WO2019216584A1

WO2019216584A1 - Method and electronic device for determining safety driving score

Info

Publication number: WO2019216584A1
Application number: PCT/KR2019/005097
Authority: WO
Inventors: Sriram Narayanaswamy Kizhakkemadam; Nabaneet DAS; Pushkaraj Vinayak SHIRVALKAR; Vignesh Lakshminarayanan; Bala Kama RAJU; Divya PRAKASH; Jinwoo JEON; Nagacharan UDUPI; Nirant KASLIWAL
Original assignee: Samsung Electronics Co., Ltd.
Priority date: 2018-05-07
Filing date: 2019-04-26
Publication date: 2019-11-14

Abstract

In embodiments disclosed herein provide a method for determining a driving performance metric of a driver. The method includes receiving, by at least one processor of an electronic device, information indicative of at least one type of event over a duration of a trip from at least one sensor coupled to the at least one processor and a driving context; determining a ruin probability based on the information indicative of the at least one type of event; determining driving behaviour of the driver based on the information indicative of the at least one event and the driving context; and determining, by the at least one processor of the electronic device, the driving performance metric based on the ruin probability and the driving behaviour.

Description

METHOD AND ELECTRONIC DEVICE FOR DETERMINING SAFETY DRIVING SCORE

The embodiments herein relate to determining driver performance, more particularly to a method and system for determining a driver safety score.

Assessing driver behaviour is based on static events and dynamic events occurring when a driver drives a vehicle during a trip. Static events can be but not limited to a number of traffic violations and the like. Dynamic results can be directed to hard braking or hard acceleration. Penalizing a driver under conventional methods of assessing a performance of the driver does not deter the driver from repeating past driving violations. Further existing mechanisms to assess a performance of a driver fail to reflect any driver behaviour where the driver mends his/her driving upon being penalized.

Conventional methods of assessing driver performance are also heuristics driven. Heuristics patterns fail to limit the recurrence of risky behaviour. Thus, there is a need for a mechanism to assess driver performance such that repetition of past driving violations and improvement in driving behaviour is taken into account.

The above information is presented as background information only to help the reader to understand the present invention. Applicants have made no determination and make no assertion as to whether any of the above might be applicable as Prior Art with regard to the present application.

The principal object of the invention herein is to provide a method for determining a driving performance metric of a driver in various driving contexts.

Another object of the invention herein is to provide a method to determine a probability of risky behaviour of the driver.

Accordingly, embodiments disclosed herein provide a method for determining a driving performance metric of a driver. The method includes receiving, by an electronic device, information indicative of at least one type of event over a duration of a trip from a plurality of sensors in a vehicle and a driving context. The method includes determining a ruin probability based on the information indicative of at least one type of event, determining driving behaviour of the driver based on information indicative of at least one event and the driving context and determining, by the electronic device, the driving performance metric of the driver driving the vehicle based on the ruin probability and the driving behaviour.

In an embodiment, the driving performance metric is determined by:

where, S[n,j,k] is a driving performance metric at a discrete time instant n, an event type j and a driving context k at the time instant n, S[n-1] is a driving performance metric at a discrete time instant n - 1, an event type j and a driving context k at the time instant (n-1), T is a number of discrete samples in a scoring interval, P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.

In an embodiment, the driving performance metric is estimated by:

where S is the driving performance metric, RecoveryValue_i is a recovery parameter corresponding to event i and PenalizationValue_i is a penalization value corresponding to the event i given by,

where P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.

In an embodiment, the ruin probability is estimated by:

where S[n-1] is a driving performance metric at a discrete time instant n, λ is a mean of a Poisson distribution fitted to the inter-arrival times of the at least one type of event, μ is a mean of an exponential distribution fitted to the severities of the at least one type of event, ｗ_ｒ is a statistical reward of the driving behaviour over a duration of the trip calculated as the time average of the driving behaviour of the previous trip and is constant for a given trip.

In an embodiment, ｗ_ｒ, a statistical measure of the driving behaviour over a duration of the trip, is determined as the time average of the driving behaviour of the previous trip and is constant for all the trips in a given time period.

In an embodiment, the ruin probability is estimated using a non-parametric sample-reuse method using:

where,

where ｎ is the number of samples available from the driver's driving history, X_k ^*b are the severities of the events drawn in the permutation ｂ at time instant ｋ, N^*b(t) is the number of events arrived by time ｔ, S_n is the duration of the data available, P_rn ^*b(v) is the indicator of the supremum of the driver's past liabilities being greater than the initial reserve ｖ, Ｂ is the number of permutations performed which is decided according to

.

