Claims:We claim:
1. A method for determining a driving score of an electric vehicle (EV) user, comprising:
receiving, by a telematic control unit (TCU) (103), from a plurality of electronic control unit (ECUs) (102) in the vehicle, one or more vehicle parameters and one or more powertrain parameters in real-time;
obtaining, by the telematic control unit (TCU) (103), one or more threshold values/ range for each of the one or more vehicle parameters and the one or more powertrain parameters associated with each of the one or more threshold values/ range and one or more weightage values associated with each of the one or more vehicle parameters and one or more powertrain parameters, wherein one or more threshold values/ range and the one or more weightage values is determined using one or more Artificial Intelligence (AI) models;
calculating, by the telematic control unit (TCU) (103), a driving score of the EV (101) based on the one or more threshold values/ range and the one or more weightage values for the one or more vehicle parameters and the one or more powertrain parameters using one or more computing models;
and
indicating, by the telematic control unit (TCU) (103), driving performance of the vehicle based on the driving score of the EV (101) to user of the EV (101).

2. The method as claimed in claim 1, wherein the one or more artificial intelligence (AI) model is at least one of a machine learning (ML) or a deep neural network (DNN).

3. The method as claimed in claim 1, wherein the one or more computing model is one of an edge computing model and/or a cloud computing model.

4. The method as claimed in claim 1, wherein the one or more vehicle parameters comprises at least one of, an acceleration value, a braking value, a steering value, a speed value, idling time, driving duration.

5. The method as claimed in claim 1, wherein the one or more powertrain parameters comprises at least one of, a traction efficiency, a generator efficiency, an auxiliary energy consumption, a regeneration fraction.

6. The method as claimed in claim 1, wherein the driving score of the EV (101) is calculated using a weighted summation of the individual scores and the one or more weightage values for each of the one or more vehicle parameters and the one or more powertrain parameters.

7. The method as claimed in claim 1, wherein determining the one or more thresholds/ range using the one or more AI models comprises:
obtaining the one or more threshold values for each of the one or more vehicle parameters and the one or more powertrain parameters based on the training data;
generating individual score from the threshold range for each of the one or more vehicle parameters and the one or more powertrain parameters.

8. The method as claimed in claim 1, wherein determining the one or more weightages using the one or more AI models comprises:
obtaining the one more weighted values for each of the one or more vehicle parameters and the one or more powertrain parameters based on the training data;
determining weightages from one or more ranks for each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction.

9. The method as claimed in claim 1, wherein indicating the driving performance includes
displaying the overall driving score on to one of the instrument cluster and driving unit of the EV (101).

10. The method as claimed in claim 1, wherein indicating the driving performance includes transmitting the overall driving score to an electronic unit associated with the EV (101).

11. The method as claimed in claim 1, wherein the one or more AI models are trained with a big data collected by training vehicles, tested at different regions and/or conditions.

12. A Telematic control unit (TCU) (103) for determining a driving score of an electric vehicle (EV) user, comprising: a processor; and a memory; wherein the processor is configured to:
receive from a plurality of electronic control unit (ECUs) (102) in the vehicle, one or more vehicle parameters and one or more powertrain parameters in real-time;
obtain one or more threshold values/ range for each of the one or more vehicle parameters and the one or more powertrain parameters associated with each of the one or more threshold values/ range and one or more weightage values associated with each of the one or more vehicle parameters and one or more powertrain parameters, wherein one or more threshold values/ range and the one or more weightage values is determined using one or more Artificial Intelligence (AI) models;
calculate a driving score of the EV (101) based on the one or more threshold values/ range and the one or more weightage values for the one or more vehicle parameters and the one or more powertrain parameters using one or more computing models; and
indicate driving performance of the vehicle which is derived based on the driving score of the EV (101) to user of the EV (101).

13. The Telematic controller unit (TCU) (103) as claimed in claim 11, wherein the one or more powertrain parameters comprises at least one of, a traction efficiency, a generator efficiency, an auxiliary energy consumption, a regeneration fraction.

14. The Telematic controller unit (TCU) (103) as claimed in claim 11, wherein determining the one or more thresholds/ range using the one or more AI models comprises:
obtaining the one or more threshold values for each of the one or more vehicle parameters and the one or more powertrain parameters based on the training data;
generating individual score from the threshold range for each of the one or more vehicle parameters and the one or more powertrain parameters.

