Method and system for assessing stress level of user during a driving session

Abstract

A method 600 and system 200 for assessing a stress level of a user during a driving session is disclosed A processor 502 receives physiological data of the user from one or more biometric sensors 316 embedded in a wearable ring 202. Vehicular data associated with the driving session is received from a vehicular API 410 embedded in a vehicle computing device 204. The physiological data is correlated with the vehicular data on time-synchronized timestamps to identify one or more stress-inducing driving conditions. A stress score is computed for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods. The stress score normalized on a predetermined scale is displayed via a user interface 504. The stress score is displayed in association with the one or more identified stress-inducing conditions.

Description

METHOD AND SYSTEM FOR ASSESSING STRESS LEVEL OF USER DURING A DRIVING SESSIONFIELD OF INVENTION

[0001] The present invention generally relates to the field of physiological monitoring systems. More specifically, the present invention relates to a method and system for assessing a stress level of a user during a driving session.BACKGROUND OF THE INVENTION

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the present technology.

[0003] Driving is a complex activity that often involves multitasking, situational awareness, and rapid decision-making. Various factors such as traffic conditions, road quality, time of day, and driver workload can contribute to elevated stress levels during driving. Prolonged or acute stress while driving may affect driver performance, attention span, and overall well-being.

[0004] Stress assessment has traditionally been performed in clinical or sedentary settings, which do not reflect the dynamic and unpredictable nature of driving scenarios. While biometric sensors are increasingly used to monitor physiological data in everyday settings, interpreting this data meaningfully within the context of driving remains challenging. Additionally, driving-related information such as vehicle speed, location, and behavioral events (e.g., braking or acceleration) may be available through vehicle systems but are not always integrated into stress evaluation frameworks.

[0005] Therefore, there is a need for improved methods for assessing stress level of users during driving session in a timely and context-aware manner.SUMMARY OF THE INVENTION

[0006] This summary is provided to introduce aspects related to a method and system for assessing stress level of user during a driving session, and the aspects are further described below in the detailed description. This summary is not intended to identify essential features of the present subject matter, nor is it intended for use in determining or limiting the scope of the present subject matter.

[0007] A method for assessing a stress level of a user during a driving session is disclosed. The method may include receiving, by a processor and from one or more biometric sensors embedded in a wearable ring, physiological data of the user. The physiological data may include at least heart rate variability, skin temperature, and electrodermal activity. The method may further include receiving, by the processor and from a vehicular application programming interface (API) embedded in a vehicle computing device of a vehicle, vehicular data associated with the driving session. The vehicular data may include at least a start time, a duration, a vehicle speed, a braking intensity, acceleration patterns, and a geographic location obtained from global positioning system (GPS) data of the vehicle. The method may further include correlating, by the processor, the physiological data with the vehicular data on time- synchronized timestamps to identify one or more stress-inducing driving conditions. The method may further include computing, by the processor, a stress score for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods. The method may further include displaying, by the processor and via a user interface, the stress score normalized on a predetermined scale. The stress score may be displayed in association with the one or more identified stress-inducing driving conditions. In an embodiment, a higher stress score may correspond to a higher level of stress experienced by the user during the driving session.

[0008] In order to compute the stress score, the method may include filtering, by the processor, noise in the physiological data by applying one or more signal processing algorithms. The method may further include determining, by the processor, temporal variations in the electrodermal activity and the heart rate variability.

[0009] The method may further include updating, by the processor, a user-specific stress profile based on stress scores computed across a plurality of driving sessions. The method may further include associating, by the processor, the updated user-specific stress profile with recurring driving conditions, road segments, or times of day derived by identifying patterns across the vehicular data received during the plurality of driving sessions.

[0010] The method may further include generating, by the processor, one or more real-time recommendations based on the stress score. The method may further include displaying, by the processor and via the user interface, the one or more real-time recommendations to the user, the one or more real-time recommendations comprising at least one of: suggesting a break, proposing an alternate route, or initiating a calming activity.

[0011] In order to identify the one or more stress-inducing vehicular events, the method may include detecting, by the processor, a temporal correspondence between variations in the physiological data and variations in the vehicular data.

[0012] A system for assessing a stress level of a user during a driving session is disclosed. The system may include one or more biometric sensors embedded in a wearable ring. The system may further include a vehicle computing device disposed in a vehicle and enabling a vehicular application programming interface (API). The system may further include a processor communicatively coupled to the one or more biometric sensors and the vehicle computing device. The system may further include a user interface communicatively coupled to the processor. The system may further include a memory communicatively coupled to the processor, wherein the memory storing processor-executable instructions that, when executed by the processor, cause the processor to receive, from the one or more biometric sensors, physiological data of the user. The physiological data may include at least heart rate variability, skin temperature, and electrodermal activity. The processor may further receive, from the vehicular API, vehicular data associated with the driving session. The vehicular data may include at least a start time, a duration, a vehicle speed, a braking intensity, acceleration patterns, and a geographic location obtained from global positioning system (GPS) data of the vehicle. The processor may further correlate the physiological data with the vehicular data on time-synchronized timestamps to identify one or more stress-inducing driving conditions. The processor may further compute a stress score for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods. The processor may further display, via the user interface, the stress score normalized on a predetermined scale. The stress score may be displayed in association with the one or more identified stress-inducing driving conditions. In an embodiment, a higher stress score may correspond to a higher level of stress experienced by the user during the driving session.

[0013] In order to compute the stress score, the processor-executable instructions, when executed by the processor, may cause the processor to filter noise in the physiological data by applying one or more signal processing algorithms. The processor may further determine temporal variations in the electrodermal activity and the heart rate variability.

[0014] The processor-executable instructions, when executed by the processor, may further cause the processor to update a user-specific stress profile based on stress scores computed across a plurality of driving sessions. The processor may further associate the updated userspecific stress profile with recurring driving conditions, road segments, or times of day derived by identifying patterns across the vehicular data received during the plurality of driving sessions.

[0015] The processor-executable instructions, when executed by the processor, may further cause the processor to generate one or more real-time recommendations based on the stress score. The processor may further display, via the user interface, the one or more real-time recommendations to the user, the one or more real-time recommendations comprising at least one of suggesting a break, proposing an alternate route, or initiating a calming activity.

[0016] In order to identify the one or more stress -inducing vehicular events, the processorexecutable instructions, when executed by the processor, may cause the processor to detect a temporal correspondence between variations in the physiological data and variations in the vehicular data.

