DESC:DRIVING DATA-BASED FUEL ECONOMY INSIGHTS FOR VEHICLES
DESCRIPTION
Technical Field
[001] This disclosure relates generally to vehicle fleet management, and more particularly to method and system for providing fuel economy insights for vehicles.
Background
[002] Fuel efficiency (or fuel economy) is an important factor related to vehicle performance, driven by both environmental concerns and economic considerations. Typically in a vehicle fleet, a plurality of vehicles may be deployed (e.g., tens or hundreds of vehicles). Varying fuel economy for similar vehicles (i.e., identical vehicles or vehicles in a same vehicle category) operating under similar running conditions may cause confusion to stakeholders, such as owner of the vehicle fleet.
[003] Furthermore, the stakeholders have limited information as to the performance of the plurality of vehicles and may fail to determine strategies to improve the fuel economy of the plurality of vehicles. Black box models (such as traditional Artificial Intelligence (AI) or Machine Learning (ML)-based models) may provide values corresponding to the fuel economy of the vehicles. However, such models lack explainability, and therefore, fail to provide credible analysis. There is, therefore, a need in the present state of art for techniques to reliably provide fuel economy insights for the plurality of vehicles.
SUMMARY
[004] In one embodiment, a method for providing fuel economy insights of vehicles is disclosed. In one example, for a vehicle for a predefined time interval, the method may include receiving a set of driving parameters from the vehicle. The method may further include determining a set of driving features based on the set of driving parameters. Each of the set of driving features may be derived from one or more driving parameters. The method may further include estimating, through a regression model, a fuel economy value for the vehicle based on the set of driving features. The method may further include generating fuel economy insights corresponding to the vehicle based on the fuel economy value using the regression model. The fuel economy insights may include adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications.
[005] In one embodiment, a system for providing fuel economy insights of vehicles may be disclosed. In one example, the system may include a processor and a computer-readable medium communicatively coupled to the processor. The computer-readable medium may store processor-executable instructions, which, on execution, may cause the processor to, for a vehicle for a predefined time interval, receive a set of driving parameters from the vehicle. The processor-executable instructions, on execution, may further cause the processor to determine a set of driving features based on the set of driving parameters. Each of the set of driving features may be derived from one or more driving parameters. The processor-executable instructions, on execution, may further cause the processor to estimate, through a regression model, a fuel economy value for the vehicle based on the set of driving features. The processor-executable instructions, on execution, may further cause the processor to generate fuel economy insights corresponding to the vehicle based on the fuel economy value using the regression model. The fuel economy insights may include adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications.
[006] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
BRIEF DESCRIPTION OF THE DRAWINGS
[007] 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.
[008] FIG. 1 illustrates a functional block diagram of an exemplary system for providing fuel economy insights of vehicles, in accordance with some embodiments.
[009] FIG. 2 illustrates a flow diagram of an exemplary process for providing fuel economy insights of vehicles, in accordance with some embodiments.
[010] FIG. 3 illustrates a flow diagram of an exemplary process for determining a first feature of the set of driving features, in accordance with some embodiments.
[011] FIG. 4 illustrates a flow diagram of an exemplary process for determining a second feature of the set of driving features, in accordance with some embodiments.
[012] FIG. 5 illustrates exemplary fuel economy insights corresponding to accelerator pedal position driving feature for a vehicle, in accordance with an embodiment.
[013] FIG. 6 illustrates exemplary fuel economy insights corresponding to vehicle speed driving feature for a vehicle, in accordance with an embodiment.
[014] FIG. 7 illustrates exemplary fuel economy insights corresponding to engine performance bias mode and engine speed driving features for a vehicle, in accordance with an embodiment.
[015] FIG. 8 illustrates exemplary fuel economy insights corresponding to gear shift adherence and idling driving features for a vehicle, in accordance with an embodiment.
[016] FIG. 9 is a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.
DETAILED DESCRIPTION
[017] Exemplary embodiments are described with reference to the accompanying drawings. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.
[018] Referring now to FIG. 1, a functional block diagram of an exemplary system 100 for providing fuel economy insights of vehicles is illustrated, in accordance with some embodiments. The system 100 may be a part of a vehicle 102 or may be remote from the vehicle 102 (i.e., cloud-based system). The system 100 may include a computing device 104 (for example, server, desktop, laptop, notebook, netbook, tablet, smartphone, mobile phone, or any other computing device), in accordance with some embodiments of the present disclosure. By way of an example, the vehicle 102 may be a passenger vehicle (such as a car,) or a commercial vehicle (such as a tipper, a truck, a trailer, a container, a tractor, a transit mixer, an ambulance, a fire brigade, etc.). In an embodiment, the vehicle 102 may be a part of a vehicle fleet. The computing device 102 may provide fuel economy insights of vehicles in the vehicle fleet to, for example, an owner of the vehicle fleet.
[019] The system 100 may further include a display 106. The system 100 may interact with a user via a user interface 108 accessible via the display 106. The computing device 104 may interact with the vehicle 102 over a communication network 110 for sending or receiving various data. The system 100 may also include one or more external devices (not shown). In some embodiments, the computing device 104 may also interact with the one or more external devices over the communication network 110 for sending or receiving various data. The external devices may include, but may not be limited to, a remote server, a digital device, or another computing system.
[020] In some embodiments, the computing device 104 may include one or more processors 112 and a memory 114. The memory 114 may store instructions that, when executed by the one or more processors 112, cause the one or more processors 112 to provide fuel economy insights of vehicles, in accordance with aspects of the present disclosure. The memory 114 may also store various data (for example, driving parameters, driving features, regression model data, fuel economy value, benchmark fuel economy value, penalization score, fuel economy insights, and the like) that may be captured, processed, and/or required by the system 100. The memory 114 may include a feature determining module 116, a fuel economy estimating module 118, an insights generating module 120, and a database 122. The fuel economy estimating module 118 may include a regression model 124. Alternatively, the fuel economy estimating module 118 may retrieve the regression model 124 from the database 122.
[021] For the vehicle 102 for a predefined time interval (e.g., one hour, one day, one week, etc.), the feature determining module 116 may receive a set of driving parameters from the vehicle 102. The vehicle 102 may include one or more Electronic Control Units (ECUs) 126 and a plurality of sensors 128. The ECUs 126 may capture the set of driving parameters from the plurality of sensors 128 over a Controller Area Network (CAN). Additionally, ECUs 126 may capture the set of driving parameters telemetry and event data files corresponding to the vehicle. The feature determining module 116 may capture the set of driving parameters from the ECU 126 of the vehicle 102. By way of an example, the plurality of sensors 128 may include, but may not be limited to, a fuel level sensor, a fuel pressure sensor, a vehicle speed sensor, an engine speed sensor, an engine oil sensor, a temperature sensor, a transmission shifting sensor, a brake pedal sensor, a Throttle Position Sensor (TPS), a tire pressure sensor, an airbag sensor, or the like.
