driving environment such that nearby vehicles may also be experiencing or detecting the same or similar events. Therefore, according to an exemplary embodiment of the present invention, the confidence level and/or the priority level may also be calculated by considering the reporting frequency of the same or similar events within the predetermined time period in the peripheral predetermined area of the corresponding geographical location.
For example, after the vehicle backend data monitoring platform 13 receives the event type reported manually or automatically by the vehicle carrying the vehicle-mounted internet-of-vehicles module 11, the running speed of the event reporting vehicle at the reporting event time, and the geographic location of the reporting event time, the confidence and/or the priority of the reported event data are calculated at least based on the event type and the deviation between the running speed of the event reporting vehicle at the reporting event time and the historical traffic flow speed at the corresponding geographic location. Additionally, the number (frequency) of times or corresponding frequency parameters of the same or similar events reported by other vehicles in a predetermined area around the geographic location, for example, a road section of 1km before and after the geographic location, within a predetermined time period, for example, 1 minute, may also be used as parameters for calculating the confidence and/or priority of the reported event data.
According to an exemplary embodiment of the present invention, if the vehicle back-end data monitoring platform 13 decides to dispatch corresponding information to other related vehicles based on the calculation result of the confidence level and/or the priority, it may decide to dispatch corresponding information to which vehicles based on the reported geographic location of the event occurrence, for example, to a vehicle carrying the vehicle networking module 11 in a road section within 3km around the geographic location.
In the following, how the vehicle back-end data monitoring platform 13 performs confidence and/or priority analysis on the reported event data will be described in a more specific exemplary embodiment.
The confidence and/or priority C may be calculated, for example, by the following functional formula (1):
wherein C represents confidence and/or priority;
e is an event risk parameter representing the influence weight of the event type;
f is a frequency parameter representing the reporting frequency of the same or similar events at the corresponding geographic position in a preset time period; and
v is a speed deviation parameter characterizing the deviation between the travel speed of the event reporting vehicle at the time of the event reporting and the historical traffic flow speed at the corresponding geographical location.
1) Event risk degree parameter corresponding to event type
Different event types determine the degree of influence of the event on the vehicle, for example, information that an irregular oversized vehicle exists in front of the vehicle, a slowly running vehicle exists in front of the vehicle has less potential threat and influence on the rear vehicle, and information that an accident happens to the vehicle in front of the vehicle and the vehicle in front of the vehicle catches fire has greater potential threat and influence on the rear vehicle. Thus, different events defined for the event repository may be assigned different event risk parameters e. The higher the event risk degree parameter e of the reported event is, the higher the reference value of the calculation result of the confidence degree and/or the priority C is.
Therefore, the event risk degree parameter e corresponding to the event type can be classified and preset according to the influence of the event. According to an exemplary embodiment, the range of the value of the event risk parameter e may be [0.1,1], and the greater the influence of the event, the higher the event risk parameter e, for example, the value of e corresponding to the detection of a danger warning flash lamp is 0.5, the value of e corresponding to the failure of a front automobile is 0.55, the value of e corresponding to the wet and slippery ground in front is 0.7, the value of e corresponding to the detection of rain and snow fog is 0.75, the value of e corresponding to the detection of a motorcycle on the highway is 0.8, and the value of e corresponding to the danger of a front road is 0.9.
2) Deviation between the travel speed of the event reporting vehicle at the time of the event report and the historical traffic flow speed at the corresponding geographical location
And judging the current running state of the reporting vehicle according to the running speed x of the reporting vehicle at the moment of reporting the event and the historical traffic flow speed z at the corresponding geographical position according to the event of the reporting vehicle, and reflecting the real-time traffic state of the road at the current geographical position.
The vehicle back-end data monitoring platform 13 may record and store a time period around the reporting time in the past period of time, a historical traffic flow speed z at the corresponding geographic location (which may also include a predetermined nearby area), or record and store a position parameter and a scale parameter of a normal distribution curve fitted with statistical data of the traffic flow speed at the reporting time in the past period of time at the corresponding geographic location (which may also include a predetermined nearby area). For example, the traffic speed or the statistical data parameter value in 15 minutes around the reporting time of the last 7 days, and in a road section of 1km around the reported geographical position may be used. Those skilled in the art will appreciate that the time interval, time period, predetermined vicinity may be adjusted as appropriate. The invention is not limited in this regard. It will be understood by those skilled in the art that the normal distribution curve is a general velocity distribution curve, and other probability statistical distribution models, such as poisson distribution, bernoulli distribution, uniform distribution, exponential distribution, etc., are not limited in this respect if they can more accurately represent the historical traffic flow velocity of the actual road environment.