In an embodiment, the method further comprises receiving, by an electronic device, information indicative of at least one type of event over a duration of a trip from a plurality of sensors in a vehicle and a driving context, determining, by the electronic device, a penalization value based on the information indicative of at least one type of event, estimating, by the electronic device, a recovery parameter as a function of the penalization value and a recovery time, wherein the recovery time is a time duration between consecutive events occurring during the trip and estimating, by the electronic device, the driving performance metric based on the recovery parameter and the penalization parameter.

In an embodiment, the driving behaviour is estimated by:

where f is a function that maps the event type to a severity score indicative of a severe or a good driving behaviour, q and ρ are constants calculated from policies for safety.

In an embodiment, the at least one type of event is indicative of velocity, hard acceleration, hard braking, hard cornering and external vehicle proximity.

In an embodiment, the driving context is indicative of traffic information, weather information and location information.

These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

Various applications and/or use cases can be provided through the driving performance metric such as vehicle health, parental control, driver behavior, and fuel modeling.

For example, motor insurance companies can adjust premiums of their subscribers dynamically according to their driving performance inferred from the proposed driving safety metric.

This invention is illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:

FIG. 1 illustrates various hardware components of an electronic device, according to an embodiment as disclosed herein;

FIG. 2A is a flow diagram illustrating a method to determine a driving performance metric based on driving events, according to an embodiment as disclosed herein;

FIG. 2B is a graphical illustration of an idealized curve representing the driving performance metric over a trip, according to an embodiment as disclosed herein;

FIG. 3 is a flow diagram illustrating a data flow to determine the driving score, according to an embodiment as disclosed herein;

FIG. 4 is a flow diagram illustrating a method for determining a driving performance metric, according to an embodiment as disclosed herein;

FIG. 5 is a flow diagram illustrating a method for determining a driving performance metric, according to an embodiment as disclosed herein;

Various embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. In the following description, specific details such as detailed configuration and components are merely provided to assist the overall understanding of these embodiments of the present disclosure. Therefore, it should be apparent to those skilled in the art that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. Herein, the term "or" as used herein, refers to a non-exclusive or, unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein. Further it should be possible to combine the flows specified in different figures to derive a new flow.

As is traditional in the field, embodiments may be described and illustrated in terms of blocks which carry out a described function or functions. These blocks, which may be referred to herein as managers, engines, controllers, units or modules or the like, are physically implemented by analog and/or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits and the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, or by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the disclosure. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the disclosure.

Conventional methods are directed to assessing driver behaviour is based on events occurring when a driver drives a vehicle during a trip. Examples of such events include traffic violations, hard braking or hard acceleration. Penalizing a driver under conventional methods of assessing a performance of the driver does not deter the driver from repeating past driving violations. Conventional methods provide no solutions to determine the probability of occurrence of a risky behavior in the future. Further existing mechanisms to assess a performance of a driver fail to reflect any driver behaviour where the driver mends his/her diving upon being penalized. Conventional methods of assessing driver performance are also heuristics driven. Heuristics patterns fail to limit the recurrence of risky behaviour.

Accordingly the embodiments herein is to provide a method to determine a driving performance metric of a driver. The method includes receiving, by at least one processor of an electronic device, information indicative of at least one type of event over a duration of a trip from at least one sensor coupled to the at least one processor and a driving context. The method includes determining a ruin probability based on the information indicative of at least one type of event, determining driving behaviour of the driver based on information indicative of at least one event and the driving context and determining, by the at least one processor of the electronic device, the driving performance metric of the driver driving the vehicle based on the ruin probability and the driving behavior.

Referring now to the drawings and more particularly to FIGS. 1 through 5, where similar reference characters denote corresponding features consistently throughout the figure, there are shown preferred embodiments.

FIG. 1 illustrates an electronic device 100 with various hardware components. The electronic device 100 may include at least one sensor 110, at least one processor 105, and a memory 150. The at least one processor 105 may comprise an event engine 120, a driving analyzer 130, and a performance enhancer 140. The electronic device 100 can be but not limited to a vehicle, a mobile device communicably coupled to a vehicle or a mobile device with the driver. The electronic device 100 can further be but not limited to a smartphone, a tablet computer, or a wearable device.

In some embodiments, the electronic device 100 can include communication units pertaining to communication with remote computers, servers or remote databases over a communication network. The communication network can include a data network such as, but not restricted to, the Internet, local area network (LAN), wide area network (WAN), metropolitan area network (MAN) etc. In certain embodiments, the communication network can include a wireless network, such as, but not restricted to, a cellular network and may employ various technologies including enhanced data rates for global evolution (EDGE), general packet radio service (GPRS), global system for mobile communications (GSM), Internet protocol multimedia subsystem (IMS), universal mobile telecommunications system (UMTS) etc. Accordingly, the electronic device 100 is included with communication components facilitating communications over the communication network. In some embodiments, the electronic device 100 can be part of an Internet of Things (IoT) network.