15. The Telematic controller unit (TCU) (103) as claimed in claim 11, wherein determining the one or more weightages using the one or more AI models comprises:
obtaining the one more weighted values for each of the one or more vehicle parameters and the one or more powertrain parameters based on the training data;
determining weightages from one or more ranks for each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction.

16. The Telematic controller unit (TCU) (103) as claimed in claim 11, wherein indicating the driving performance includes displaying the overall driving score on to one of the instrument cluster and driving unit of the EV (101).

17. The Telematic controller unit (TCU) (103) as claimed in claim 11, wherein indicating the driving performance includes transmitting the overall driving score to an electronic unit associated with the EV (101).

18. The Telematic controller unit (TCU) (103) as claimed in claim 11, wherein the one or more AI models are trained with a big data collected by training vehicles, tested at different regions and/or conditions.

19. A Cloud Server (104) comprising: one or more processors and a memory; wherein the one or more processors are configured to:
determine one or more threshold values/ range for each of one or more vehicle parameters and the one or more powertrain parameters of the training data using on one or more supervised or unsupervised AI models;
generate individual score for each of the one or more threshold values/ range;
determine one or more weighted values for each of the one or more vehicle parameters and the one or more powertrain parameters of the training data using one or more regression AI models;
determine weightages from one or more ranks for each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction;
transmit to the TCU (103) the one or more threshold values/ range and the one or more weightages for calculating the driving score.
, Description:TECHNICAL FIELD
The present disclosure relates in general to automobiles. Particularly, but not exclusively, the present disclosure relates to a method and system for determining a driving score of an electric vehicle (EV) user.

BACKGROUND
Electric Vehicles (EVs) presence is growing in the market as it is a solution for clean energy. One of a major selling point of EV vendors or Original Equipment Manufacturers (OEMs) is the EV range. Various solutions are provided to assist customer to get practical EV range. One such solution is to enable drivers to drive the EV inefficient manner. Enabling drivers to drive in an efficient manner is possible by providing a quantitative driving score with respect to his/ her driving style. Generally, the driving score is determined to represent driving behavior or driving pattern of a driver considering various actions of the driver. The driving score is a feedback mechanism by which driving performance can be improved. In an electric vehicle (EV), the driving performance plays an important role in achieving key performance attributes such as range of the EV.

Conventional internal combustion engines (ICE) have been on the market for more than three decades, and customers are familiar with them. However, because EV powertrain characteristics differ significantly from those of regular ICE vehicles, drivability must be redefined for EV customers. In the existing scenario, range anxiety is a major concern for customers when it comes to the EV as charging infrastructure is gradually maturing. Practical vehicle range is affected by multiple elements such as terrain, traffic, ambient conditions, powertrain health, load on the vehicle, driving style, and the like. Challenges faced by EV customers can be addressed by powertrain redesigning, environment conditioning and proper driving training. As powertrain is designed considering technology, economy and vehicle performance attributes, redesigning it has its own limitation. For environment conditioning, factors like terrain, traffic, wind speed and ambient conditions are beyond user control. Driving style is an independent factor which can be modified if proper training is deployed to characterize driving style. Driving score is the customized way to train the customer efficiently. In the existing approaches, various Original Equipment Manufacturers (OEMs) provide driving score solution to their customers by only considering various vehicle parameters of driver’s action like harsh acceleration, harsh braking, rash turning, over speeding etc. In addition, regional customized driving conditions are also ignored in most of the solutions and are not correlated with vehicle range. Thus, there is need to improve the scope of existing driving score solution by eliminating biasedness and making it more realistic for EVs by correlating it with practical vehicle range and providing EV customized drivability.

The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgment or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

SUMMARY
Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.