[0017] Other aspects and advantages of the invention will become apparent from the following description, taken in conjunction with the accompanying drawings, illustrating by way of example the principles of the invention.OBJECTIVE OF THE INVENTION

[0018] It is an object of the present invention to provide a system and method for assessing the stress level of a user during a driving session based on physiological data.

[0019] It is another object of the present invention to utilize biometric sensors embedded in a wearable device to acquire physiological measurements such as heart rate variability, skin temperature, and electrodermal activity during driving.

[0020] It is yet another object of the present invention to acquire vehicular data associated with a driving session, including but not limited to vehicle speed, acceleration patterns, braking intensity, and geographic location, from a vehicle computing unit.

[0021] It is a further object of the present invention to correlate physiological data with vehicular data on a time- synchronized basis in order to identify driving conditions that may be associated with elevated user stress levels.

[0022] It is also an object of the present invention to compute a stress score for the user by comparing real-time physiological responses with baseline physiological measurements obtained during non-driving periods.

[0023] It is an additional object of the present invention to provide a real-time visual output of the computed stress score and optionally deliver one or more personalized recommendations to the user through a user interface.

[0024] These and other objects of the present invention will become more readily apparent from the following detailed description, which should be understood to illustrate, but not limit, the scope of the invention.BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings constitute a part of the description and are used to provide a further understanding of the present invention.

[0026] Figure 1 illustrates an exemplary environment diagram in which a user wears a wearable ring during a driving session inside a vehicle, in accordance with the present disclosure.

[0027] Figure 2 illustrates a block diagram of a system for assessing a stress level of a user during a driving session, in accordance with the present disclosure.

[0028] Figure 3 illustrates a detailed block diagram of the wearable ring, in accordance with the present disclosure.

[0029] Figure 4 illustrates a detailed block diagram of the vehicle computing device, in accordance with the present disclosure.

[0030] Figure 5 illustrates a block diagram of a computing device for assessing the stress level of the user during the driving session, in accordance with the present disclosure.

[0031] Figures 6A and 6B illustrates a flowchart of a method for assessing a stress level of a user during a driving session, in accordance with the present disclosure.

[0032] Figure 7 illustrates a detailed flowchart of a method of computing the stress score, in accordance with the present disclosure.

[0033] A more complete understanding of the present invention and its embodiments thereof may be acquired by referring to the following description and the accompanying drawings.DETAILED DESCRIPTION OF THE INVENTION

[0034] Exemplary embodiments now will be described with reference to the accompanying drawings. The disclosure may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey its scope to those skilled in the art. The terminology used in the detailed description of the particular exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting. In the drawings, like numbers refer to like elements.

[0035] It is to be noted, however, that the reference numerals used herein illustrate only typical embodiments of the present subject matter, and are therefore, not to be considered for limiting its scope, for the subject matter may admit to other equally effective embodiments.

[0036] The detailed description includes specific details for the purpose of providing a thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without these specific details.

[0037] Referring now to Figure 1, an exemplary environment diagram 100 in which a user 108 wears a wearable ring 102 during a driving session inside a vehicle 106, is illustrated, in accordance with the present disclosure. The user 108 is shown seated in the driver seat of the vehicle 106 and wearing the wearable ring 102 on a finger. The wearable ring 102 may be embedded with one or more biometric sensors (not visible in Figure 1).

[0038] A computing device 104 is shown mounted within the vehicle 106 and may be positioned on or near the dashboard. The computing device 104 may be communicatively coupled to the wearable ring 102 and may serve as an interface to display stress scores or other feedback generated during or after a driving session. In some embodiments, the computing device 104 may correspond to a vehicle computing device, a mobile device docked within the vehicle 106, or another form of companion device associated with the user 108.

[0039] As illustrated, the vehicle 106 encompasses an in-cabin environment where physiological data and vehicular data are acquired concurrently. The physiological data is received from the wearable ring 102, while vehicular data such as speed, braking intensity, and location may be acquired via an application programming interface (API) embedded within the vehicle computing device (not separately shown in this figure).

[0040] Referring now to Figure 2, a block diagram of a system 200 for assessing a stress level of a user during a driving session, is illustrated, in accordance with the present disclosure. The system 200 may include a wearable ring 202, a vehicle computing device 204, a computing device 206, and a data server 208, communicatively coupled to each other either directly or indirectly via a communication network 210.

[0041] The wearable ring 202 may be worn by a user (e.g., user 108 as shown in Figure 1) and may include one or more embedded biometric sensors to collect physiological data of the user during a driving session. The biometric sensors may include, for example, heart rate sensors, temperature sensors, and electrodermal activity (EDA) sensors. The physiological data obtained by the wearable ring 202 may be transmitted to other components (e.g., the computing device 206) of the system 200 via the communication network 210.

[0042] The vehicle computing device 204 may be disposed within a vehicle (e.g., vehicle 106 of Figure 1) and may include a vehicular application programming interface (API) to acquire vehicular data associated with the driving session. The vehicular data may include, but is not limited to, a start time, a duration, a vehicle speed, a braking intensity, acceleration patterns, and a geographic location. The vehicle computing device 204 may be communicatively coupled to vehicle sensors and subsystems to retrieve the vehicular data in real time or near real time.

[0043] The computing device 206 may be a local or cloud-based processing device, such as a mobile device, a companion application on a smartphone, a tablet, a wearable hub, or a backendanalytics server. The computing device 206 may include one or more processors and memory modules storing executable instructions that perform various operations such as correlating physiological and vehicular data, computing a stress score, generating a user-specific stress profile, and displaying stress scores or recommendations via a user interface. The computing device 206 may be communicatively coupled to the wearable ring 202 and the vehicle computing device 204. In one embodiment, part of the processing may be performed locally on the computing device 206, such as initial signal filtering, real-time physiological data analysis, or user interface rendering. In another embodiment, more computationally intensive tasks, such as long-term pattern recognition, stress model refinement, or aggregation of data across multiple driving sessions, may be performed on a cloud-based infrastructure communicatively coupled to the computing device 206. This distribution of processing enables optimized performance while reducing latency for real-time feedback and conserving on- device resources.

[0044] The data server 208 may be a remote or a cloud-based server. The data server 208 may include a database (not shown in Figure) configured to store historical data, including physiological data, vehicular data, stress scores, user-specific stress profiles, and generated recommendations. The data server 208 may enable retrieval and analysis of past data across multiple driving sessions. In some embodiments, the data server 208 may also provide training data for refining stress computation models and improving recommendation accuracy.