The larger the deviation between the reported vehicle speed x and the historical traffic flow speed z is, the larger the influence degree of the vehicle speed x is, and the higher the value of the calculation result of the confidence coefficient and/or the priority C is.
It will be appreciated that the historical flow velocity z is a statistical value, for example, which may conform to a normal distribution. In this case, the historical traffic speed z may be characterized by an average value μ (position parameter) of the historical traffic speed z and a scale parameter σ, i.e., z (μ, σ)2) Wherein the scale parameter sigma reflects the variation amplitude of the historical traffic flow speed z, and different z (mu, sigma) can be recorded and stored in different position areas and different time periods2) The parameter values.
In practice, the real-time running state of the current reporting vehicle can be judged according to the difference value Δ x between the running speed x of the event reporting vehicle at the time of reporting the event and the average value μ of the historical traffic flow speed z, and the speed deviation parameter v is assigned, as described above, so that the real-time traffic state of the current road can be indirectly reflected.
According to an exemplary embodiment of the present invention, the velocity deviation parameter v may be assigned based on a difference Δ x between a travel speed x of the event reporting vehicle at the time of the reporting event and an average μ of the historical traffic speed z, and with reference to a scale parameter σ representing a magnitude of change of the historical traffic speed z.
For example, Δ x ═ x- μ, when-1.65 σ ≦ Δ x ≦ 0, v ═ 0.7; when the delta x is less than or equal to-1.96 sigma and less than-1.65 sigma, v is 0.8; when delta x is less than or equal to-2.58 sigma and less than-1.96 sigma, v is 0.9; when Δ x > 0, it is stated that the travel speed x of the vehicle at the time of reporting the event is higher than the average value μ of the historical traffic flow speed z, and at this time, it can be considered that the current travel of the vehicle is not affected or the influence is negligible, and v is 1. Thus, for this case, the value of v can be expressed mathematically as v ∈ {0.7,0.8,0.9,1 }. Or, in the case where Δ x > 0, v may be made closer to 1, i.e., v → 1.
It will be understood by those skilled in the art that the above division of the interval range is only exemplary, and any other suitable division of the interval can be used according to the actual situation, for example, the division can be performed by the numerical points-3 σ, -2 σ, - σ and 0. Preferably, for the normal distribution exemplarily listed herein, regardless of the value of μ, σ is defined, and such interval division is performed according to the principle of constant area ratio, or further, regardless of the value of μ, σ is defined, and the value of v is associated with the following probability density function (2).
Of course, the relationship between the travel speed x of the event reporting vehicle at the time of reporting the event and the historical traffic flow speed z can also be described and obtained in other ways. For example, according to an exemplary embodiment of the present invention, the relationship between the travel speed x of the event reporting vehicle at the reporting event time and the historical traffic flow speed z may be obtained by any suitable multivariate functional relationship, probability distribution relationship or big data based machine learning method.
It will be understood by those skilled in the art that other characterization methods may be used for the velocity deviation parameter v, as long as it is advantageous to determine the confidence level and/or priority level, and the present invention is not limited thereto.
There are many ways in which the data source for the historical traffic speed z may be, and the invention is not limited in this regard.
For example, according to an exemplary embodiment of the present invention, the historical traffic speed z may be obtained by integrating the vehicle rear end data monitoring platform 13 according to the historical data of the vehicle under monitoring by the vehicle rear end data monitoring platform 13.
According to another exemplary embodiment of the present invention, the historical traffic speed z can be determined by the vehicle back-end data monitoring platform 13 in cooperation with other monitoring platforms, so that the accuracy of the subsequent calculation can be further improved.