Disclosed herein is a method for determining a driving performance of an electric vehicle (EV) user. The method comprises receiving, by a telematic control unit (TCU), from a plurality of electronic control unit (ECUs) in the vehicle, one or more vehicle parameters and one or more powertrain parameters in real-time. Further, the method comprises obtaining one or more threshold values/ range and one or more weightage values associated with each of the one or more vehicle parameters and the one or more powertrain parameters. The one or more threshold values/ range, and the one or more weightage values are determined using one or more Artificial Intelligence (AI) models. Furthermore, calculating a driving score of the EV (101) based on the one or more threshold values/ range and the one or more weightage values for the one or more vehicle parameters and the one or more powertrain parameters using one or more computing models. Finally, indicating the driving performance of the EV user on a display.

Further, the present disclosure discloses a telematic control unit (TCU) for determining a driving performance of an electric vehicle (EV) user. The telematic control unit comprises a processor and a memory. The processor is configured to receive from a plurality of electronic control unit (ECUs) in the vehicle, one or more vehicle parameters and one or more powertrain parameters in real-time. Further, the processor is configured to obtain one or more threshold values/ range for each of the one or more vehicle parameters and the one or more powertrain parameters, individual scores associated with each with each of the one or more threshold values/ range and one or more weightage values associated with each of the one or more vehicle parameters and the one or more powertrain parameters. The one or more threshold values/ range, and the one or more weightage values are determined using one or more Artificial Intelligence (AI) models on a cloud server associated with the TCU. Furthermore, the processer is configured to calculate a driving score of the EV (101) user based on the individual score associated with the one or more threshold values/ range and the one or more weightage values for the one or more vehicle parameters and the one or more powertrain parameters using one or more computing models. Thereafter, the processor indicates the driving score to user of the EV on a display.

Furthermore, the present disclosure discloses a cloud server (104) for determining threshold values/ range and weightage parameters for the one or more vehicle parameters and the one or more powertrain parameters. This is achieved by training one or more AI models. Training comprises obtaining the one or more threshold values/ranges and weightages for each of one or more vehicle parameters and one or more powertrain parameters based on the training data. Further, the one or more processors (cloud processor) are configured to generate individual score from the one or more threshold values /range for each of the one or more vehicle parameters and the one or more powertrain parameters. Furthermore, the one or more processors (cloud processor) are configured to determine weightages from a ranks of each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction. Thereafter, the one or more processors (cloud processor) are configured to the transmit the one or more thresholds and the one or more weightages to the TCU (103) for calculating the driving score.

The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features may become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
The novel features and characteristic of the disclosure are set forth in the appended claims. The disclosure itself, however, as well as a preferred mode of use, further objectives, and advantages thereof, may best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. One or more embodiments are now described, by way of example only, with reference to the accompanying figures wherein like reference numerals represent like elements and in which:

Fig. 1 shows an environment illustrating determining a driving performance of an electric vehicle (EV) user, in accordance with some embodiments of the present disclosure;

Fig. 2 shows a detailed block diagram of TCU for determining a driving performance of an electric vehicle (EV) user, in accordance with some embodiments of the present disclosure;

Fig. 3 shows a flowchart illustrating method steps for determining a driving performance of an electric vehicle (EV) user, in accordance with some embodiments of the present disclosure;

Fig. 4 illustrates an artificial intelligence model for determining a driving score of an electric vehicle (EV) user, in accordance with some embodiments of the present disclosure;

Fig. 5a depicts an exemplary display model for displaying driving score of an EV, in accordance with some embodiments of the present disclosure; and

Fig. 5b depicts an exemplary display model for displaying ideal driving score of an EV, in accordance with some embodiments of the present disclosure.

It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it may be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes, which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION
In the present document, the word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment or implementation of the present subject matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and may be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.

The terms “comprises”, “includes” “comprising”, “including” or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” or “includes…a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus.

In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

Fig. 1 shows an environment illustrating determining driving performance of an EV user. The environment includes an electric vehicle (101), an electronic control units (ECUs) (102) present inside the vehicle (101), a telematic control unit (TCU) (103), a cloud server (104), a display unit (105). The system (100) comprises receiving one or more vehicle parameters and one or more powertrain parameters in real-time from a plurality of ECUs (102) (not shown) of the EV (101). In an embodiment, the vehicle (101) may comprise plurality of ECUs ECU 1 (1021), ECU 2 (1022) …ECUn (102n) (collectively referred as ECUs 102). For example, a first ECU of the plurality of ECUs (102) to monitor and control a steering, a second ECU of the plurality of ECUs (102) to monitor and control a brake pedal, a third ECU of the plurality of ECUs (102) to monitor and control an accelerator pedal, and so on. Further, the one or more vehicle parameters and the one or more powertrain parameters of an electric vehicle (EV) (101) are passed on to the telematic control unit (TCU) (103).