[0045] The communication network 210 may include any suitable wired or wireless network such as a Wi-Fi network, a cellular network (e.g., 4G, 5G), Bluetooth, a local area network (LAN), or a wide area network (WAN), including the Internet. The communication network 210 may facilitate the exchange of data between the wearable ring 202, vehicle computing device 204, computing device 206, and data server 208, either in real-time or asynchronously.

[0046] Referring now to Figure 3, a detailed block diagram of the wearable ring 202, is illustrated, in accordance with the present disclosure. The wearable ring 202 is a finger-worn electronic device comprising multiple electronic components configured to acquire, process, and transmit physiological data of a user during a driving session. In one embodiment, the wearable ring 202 may be implemented in a unibody or segmented ring structure fabricated using biocompatible materials such as silicone, thermoplastic elastomers, or polymers embedded with metallic or ceramic shielding.

[0047] The wearable ring 202 may include a battery 302, a charging unit 304, a controller 306, a sensor unit 314, a user input unit 318, and a communication unit 322. These components are communicatively and operably coupled to enable continuous acquisition and transmission of biometric data.

[0048] The battery 302 may be a compact, rechargeable battery such as a lithium-polymer (Li- Po) or lithium-ion (Li-Ion) cell. The battery 302 is electrically coupled to the charging unit 304, the controller 306, the sensor unit 314, the user input unit 318, and the communication unit 322. The battery 302 is configured to supply electrical power to the electronic components of the wearable ring 202. The charging unit 304 may include a wireless charging coil or a contactbased interface configured to enable inductive or conductive charging through an external charging dock or connector. The charging unit 304 may further include charging control circuitry to regulate current flow and prevent overcharging.

[0049] The controller 306 may include a processing unit 308 and a memory unit 310. The processing unit 308 may include a microcontroller unit (MCU), a system-on-chip (SoC), or a low-power embedded processor capable of executing signal processing and data acquisition routines. The memory unit 310 may include volatile and / or non-volatile storage such as static RAM (SRAM), flash memory, EEPROM, or similar integrated memory modules. The memory unit 310 stores a physiological data acquiring module 312 that contains processor-executable instructions to acquire and temporarily store biometric signals such as electrodermal activity (EDA), skin temperature, and heart rate variability (HRV) from the sensor unit 314.

[0050] The sensor unit 314 may include one or more biometric sensors 316, which may include, but are not limited to, photoplethysmography (PPG) sensors for heart rate and HRV detection, galvanic skin response (GSR) sensors for measuring electrodermal activity, thermistors or thermocouples for skin temperature measurement, and accelerometers or gyroscopes for motion tracking. The biometric sensors 316 may be embedded along the inner circumference of the wearable ring 202 to maintain consistent skin contact and ensure reliable data acquisition during various finger movements and orientations.

[0051] The user input unit 318 may include one or more touch- sensitive surfaces, capacitive buttons, or gesture-based input sensors to enable user interaction with the wearable ring 202. The output unit 320 may include visual, haptic, or auditory feedback mechanisms such as an LED indicator, vibration motor, or miniature speaker. The output unit 320 is configured todisplay simple alerts, feedback, or cues to the user, such as readiness indication, low battery warning, or summary notifications.

[0052] The communication unit 322 enables wireless data transmission to one or more external computing systems. The communication unit 322 may include a Bluetooth Low Energy (BLE) transceiver, Wi-Fi module, Near-Field Communication (NFC), or other wireless interface capable of short-range data transmission. The communication unit 322 is responsible for transmitting the acquired physiological data to the vehicle computing device or a remote computing device for further analysis.

[0053] In operation, the wearable ring 202 acquires physiological data through the biometric sensors 316 during a driving session. The data is processed locally within the controller 306 using the physiological data acquiring module 312 and is periodically transmitted via the communication unit 322 to the computing device 206. The wearable ring 202 may be worn continuously by the user to facilitate both pre-driving readiness assessment and post-driving stress evaluation. In some embodiments, the wearable ring 202 may also be synchronized with cloud-based services to allow longitudinal tracking of stress profiles and generate sessionspecific stress scores.

[0054] In one embodiment, the wearable ring 202 is configured not only to capture physiological data during a driving session but also to record biometric signals before and after the driving session. Specifically, the biometric sensors 316 embedded within the wearable ring 202 such as photoplethysmography (PPG) sensors, galvanic skin response (GSR) sensors, and temperature sensors are operable to acquire physiological data continuously while the user wears the wearable ring 202, including during stationary or idle states prior to ignition (predrive) and after the vehicle has stopped (post-drive). The physiological data acquiring module 312 processes these pre-drive and post-drive signals locally within the controller 306 to compute baseline parameters such as resting heart rate variability (HRV), baseline skin temperature, and resting electrodermal activity (EDA). These baseline parameters are periodically transmitted via the communication unit 322 to the computing device 206 and may be stored locally or further synchronized with cloud-based services for longitudinal monitoring.

[0055] Referring now to Figure 4, a detailed block diagram of the vehicle computing device 204, is illustrated, in accordance with the present disclosure. The vehicle computing device 204 is a vehicle-integrated electronic subsystem configured to acquire, process, and transmitvehicular data relating to a driving session. The vehicular data, in conjunction with physiological data received from the wearable ring 202, enables assessment of a user stress level during the driving session. The vehicle computing device 204 may be implemented as part of an on-board diagnostics (OBD) module, a telematics control unit (TCU), or an infotainment system.

[0056] The vehicle computing device 204 may include a sensor interface 402, a controller 404, a memory 406 including a vehicular data acquiring module 408, a vehicular API 410, and a communication interface 412. These components are communicatively coupled within the vehicle computing device 204 to facilitate seamless collection, formatting, and transmission of vehicular parameters.

[0057] The sensor interface 402 is configured to interface with various in-vehicle sensors and subsystems to retrieve during-related parameters. These may include, but are not limited to, vehicle speed sensors, break pressure sensors, accelerometers, GPS units, engine control modules (ECMs), and steering angle sensors. The sensor interface 402 acts as a data abstraction layer that provides time-stamped measurements from these sensors to the controller 404.