[022] Further, the feature determining module 116 may determine a set of driving features based on the set of driving parameters. Each of the set of driving features may be derived from one or more driving parameters. To determine a first driving feature (an exemplary feature from the set of driving features), the feature determining module 116 may capture values of the first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval. Further, the feature determining module 116 may count a number of timestamps for which a value of the driving parameter was in a first range of values. The value of the first driving feature is the counted number of timestamps. By way of an example, the first driving parameter may be accelerator pedal position. The first driving feature may be accelerator pedal position within a range of A% to B% (i.e., the first range of values is A% to B%). Thus, the feature determining module 116 may capture the accelerator pedal position at each of the plurality of time stamps. At each time stamp where the accelerator pedal position is between A% to B%, the feature determining module 116 may increment a count of time stamps for the first driving feature (i.e., accelerator pedal position within the range of A% to B%) by one. Upon completion of the predefined interval, the feature determining module 116 may output the value of the first driving feature as the number of time stamps counted for the first driving feature.
[023] As another example, to determine a second driving feature (another exemplary feature from the set of driving features), the feature determining module 116 may capture values of a first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval. Additionally and simultaneously, the feature determining module 116 may capture values of a second driving parameter of the set of driving parameters at the plurality of time stamps. Further, the feature determining module 116 may count a number of time stamps for which a value of the first driving parameter was in a first range of values and the value of the second driving parameter was in a second range of values. The value of the second driving feature may be the counted number of timestamps. By way of an example, the first driving parameter may be torque and the second driving parameter may be engine speed. The second driving feature may be of the torque in a range of A Nm to B Nm (i.e., the first predefined range is A Nm to B Nm) and the engine speed in a range of A’ RPM to B’ RPM (i.e., the second predefined range is A’ RPM to B’ RPM). Thus, the feature determining module 116 may capture the torque and the engine speed at each of the plurality of time stamps. At each time stamp where the torque is between A Nm to B Nm and the engine speed is also between A’ RPM to B’ RPM, the feature determining module 116 may increment a count of time stamps for the second driving feature (i.e., the torque in the range of A Nm to B Nm and the engine speed in the range of A’ RPM to B’ RPM) by one. Upon completion of the predefined interval, the feature determining module 116 may output the value of the second driving feature as the number of time stamps counted for the second driving feature.
[024] Once the set of driving features is determined, the fuel economy estimating module 118 may estimate, through the regression model 124, a fuel economy value for the vehicle 102 based on the set of driving features. The regression model 124 indicates a dependency of the fuel economy value on the each of the set of driving features. For example, the regression model 124 may include a set of coefficients corresponding to the set of driving features. The set of coefficients may be predetermined and optimized by training the regression model 124 using data from a plurality of vehicles within a vehicle category of the vehicle 102. In an embodiment, the vehicle category may be based on predefined criteria (such as a tonnage of the vehicle 102, type of fuel (i.e., diesel, CNG, etc.), type of gearbox, etc.). For example, the vehicle category may be one of a Light Commercial Vehicle (LCV), an Intermediate Commercial Vehicle (ICV), or a Heavy Commercial Vehicle (HCV). Alternatively, the vehicle category may be one of 30 tonnage vehicles, 40 tonnage vehicles, 50 tonnage vehicles, etc. It should be noted that the regression model 124 may be uniquely trained for each vehicle category based on the data collected from each of the plurality of vehicles in that vehicle category. In an embodiment, the regression model 124 is formed based on the data collected from 4.92 lakhs vehicles.
[025] To estimate the fuel economy value, the fuel economy estimating module 118 may substitute the value of each of the set of driving features in the regression model 124. The fuel economy estimating module 118 may then output the fuel economy value of the vehicle 102 for the predefined time interval. The fuel economy value may be a numerical value, for example, in kilometer per liter (km/L) units.
[026] In an embodiment, the regression model 124 may be a linear regression model that may estimate the fuel economy value with a low Mean Absolute Percentage Error (MAPE) (e.g., about 6% to about 13%). By way of an example, the regression model may be represented as equation (1).
FE = Const + Acceleratorpedalposition_A-B*X1 + Acceleratorpedalposition_B-C*X2 +
Acceleratorpedalposition_C-D*X3 + Acceleratorpedalposition_D-E*X4 +
Acceleratorpedalposition_E-F*X5 +
DieselParticulateFilterActiveRegenerationStatus_1*X6 +
Down_Hill_Odometer_percent*X7 + EnginePerformanceBiasLevel_0*X8 +
Flat_Stretch_Odometer_percent*X9 + GSA*X10 +
Idling_Percent_Duration*X11 + Inhibitor_Percent_Duration*X12 +
Neutral_Running_Percent_Duration*X13 + Night_Drive_Duration*X14 +
Torque_A’-B’_RPM_A’’-B’’*X15 + Torque_B-C’_RPM_A’’-B’*X16 +
Torque_C’-D’_RPM_A’’-B’’*X17 + Torque_D-E’_RPM_A’’-B’*X18 +
Torque_E’-F’_RPM_A’’-B’’*X19 + Torque_F’-G’_RPM_A’’-B’’*X20 +
Torque_G’-H’_RPM_A’’-B’’*X21 + TransCurrentGear_9_0*X22 +
WheelBaseVehicleSpeed_A’’’-B’’’*X23 + WheelBaseVehicleSpeed_B’’’-
C’’’*X24 + WheelBaseVehicleSpeed_C’’’-D’’’_RPM_A’’-B’’*X25 +
WheelBaseVehicleSpeed_D’’’-E’’’*X26 + WheelBaseVehicleSpeed_E’’’-
F’’’*X27 + green_band*X28 (1)
where FE is the fuel economy value,
Const is a predetermined constant, and
X1, X2, …, X28 are the set of coefficients for each of the set of driving features.
[027] Once the fuel economy value is estimated, the insights generating module 120 may generate fuel economy insights corresponding to the vehicle 102 based on the fuel economy value using the regression model 124. The fuel economy insights may include adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications. The adjustment recommendations may correspond to recommendations for changing the one or more of the set of driving parameters to improve the fuel economy value of the vehicle 102. The indications of the quantitative improvement in the fuel economy value may be an estimated change in the fuel economy value when the adjustment recommendations to the one or more of the set of driving parameters are successfully implemented in the vehicle 102.