In an embodiment, the TCU (103) can be resembled with Gateway ECUs or telematics device or T-box or CAN2WiFi or CAN2Bluetooth devices and the like. The TCU (103) or any equivalent electronic component may be capable of establishing communication between the vehicle (101) and the cloud server (104). One or more thresholds and one or more weightages associated with each of the one or more vehicle parameters and one or more powertrain parameters are determined using one or more artificial intelligence (AI) models implemented in the cloud server (104). The one or more thresholds are also referred as the one or more threshold values/ range. The one or more weightages are also referred as the one or more weightage values in the present disclosure. The one or more AI models are trained for deriving the one or more thresholds and weightages on the cloud server (104) at regular time intervals. Thereafter, individual scores are assigned or mapped to each of the one or more thresholds. The cloud server then transmits the one or more threshold, the mapped individual scores and the one or more weightages to the TCU (103) preferably via wireless interface. A driving score is calculated by the TCU (103) for measured one or more parameters based on the received one or more thresholds, mapped individual scores and the weightages of each of the one or more parameters using one or more computing models. Further, the one or more thresholds and weightages are being updated through continuous model training through region based new data obtained from the vehicle (101) and transmitted by the cloud server (105) to the TCU (103) regularly. The TCU (103) can use the updated one or more thresholds and weightages to calculate the driving score for measurements made in different regions. Thereafter, the driving performance based on the driving score value is displayed on a user device such as a mobile phone or vehicle instrument cluster or infotainment system or customer app. In an embodiment, the individual scores corresponding to each parameter can also be displayed. This enables the driver to identify the specific areas of improvement and thus increase the overall driving performance of the electric vehicle user (101).

Fig. 2 shows a detailed block diagram of the TCU (103). The TCU (103) may include Central Processing Unit (“CPU” or “processor”) (203) and a memory (202) storing instructions executable by the processor (203). The processor (203) may include at least one data processor for executing program components for executing user or system-generated requests. The memory (202) may be communicatively coupled to the processor (203). The TCU (103) further includes an Input/ Output (I/O) interface (201). The I/O interface (201) may be coupled with the processor (203) through which an input signal or/and an output signal may be communicated. In some embodiments, TCU (103) comprises modules (204). The modules (204) may be stored within the memory (202). In an example, the modules (204) are communicatively coupled to the processor (203) configured in the computing system (100) and may also be present outside the memory (202) as shown in Fig. 2 and implemented as hardware. As used herein, the term modules (204) may refer to an application specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA), an electronic circuit, a processor (203) (shared, dedicated, or group), and memory (202) that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality. In some other embodiments, the modules (204) may be implemented using at least one of ASICs and FPGAs.

In an embodiment, an I/O interface (201) may enable communication between the ECUs (102) and the TCU (103). The I/O interface (201) may include at least one of, a CAN port, an Ethernet port, a Flex Ray port, and the like.

In one implementation, the modules (204) may include, for example, a communication module (205), an obtaining module (206), a determining module (209) and a computation module (207). It may be appreciated that such aforementioned modules (204) may be represented as a single module or a combination of different modules (204).

In an embodiment the communication module (205) is configured to receive one or more vehicle parameters and one or more powertrain parameters either from the plurality of ECU (102) or sensors via the I/O interface (201). These one or more vehicle parameters and one or more powertrain parameters are obtained by the TCU (103). The one or more vehicle parameters and the one or more powertrain parameters are received in real-time at regular intervals. The one or more vehicle parameters comprises at least one of, an acceleration value, a braking value, a steering value, a speed value, idling time, driving duration and the like. The one or more powertrain parameters comprises at least one of, a traction efficiency, a generator efficiency, an auxiliary energy consumption, a regeneration fraction and the like. These parameters are collected by the communication module of the TCU (103) from the plurality of ECUs (102) and passed on to the processor (203) of TCU (103) to determine driving score of the EV (101) user. As the user drives the EV, the one or more vehicle parameters and the one or more powertrain parameters in real time are used for overall driving score calculation. In an embodiment, the one or more vehicle parameters may be obtained from the one or more sensors/ ECU’s (102).