[0058] The controller 404 may include one or more microprocessors, digital signal processors (DSPs), or embedded controllers capable of executing stored instructions and performing realtime signal processing. The controller 404 manages all internal operations of the vehicle computing device 204 and is configured to coordinate data acquisition from the sensor interface 402 and facilitate interaction with external devices via the communication interface 412.

[0059] The memory 406 may include volatile and / or non-volatile memory components such as DRAM, SRAM, EEPROM, or flash memory, and is communicatively coupled to the controller 404. Stored within the memory 406 is a vehicular data acquiring module 408, which includes processor-executable instructions for retrieving and organizing vehicular data. These instructions may include routines for filtering redundant values, time-aligning data streams, and formatting the data for downstream analysis or transmission.

[0060] The vehicular API 410 represents a software interface layer that facilitates structured access to vehicular data by external systems or software agents. The vehicular API 410 may expose one or more endpoints or data protocols (e.g., REST, gRPC, or CAN bus wrappers) through which external applications such as a cloud analytics engine or mobile companion app may query or subscribe to real-time vehicular parameters. In one embodiment, the vehicularAPI 410 enables the processor of the stress assessment system to access time-synchronized vehicular data such as speed, braking intensity, acceleration patterns, GPS coordinates, and session metadata (e.g., duration, start / end times).

[0061] The communication interface 412 is configured to enable wired or wireless communication between the vehicle computing device 204 and external computing systems such as the computing device 206. It may include one or more of a Bluetooth transceiver, WiFi module, cellular modem (e.g., LTE, 5G), or vehicle-to-everything (V2X) interface. The communication interface 412 enables the vehicle computing device 204 to transmit vehicular data to the wearable ring 202, a smartphone app, or a remote server, either in real time or in batch after the drive session.

[0062] In operation, the vehicle computing device 204 continuously or periodically acquires vehicular data via the sensor interface 402 during a driving session. The controller 404, in conjunction with the vehicular data acquiring module 408, formats and synchronizes the vehicular data and makes it available to external systems via the vehicular API 410 and the communication interface 412. The vehicular data may include time- series values such as changes in vehicle speed, braking events, steering corrections, acceleration bursts, and geometric position, all of which may be aligned with biometric data to identify stress-inducing driving conditions.

[0063] Referring now to Figure 5, a block diagram of a computing device 206 for assessing the stress level of the user during the driving session, is illustrated, in accordance with the present disclosure. The computing device 206 may be implemented as a mobile device, a tablet, a cloud-based processing server, or a local embedded unit operably coupled to the vehicle computing device 206 and the wearable ring 202. In certain embodiments, the computing device 206 may be partially integrated into the vehicle computing device 204 or may operate independently and receive data via the communication network 210.

[0064] As illustrated, the computing device 206 may include at least one processor 502, one or more user interfaces 504, and a memory 506. These components are operatively connected via a system bus or equivalent communication architecture to support collaborative processing of data from biometric and vehicular sources.

[0065] The processor 502 may include one or more central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), or application-specific integratedcircuits (ASICs) configured to execute instructions stored in memory. The processor 502 is responsible for executing logic and algorithms associated with acquiring, analyzing, and presenting stress-related information derived from physiological and vehicular inputs.

[0066] The user interface(s) 504 may include any suitable output and / or input mechanisms such as a touchscreen display, speaker, microphone, keyboard, mouse, or haptic feedback system. In some embodiments, the user interface 504 may include a graphical user interface (GUI) accessible through a mobile application or wearable companion interface. The user interface is operable to display visual indicators of stress level and optionally receive user input for an adjusting system parameters or providing feedback.

[0067] The memory 506 may include one or more tangible, non-transitory computer-readable media such as flash memory, hard disk drives, or solid-state drives. The memory 506 stores various function modules configured to execute discrete operations for processing incoming data and generating stress assessment outputs. The memory 506 may also be partitioned logically to support modular execution and future extensibility.

[0068] The memory 506 may include a physiological data receiving module 508, a vehicular data receiving module 510, a correlating module 512, a stress score computing module 514, a stress score displaying module 516, a recommendations generation module 518, a recommendation displaying module 520, a stress profile updating module 522, and a stress profile associating module 524. These modules, when executed by the processor 502, cause the processor to assess a stress level of a user during a driving session.

[0069] By way of an example, the physiological data receiving module 508 may receive the physiological data of the user from the one or more biometric sensors 316 embedded in the wearable ring 202. The biometric sensors 316 may include, for instance, photoplethysmography (PPG) sensors, galvanic skin response (GSR) sensors, temperature sensors, and inertial sensors such as accelerometers or gyroscopes. The physiological data may include, but is not limited to, heart rate variability (HRV), which is derived from PPG waveforms and reflects fluctuations in time intervals between successive heartbeats; skin temperature, which may vary with stress-induced vasoconstriction; and electrodermal activity (EDA), indicative of sympathetic nervous system activation and measurable through changes in skin conductance via GSR sensors.

[0070] For example, during a stressful highway merging scenario, the user HRV may decrease, EDA may spike due to heightened sympathetic arousal, and skin temperature may drop due to peripheral vasoconstriction. The physiological data receiving module 508 is configured to collect such variations and transfer them to downstream processing modules, such as the correlating module 512 and the stress score computing module 514, for further analysis. In one embodiment, the physiological data may be received as timestamped digital packets transmitted wirelessly from the communication unit 322 of the wearable ring 202 to the computing device 206 via the communication network 210.

[0071] In one embodiment, the physiological data receiving module 508 may be operable not only to receive physiological data of the user during a driving session, but also to collect physiological data from one or more non-driving periods, such as pre-drive and post-drive intervals, to establish one or more baseline physiological measurements. The physiological data may be acquired from the biometric sensors 316 embedded in the wearable ring 202, including, for example, photoplethysmography (PPG) sensors, galvanic skin response (GSR) sensors, temperature sensors, and inertial measurement sensors such as accelerometers or gyroscopes. The physiological data may include, but is not limited to, heart rate variability (HRV) derived from PPG waveforms, skin temperature, and electrodermal activity (EDA) as measured via GSR sensors. The physiological data receiving module 508 may continuously monitor and tag such data during non-driving periods such as prior to vehicle ignition or after engine shutdown using time-synchronized markers or session boundaries. These baseline measurements may be stored and later used by the stress score computing module 514 to compare against in-drive physiological deviations, thereby improving the personalization and contextual accuracy of the computed stress score.