[028] The fuel economy insights may also be dynamically derived from the regression model 124. In an embodiment, a user (for example, the owner of the vehicle fleet) may provide a value of a driving feature to directly check an impact of the value on the estimated fuel economy value. By way of an example, for a current value of the accelerator pedal position within a range of a to b, the user may check a change in the fuel economy value if the current value is increased or decreased. Advantageously, such actionable and meaningful fuel economy insights are obtained due to the regression model 124. Traditional Blackbox models (such as Artificial Neural Networks (ANNs), or other Artificial Intelligence (AI) models) may fail to justifiably provide such fuel economy insights. This is further explained in detail in conjunction with FIGS. 5-8.
[029] In some embodiments, the insights generating module 120 may compare the fuel economy value with a benchmark fuel economy value of the vehicle category associated with the vehicle 102. The benchmark fuel economy value of the vehicle category may be stored in the database 122. Further, the insights generating module 120 may calculate a driver score based on the comparison and a penalization score (PS). The PS may be based on one or more penalization events identified from the set of driving parameters. By way of an example, the one or more penalization events may include, but may not limited to, harsh acceleration, harsh braking, rash turning, overspeeding, etc.
[030] Thus, the driver score may be indicative of a performance of the vehicle 102. Through the driver score, the owner of the vehicle fleet may manage allocation of drivers to the vehicle 102 or other vehicles in the vehicle fleet. For example, if the fuel economy value or the driver score decreases or fails to improve for a long period of time, the owner may designate a different driver to the vehicle 102. In an embodiment, output of the comparison may be a percentage or a ratio of the fuel economy value with respect to the benchmark fuel economy value. The PS may then be subtracted from the output of the comparison to obtain the driver score. Alternatively, the driver score may be determined in form of a rating (e.g., a rating out 5 or a rating out of 10) relative to the benchmark rating of the vehicle category.
[031] By way of an example, Table 1 shows calculation of the driver score based on the comparison and the penalization score, in accordance with an embodiment of the present disclosure.
Table 1: An exemplary calculation of the driver score.
Estimated Fuel Economy 5
Benchmark Fuel Economy (Computed based on fuel economy of a plurality of vehicles of similar vehicle category) 6.5
Base score (BS) Estimated / benchmark
= 76.92 (Out of 100)

Penalization Events Actual Max possible value Proportion (Actual/Max possible value) Max Impact on FE Applicable Impact (Proportion * max impact)
Harsh acceleration 5 20 25% 2% 0.50%
Over Speeding 3 16 19% 2% 0.38%
Harsh Turning 0 5 0% 2% 0.00%
OBD 0 1 0% 1% 0.00%
Air filter clogging 1 3 33% 1% 0.33%
Regeneration 0 1 0% 1% 0.00%
Total PS= 1.21%

Final Score = (BS – PS) 76.92 - 1.21% of 76.92 = 75.99
[032] In an embodiment, the insights generating module 120 may generate the fuel economy insights corresponding to each vehicle of the vehicle fleet. Further, the insights generating module 120 may display the fuel economy value and the fuel economy insights on a dashboard. The dashboard may be accessed by the owner of the vehicle fleet through a user device. In some embodiments, the dashboard may be accessible to the owner upon a successful login to a user account associated with the owner.
[033] In some embodiments, the owner of the vehicle fleet may store a driver record corresponding to each of a plurality of drivers employed by the owner. The driver record may include details of the vehicle operated by the driver for each day. Through the driver record, the driver score of the vehicle operated by the driver may be mapped with the driver. Thus, a performance of the driver may be evaluated. Alternatively, the driver record may include identification details corresponding to the driver, for example, biometric details, Radio Frequency Identifier (RFID) tag, etc. Upon entering the vehicle, the driver may be required to enter the identification details prior to initiating the vehicle operations. Thus, the driver record for the driver may be automatically maintained and the driver score may be determined for each of the plurality of drivers.
[034] It should be noted that all such aforementioned modules 116 – 120 and the database 122 may be represented as a single module or a combination of different modules and. Further, as will be appreciated by those skilled in the art, each of the modules 116 – 122 may reside, in whole or in parts, on one device or multiple devices in communication with each other. In some embodiments, each of the modules 116 – 120 and the database 122 may be implemented as dedicated hardware circuit comprising custom application-specific integrated circuit (ASIC) or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. Each of the modules 116 – 120 and the database 122 may also be implemented in a programmable hardware device such as a field programmable gate array (FPGA), programmable array logic, programmable logic device, and so forth. Alternatively, each of the modules 116 – 120 and the database 122 may be implemented in software for execution by various types of processors (e.g., the one or more processors 112). An identified module of executable code may, for instance, include one or more physical or logical blocks of computer instructions, which may, for instance, be organized as an object, procedure, function, or other construct. Nevertheless, the executables of an identified module or component need not be physically located together, but may include disparate instructions stored in different locations which, when joined logically together, include the module and achieve the stated purpose of the module. Indeed, a module of executable code could be a single instruction, or many instructions, and may even be distributed over several different code segments, among different applications, and across several memory devices.
[035] As will be appreciated by one skilled in the art, a variety of processes may be employed for providing fuel economy insights of vehicles. For example, the exemplary system 100 and the associated computing device 104 may provide fuel economy insights of vehicles by the processes discussed herein. In particular, as will be appreciated by those of ordinary skill in the art, control logic and/or automated routines for performing the techniques and steps described herein may be implemented by the system 100 and the computing device 104 either by hardware, software, or combinations of hardware and software. For example, suitable code may be accessed and executed by the one or more processors 112 on the system 100 to perform some or all of the techniques described herein. Similarly, application specific integrated circuits (ASICs) configured to perform some or all of the processes described herein may be included in the one or more processors 112 on the system 100.
[036] Referring now to FIG. 2, an exemplary process 200 for providing fuel economy insights of vehicles is depicted via a flowchart, in accordance with some embodiments. In an embodiment, the process 200 may be implemented by the computing device 104 of the system 100. For a vehicle (such as the vehicle 102) for a predefined time interval, the process 200 includes receiving, by a feature determining module (such as the feature determining module 116), a set of driving parameters from the vehicle, at step 202. It should be noted that the vehicle may be a part of a vehicle fleet. By way of an example, the set of driving parameters may include at least one of accelerator pedal position, vehicle speed, engine performance bias, current gear, engine speed, torque, brake switch pressing, and clutch switch pressing. By way of an example, the set of driving features may include at least one of accelerator pedal position within a set of predefined ranges, combinations of the torque in a first predefined range and the engine speed in a second predefined range, diesel particulate filter active regeneration status, downhill odometer percent, engine performance bias level, flat stretch odometer percent, gear shift adherence, idling percent duration, inhibitor percent duration, neutral running percent duration, night drive duration, optimal trans current gear, wheel base vehicle speed, and the engine speed in green band.