The at least one sensor 110 can include but not limited to inertial sensors, global positioning system (GPS) sensors, microphones, radio frequency sensors, velocity sensors, brakes, proximity sensors and the like. Information indicative of hard acceleration, hard braking, hard cornering, risky maneuvers, external vehicle proximity and the like is obtained from the at least one sensor 110. In some embodiments, the at least one sensor 110 can also include thermometers or any weather sensors that detect the weather. In some other embodiments, the at least one sensor 110 can be communicably coupled to a remote computer or the Internet via a communication device or communication unit, through which the sensors 110 can receive data indicative of weather, potential traffic, GPS waypoints, potential routes. The driving score is determined based on the information obtained by the at least one sensor 110.

In an embodiment, the electronic device 100 may receive information indicative of a type of event over a duration of a trip from the at least one sensor 110. The event can be but not limited to hard acceleration, hard braking, hard cornering, risky maneuvers, collisions with other vehicles, excessive speeds and the like. The event engine 120 may determine the type of event based on the information from the sensors 110. The event engine 120 may further determine a driving context to the information received. The driving context can be directed to past events that have occurred over the course of the trip. A risky maneuver in response to a close encounter with an external vehicle can result in a lesser penalization in the driver performance. The driving context may be further indicative of traffic information, weather information and location information pertaining to the driver.

The driving analyzer 130 may determine a ruin probability based on the type of event determined. The driving behavior of the driver may be further estimated based on the type of event and the driving context. The driving performance metric may be finally estimated based on the ruin probability and the driving behavior.

In some embodiments, the ruin probability may be estimated by: equation (1)

where S[n-1] is a driving performance metric at a discrete time instant n - 1, λ is a mean of a Poisson distribution fitted to the inter-arrival times of the at least one type of event, μ is a mean of an exponential distribution fitted to the severities of the at least one type of event, ｗ_ｒis a statistical reward of the driving behaviour over a duration of the trip calculated as the time average of the driving behaviour of the previous trip and is constant for a given trip. ｗ_ｒ is a statistical measure of the driving behaviour over a duration of the trip, is determined as the time average of the driving behaviour of the previous trip and is constant for all the trips in a given time period.

Using equation (1) due credit to past driving may be accounted for by the exponential of past score. A statistical reward for good driving is captured in ｗ_ｒ.

In some embodiments, the ruin probability may be estimated by using a non-parametric sample-reuse method using: equation (2)

Where, equation (3)

where ｎ is the number of samples available from the driver's driving history, X_k ^*bare the severities of the events drawn in the permutation ｂ at time instant ｋ, N^*b(t) is the number of events arrived by time ｔ, S_n is the duration of the data available, P_rn ^*b(ｖ)is the indicator of the supremum of the driver's past liabilities being greater than the initial reserve ｖ, Ｂ is the number of permutations performed which is decided according to: equation (4)

Eventually, the driving analyzer 130 may determine the driving performance metric based on the ruin probability by: equation (5)

where, S[n,j,k] is a driving performance metric at a discrete time instant n, an event type ｊ and a driving context ｋ at the time instant ｎ, S[n-1] is a driving performance metric at a discrete time instant ｎ－1, an event type j and a driving context k at the time instant (n-1), T is a number of discrete samples in a scoring interval, P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.

The driving behaviour is further modelled using: equation (6)

where f is a function that maps the event type to a severity score indicative of a severe or a good driving behaviour, ｑ and ρ are constants calculated from policies for safety.

In some embodiments, the driving analyzer 130 can determine a penalization value based on the type of event determined by the event engine 120. A recovery parameter as a function of the penalization value and a recovery time is further estimated. The recovery time is a time duration between consecutive events occurring during the trip. The driving performance metric is determined based on the recovery parameter and the penalization parameter.

Accordingly, the driving performance metric is estimated by: equation (7)

where S is the driving performance metric, RecoveryValue_i is a recovery parameter corresponding to event i and PenalizationValue_i is a penalization value corresponding to the event i given by, equation (8)

Examples of penalization value calculated based on event severity may be given below:

The processor 105 can be, but not restricted to, a Central Processing Unit (CPU), a microprocessor, or a microcontroller. The processor 105 may be coupled to the memory 150, the at least one sensor 110. The processor 140 may execute sets of instructions stored on the memory 150.