[0072] Further, the vehicular data receiving module 510 may receive vehicular data from the vehicular API 410 embedded in the vehicle computing device 204. The vehicular API 410 may be configured to expose access to real-time or recorded vehicular telemetry parameters by interfacing with one or more sensor systems and control modules present within the vehicle, such as the electronic control unit (ECU), anti-lock braking system (ABS), and onboard GPS module. The vehicular data may include, but is not limited to, start time and duration of the driving session, derived from engine ignition signals or trip logging services; vehicle speed, captured from wheel speed sensors or GPS -derived velocity estimates; Braking intensity, which may be quantified by measuring deceleration patterns and break pedal force signalsavailable through the ABS or braking subsystem; Acceleration patterns, including rapid acceleration (e.g., pedal-to-floor events) or fluctuating acceleration-deceleration cycles during stop-go traffic; and Geographic location, typically determined by a GPS module and available in the form of timestamped latitude-longitude coordinates.

[0073] In one embodiment, the vehicular API 410 may comply with standard telematics protocols such as OBD-II (On-Board Diagnostics), CAN bus (Controller Area Network), or proprietary APIs provided by automobile manufacturers, allowing the vehicle computing device 204 to expose structured telemetry data. The vehicular data receiving module 510 may access this data over the communication network 210. By way of example, during a driving session, the vehicular API 410 may transmit a timestamped data stream reflecting a sudden deceleration from 70 km / h to 20 km / h within three seconds while the geographic location matches a known highway exit curve. Simultaneously, the vehicular API may report a concurrent spike in braking intensity and minor lateral acceleration from gyroscope readings.

[0074] Further, the correlating module 512 may correlate the physiological data with the vehicular data on time- synchronized timestamps to identify one or more stress-inducing driving conditions. In order to identify the one or more stress-inducing vehicular events, the correlating module 512 may detect a temporal correspondence between variations in the physiological data and variations in the vehicular data.

[0075] The correlation process may be implemented by temporally aligning streams of biometric and vehicular data that are each tagged with synchronized timestamps, enabling the system to observe changes in the user’s physiological state in conjunction with corresponding vehicular dynamics. In one embodiment, the physiological data (e.g., heart rate variability, electrodermal activity, and skin temperature) captured by one or more biometric sensors 316 of the wearable ring 202 may be sampled at fixed intervals (e.g., every 1-5 seconds) and synchronized with vehicular telemetry data such as speed, braking intensity, acceleration patterns, and GPS -based location received via the vehicular API 410.

[0076] The correlating module 512 may execute one or more signal processing or machine learning techniques to detect a temporal correspondence between abrupt or anomalous changes in the physiological signals and concurrent vehicular events. For example, a sharp spike in electrodermal activity (EDA) coupled with a sudden deceleration event or hard braking instance may be flagged as a stress-inducing vehicular condition. Similarly, a rise in heart ratevariability (HRV) variability during aggressive lane changing or while navigating high-traffic areas may be attributed to stress induction caused by complex driving environments.

[0077] In another embodiment, the correlating module 512 may detect pattern-based correspondences by evaluating not just instantaneous changes but also cumulative variations over time. For instance, prolonged driving in stop-go traffic exhibiting frequent braking and acceleration cycles, when paired with sustained elevations in EDA or a drop-in skin temperature (indicative of sympathetic nervous system activation), may be tagged as a high- stress interval within the session. The correlating module 512 may also integrate geolocation data to detect whether certain road segments or time-of-day windows (e.g., peak-hour driving in urban areas) consistently coincide with elevated stress markers. These patterns may later be associated with the user-specific stress profile by the stress profile associating module 524. In essence, the correlating module 512 enables the system to perform drive-event-to- physiological-response mapping.

[0078] Further, the stress score computing module 514 may compute a stress score for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods (e.g., at rest, pre-drive idle state, or other low-stress contexts). In order to compute the stress score, the stress score computing module 514 may filter noise in the physiological data by applying one or more signal processing algorithms. The stress score computing module 514 may further determine temporal variations in the electrodermal activity and the heart rate variability.

[0079] In an embodiment, to ensure the accuracy and relevance of the stress score, the stress score computing module 514 may apply one or more signal processing algorithms to filter noise from the raw physiological data. For instance, motion artifacts or sudden sensor displacement effects in electrodermal activity (EDA) signals may be mitigated using low-pass filters or wavelet-based denoising techniques. Similarly, heart rate variability (HRV) values computed from inter-beat intervals may be corrected using moving average smoothing, Kalman filters, or peak detection correction methods to avoid spikes caused by transient sensor errors. Once the physiological signal streams are cleaned, the stress score computing module 514 may analyze temporal variations in the biometric parameters to detect physiological signatures of acute or accumulated stress. For example:• Electrodermal Activity (EDA): A rise in skin conductance level or an increased frequency of non-specific skin conductance responses (NS-SCRs) over a given time window (e.g., per minute) may indicate elevated sympathetic arousal, a known correlate of stress.• Heart Rate Variability (HRV): A significant decrease in HRV measured using time-domain metrics (e.g., RMSSD) or frequency-domain metrics (e.g., LF / HF ratio) may suggest a shift toward sympathetic dominance, reflecting stress response.• Skin Temperature: A consistent drop in peripheral skin temperature, due to vasoconstriction, may also serve as an auxiliary indicator of stress activation.

[0080] The stress score computing module 514 may compute the stress score by aggregating these biometric indicators over the duration of the driving session and comparing them to baseline ranges established for the individual user during low-stress conditions. The baseline may be dynamic, periodically recalibrated using measurements taken during pre-drive periods or during known rest phases (e.g., early morning, sleep states, or controlled relaxation sessions logged via the companion app). In one implementation, a weighted scoring algorithm may be used, where each physiological indicator contributes proportionally to the overall score. The resulting stress score may be normalized to a scale of 0-100, where higher values indicate elevated stress levels during the driving session.

[0081] Further, the stress score displaying module 516 may display the stress score normalized on a predetermined scale (e.g., 0-100), via the user interface 504. The stress score may be displayed in association with the one or more identified stress-inducing driving conditions. In an embodiment, a higher stress score corresponds to a higher level of stress experienced by the user during the driving session.

[0082] In one embodiment, the stress score is presented in conjunction with one or more stressinducing driving conditions that were identified through the correlation of physiological data and vehicular data, as described previously. These associated conditions may include, but are not limited to: Aggressive braking events, High-speed segments on curved roads, Prolonged stop-and-go traffic, Sharp accelerations or sudden decelerations, Time-of-day or locationbased patterns (e.g., rush hour or busy intersections).