In an embodiment, the communication module (205) may use interfaces such as controller area network (CAN)/ FlexRay for receiving the one or more vehicle parameters and the one or more powertrain parameters. In an embodiment, the communication module (205) is configured to receive the one or more thresholds, corresponding individual scores and the weightages from the cloud server (104). The one or more thresholds, the individual scores and the weightages are used in calculating the driving score when the one or more vehicle parameters and the one or more powertrain parameters are received in real-time. Further, the communication module (205) transmits the determined driving score value to a display unit/ instrument cluster (105) for displaying the driving score to the user. The one or more thresholds / range and the one or more weightage values is determined using one or more Artificial Intelligence (AI) models in the cloud server (104).

In an embodiment, the computation module (207) may be configured to calculate the driving score based on the obtained the individual scores associated with the one or more thresholds and the one or more weightages of each of the one or more parameters, using one or more computing models present inside the TCU (103). More specifically, the driving score is calculated using a weighted summation of individual scores and weightages of each of the one or more vehicle parameters and the one or more powertrain parameters.

As described before, the cloud server (104) is configured to determine the one or more threshold values/ range and one or more weightage values associated with each of the one or more vehicle parameters and the one or more powertrain parameters using the one or more AI models present in the cloud server (104). The cloud server comprises a memory and one or more processors (not shown in Figure). The one or more AI models are trained with a big data collected by one or more training vehicles, tested at different regions and conditions. The training with big data occurs in the cloud server (104). The big data may be from those specific region vehicles, named training vehicles to train model based on region-wise. There are two major steps in model training namely threshold derivation and weightage derivation. Threshold derivation is performed to segregate parametric value range into different categories based on location and driving conditions. Further, the individual scores for each of the one or more vehicle parameters and one or more powertrain parameters is mapped for each threshold value range. The one or more artificial intelligence (AI) model is one of a machine learning (ML) or a deep neural network (DNN). In one embodiment, determining the one or more thresholds using the one or more AI models comprises using one or more unsupervised clustering models to generate clusters of values for each of the one or more vehicle parameters and one or more powertrain parameters. Each cluster may represent the threshold value/ range. The determined thresholds can be dynamic value. The dynamic value herein may be the thresholds calculated according to different regional driving conditions. These dynamic thresholds aid in calculating realistic driving score according to different driving conditions which enables to guide the driver in better driving according to the driving conditions. The individual scores are the rank, which are mapped with the threshold values/ range. In an exemplary embodiment, the worst threshold range for a particular parameter may lead to least individual score while best threshold range leads to best individual score for that parameter. The threshold range is the range in which each of the parameter value lies.

In an embodiment, determining the weightages using the one or more AI models present in the cloud server (104) comprises obtaining the one or more weighted values for each of the one or more vehicle parameters and the one or more powertrain parameters based on the training data using one or more AI models. The one or more AI models used herein to determine the weightages may include but not limited to ML regression models or deep learning models or neural networks. The weightages are determined from ranks for each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction. The ranks are the values associated with each of the one or more vehicle parameters and the one or more powertrain parameters assigned according to the dependency of the parameters in energy consumption. The cloud server (104) is further used to determine a weightages of each of the one or more vehicle parameters and the one or more powertrain parameter that is trained with a dataset to obtain optimum set of coefficients that map the input parameters to target variables (energy consumption values). A person skilled will appreciate that other AI models can also be used to characterize the driving performance of the EV (101) user using cloud computing model and edge computing model. The thresholds and weightages may be intelligently updated region-wise through AI/ML model at regular interval model training in the cloud server (104). The determined thresholds, individual scores and weightages are stored or updated in the cloud server (104) and can be further transmitted to the TCU (103) to calculate overall driving score in real-time. In an embodiment, parameters referred herein are combination of the one or more vehicle parameters and the one or more powertrain parameters.