3) Frequency of reporting of same or similar events at respective geographical locations within a predetermined time period
The reporting frequency of the same or similar events can indicate the reliability of the events and the number of the vehicles affected. Therefore, the frequency parameter f is defined according to the reporting frequency (which may be the total reporting frequency within a predetermined distance and a predetermined time period before and after reporting the geographical location) of the same or similar event at the corresponding geographical location. The relationship between the frequency and the frequency parameter is determined by calculating the relationship, for example, for the relationship described in the present invention, the value of the frequency parameter f may be the reciprocal of the reporting times. For example, if the number of reports is 10, the frequency parameter f is 1/10, i.e. 0.1.
Preferably, the frequency parameter f may also be determined by the reporting frequency of the same or similar events and the total number of vehicles carrying the vehicle networking module 11 passing through the corresponding geographic location (which may include a predetermined nearby area). For example, the total number of vehicles passing through the corresponding geographic location and carrying the vehicle-carrying networking module 11 is 24, and if the number of reporting times is 10, for example, the frequency parameter f is [ (24-10) +1]/25 is 0.6; if the number of times of reporting is 15, the frequency parameter f ═ [ (24-15) +1]/25 ═ 0.4.
Therefore, the frequency parameter f may have a value range of (0, 1).
The greater the number of reports of the same or similar events or the greater the proportion of the total number of vehicle involved, the higher the value of the calculation result of the confidence and/or priority C.
It is obvious to a person skilled in the art that the frequency parameter f may also be characterized in other calculation ways, which is not limited by the present invention.
Furthermore, it will be understood by those skilled in the art that the above function (1) is only an exemplary function for calculating the confidence level and/or the priority C, and it is obvious that any other suitable function may be adopted, for example, various types of functions shown in (3), (4), etc. may be adopted.
C＝ef·va(3)
C＝ea·(1/f)b·vc(4)
According to an exemplary embodiment of the present invention, the confidence and/or the priority C may also be calculated based on a machine learning method of big data under the condition that the input parameters are unchanged.
According to an exemplary embodiment of the present invention, the present invention further relates to a method for determining a confidence level and/or a priority C of reporting event data, as shown in fig. 2, the method may include the following steps:
and S1, the vehicle back end data monitoring platform 13 receives the reported event data from the vehicle. The reported event data may include at least a specific event type, a travel speed of the event reporting vehicle at the reported event time, and geographical location information of the event.
S2: after receiving the reported event data, the vehicle rear-end data monitoring platform 13 acquires information required for calculating the confidence and/or priority of the reported event data; which may include:
s21: acquiring an event risk degree parameter e corresponding to the event type based on the reported event type;
s22: acquiring historical traffic flow speed z at a corresponding geographical position based on the reported geographical position, and then reporting the deviation between the running speed x of the vehicle at the moment of reporting the event and the historical traffic flow speed z based on the event to obtain a speed deviation parameter v;
s23: optionally, the frequency parameter f is obtained at least based on the reporting frequency of the same or similar events at the corresponding geographic location within a predetermined time period; and
s3: calculating the confidence coefficient and/or priority C of reported event data according to an event danger degree parameter e corresponding to the event type, a speed deviation parameter v of a running speed x and a historical traffic flow speed z of an event reporting vehicle at the event reporting time and/or a reporting frequency parameter f of the same or similar event at the corresponding geographic position in a preset time period;
s4: reliable event information (and optionally the confidence and/or priority calculations/values for the event information) is dispatched to relevant vehicles, such as potentially affected vehicles in the vicinity of the geographic location where the event occurred, based on the confidence and/or priority C calculations/values for the event data.
According to an exemplary embodiment of the present invention, the confidence and/or priority C is expressed in percentage terms, with a range of 0, 1. When the confidence coefficient and/or the priority C is 0, the event information is considered to be completely untrustworthy and/or the priority is lowest; when the confidence and/or priority C is 1, the event information is considered to be completely trusted and/or highest in priority.
According to an exemplary embodiment of the present invention, the reporting event data may be classified into three categories according to the confidence level and/or the priority result/value determined by the vehicle back-end data monitoring platform 13: invalid information, prompt information, warning information.
According to an exemplary embodiment of the present invention, there are different processing manners for different information classifications, and the following description will be given by taking a classification threshold of {0.5,0.9} as an example:
1. invalid information
And the confidence coefficient and/or priority calculation result interval is [0,0.5], and the event information is stored in the back-end data monitoring platform 13 and is not distributed to the relevant vehicles.