[0083] For example, the user interface 504 may present a timeline visualization that overlays the user's heart rate variability or electrodermal activity with driving events like "hard break at 9:42 AM" or "sharp turn at 9:50 AM", thereby contextualizing the stress score withenvironmental triggers. Such temporal mapping may allow users to reflect on how specific moments or driving behaviors impacted their physiological state.

[0084] In an embodiment, the normalized score is calculated such that a higher stress score corresponds to a higher level of stress experienced by the user during the driving session. This one-directional mapping simplifies user understanding and allows for meaningful trend comparison across sessions. For instance, a stress score of 82 may indicate significantly higher physiological stress than a previous session with a score of 47 under otherwise similar driving conditions.

[0085] Further, the recommendations generation module 518 may generate one or more realtime recommendations based on the stress score. These recommendations are dynamically tailored to the magnitude of the stress score, the rate of stress accumulation, and the contextual driving conditions derived from the vehicular data. For instance, if the system 200 identifies a rapid escalation in stress level during a segment of congested traffic or following a series of hard braking events, the recommendations generation module 518 may be triggered to formulate an appropriate feedback suggestion. The one or more real-time recommendations may include at least one of suggesting a break, proposing an alternate route, or initiating a calming activity. In an embodiment, the generated recommendations may include behavioral cues or actionable prompts, such as:• Suggesting a break: e.g., “You appear stressed. Consider taking a 5 -minute rest at the upcoming rest area.”• Proposing an alternate route: e.g., “High stress levels detected in traffic. An alternate route with lighter traffic is available.”• Initiating a calming activity: e.g., “Would you like to begin a 2-minute guided breathing session?” or “Play calming music playlist?”

[0086] These recommendations may be based on rule -based heuristics, machine-learned patterns from historical stress data, or a hybrid of both. In one embodiment, the magnitude of the stress score (e.g., >80 on a 0-100 scale), coupled with certain driving conditions (e.g., prolonged stop-and-go traffic), may form a predefined trigger condition for initiating suggestions.

[0087] Further, the recommendations displaying module 520 may display the one or more realtime recommendations to the user. In an embodiment, the recommendations displaying module 520, communicatively coupled to the user interface 504, may present these suggestions in real time in a non-intrusive and context-sensitive manner. The user interface 504 may employ modal or non-modal popups, haptic alerts on the wearable ring 202, or audio prompts via an in-vehicle infotainment system or companion mobile application.

[0088] Further, the stress profile updating module 522 may update a user-specific stress profile based on stress scores computed across a plurality of driving sessions. In one embodiment, each completed driving session generates a session- specific stress score derived using physiological data and corresponding vehicular data, as detailed earlier. The stress profile updating module 522 accumulates and processes these session-specific stress scores to build a longitudinal dataset that reflects the user's stress responses over time.

[0089] Further, the stress profile associating module 524 may associate the updated userspecific stress profile with recurring driving conditions, road segments, or times of day derived by identifying patterns across the vehicular data received during the plurality of driving sessions. In particular, once a user's stress profile is updated based on stress scores over multiple sessions, the stress profile associating module 524 applies pattern recognition techniques such as statistical correlation, clustering, or rule -based heuristics to detect recurring environmental or behavioral factors contributing to elevated stress. For example, the stress profile associating module 524 may identify that stress levels consistently spike during stop- and-go traffic patterns recorded during evening rush hours; detect that specific road segments (e.g., sharp turns, high-speed merging zones) are frequently associated with increased physiological markers of stress; correlate high stress scores with braking events at specific GPS coordinates, indicating problematic intersections; associate elevated electrodermal activity with late-night or low-light driving conditions, suggesting time-of-day sensitivity.

[0090] In an exemplary scenario, consider a commuter named Alex, who wears a biometrically-instrumented wearable ring 202 equipped with photoplethysmography (PPG) sensors, galvanic skin response (GSR) sensors, and skin temperature sensors, all communicatively coupled with a computing device 206 through a communication unit 322 over a secure wireless network 210. Before Alex begins driving, the system captures a pre-ride readiness index using biometric readings collected while Alex is idle or relaxed, establishing a personalized physiological baseline. These baseline readings are stored in the computingdevice 206 and include: a resting HRV value (e.g., RMSSD of 58 ms), a stable skin temperature (e.g., 34.5°C), and a neutral EDA conductance level (e.g., 5 pS). This baseline marker enables the system to contextualize physiological changes observed during driving.

[0091] Alex begins a typical weekday commute involving a mix of highway segments and urban congestion. As driving commences, the physiological data receiving module 508 continuously streams real-time biometric data (HRV, EDA, skin temperature) from the ring 202 to the computing device 206. Concurrently, the vehicular data receiving module 510 obtains vehicular telemetry from the vehicular API 410 on the vehicle computing device 204. This API conforms to CAN bus protocol and retrieves data such as: Vehicle speed (e.g., 0-90 km / h), Braking intensity from ABS, Acceleration patterns, and GPS coordinates tagged with timestamps.

[0092] At 9:41 AM, Alex approaches a high-speed merging ramp on the highway:• A sudden deceleration from 80 km / h to 30 km / h is logged by the vehicular API 410.• Simultaneously, EDA spikes to 12 pS, HRV drops to 35 ms, and skin temperature dips by 1°C, suggesting vasoconstriction.

[0093] The correlating module 512, using synchronized timestamps, detects this temporal alignment between the physiological and vehicular changes, marking this event as stressinducing. To ensure reliability, the stress score computing module 514 filters the raw biometric signals using: Low-pass filters to remove motion artifacts from EDA, Kalman filters for HRV smoothing, Thresholding to eliminate false temperature fluctuations. Over the entire 35-minute session, the module evaluates the temporal trends: Three hard-braking zones with EDA spikes, Two prolonged stop-go segments with HRV suppression and elevated EDA. Using a weighted scoring algorithm, the stress score computing module 514 compares these biometrics against the baseline and computes a session-specific stress score of 83 (on a 0-100 scale).

[0094] Once the vehicle stops at 10: 18 AM, the stress score displaying module 516 presents a visual report via the user interface 504 on Alex’s dashboard companion app. It includes: A color-coded timeline with annotated events: e.g., "Sharp deceleration at 9:41 AM - EDA spike + HRV drop", A cumulative score: "Session stress level: 83 - High."