In an embodiment, the auxiliary module (208) may include a display module or alert module indicating driving performance of the vehicle which is derived based on the driving score of the EV (101) to user of the EV (101). Indicating the driving performance includes displaying the overall driving score on to one of the instrument cluster and driving unit of the EV (101) and transmitting the overall driving score to an electronic unit associated with the EV (101). For example, when user of the EV (101) drives the vehicle with higher speed, then driving score value indicated on the display unit (105) is in critical range with low driving score value. Thus, it alerts the user to drive the EV (101) in recommended speed. Overall driving score is indicated on display unit like on vehicle cluster, infotainment system or customer App.

Fig. 3 shows a flowchart illustrating a method for determining a driving performance of an electric vehicle (EV) (101), in accordance with some embodiment of the present disclosure. The order in which the method (300) may be described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method may be implemented in any suitable hardware, software, firmware, or combination thereof.

At the step (301), receiving from a plurality of electronic control unit (ECUs) (102) in the vehicle, one or more vehicle parameters and one or more powertrain parameters in real-time. As described, the one or more vehicle parameters comprises at least one of, an acceleration value, a braking value, a steering value, a speed value, an idle time, a driving duration. Further, the one or more powertrain parameters comprises at least one of, a traction efficiency, a generator efficiency, an auxiliary energy consumption, a regeneration fraction. Further, the one or more parameters are obtained at regular intervals. The one or more vehicle parameters and one or more powertrain parameters are then passed on to the cloud server (104) using telematics unit/TCU (103) at regular intervals for training/ updating the one or more AI models to derive or update the one or more thresholds and the one or more weightages. Further, the one or more thresholds and the one or more weightages that are determined by the cloud server (104) are received and used by the TCU (103) to determine overall driving score using the one or more computing models

At step (302), obtaining the one or more thresholds and the one or more weightages associated with each of the one or more vehicle parameters and one or more powertrain parameters from the cloud server (104). In an embodiment, the one or more thresholds and the one or more weightages are determined at the cloud server (104) using the one or more artificial intelligence (AI) models. The one or more artificial intelligence (AI) models is one of a machine learning (ML) or a deep neural network (DNN). The one or more AI models are trained with a big data collected at one or more training vehicles, tested at different regions and conditions. The big data may be from those specific region vehicles, named training vehicles to train model based on region-wise. There are two phases in model training namely threshold derivation and weightage derivation. The threshold derivation is performed to get individual scores for each of the one or more vehicle parameters and one or more powertrain parameters. For example, the training vehicles driving performance may be recorded at different regions like highway road, hill station, ice road and the like and these values are passed as big data to the one or more AI models to determine the correct and real-time driving performance of the EV (101) at all kinds of road conditions. Further, the individual scores are assigned or mapped to the one or more thresholds. Then, the cloud server (104) transmits the one or more thresholds, the corresponding individual scores and the weightages to the TCU (103). Details of determining the thresholds, the individual scores and the weightages are described further in the present disclosure.

Further, the one or more threshold values/ range, the individual scores and the one or more weightage values are obtained by the TCU (103) for calculating the overall driving score using the one or more computing models. The one or more vehicle parameters and the one or more powertrain parameters includes at least speed, acceleration, deceleration, idling time, driving duration, traction efficiency, generator efficiency, regeneration fraction and auxiliary energy consumption. The pre-processed data is provided as input to machine learning clustering model to derive thresholds using clustering algorithms like K-means, DBSCAN, GMM, Fuzzy K-mean and the like. Further, the individual scores are mapped to each threshold value/ range. For example, a domain expert may associate each threshold value/ range with the individual score. As seen in table 1, the domain expert may associate the speed range of 15-19 with a score of 9, likewise associate the speed range of 20-23 with a score 8. In an embodiment, the individual score may be different for different driving conditions. Considering the same example, the individual scores may be applicable for city driving conditions. The individual scores and the threshold values/ range may vary for different driving conditions. The individual score for parameters from highest to lowest score range are as shown in the Table 1. In another example, consider the parameter speed and its value as 21. The speed value 21 falls in the range with minimum value of 20 and maximum value 23. Hence, it falls in the threshold 2 range having the individual score of 8. The individual score is assigned as 8 based on speed value. Unlike, conventional techniques the threshold value is not fixed, and it is determined based on driving conditions and provides updated driving score.