[037] Further, the process 200 includes determining, by the feature determining module, a set of driving features based on the set of driving parameters, at step 204. Each of the set of driving features is derived from one or more driving parameters.
[038] Further, the process 200 includes estimating, by a fuel economy estimating module (such as the fuel economy estimating module 118) through a regression model, a fuel economy value for the vehicle based on the set of driving features, at step 206. The regression model indicates a dependency of the fuel economy value on each of the set of driving features. To estimate the fuel economy value for the vehicle, a value of each of the set of driving features may be substituted in the regression model.
[039] Further, the process 200 includes generating, by an insights generating module (such as the insights generating module 120), fuel economy insights corresponding to the vehicle based on the fuel economy value using the regression model, at step 208. The fuel economy insights include adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications.
[040] In some embodiments, the step 208 may include steps 210 and 212. The process 200 includes comparing, by the insights generating module, the fuel economy value with a benchmark fuel economy value of a vehicle category associated with the vehicle, at step 210. Further, the process 200 includes calculating, by the insights generating module, a driver score based on the comparison and a penalization score, at step 212. The penalization score is based on one or more penalization events identified from the set of driving parameters.
[041] In some embodiments, the process 200 may include generating, by the insights generating module, fuel economy insights corresponding to each vehicle of the vehicle fleet. Further, the process 200 may include displaying, by the insights generating module, the fuel economy value and the fuel economy insights on a dashboard. In an embodiment, the dashboard may be presented on a user device operated by an owner or administrator of the vehicle fleet. Alternatively, the dashboard may be presented on a display of the vehicle.
[042] Referring now to FIG. 3, an exemplary process 300 for determining a first feature of the set of driving features is depicted via a flow chart, in accordance with some embodiments. In an embodiment, the process 300 may be implemented by the computing device 104 of the system 100. The first feature may be derived from a first driving parameter. To determine the first feature, the process 300 may include capturing, by a feature determining module (such as the feature determining module 116), values of a first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval, at step 302. Further, the process 300 may include counting, by the feature determining module, a number of timestamps for which a value of the driving parameter was in a first range of values, at step 304. The value of the first feature is the counted number of timestamps.
[043] Referring now to FIG. 4, an exemplary process 400 for determining a second feature of the set of driving features is depicted via a flow chart, in accordance with some embodiments. In an embodiment, the process 400 may be implemented by the computing device 104 of the system 100. The second feature may be derived from a first driving parameter and a second driving parameter. To determine the second feature, the process 400 may include capturing, by a feature determining module (such as the feature determining module 116), values of a first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval, at step 402. Further, the process 400 may include capturing, by the feature determining module, values of a second driving parameter of the set of driving parameters at the plurality of time stamps, at step 404. Further, the process 400 counting, by the feature determining module, a number of time stamps for which a value of the first driving parameter was in a first range of values and the value of the second driving parameter was in a second range of values, at step 406. The value of second feature is the counted number of timestamps.
[044] Referring now to FIG. 5, exemplary fuel economy insights 500 corresponding to accelerator pedal position driving parameter for a vehicle (such as the vehicle 102) are illustrated, in accordance with an embodiment. The fuel economy insights 500 include a first section 502 corresponding to actual acceleration pedal position data and a second section 504 corresponding to benchmark acceleration pedal position data. An actual fuel economy value calculated by the fuel economy estimating module 118 through the regression model 124 is 3.84 km/L. An expected fuel economy value, which may be achieved by following the provided recommendations, is 4.28 km/L (a fuel economy improvement of 11.57% over the actual fuel economy value).
[045] As has been discussed in detail in conjunction with FIG. 1, the insights generating module 120 may generate the fuel economy insights based on the fuel economy value and the set of driving features using the regression model 124. The fuel economy insights may include adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications. Thus, upon achieving the quantitative improvement in the actual fuel economy value of 3.84 by modifying the one or more of the set of driving parameters in the vehicle, the expected fuel economy value of 4.28 km/L may be obtained.
[046] The first section 502 of the fuel economy insights 500 presents an actual accelerator pedal contribution (i.e., -1.99 km/L) to the actual fuel economy value. The actual accelerator pedal contribution may correspond to a current impact of the accelerator pedal position on the actual fuel economy value. Additionally, the first section 502 includes a first graph showing distribution of the accelerator pedal position in a set of buckets (i.e., predefined range of values) for a predefined time interval (i.e., a day). The first graph is a bar chart that represents a percentage of duration during the day of the accelerator pedal position in each of the set of buckets. For example, 10% of the plurality of time stamps in the day were counted by the feature determining module 116 where the value of the accelerator pedal position was in a range of C% to D%.
[047] The first graph also represents an adjustment recommendation to modify the accelerator pedal position for an incremental contribution (i.e., quantitative improvement of 0.22 km/L) to the actual fuel economy value. The adjustment recommendation indicates increasing the duration of the accelerator pedal position between C% to D% from 10% to 21%.
[048] The second section 504 of the fuel economy insights 500 presents a benchmark accelerator pedal position contribution (i.e., -1.77 km/L) to the benchmark fuel economy value (or the expected fuel economy value). The benchmark accelerator pedal position may be obtained based on accelerator pedal position values of several vehicles of the same vehicle category as the vehicle 102. In an example, the benchmark value may be 75th percentile value of the monitored vehicles.
[049] The benchmark accelerator pedal position contribution may correspond to an expected impact of the accelerator pedal position on the expected fuel economy value. Thus, the benchmark accelerator pedal position contribution is obtained upon adding the incremental accelerator pedal contribution (i.e., 0.22 km/L) to the actual accelerator pedal position contribution (i.e., -1.99 km/L). Additionally, the second section 504 includes a second graph showing distribution of the accelerator pedal position in the set of buckets (i.e., predefined range of values) for a predefined time interval of a day, upon implementing the adjustment recommendation. The second graph is a bar chart that represents a benchmark percentage of duration during the day of the accelerator pedal position in each of the set of buckets.
[050] For example, 21% of the plurality of time stamps in the day may be counted by the feature determining module 116 where the value of the accelerator pedal position is in a range of C% to D%. It is worth noting that 21% was also the adjustment recommendation shown in the first graph in the first section 502. Additionally, the second graph shows a relative reduction in the durations corresponding to the accelerator pedal position range E% to F% (i.e., 28%), the accelerator pedal position range F% to G% (i.e., 2%), and the accelerator pedal position range G% to H% (i.e., 2%) in comparison with the corresponding durations of the first graph (i.e., 33%, 6%, and 4%, respectively).