The memory 150 may include storage locations to be addressable through the processor 140. The memory 150 is not limited to a volatile memory and/or a non-volatile memory. Further, the memory 150 can include one or more computer-readable storage media. The memory 150 can include non-volatile storage elements. For example, non-volatile storage elements can include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In some embodiments, the memory 150 may store a plurality of voice sets (hereinafter interchangeably used with voice prompts) from which the most relevant voice set is used to provide an interactive voice response to the user.

FIG. 2A is a flow diagram 200 illustrating a method to determine a driving score based on driving events. The event engine 120 determines the type of event occurred during the trip from information received from the at least one sensor 110. Based on the type of event, the driving analyzer 130 determines the driving performance metric. At step 202, the driving analyzer 130 can determine if the event requires penalization. At step 204, the driving analyzer 130 can determine a penalization value, in accordance with equation (8), based on the type of event determined by the event engine 120. A recovery parameter as a function of the penalization value and a recovery time may be further estimated. The recovery time is a time duration between consecutive events occurring during the trip. At step 206, the driving performance metric may be determined, in accordance with equation (7), based on at least one of the recovery parameter or the penalization parameter. If no penalization is required, the driving analyzer 130 may directly proceed to step 206 to determine the driving performance metric in accordance with equation (5). In both the aforementioned scenarios, the ruin probability can be determined based on equations (1) and (2) while the driving behaviour is modelled in accordance with equation (6).

In some embodiments, the driving performance metric can be modelled as a straight line with slope θ, as shown in FIG. 2B, given by: equation (9)

Where duration refers to the trip duration. The driving performance metric is idealized as the straight line with a range of zero and hundred. This means an ideal performance metric at the end of the trip is 100. In case any event occurs, and penalization is applied, the driving performance metric is reduced at the point of time. The driving performance metric is allowed to recover with a slope of θ + θ', where θ' is given by: equation (10)

and equation (11)

FIG. 3 is a flow diagram 300 illustrating a data flow in the electronic device 100 to determine the driving score. Information indicative of the type of event is obtained from the at least one sensor 110 present in a hardware layer 330. The sensor data is utilized to determine the event, and subsequently the driving performance metric in a programmable layer 320 using the events engine 120 and the driving analyzer 130. Various applications and/or use cases can be provided through the driving performance metric such as vehicle health, parental control, driver behavior, and fuel modeling. For example, motor insurance companies can adjust premiums of their subscribers dynamically according to their driving performance inferred from the proposed driving safety metric.

FIG. 4 is a flow diagram illustrating a method 400 for determining a driving performance metric. At step 402, information indicative of at least one type of event over the duration of the trip from the at least one sensor 110 in a vehicle and a driving context may be received. The events engine 120 can determine the type of event based on the information received. At step 404, the ruin probability may be determined by the driving analyzer 130 using any or a combination of the equations (1) and (2). At step 406, the driving behaviour may be estimated based on the equation (6). At step 408, the driving performance metric may be further determined based on the ruin probability and the driving behaviour using the equation (5).

FIG. 5 is a flow diagram illustrating a method 500 for determining a driving performance metric using penalization values. At step 502, the at least one sensor 110 may receive information indicative of at least one type of event over a duration of a trip from at least one sensor in a vehicle and the driving context. The events engine 120 may determine the type of event based on the received information. At step 504, the penalization value may be determined based on the type of event. the driving analyzer 130 may further check if the event occurrence in a recovery time duration results in a deviation from the ideal slope of the driving performance metric over the course of the trip. Accordingly, the penalization value can be determined using equation (8). Based on the recovery time and the penalization value, a recovery parameter can be estimated at step 506. At step 508, the driving performance metric can be determined by the driving analyzer using the equation (7).

The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements shown in FIGS. 1-5 include blocks which can be at least one of a hardware device, or a combination of hardware device and software module.

The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

While embodiments of the present disclosure are described herein by way of example using several illustrative drawings, those skilled in the art will recognize the present disclosure is not limited to the embodiments or drawings described. It should be understood the drawings and the detailed description thereto are not intended to limit the present disclosure to the form disclosed, but to the contrary, the present disclosure is to cover all modification, equivalents and alternatives falling within the spirit and scope of embodiments of the present disclosure as defined by the appended claims.