[0095] Based on this high score, the recommendations generation module 518 triggers a rulebased suggestion: "Would you like to play your calming music playlist or take a 5-minute breathing break?" This suggestion is presented non-intrusively via haptic feedback on the ring and a modal popup on the user interface 504, through the recommendations displaying module 520.

[0096] The stress profile updating module 522 archives Alex’s stress score and associated biometrics with session metadata (e.g., route ID, time, environmental data). Over several weeks, the stress profile associating module 524 detects a recurring pattern of elevated stress between 9:30-10:00 AM on weekdays during specific highway segments. These patterns are associated with: High-speed merge zones, Morning traffic near GPS-tagged bottlenecks.

[0097] Referring now to Figures 6A and 6B, a flowchart of a method 600 for assessing a stress level of a user during a driving session, is illustrated, in accordance with the present disclosure. The method 600 may be performed by the computing device 206. The method 600 includes steps that are performed via modules stored in the memory 506 and executed by the one or more processors 502.

[0098] At step 602, the method includes receiving, from one or more biometric sensors embedded in a wearable ring (e.g., biometric sensors 316 in wearable ring 202), physiological data of the user. The physiological data may include heart rate variability, electrodermal activity, and skin temperature, among others. This data may be sampled periodically or continuously throughout the driving session.

[0099] At step 604, the method includes receiving, from a vehicular application programming interface (API) embedded in a vehicle computing device (e.g., vehicular API 410 of vehicle computing device 204), vehicular data associated with the driving session. The vehicular data may include but is not limited to: a start time and end time of the drive, duration, vehicle speed, braking intensity, acceleration patterns, and geographic location obtained from GPS data.

[0100] At step 606, the method includes correlating the physiological data with the vehicular data on time-synchronized timestamps to identify one or more stress-inducing driving conditions. In an embodiment, this is performed by the correlating module 512. The temporal alignment enables precise mapping of physiological responses to specific vehicular events.

[0101] At sub-step 608, the method includes detecting a temporal correspondence between variations in the physiological data and variations in the vehicular data. For instance, a sudden increase in heart rate variability or electrodermal activity may be temporally aligned with hard braking, rapid lane changes, or stop-and-go traffic conditions to infer stress-inducing events.

[0102] At step 610, the method includes computing a stress score for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods. This stress score may be computed by the stress score computing module 514. The baseline may be obtained during periods of rest or non-driving activity to normalize individual physiological variations. In an embodiment, signal processing techniques such as filtering, smoothing, or Fourier analysis may be applied to denoise the physiological signals.

[0103] At step 612, the method includes displaying, via a user interface (e.g., user interface 504), the stress score normalized on a predetermined scale, such as a range from 0 to 100. A higher score indicates a higher level of stress. The stress score may be visually rendered along with annotated driving conditions, road segments, or timestamps corresponding to the periods of elevated stress.

[0104] At step 614, the method includes generating one or more real-time recommendations based on the stress score. These may include, for example, suggesting a short break, initiating a calming activity such as guided breathing, or recommending an alternate route.

[0105] At step 616, the method includes displaying, via the user interface, the one or more realtime recommendations to the user. At step 618, the method includes updating a user-specific stress profile based on stress scores computed across a plurality of driving sessions. This profile may include trends related to road type, time of day, or driving duration, and may adapt over time based on new data received during subsequent sessions.

[0106] At step 620, the method includes associating the updated user-specific stress profile with recurring driving conditions, road segments, or times of day derived by identifying patterns across the vehicular data received during the plurality of driving sessions. This enables predictive insights into likely stress responses based on prior user-specific patterns.

[0107] Referring now to Figure 7, a detailed flowchart of a method 610 of computing the stress score, is illustrated, in accordance with the present disclosure. The method 610 may beperformed by the stress score computing module 514 of the computing device 206 and includes operations for transforming physiological sensor data into a meaningful, normalized stress score indicative of the user stress during a driving session.

[0108] At step 702, the method includes filtering noise in the physiological data by applying one or more signal processing algorithms. The physiological data may include, for example, heart rate variability (HRV), electrodermal activity (EDA), and skin temperature, acquired via the biometric sensor(s) 316 embedded in the wearable ring 202. Due to motion artifacts, environmental noise, and other non-physiological interferences, the raw data may be subject to distortion. Accordingly, signal processing techniques such as band-pass filtering, moving average smoothing, adaptive thresholding, and wavelet transform may be applied to isolate meaningful physiological trends and remove transient noise components. In one embodiment, separate filters may be applied to different physiological streams (e.g., EDA vs. HRV) based on their frequency characteristics.

[0109] At step 704, the method includes determining temporal variations in the electrodermal activity and the heart rate variability. Temporal variations refer to fluctuations in signal values over a defined time window, which may be sampled continuously or at discrete intervals. For example, a rising trend in EDA levels combined with a reduction in HRV over a 5 -minute span may indicate heightened sympathetic arousal and reduced parasympathetic modulation, both indicative of acute stress responses. These variations may be detected using statistical metrics such as standard deviation, peak-to-peak amplitude, or derivative-based trend analysis. Additionally, sudden spikes or drops may be mapped against synchronized vehicular events for contextual stress evaluation.

[0110] Thus, the method 600 and the system 200 overcome the limitations of conventional vehicle-based stress assessment solutions by providing an integrated, session-specific framework that spans pre-drive, in-drive, and post-drive stages. Unlike existing systems that rely solely on discrete sensor inputs or lack continuity across the driving session, the present disclosure utilizes a continuous stream of physiological and vehicular data to generate a dynamic, real-time stress score.

[0111] One technical advantage of the present disclosure is the use of a wearable ring 202 with embedded biometric sensor(s) 316 that unobtrusively monitor user-specific physiological parameters such as electrodermal activity, heart rate variability, and skin temperature. Thisconfiguration facilitates passive data capture without the need for intrusive body-mounted hardware, enabling seamless adoption by users.

[0112] Another advantage is the correlation of physiological data with vehicular parameters through a time- synchronized fusion mechanism implemented via the correlating module 512. This enables the system to identify stress-inducing events, such as rapid acceleration, frequent braking, or congested routes, by detecting physiological responses that are temporally aligned with such driving patterns.