[051] In an embodiment, the adjustment recommendation may be presented in a natural language text format, for example, “increase driving percentage duration between about C% pedal to less than D% pedal from 10% to 21% and the driver can spend maximum time in this position based on driving condition to increase the fuel economy value.”
[052] Referring now to FIG. 6, exemplary fuel economy insights 600 corresponding to vehicle speed driving parameter for a vehicle (such as the vehicle 102) are illustrated, in accordance with an embodiment. The fuel economy insights 600 include a first section 602 corresponding to actual vehicle speed data and a second section 604 corresponding to benchmark vehicle speed data. An actual fuel economy value calculated by the fuel economy estimating module 118 through the regression model 124 is 3.84 km/L. An expected fuel economy value is 4.28 km/L (a fuel economy improvement of 11.57% over the actual fuel economy value).
[053] The first section 602 of the fuel economy insights 600 presents an actual vehicle speed contribution (i.e., 2.80 km/L) to the actual fuel economy value. The actual vehicle speed contribution may correspond to a current impact of the vehicle speed on the actual fuel economy value. Additionally, the first section 602 includes a first graph showing distribution of the vehicle speed in a set of buckets (i.e., predefined range of values) for a predefined time interval (i.e., a day). The first graph is a bar chart that represents a percentage of duration during the day of the vehicle speed in each of the set of buckets. For example, 23% of the plurality of time stamps in the day were counted by the feature determining module 116 where the value of the vehicle speed was in a range of C km/h to D km/h.
[054] The first graph also represents an adjustment recommendation to modify the vehicle speed for an incremental contribution (i.e., quantitative improvement of 0.06 km/L) to the actual fuel economy value. The adjustment recommendation indicates increasing the duration of the vehicle speed between C km/h to D km/h from 23% to 35%.
[055] The second section 604 of the fuel economy insights 600 presents a benchmark vehicle speed contribution (i.e., 2.85 km/L) to the benchmark fuel economy value (or the expected fuel economy value). The benchmark vehicle speed may be obtained based on vehicle speed values of several vehicles of the same vehicle category as the vehicle 102. In an example, the benchmark value may be 75th percentile value of the monitored vehicles. The benchmark vehicle speed contribution may correspond to an expected impact of the vehicle speed on the expected fuel economy value. Thus, the benchmark vehicle speed contribution is obtained upon adding the incremental vehicle speed contribution (i.e., 0.06 km/L) to the actual vehicle speed contribution (i.e., 2.80 km/L). Additionally, the second section 604 includes a second graph showing distribution of the vehicle speed in the set of buckets (i.e., predefined range of values) for the predefined time interval of the day, upon implementing the adjustment recommendation. The second graph is a bar chart that represents a benchmark percentage of duration during the day of the vehicle speed in each of the set of buckets.
[056] For example, 35% of the plurality of time stamps in the day may be counted by the feature determining module 116 where the value of the vehicle speed is in a range of C km/h to D km/h. It is worth noting that 35% was also the adjustment recommendation shown in the first graph in the first section 602. Additionally, the second graph shows a relative reduction in the durations corresponding to the vehicle speed range D km/h to E km/h (i.e., 4%) and the vehicle speed range E km/h to F km/h (i.e., 1%) in comparison with the corresponding durations of the first graph (i.e., 16% and 33%, respectively).
[057] In an embodiment, the adjustment recommendation may be presented in a natural language text format, for example, “Try to increase the percentage duration of speed between C -D km/h in a day from 23% to 35%, and reduce the duration for which the vehicle is driven above D km/h, and the driver can spend maximum time in this speed based on driving condition to increase the fuel economy value.”
[058] Referring now to FIG. 7, exemplary fuel economy insights 700 corresponding to engine performance bias mode and engine speed driving features for a vehicle (such as the vehicle 102) are illustrated, in accordance with an embodiment. The fuel economy insights 700 include a first section 702 and a second section 704. The first section 702 includes a first sub-section 702A corresponding to actual engine performance bias mode data and a second sub-section 702B corresponding to actual engine speed data. The second section 704 includes a third sub-section 704A corresponding to benchmark engine performance bias mode data and a fourth sub-section 704B corresponding to benchmark engine speed data. An actual fuel economy value calculated by the fuel economy estimating module 118 through the regression model 124 is 3.84 km/L. An expected fuel economy value is 4.28 km/L (a fuel economy improvement of 11.57% over the actual fuel economy value).
[059] The first sub-section 702A of the fuel economy insights 700 presents an actual engine performance bias mode (or fuel economy mode) contribution (i.e., - 0.02 km/L) to the actual fuel economy value. The actual engine performance bias mode contribution may correspond to a current impact of the engine performance bias mode on the actual fuel economy value. Additionally, the first sub-section 702A includes a first graph showing distribution of the engine performance bias mode in a set of buckets (i.e., predefined modes (e.g., A mode, B mode, and C mode)) for a predefined time interval (i.e., a day). The first graph is a bar chart that represents a percentage of duration during the day of the engine performance bias mode in each of the set of buckets. For example, 77% of the plurality of time stamps in the day were counted by the feature determining module 116 where the value of the engine performance bias mode was in A mode.
[060] The first graph also represents an adjustment recommendation to modify the engine performance bias mode for an incremental contribution (i.e., quantitative improvement of 0.01 km/L) to the actual fuel economy value. The adjustment recommendation indicates increasing the duration of the A mode engine performance bias mode from 77% to 95%.
[061] Similarly, the second sub-section 702B of the fuel economy insights 700 presents an actual engine speed (in RPM) contribution (i.e., 0.02 km/L) to the actual fuel economy value. The actual engine speed contribution may correspond to a current impact of the engine speed on the actual fuel economy value. Additionally, the second sub-section 702B includes a second graph showing distribution of the engine speed in a set of buckets (i.e., predefined modes (e.g., A’ RPM band, B’ RPM band, and C’ RPM band)) for the predefined time interval (i.e., a day). The second graph is a bar chart that represents a percentage of duration during the day of the engine speed in each of the set of buckets. For example, 73% of the plurality of time stamps in the day were counted by the feature determining module 116 where the value of the engine speed was in B’ RPM band.
[062] The second graph also represents an adjustment recommendation to modify the engine speed for an incremental contribution (i.e., quantitative improvement of 0.00 km/L) to the actual fuel economy value. The adjustment recommendation indicates decreasing the duration of the engine speed in the B’ RPM band from 79% to 73%. However, no change (or negligible change) in the fuel economy value may be observed upon implementing the adjustment recommendation as the engine speed incremental contribution to the fuel economy value is 0.00 km/L. This may also indicate that the vehicle is performing better than or is at par with the benchmark performance with respect to the engine speed.