Thresholds Minimum Maximum Score
Threshold 1 15 19 9
Threshold 2 20 23 8
Threshold 3 24 26 7
Threshold 4 27 29 6
Threshold 5 30 31 5
Threshold 6 32 34 4

Table 1

Further, determining by the cloud server (104) the weightages using the one or more AI models. The one or more AI models may include at least one of the machine learning (ML) regression models or deep learning model or neural networks model. The weightages are determined from ranks, weights for each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction. Weights are assigned based on ranks. The ranks are the values associated with each of the one or more vehicle parameters and the one or more powertrain parameters assigned according to the dependency of the parameters in energy consumption. The ranking techniques are used after regression model to determine the weightages associated with each of the one or more vehicle parameters and the one or more powertrain parameters. Ranking techniques can be permutation feature importance ranking, regression feature importance raking, Shapley algorithm and like. An example of determining the weightages is as follows. If ??1,??2,??3…,???? are n variables, herein ??1,??2,??3…,???? indicates the one or more vehicle parameters and one or more powertrain parameters in the present invention, y is the dependent variable then regression methods establish relation between these input and output variables as function f;

?? = f(??1,??2,??3…,????)

To understand, let’s assume there is linear relationship between input and output then it can be expanded as:

?? = ??1* ??1+ ??2*??2+??3*??3+?+????*????

Here ??1, w2, ??3…,???? are weightages respects to ??1, ??2, ??3…, ???? variables which can be extracted from relation. Further, feature importance ranking technique are applied on the developed regression model to derive the weightages of each individual parameter. These updated weightages are normalized in post processing and transferred to TCU (103) for further processing of weighted summation. As all the computation or model training to derive thresholds and weightages, is cloud server based, so it is termed as cloud computing approach.

At step (303), calculating a driving score of the vehicle based on the determined thresholds and the weightages using one or more computing models. The one or more computing model is one of an edge computing and/or a cloud computing. The driving score is derived by calculating the weighted summation of individual scores for each of the vehicle parameters and powertrain parameters. The updated thresholds and weightages are received by TCU (103) of on-field vehicle and it starts determining threshold zone for each of parameter according to acquired real time field data and scores for each of parameters respectively. Then weighted summation of individual scores for each of parameter is calculated to derive overall driving score. For example, if ??1, ??2, ??3…, ???? are individual score for n parameters and ??1, ??2, ??3…,???? are corresponding weightages then overall driving score can be defined as

Driving score = ?_(i=1)^n¦w_i * s_i
.
As all the real time computation to derive overall driving score is happening in TCU (103), which is acting as media, so it is termed as edge computing.

At step (304), indicating driving performance of the vehicle which is derived based on the overall driving score of the EV (101) to user of the EV (101). Indicating the driving performance includes displaying the overall driving score on to one of the instrument cluster and driving unit of the EV (101). Further, indicating the driving performance includes transmitting the overall driving score to an electronic unit associated with the EV (101). The overall driving score can be displayed on display unit like vehicle cluster, infotainment system or customer App.

Fig. 4 illustrates an artificial intelligence model for determining the threshold and the weightages, in accordance with some embodiments of the present disclosure. Firstly, the one or more vehicle parameters and the one or more powertrain parameters are received by the ECUs (102). Further, these one or more vehicle parameters and one or more powertrain parameters are obtained by the TCU (103) from the ECUs (102). The TCU (103) communicates the one or more vehicle parameters and the one or more powertrain parameters to the cloud server (104) for determining the thresholds and the weightages. The one or more artificial intelligence (AI) model is one of a machine learning (ML) or a deep neural network (DNN). The one or more AI models are trained with a big data collected by one or more training vehicles, tested at different regions and conditions. The big data may be from those specific region vehicles, named training vehicles to train the model region-wise. There are two phases in model training, threshold derivation and weightage derivation. The threshold derivation to get scores for each of the one or more vehicle parameters and one or more powertrain parameters and weightage derivation to perform weighted summation for overall driving score. To derive individual score for each of the one or more vehicle parameters and one or more powertrain parameters, thresholds may be attained using machine learning unsupervised clustering method, wherein the pre-processed data is provided as input to machine learning clustering model to derive thresholds using clustering algorithms like K-means, DBSCAN, GMM, Fuzzy K-mean and the like. The weightages are determined from a ranks and weights for each of the one or more vehicle parameters and the one or more powertrain parameters to optimize vehicle range with targeting drivability and to minimize energy consumption in traction. In model training process, the pre-processed data is provided as input to machine learning regression model to establish correlation between energy consumption as output and all considered input parameters. Decision tree, random forest, gradient boosting, extreme gradient boosting, and the like algorithms may be used in regression methods or deep learning methods or neural networks. These finalized or updated thresholds and weightages will be transferred to TCU (103) through wireless communication for further processing. Acquired real time data to derive individual score and overall driving score will be processed by TCU (103) with the help of cloud computed threshold & weightage as edge computing.