[0113] A further advantage is the ability of the system 200 to compute a normalized stress score using baseline physiological measurements obtained during non-driving periods. This adaptive baseline approach provides user-specific calibration, thereby enhancing the sensitivity and accuracy of stress detection regardless of inter-user variability in biometric signals.

[0114] Additionally, the system 200 enhances user insight through visual output of the computed stress score and corresponding contextual recommendations via a user interface 504. The output, rendered through modules 516 and 520, is strictly informational and does not perform automated vehicle interventions, preserving driver autonomy while promoting self- awareness and behavioral regulation.

[0115] Collectively, the system 200 and method 600 offer a full-cycle, edge-cloud hybrid solution for real-time stress assessment and longitudinal stress profiling in driving contexts. The modular and distributed architecture encompassing the wearable ring 202, vehicle computing device 204, and computing device 206 provides scalability and privacy, across vehicular platforms and user types.

[0116] This does not necessarily imply that each such reference is to the same embodiment(s), or that the feature only applies to a single embodiment. Single features of different embodiments may also be combined to provide other embodiments.

[0117] As used herein, the terms “include”, “comprises”, “including” and / or “comprising” when used in this specification, specify the presence of stated features, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof. It will be understood that when an element is referred to as being “connected” or “coupled” to another element, it can be directly connected or coupled to the other element or intervening elements may be present.Furthermore, “connected” or “coupled” as used herein may include operatively connected or coupled. As used herein, the term “and / or” includes any and all combinations and arrangements of one or more of the associated listed items.

[0118] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure pertains. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

Claims

WE CLAIM:

1. A method 600 for assessing a stress level of a user during a driving session, the method 600 comprising: receiving 602, by a processor 502 and from one or more biometric sensors 316 embedded in a wearable ring 202, physiological data of the user, the physiological data comprising at least heart rate variability, skin temperature, and electrodermal activity; receiving 604, by the processor 502 and from a vehicular application programming interface (API) 410 embedded in a vehicle computing device 204 of a vehicle, vehicular data associated with the driving session, the vehicular data comprising at least a start time, a duration, a vehicle speed, a braking intensity, acceleration patterns, and a geographic location obtained from global positioning system (GPS) data of the vehicle; correlating 606, by the processor 502, the physiological data with the vehicular data on time-synchronized timestamps to identify one or more stress-inducing driving conditions; computing 610, by the processor 502, a stress score for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods; and displaying 612, by the processor 502 and via a user interface 504, the stress score normalized on a predetermined scale, wherein the stress score is displayed in association with the one or more identified stress-inducing driving conditions, and wherein a higher stress score corresponds to a higher level of stress experienced by the user during the driving session.

2. The method 600 as claimed in claim 1, wherein computing 610 the stress score further comprises: filtering 702, by the processor 502, noise in the physiological data by applying one or more signal processing algorithms; anddetermining 704, by the processor 502, temporal variations in the electrodermal activity and the heart rate variability.

3. The method 600 as claimed in claim 1, further comprising: updating 618, by the processor 502, a user-specific stress profile based on stress scores computed across a plurality of driving sessions; and associating 620, by the processor 502, the updated user-specific stress profile with recurring driving conditions, road segments, or times of day derived by identifying patterns across the vehicular data received during the plurality of driving sessions.

4. The method 600 as claimed in claim 1, further comprising: generating 614, by the processor 502, one or more real-time recommendations based on the stress score, the one or more real-time recommendations comprising at least one of: suggesting a break, proposing an alternate route, or initiating a calming activity; and displaying 616, by the processor 502 and via the user interface 504, the one or more real-time recommendations to the user.

5. The method 600 as claimed in claim 1, wherein identification of the one or more stressinducing vehicular events comprises: detecting 608, by the processor 502, a temporal correspondence between variations in the physiological data and variations in the vehicular data.

6. A system 200 for assessing a stress level of a user during a driving session, the system 200 comprising: one or more biometric sensors 316 embedded in a wearable ring 202; a vehicle computing device 204 disposed in a vehicle and enabling a vehicular application programming interface (API) 410; a processor 502 communicatively coupled to the one or more biometric sensors 316 and the vehicle computing device 204; a user interface 504 communicatively coupled to the processor 502;a memory 506 communicatively coupled to the processor 502, wherein the memory 506 storing processor-executable instructions that, when executed by the processor 502, cause the processor 502 to: receive, from the one or more biometric sensors 316, physiological data of the user, the physiological data comprising at least heart rate variability, skin temperature, and electrodermal activity; receive, from the vehicular API 410, vehicular data associated with the driving session, the vehicular data comprising at least a start time, a duration, a vehicle speed, a braking intensity, acceleration patterns, and a geographic location obtained from global positioning system (GPS) data of the vehicle; correlate the physiological data with the vehicular data on time -synchronized timestamps to identify one or more stress-inducing driving conditions; compute a stress score for the user during the driving session based on a comparison of the physiological data with one or more baseline physiological measurements of the user obtained during non-driving periods; and display, via the user interface 504, the stress score normalized on a predetermined scale, wherein the stress score is displayed in association with the one or more identified stress-inducing driving conditions, and wherein a higher stress score corresponds to a higher level of stress experienced by the user during the driving session.

7. The system 200 as claimed in claim 6, wherein to compute the stress score, the processorexecutable instructions, when executed by the processor 502, cause the processor 502 to: filter noise in the physiological data by applying one or more signal processing algorithms; and determine temporal variations in the electrodermal activity and the heart rate variability.

8. The system 200 as claimed in claim 6, wherein the processor-executable instructions, when executed by the processor 502, further cause the processor 502 to:update a user-specific stress profile based on stress scores computed across a plurality of driving sessions; and associate the updated user-specific stress profile with recurring driving conditions, road segments, or times of day derived by identifying patterns across the vehicular data received during the plurality of driving sessions.

9. The system 200 as claimed in claim 6, wherein the processor-executable instructions, when executed by the processor 502, further cause the processor 502 to: generate one or more real-time recommendations based on the stress score, the one or more real-time recommendations comprising at least one of: suggesting a break, proposing an alternate route, or initiating a calming activity; and display, via the user interface 504, the one or more real-time recommendations to the user.

10. The system 200 as claimed in claim 6, wherein to identify the one or more stress-inducing vehicular events, the processor-executable instructions, when executed by the processor 502, cause the processor 502 to: detect a temporal correspondence between variations in the physiological data and variations in the vehicular data.

Images