[063] The third sub-section 704A of the fuel economy insights 700 presents a benchmark engine performance bias mode contribution (i.e., 0.00 km/L) to the benchmark fuel economy value (or the expected fuel economy value). The benchmark engine performance bias mode may be obtained based on engine performance bias mode values of several vehicles of the same vehicle category as the vehicle 102. In an example, the benchmark value may be 75th percentile value of the monitored vehicles. The benchmark engine performance bias mode contribution may correspond to an expected impact of the engine performance bias mode on the expected fuel economy value. Thus, the benchmark engine performance bias mode contribution is obtained upon adding the incremental engine performance bias mode contribution (i.e., 0.01 km/L) to the actual engine performance bias mode contribution (i.e., -0.02 km/L). Additionally, the third sub-section 704A includes a third graph showing distribution of the engine performance bias mode in the set of buckets (i.e., predefined modes) for the predefined time interval, upon implementing the adjustment recommendation. The third graph is a bar chart that represents a benchmark percentage of duration during the day of the engine performance bias mode in each of the set of buckets.
[064] For example, 95% of the plurality of time stamps in the day may be counted by the feature determining module 116 where the value of the engine performance bias mode is in A mode. It is worth noting that 95% was also the adjustment recommendation shown in the first graph in the first sub-section 702A. Additionally, the third graph shows a relative reduction in the durations corresponding to the engine performance bias mode C mode (5%) in comparison with the corresponding durations of the first graph (i.e., 23%).
[065] In an embodiment, the adjustment recommendation may be presented in a natural language text format, for example, “Try to increase the percentage duration of A mode in a day from 77% to 95% and the driver can spend maximum time in this mode based on driving condition to increase the fuel economy value.”
[066] Similarly, the fourth sub-section 704B of the fuel economy insights 700 presents a benchmark engine speed contribution (i.e., 0.02 km/L) to the benchmark fuel economy value (or the expected fuel economy value). The benchmark engine speed may be obtained based on engine speed values of several vehicles of the same vehicle category as the vehicle 102. In an example, the benchmark value may be 75th percentile value of the monitored vehicles. The benchmark engine speed contribution may correspond to an expected impact of the engine speed on the expected fuel economy value. Thus, the benchmark engine speed contribution is obtained upon adding the incremental engine speed contribution (i.e., 0.00 km/L) to the actual engine speed contribution (i.e., -0.02 km/L). Additionally, the fourth sub-section 704B includes a fourth graph showing distribution of the engine speed in the set of buckets (i.e., predefined modes) for the predefined time interval, upon implementing the adjustment recommendation. The fourth graph is a bar chart that represents a benchmark percentage of duration during the day of the engine speed in each of the set of buckets.
[067] For example, 79% of the plurality of time stamps in the day may be counted by the feature determining module 116 where the value of the engine speed is in B’ RPM band. It is worth noting that 79% was also the value of the actual engine speed in the B’ RPM band shown in the second graph in the second sub-section 702B. Additionally, the fourth graph shows no change in the durations corresponding to the engine speed A’ RPM band or the engine speed B’ RPM band in comparison with the corresponding durations of the second graph.
[068] In an embodiment, the adjustment recommendation may be presented in a natural language text format, for example, “You can reduce the percentage duration of B’ RPM band in a day from 79% to 73% without any significant impact on the fuel economy value.”
[069] Referring now to FIG. 8, exemplary fuel economy insights 800 corresponding to gear shift adherence and idling driving features for a vehicle (such as the vehicle 102) are illustrated, in accordance with an embodiment. The fuel economy insights 800 include a first section 802 and a second section 804. The first section 802 includes a first sub-section 802A corresponding to actual gear shift adherence data and a second sub-section 802B corresponding to actual idling data. The second section 804 includes a third sub-section 804A corresponding to benchmark gear shift adherence data and a fourth sub-section 804B corresponding to benchmark idling data. An actual fuel economy value calculated by the fuel economy estimating module 118 through the regression model 124 is 3.84 km/L. An expected fuel economy value is 4.28 km/L (a fuel economy improvement of 11.57% over the actual fuel economy value).
[070] The first sub-section 802A of the fuel economy insights 800 presents an actual gear shift adherence contribution (i.e., 0.05 km/L) to the actual fuel economy value. The actual gear shift adherence contribution may correspond to a current impact of the gear shift adherence on the actual fuel economy value. Additionally, the first sub-section 802A includes a first graph showing duration of the gear shift adherence (i.e., time stamps where the current gear of the vehicle was optimal for the engine speed) for a predefined time interval (i.e., a day). The first graph is a gauge chart that represents a percentage of duration during the day of when the gear shift adherence was optimal. For example, 51% of the plurality of time stamps in the day were counted by the feature determining module 116 where the gear shift adherence was optimal.
[071] The first graph also represents an adjustment recommendation to modify the gear shift adherence duration for an incremental contribution (i.e., quantitative improvement of 0.05 km/L) to the actual fuel economy value. The adjustment recommendation indicates increasing the duration of the gear shift adherence from 51% to 100%.
[072] Similarly, the second sub-section 802B of the fuel economy insights 800 presents an actual idling contribution (i.e., -0.25 km/L) to the actual fuel economy value. The actual idling contribution may correspond to a current impact of the idling on the actual fuel economy value. Additionally, the second sub-section 802B includes a second graph showing duration of the idling for the predefined time interval (i.e., a day). The second graph is a gauge chart that represents a percentage of duration during the day of the idling. For example, 10% of the plurality of time stamps in the day were counted by the feature determining module 116 where the idling of the vehicle was detected.
[073] The second graph also represents an adjustment recommendation to modify the idling duration for an incremental contribution (i.e., quantitative improvement of 0.10 km/L) to the actual fuel economy value. The adjustment recommendation indicates decreasing the idling duration from 10% to 6%.
[074] The third sub-section 804A of the fuel economy insights 800 presents a benchmark gear shift adherence contribution (i.e., 0.10 km/L) to the benchmark fuel economy value (or the expected fuel economy value). The benchmark gear shift adherence may be obtained based on gear shift adherence values of several vehicles of the same vehicle category as the vehicle 102. In an example, the benchmark value may be 75th percentile value of the monitored vehicles. The benchmark gear shift adherence contribution may correspond to an expected impact of the gear shift adherence on the expected fuel economy value. Thus, the benchmark gear shift adherence contribution is obtained upon adding the incremental gear shift adherence contribution (i.e., 0.05 km/L) to the actual gear shift adherence contribution (i.e., 0.05 km/L). Additionally, the third sub-section 804A includes a third graph showing duration of the gear shift adherence for the predefined time interval, upon implementing the adjustment recommendation. The third graph is a gauge chart that represents a benchmark percentage of duration during the day of the gear shift adherence.