2. Prompt information
The confidence and/or priority calculation result interval is [0.5,0.9], and the information is sent to relevant vehicles, such as vehicles which are possibly affected near the geographic position of the event occurrence for prompting. Preferably, the prompting manner may be displaying an icon on a screen of the relevant vehicle, making a voice, or the like.
3. Warning message
The confidence and/or priority calculation result interval is [0.9,1], and the information is dispatched to relevant vehicles, for example, vehicles which are possibly affected near the geographic position of the event occurrence and are correspondingly operated. Preferably, the corresponding operation may be displaying an icon on a screen of the associated vehicle, making a voice, or the like. Preferably, if the dispatched vehicle is an autonomous vehicle with a network security interface, the information may also be applied to control of the associated vehicle.
Of course, the above only shows an exemplary classification interval, and different classification intervals may also be divided by changing the classification threshold.
It can be understood by those skilled in the art that the above-described technical solutions are also applicable to the confidence and/or priority analysis of the event data collected, reported or issued by the roadside devices of the car networking system 1, and at this time, the roadside devices may logically correspond to the vehicles for understanding. Here, the description is omitted.
According to other exemplary embodiments of the present invention, the method of determining the confidence level and/or priority level C of reported event data according to the present invention may also be used for an information receiving vehicle to determine the confidence level and/or priority level of event information (e.g., direct communication between vehicles, V2V, transmitted/received information) it receives that is transmitted by other vehicles. Accordingly, the method may comprise the steps of:
s1', the information receiving vehicle receives the reported event data from other vehicles. The reported event data may include at least a specific event type, a travel speed of the event reporting vehicle at the reported event time, and geographical location information of the event.
S2': after the information receiving vehicle receives the reported event data, acquiring information required for calculating the confidence coefficient and/or priority of the reported event data; which may include:
s21': acquiring an event risk degree parameter e corresponding to the event type based on the reported event type;
s22': acquiring historical traffic flow speed z at a corresponding geographical position based on the reported geographical position, and obtaining a speed deviation parameter v based on the deviation between the running speed x of the vehicle at the time of reporting the event and the historical traffic flow speed z;
s23': optionally, the frequency parameter f is obtained at least based on the reporting frequency of the same or similar events at the corresponding geographic location within a predetermined time period; and
s3': the information receiving vehicle calculates the confidence coefficient and/or priority C of the reported event data according to an event danger degree parameter e corresponding to the event type, a speed deviation parameter v of a running speed x and a historical traffic flow speed z of the event reporting vehicle at the event reporting time and/or a reporting frequency parameter f of the same or similar event in a preset time period based on the corresponding geographic position;
s4': the information receiving vehicle dispatches reliable event information (and optionally the confidence and/or priority calculations/values of the event information) to other relevant vehicles, such as potentially affected vehicles in the vicinity of the geographic location of the event or the vicinity of the information receiving vehicle, based on the confidence and/or priority C calculation/value of the event data.
In addition, the confidence and/or priority analysis results may also be archived as data, e.g., for insurance, accident, municipality, etc. invocations. Of course, other application scenarios for the confidence and/or priority analysis results are also contemplated, as the invention is not limited in this respect.
Table 1 below illustrates an example data archive for a confidence and/or priority analysis process.
TABLE 1
It will be appreciated by those skilled in the art that the present invention also relates to a computer readable program carrier having stored thereon program instructions capable of executing the method described above.
Although specific embodiments of the invention have been described herein in detail, they have been presented for purposes of illustration only and are not to be construed as limiting the scope of the invention. Various substitutions, alterations, and modifications may be devised without departing from the spirit and scope of the present invention.
Claims (10)
1. A method for determining confidence and/or priority of reported event data reported by vehicles in a vehicle networking system (1), the method comprising at least the steps of:
acquiring an event risk parameter corresponding to an event type based on the event type reported by the vehicle, acquiring a historical traffic flow speed at a corresponding geographical position based on the reported geographical position, and acquiring a speed deviation parameter based on the deviation between the running speed of the vehicle reporting the event at the moment and the historical traffic flow speed; and
and determining the confidence degree and/or priority of the reported event data at least based on the event risk degree parameter and the speed deviation parameter.