Claims

A method for determining a driving performance metric of a driver, the method comprising:

receiving, by at least one processor of an electronic device, information indicative of at least one type of event over a duration of a trip from at least one sensor coupled to the at least one processor and a driving context;

determining a ruin probability based on the information indicative of the at least one type of event;

determining driving behaviour of the driver based on the information indicative of the at least one event and the driving context; and

determining, by the at least one processor of the electronic device, the driving performance metric based on the ruin probability and the driving behaviour.
The method of claim 1, wherein the driving performance metric is determined by:

where, S[n,j,k] is a driving performance metric at a discrete time instant n, an event type j and a driving context k at the time instant n, S[n-1] is a driving performance metric at a discrete time instant n - 1, an event type j and a driving context k at the time instant (n-1), T is a number of discrete samples in a scoring interval, P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.
The method of claim 1, wherein the driving performance metric is estimated by:

where S is the driving performance metric, RecoveryValue_i is a recovery parameter corresponding to event i and PenalizationValue_i is a penalization value corresponding to the event i given by,

where P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.
The method of claims 2 and 3, wherein the ruin probability is estimated by:

where S[n-1] is a driving performance metric at a discrete time instant n - 1, λ is a mean of a Poisson distribution fitted to the inter-arrival times of the at least one type of event, μ is a mean of an exponential distribution fitted to the severities of the at least one type of event, ｗ_ｒ is a statistical reward of the driving behaviour over a duration of the trip calculated as the time average of the driving behaviour of the previous trip and is constant for a given trip.
The method of claim 4 wherein ｗ_ｒ, a statistical measure of the driving behaviour over a duration of the trip, is determined as the time average of the driving behaviour of the previous trip and is constant for all the trips in a given time period.
The method of claim 2 and 3, wherein the ruin probability is estimated using a non-parametric sample-reuse method using:

Where,

where ｎ is the number of samples available from the driver's driving history, X_k ^*b are the severities of the events drawn in the permutation ｂ at time instant ｋ, N^*b(t) is the number of events arrived by time ｔ, S_n is the duration of the data available, P_rn ^*b(v) is the indicator of the supremum of the driver's past liabilities being greater than the initial reserve ｖ, Ｂ is the number of permutations performed which is decided according to
.
The method of claim 1 further comprising:

determining, by the at least one processor of the electronic device, a penalization value based on the information indicative of at least one type of event;

estimating, by the at least one processor of the electronic device, a recovery parameter as a function of the penalization value and a recovery time, wherein the recovery time is a time duration between consecutive events occurring during the trip; and

estimating, by the at least one processor of the electronic device, the driving performance metric based on the recovery parameter and the penalization parameter.
The method of claim 1, wherein the driving behaviour is estimated by:

where f is a function that maps the event type to a severity score indicative of a severe or a good driving behaviour, q and ρ are constants calculated from policies for safety.
The method of claim 1, wherein the at least one type of event is indicative of at least one of velocity, hard acceleration, hard braking, hard cornering, or external vehicle proximity.
The method of claim 1, wherein the driving context is indicative of at least one of traffic information, weather information, or location information.
An electronic device for determining a driving performance metric of a driver, the electronic device comprising:

an event engine receiving information indicative of at least one type of event over a duration of a trip from at least one sensor and a driving context; and

a driving analyzer coupled to the event engine, the driving analyzer configured to:

determine a ruin probability based on the information indicative of the at least one type of event,

determine driving behaviour of the driver based on the information indicative of the at least one event and the driving context; and

determine the driving performance metric based on the ruin probability and the driving behaviour.
The electronic device of claim 11, wherein the driving performance metric is determined by:

where, S[n,j,k] is a driving performance metric at a discrete time instant n, an event type j and a driving context k at the time instant n, S[n-1] is a driving performance metric at a discrete time instant n - 1, an event type j and a driving context k at the time instant (n-1), T is a number of discrete samples in a scoring interval, P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.
The electronic device of claim 11, wherein the driving performance metric is estimated by:

where S is the driving performance metric, RecoveryValue_i is a recovery parameter corresponding to event i and PenalizationValue_i is a penalization value corresponding to the event i given by,

where P_r[i,j,k] is a probability of risky behaviour of the driver, w[i,j,k] is indicative of driving behaviour occurred at time i, in a driving context k for the event type j.
The electronic device of claims 12 and 13, wherein the ruin probability is estimated by:

where S[n-1] is a driving performance metric at a discrete time instant n - 1, λ is a mean of a Poisson distribution fitted to the inter-arrival times of the at least one type of event, μ is a mean of an exponential distribution fitted to the severities of the at least one type of event, ｗ_ｒ is a statistical reward of the driving behaviour over a duration of the trip calculated as the time average of the driving behaviour of the previous trip and is constant for a given trip.
The electronic device of claim 14 wherein ｗ_ｒ, a statistical measure of the driving behaviour over a duration of the trip, is determined as the time average of the driving behaviour of the previous trip and is constant for all the trips in a given time period.