[075] For example, 100% of the plurality of time stamps in the day may be counted by the feature determining module 116 where the gear shift adherence is optimal. It is worth noting that 100% was also the adjustment recommendation shown in the first graph in the first sub-section 802A. In an embodiment, the adjustment recommendation may be presented in a natural language text format, for example, “Follow the GSA recommendation in the dashboard. Increase GSA percentage from 51% to 100%.”
[076] Similarly, the fourth sub-section 804B of the fuel economy insights 800 presents a benchmark idling contribution (i.e., -.15 km/L) to the benchmark fuel economy value (or the expected fuel economy value). The benchmark idling may be obtained based on idling values of several vehicles of the same vehicle category as the vehicle 102. In an example, the benchmark value may be 75th percentile value of the monitored vehicles. The benchmark idling contribution may correspond to an expected impact of the idling duration on the expected fuel economy value. Thus, the benchmark idling contribution is obtained upon adding the incremental idling contribution (i.e., 0.10 km/L) to the actual idling contribution (i.e., -0.25 km/L). Additionally, the fourth sub-section 804B includes a fourth graph showing duration of the idling for the predefined time interval, upon implementing the adjustment recommendation. The fourth graph is a gauge chart that represents a benchmark percentage of duration during the day of the idling.
[077] For example, 6% of the plurality of time stamps in the day may be counted by the feature determining module 116 where the idling of the vehicle is detected. It is worth noting that 6% was also the value of the adjustment recommendation shown in the second graph in the second sub-section 802B. In an embodiment, the adjustment recommendation may be presented in a natural language text format, for example, “Try to reduce the percentage duration of idling in a day from 10% to 6% to increase the fuel economy value.”
[078] As will be also appreciated, the above described techniques may take the form of computer or controller implemented processes and apparatuses for practicing those processes. The disclosure can also be embodied in the form of computer program code containing instructions embodied in tangible media, such as floppy diskettes, solid state drives, CD-ROMs, hard drives, or any other computer-readable storage medium, wherein, when the computer program code is loaded into and executed by a computer or controller, the computer becomes an apparatus for practicing the invention. The disclosure may also be embodied in the form of computer program code or signal, for example, whether stored in a storage medium, loaded into and/or executed by a computer or controller, or transmitted over some transmission medium, such as over electrical wiring or cabling, through fiber optics, or via electromagnetic radiation, wherein, when the computer program code is loaded into and executed by a computer, the computer becomes an apparatus for practicing the invention. When implemented on a general-purpose microprocessor, the computer program code segments configure the microprocessor to create specific logic circuits.
[079] The disclosed methods and systems may be implemented on a conventional or a general-purpose computer system, such as a personal computer (PC) or server computer. Referring now to FIG. 9, an exemplary computing system 900 that may be employed to implement processing functionality for various embodiments (e.g., as a SIMD device, client device, server device, one or more processors, or the like) is illustrated. Those skilled in the relevant art will also recognize how to implement the invention using other computer systems or architectures. The computing system 900 may represent, for example, a user device such as a desktop, a laptop, a mobile phone, personal entertainment device, DVR, and so on, or any other type of special or general-purpose computing device as may be desirable or appropriate for a given application or environment. The computing system 900 may include one or more processors, such as a processor 902 that may be implemented using a general or special purpose processing engine such as, for example, a microprocessor, microcontroller or other control logic. In this example, the processor 902 is connected to a bus 904 or other communication medium. In some embodiments, the processor 902 may be an Artificial Intelligence (AI) processor, which may be implemented as a Tensor Processing Unit (TPU), or a graphical processor unit, or a custom programmable solution Field-Programmable Gate Array (FPGA).
[080] The computing system 900 may also include a memory 906 (main memory), for example, Random Access Memory (RAM) or other dynamic memory, for storing information and instructions to be executed by the processor 902. The memory 906 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processor 902. The computing system 900 may likewise include a read only memory (“ROM”) or other static storage device coupled to bus 904 for storing static information and instructions for the processor 902.
[081] The computing system 900 may also include a storage devices 908, which may include, for example, a media drive 910 and a removable storage interface. The media drive 910 may include a drive or other mechanism to support fixed or removable storage media, such as a hard disk drive, a floppy disk drive, a magnetic tape drive, an SD card port, a USB port, a micro USB, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive. A storage media 912 may include, for example, a hard disk, magnetic tape, flash drive, or other fixed or removable medium that is read by and written to by the media drive 910. As these examples illustrate, the storage media 912 may include a computer-readable storage medium having stored therein particular computer software or data.
[082] In alternative embodiments, the storage devices 908 may include other similar instrumentalities for allowing computer programs or other instructions or data to be loaded into the computing system 900. Such instrumentalities may include, for example, a removable storage unit 914 and a storage unit interface 916, such as a program cartridge and cartridge interface, a removable memory (for example, a flash memory or other removable memory module) and memory slot, and other removable storage units and interfaces that allow software and data to be transferred from the removable storage unit 914 to the computing system 900.
[083] The computing system 900 may also include a communications interface 918. The communications interface 918 may be used to allow software and data to be transferred between the computing system 900 and external devices. Examples of the communications interface 918 may include a network interface (such as an Ethernet or other NIC card), a communications port (such as for example, a USB port, a micro USB port), Near field Communication (NFC), etc. Software and data transferred via the communications interface 918 are in the form of signals which may be electronic, electromagnetic, optical, or other signals capable of being received by the communications interface 918. These signals are provided to the communications interface 918 via a channel 920. The channel 920 may carry signals and may be implemented using a wireless medium, wire or cable, fiber optics, or other communications medium. Some examples of the channel 920 may include a phone line, a cellular phone link, an RF link, a Bluetooth link, a network interface, a local or wide area network, and other communications channels.
[084] The computing system 900 may further include Input/Output (I/O) devices 922. Examples may include, but are not limited to a display, keypad, microphone, audio speakers, vibrating motor, LED lights, etc. The I/O devices 922 may receive input from a user and also display an output of the computation performed by the processor 902. In this document, the terms “computer program product” and “computer-readable medium” may be used generally to refer to media such as, for example, the memory 906, the storage devices 908, the removable storage unit 914, or signal(s) on the channel 920. These and other forms of computer-readable media may be involved in providing one or more sequences of one or more instructions to the processor 902 for execution. Such instructions, generally referred to as “computer program code” (which may be grouped in the form of computer programs or other groupings), when executed, enable the computing system 900 to perform features or functions of embodiments of the present invention.