2. The method of claim 1, wherein the method further comprises the steps of:
receiving event data reported by vehicles, wherein the reported event data comprises the type of a reported event, the running speed of the vehicle reporting the event at the moment of reporting the event and the geographical position information of the event; and/or
The method further comprises determining a frequency parameter based at least on a reporting frequency of the same or similar event at the respective geographical location within a predetermined time period, and additionally based on the frequency parameter when determining a confidence and/or priority of reporting event data.
3. The method according to claim 2, wherein the confidence and/or priority is determined by the following functional formula (1):
wherein C represents confidence and/or priority;
e is an event risk degree parameter corresponding to the event type;
f is a frequency parameter; and
v is a velocity deviation parameter.
4. The method according to any one of claims 1-3, wherein the method further comprises:
fitting the historical traffic flow speed of each area block into normal distribution, storing the position parameters and the scale parameters of the traffic flow speed normal distribution curve of each area block after statistics, and determining speed deviation parameters based on the relation between the difference value between the running speed of an event reporting vehicle at the time of reporting the event and the average value of the historical traffic flow speed and the scale parameters of the historical traffic flow speed; and/or
The historical traffic flow speed comprises a time period near the reporting time and the historical traffic flow speed at the corresponding geographic position within a past period of time relative to the reporting time; and/or
The historical traffic flow speed also includes the reported historical traffic flow speed of vehicles in a predetermined area near the geographic location.
5. The method of any one of claims 1-4,
the historical traffic flow speed is obtained by integrating the vehicle rear end data monitoring platform (13) of the internet of vehicles system (1) according to the historical traffic flow speed of the vehicle monitored by the vehicle rear end data monitoring platform (13); or
The historical traffic flow speed is determined by the vehicle rear end data monitoring platform (13) of the vehicle networking system (1) and other monitoring platforms different from the vehicle rear end data monitoring platform (13) in a cooperation mode.
6. The method of any one of claims 2-4,
the frequency parameter is determined based on the reporting frequency and the total number of vehicles passing through the corresponding geographic position; and/or
The frequency parameter is in the range of (0,1 ].
7. The method of any one of claims 1-6,
the confidence and/or priority is determined based on a big data machine learning method; and/or
According to the determined confidence coefficient and/or priority, the reported event data is divided into three categories: invalid information, prompt information, warning information.
8. The method of any one of claims 1-7,
when the vehicle is the warning information, the corresponding information is sent to the relevant vehicle to carry out corresponding operation, the corresponding operation displays an icon on a screen of the relevant vehicle and/or sends out voice, and the corresponding information is used for controlling the relevant vehicle under the condition that the sent vehicle is an automatic driving vehicle with a network safety interface; and/or
The results of the confidence and/or priority analysis are archived as data for insurance and/or accident and/or municipal use.
9. A vehicle back end data monitoring platform (13) for a vehicle networking system (1), wherein the vehicle back end data monitoring platform (13) is configured to be capable of performing the method according to any one of claims 1-8.
10. A computer readable program carrier for a vehicle backend data monitoring platform (13) of a vehicle networking system (1), the computer readable program carrier having stored program instructions which, when executed by a processor, are capable of performing the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010488828.1A CN111698305A (en) | 2020-06-02 | 2020-06-02 | Method for determining confidence and/or priority of vehicle reported event data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010488828.1A CN111698305A (en) | 2020-06-02 | 2020-06-02 | Method for determining confidence and/or priority of vehicle reported event data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111698305A true CN111698305A (en) | 2020-09-22 |
Family