Fig. 5a depicts an exemplary display unit for indicating a driving performance based on driving score of an EV (101), in accordance with some embodiments of the present disclosure. The overall driving score along with individual parameter scores can be displayed on display unit like vehicle cluster, driving unit, infotainment system or customer App. In an embodiment, the overall driving score value is displayed by indicating the individual parameter values which helps in evaluating driving performance of the EV (101) user/ customer. In an embodiment, the driving performance may be indicated via audio, displaying driving score value and other parameters values which add value to the driving score, alert message, and the like. In an embodiment, indicating the driving performance includes transmitting the overall driving score to an electronic unit associated with the EV (101). For example, EV is driven at speed 25kmph, acceleration of 10m/sec2 and traction efficiency of 20% which leads to the overall driving score value of 4.5, out of 10 which indicates the driving performance is not good and alerts the driver/user with alert message “Please drive in recommended speed limit” to ensure better driving patterns and to encourage safe driving practices.

Fig. 5b depicts an exemplary display unit for indicating a driving performance based on ideal driving score of an EV (101), in accordance with some embodiments of the present disclosure. The overall driving score along with individual driving scores associated with each of the parameters are displayed on a display unit like vehicle cluster, driving unit, infotainment system or customer App. In an embodiment, the overall driving score along with individual scores are displayed by indicating the individual parameter values which helps in evaluating driving performance of the EV (101). In an embodiment, the driving performance can be indicated with audio, or displaying the driving score value and other parameters values which add value to the driving score, or as an alert message, and the like. In an embodiment, indicating the driving performance includes transmitting the overall driving score to an electronic unit associated with the EV (101). For example, the individual parameter scores for braking parameter is 4, regeneration fraction is 8, speed parameter is 6, idle time is 6, acceleration parameter is 4.5 and driving duration is 5 can be indicated on the display unit. Considering all these individual scores overall driving score is calculated and displayed as 7.5, which indicates the driving performance is good and alerts the driver/user as “Maintain Same Speed”. The driving performance of each ride, for each day, for every week, for every month may be indicated on the display unit for historical performance analysis of the EV.

The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise

The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise.

A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

When a single device or article is described herein, it may be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it may be readily apparent that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices, which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.

The illustrated operations of Fig. 3 show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified, or removed. Moreover, steps may be added to the above-described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.

Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is, therefore, intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

While various aspects and embodiments have been disclosed herein, other aspects and embodiments may be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

The present disclosure provides method and system for determining driving score of an EV user by considering electric vehicle powertrain’s response with driver’s action which makes the driving score more realistic with considering customized requirement for electric vehicle.
The present disclosure discloses determining and updating thresholds and weightages based on region-wise field data makes driving score more relevant and realistic to customer.
The present disclosure provides intelligent updating of threshold and weightage is unique characteristic of proposed solution which will condense biasedness in the solution.
Practice of efficient driving through driving score will provide better control in driving pattern, improving practical range and reducing range anxiety. Smooth driving will reduce powertrain fatigue hence improving durability of powertrain and reducing maintenance cost.
Driving score encourage safe driving practices by avoiding harsh driving conditions, which leads to reduction in road accidents.

REFERRAL NUMERALS:

Reference number Description
101 Electric Vehicle
102 ECUs
103 TCU
104 Cloud server
105 Display unit
201 I/O interface
202 Memory
203 Processor
204 Modules
205 Communication Module
206 Obtaining Module
207 Computation Module
208 Auxiliary Module