[085] In an embodiment where the elements are implemented using software, the software may be stored in a computer-readable medium and loaded into the computing system 900 using, for example, the removable storage unit 914, the media drive 910 or the communications interface 918. The control logic (in this example, software instructions or computer program code), when executed by the processor 902, causes the processor 902 to perform the functions of the invention as described herein.
[086] Thus, the disclosed method and system try to overcome the technical problem of providing fuel economy insights of vehicles. The method and system estimate the fuel economy value of a vehicle based on a set of driving features (which is based on a set of driving parameters) through a regression model. This enables determination of optimal values of each of the set of driving features to obtain an improved fuel economy score. The method and system provide fuel economy insights corresponding to the vehicle to the owner of the vehicle fleet. The fuel economy insights include optimal values corresponding to the driving parameters (i.e., driver controllable parameters). Thus, method and system provide actionable insights to obtain a quantitative improvement in the fuel economy value of the vehicle. The method and system facilitate monitoring of the fuel economy values of the vehicles in the vehicle fleet. This may allow the owner of the vehicle to rate driving performances of the drivers and optimize the fuel economy of the vehicle to enhance cost efficiency.
[087] As will be appreciated by those skilled in the art, the techniques described in the various embodiments discussed above are not routine, or conventional, or well understood in the art. The techniques discussed above provide for providing fuel economy insights of vehicles. For a vehicle for a predefined time interval, the techniques first receive a set of driving parameters from the vehicle. The techniques then determine a set of driving features based on the set of driving parameters. Each of the set of driving features is derived from one or more driving parameters. The techniques then estimate, through a regression model, a fuel economy value for the vehicle based on the set of driving features at a low MAPE of about 6% to about 13%. The techniques then generate fuel economy insights corresponding to the vehicle based on the fuel economy value using the regression model. The fuel economy insights include adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications.
[088] In light of the above mentioned advantages and the technical advancements provided by the disclosed method and system, the claimed steps as discussed above are not routine, conventional, or well understood in the art, as the claimed steps enable the following solutions to the existing problems in conventional technologies. Further, the claimed steps clearly bring an improvement in the functioning of the device itself as the claimed steps provide a technical solution to a technical problem.
[089] The specification has described method and system for providing fuel economy insights of vehicles. The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
[090] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[091] It is intended that the disclosure and examples be considered as exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims. ,CLAIMS:CLAIMS
I/We claim:

1. A method (200) for providing fuel economy insights of vehicles, the method (200) comprising:
for a vehicle (102) for a predefined time interval,
receiving (202), by a processor (112), a set of driving parameters from the vehicle;
determining (204), by the processor (112), a set of driving features based on the set of driving parameters, wherein each of the set of driving features is derived from one or more driving parameters;
estimating (206), by the processor (112) through a regression model (124), a fuel economy value for the vehicle (102) based on the set of driving features; and
generating (208), by the processor (112), fuel economy insights corresponding to the vehicle (102) based on the fuel economy value using the regression model (124), wherein the fuel economy insights comprise adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications.

2. The method (200) as claimed in claim 1, wherein determining a first feature of the set of driving features comprises:
capturing values of a first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval; and
counting a number of timestamps for which a value of the driving parameter was in a first range of values, wherein the value of the first feature is the counted number of timestamps.

3. The method (200) as claimed in claim 1, wherein determining a second feature of the set of driving features comprises:
capturing values of a first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval;
capturing values of a second driving parameter of the set of driving parameters at the plurality of time stamps; and
counting a number of time stamps for which a value of the first driving parameter was in a first range of values and the value of the second driving parameter was in a second range of values, wherein the value of second feature is the counted number of timestamps.

4. The method (200) as claimed in claim 2, wherein the regression model (124) indicates a dependency of the fuel economy value on the first feature and wherein estimating (206) the fuel economy value comprises:
substituting the value of the first feature in the regression model (124).

5. The method (200) as claimed in claim 1, wherein the set of driving parameters comprises at least one of: accelerator pedal position, vehicle speed, engine performance bias, current gear, engine speed, torque, brake switch pressing, and clutch switch pressing, and wherein the set of driving features comprises at least one of: accelerator pedal position within a set of predefined ranges, combinations of the torque in a first predefined range and the engine speed in a second predefined range, diesel particulate filter active regeneration status, downhill odometer percent, engine performance bias level, flat stretch odometer percent, gear shift adherence, idling percent duration, inhibitor percent duration, neutral running percent duration, night drive duration, optimal trans current gear, wheel base vehicle speed, and the engine speed in green band.

6. The method (200) as claimed in claim 1, wherein the vehicle (102) is part of a vehicle fleet, and wherein the method (200) comprises generating fuel economy insights corresponding to each vehicle of the vehicle fleet and displaying the fuel economy value and the fuel economy insights on a dashboard.

7. The method (200) as claimed in claim 1, wherein generating fuel economy insights comprises:
comparing (210) the fuel economy value with a benchmark fuel economy value of a vehicle category associated with the vehicle (102); and
calculating (212) a driver score based on the comparison and a penalization score, wherein the penalization score is based on one or more penalization events identified from the set of driving parameters.

8. A system (100) for providing fuel economy insights of vehicles, the system (100) comprising:
one or more processors (112); and
one or more memory (114) communicatively coupled to the one or more processors (112), wherein the one or more memory (114) store processor instructions, which when executed by the one or more processors (112), cause the one or more processors (112) to:
for a vehicle (102) for a predefined time interval,
receive (202) a set of driving parameters from the vehicle (102);
determine (204) a set of driving features based on the set of driving parameters, wherein each of the set of driving features is derived from one or more driving parameters;
estimate (206), through a regression model (124), a fuel economy value for the vehicle (102) based on the set of driving features; and
generate (208) fuel economy insights corresponding to the vehicle (102) based on the fuel economy value using the regression model (124), wherein the fuel economy insights comprise adjustment recommendations to modify one or more of the set of driving parameters and indications of a quantitative improvement in the fuel economy value corresponding to the recommended modifications.

9. The system (100) as claimed in claim 8, wherein to determine a second feature of the set of driving features, the processor instructions, when executed by the one or more processors (112), cause the one or more processors (112) to:
capture values of a first driving parameter of the set of driving parameters at a plurality of time stamps in the predefined time interval;
capture values of a second driving parameter of the set of driving parameters at the plurality of time stamps; and
count a number of time stamps for which a value of the first driving parameter was in a first range of values and the value of the second driving parameter was in a second range of values, wherein the value of second feature is the counted number of timestamps.

10. The system (100) as claimed in claim 8, wherein the system (100) is part of the vehicle (102) or is remote from the vehicle (102).