ID=72479261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010488828.1A Pending CN111698305A (en) | 2020-06-02 | 2020-06-02 | Method for determining confidence and/or priority of vehicle reported event data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111698305A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270840A (en) * | 2020-10-23 | 2021-01-26 | 清华大学 | Information credible identification method based on single-vehicle motion characteristics under vehicle-road cooperative environment |
| CN113192348A (en) * | 2021-04-21 | 2021-07-30 | 支付宝(杭州)信息技术有限公司 | Vehicle abnormity warning method and device and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299301A (en) * | 2007-05-04 | 2008-11-05 | 通用汽车环球科技运作公司 | Slow or stopped vehicle ahead advisor with digital map integration |
| KR20150106202A (en) * | 2014-03-11 | 2015-09-21 | 현대자동차주식회사 | Method and System for Warning Neighbor Dangerous Vehicle using Big Data |
| CN106157695A (en) * | 2016-08-03 | 2016-11-23 | 奇瑞汽车股份有限公司 | The based reminding method of dangerous driving behavior and device |
| CN106463054A (en) * | 2014-06-03 | 2017-02-22 | 宝马股份公司 | Adaptive warning management for advanced driver assistance system (ADAS) |
| CN111161527A (en) * | 2020-01-03 | 2020-05-15 | 财团法人车辆研究测试中心 | Remote monitoring system and method for self-driving |
-
2020
- 2020-06-02 CN CN202010488828.1A patent/CN111698305A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299301A (en) * | 2007-05-04 | 2008-11-05 | 通用汽车环球科技运作公司 | Slow or stopped vehicle ahead advisor with digital map integration |
| KR20150106202A (en) * | 2014-03-11 | 2015-09-21 | 현대자동차주식회사 | Method and System for Warning Neighbor Dangerous Vehicle using Big Data |
| CN106463054A (en) * | 2014-06-03 | 2017-02-22 | 宝马股份公司 | Adaptive warning management for advanced driver assistance system (ADAS) |
| CN106157695A (en) * | 2016-08-03 | 2016-11-23 | 奇瑞汽车股份有限公司 | The based reminding method of dangerous driving behavior and device |
| CN111161527A (en) * | 2020-01-03 | 2020-05-15 | 财团法人车辆研究测试中心 | Remote monitoring system and method for self-driving |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270840A (en) * | 2020-10-23 | 2021-01-26 | 清华大学 | Information credible identification method based on single-vehicle motion characteristics under vehicle-road cooperative environment |
| CN112270840B (en) * | 2020-10-23 | 2021-09-10 | 清华大学 | Information credible identification method based on single-vehicle motion characteristics under vehicle-road cooperative environment |
| CN113192348A (en) * | 2021-04-21 | 2021-07-30 | 支付宝(杭州)信息技术有限公司 | Vehicle abnormity warning method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11897460B2 (en) | Risk processing for vehicles having autonomous driving capabilities | |
| US11878643B2 (en) | Event-based connected vehicle control and response systems | |
| US10204460B2 (en) | System for performing driver and vehicle analysis and alerting | |
| US11482100B2 (en) | Technologies for detection of anomalies in vehicle traffic patterns | |
| CN110807930B (en) | Dangerous vehicle early warning method and device | |
| US11170639B2 (en) | Transportation threat detection system | |
| JP2008097376A (en) | Safe driving diagnostic device and safe driving diagnostic system | |
| CA3115091C (en) | Systems and methods for automatic breakdown detection and roadside assistance | |
| JP6696213B2 (en) | Monitoring device, monitoring system | |
| CN112614342B (en) | Early warning method for road abnormal event, vehicle-mounted equipment and road side equipment | |
| CN111698305A (en) | Method for determining confidence and/or priority of vehicle reported event data | |
| CN109448408B (en) | Method for optimizing vehicle running state at traffic light | |
| CN111311921A (en) | Method, device, computer equipment and storage medium for road overweight warning | |
| GB2485971A (en) | Transmitting recorded data in the event of a road vehicle accident | |
| CN110599791A (en) | Information monitoring method, device and equipment | |
| JP4835381B2 (en) | Road-to-vehicle communication determination system and method, determination apparatus and vehicle-mounted device used therefor | |
| CN111801954B (en) | Method for relaying event information in multi-layer V2X system | |
| JP2005293032A (en) | Vehicle operation state monitoring system and vehicle operation state monitoring program for this system | |
| TW202022648A (en) | Detection system and detection method thereof | |
| US10733885B2 (en) | Multi-vehicle prediction system | |
| US20240110800A1 (en) | Wear mitigation routing platform | |
| CN118247957A (en) | Expressway accident automatic processing method based on vehicle-road cooperation | |
| CN115955662A (en) | Road special condition monitoring and vehicle accident early warning system | |
| CN116101310A (en) | Method and device for sending early warning information in vehicle driving process | |
| CN117763366A (en) | Pavement disease detection method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Country or region after: Germany Address after: Stuttgart, Germany Applicant after: Mercedes-Benz Group Co.,Ltd. Address before: Stuttgart, Germany Applicant before: DAIMLER AG Country or region before: Germany |