Description:TECHNICAL FIELD
[001] This disclosure generally relates to reminder generation in vehicles. More particularly, the disclosure relates to a method and system for outputting reminders in vehicles.
BACKGROUND
[002] In fast-moving modern life, people may often forget to carry important things while leaving home for a place, such as office, a hospital, a travel site and the like. The important may include but are not limited to an identification card (ID card), a wallet, a passport, a laptop and medical files. Additionally, people may also forget to perform various pre-planned tasks on the way back home from the place, such as grocery shopping or picking up someone along the way. Forgetting things may have several negative consequences, potentially leading to huge losses, such as failing to board a flight if the passport or any other essential travel document is left behind, or may hinder the work at the office, and the like.
[003] Presently, for prevention of leaving essential things behind, mobile reminder applications are being used. However, there may be several problems while using mobile phones for reminders. For example, mobile reminder applications may need internet connectivity, manually typing the reminders, and may distract drivers. In many cases, a driver may forget to open the application and miss the reminders altogether.
[004] The techniques in the present state of art fail to output reminders or alerts at an optimal time in absence of internet connection. There is, therefore, a need in the present state of art for an offline system for providing reminders to the user.
SUMMARY
[005] In one embodiment, a method for outputting relevant reminders in vehicles is disclosed. The method may include receiving user voice input and contextual data from one or more data sources in the vehicle. The contextual data may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. The method may further include determining, via an embedded Artificial Intelligence (AI) model, a user profile from a set of pre-defined user profiles based on the user voice input. The method may further include identifying, via the embedded AI model, a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data. Each of the one or more predetermined travel profiles may correspond to a set of travel destinations of the user. The method may further include determining, via the embedded AI model, one or more relevant reminders from a set of user-defined reminders based on the travel profile. The set of user-defined reminders may be associated with the user profile. For each reminder of the one or more relevant reminders, the method may further include validating, via the embedded AI model, the reminder through a reminder generation criteria based on the contextual data. For each reminder of the one or more relevant reminders, the method may further include outputting, via the embedded AI model, the reminder in the vehicle in an audio format based on the validation.
[006] In another embodiment, a system for outputting relevant reminders in vehicles is disclosed. The system may include a processor, and a memory communicatively coupled to the processor. The memory may store processor-executable instructions, which, on execution, may cause the processor to receive user voice input and contextual data from one or more data sources in the vehicle. The contextual data may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. The processor-executable instructions, on execution, may further cause the processor to determine, via an embedded AI model, a user profile from a set of pre-defined user profiles based on the user voice input. The processor-executable instructions, on execution, may further cause the processor to identify, via the embedded AI model, a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data. Each of the one or more predetermined travel profiles may correspond to a set of travel destinations of the user. The processor-executable instructions, on execution, may further cause the processor to determine, via the embedded AI model, one or more relevant reminders from a set of user-defined reminders based on the travel profile. The set of user-defined reminders may be associated with the user profile. For each reminder of the one or more relevant reminders, the processor-executable instructions, on execution, may further cause the processor to validate, via the embedded AI model, the reminder through a reminder generation criteria based on the contextual data. For each reminder of the one or more relevant reminders, the processor-executable instructions, on execution, may further cause the processor to output, via the embedded AI model, the reminder in the vehicle in an audio format based on the validation.
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 is a block diagram of an exemplary system for outputting relevant reminders in vehicles, in accordance with some embodiments of the present disclosure.
[009] FIG. 2 illustrates a functional block diagram of an exemplary system for outputting relevant reminders in vehicles, in accordance with some embodiments of the present disclosure.
[010] FIG. 3 illustrates a flow diagram of an exemplary method for outputting relevant reminders in vehicles, in accordance with some embodiments of the present disclosure.
[011] FIG. 4 illustrates an exemplary method for determining the user profile from the set of pre-defined user profiles via a flowchart, in accordance with some embodiments of the present disclosure.
[012] FIG. 5 illustrates an exemplary method for identifying the travel profile via a flowchart, in accordance with some embodiments of the present disclosure.
[013] FIG. 6 illustrates an exemplary method for modifying the travel profile via a flowchart, in accordance with some embodiments of the present disclosure.
[014] FIG. 7 illustrates a flow diagram of a detailed exemplary method for outputting relevant reminders, in accordance with some embodiments of the present disclosure.
[015] FIG. 8 illustrates a flow diagram of a detailed exemplary method for outputting relevant reminders in vehicles, in accordance with some embodiments of the present disclosure.
[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 block diagram of an exemplary system 100 for outputting relevant reminders in vehicles is illustrated, in accordance with some embodiments of the present disclosure. The system 100 may be implemented in a vehicle 102 (for example, a car, a bus, a truck, an auto rickshaw, a bike, a scooter, and the like), in accordance with some embodiments of the present disclosure. The vehicle 102 may include a computing device 104. The computing device 104 may be an Electronic Control Unit (ECU) of the vehicle 102 or an embedded device installed in the vehicle 102. In an embodiment, the computing device 104 may be a single-board computer (SBC) (for example, a Raspberry Pi®). The computing device 104 may output relevant reminders in vehicles, via an embedded Artificial Intelligence (AI) model, based on user voice input and contextual data. The embedded AI model may determine one or more relevant reminders corresponding to the travel profiles associated with the user.
[019] As will be described in greater detail in conjunction with FIG. 2-9, the computing device 104 may receive user voice input and contextual data from one or more data sources in the vehicle. The contextual data may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. Upon receiving, the computing device 104 may determine, via an embedded AI model, a user profile from a set of pre-defined user profiles based on the user voice input. The computing device 104 may further identify, via the embedded AI model, a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data. Each of the one or more predetermined travel profiles may correspond to a set of travel destinations of the user. The computing device 104 may further determine, via the embedded AI model, one or more relevant reminders from a set of user-defined reminders based on the travel profile. The set of user-defined reminders may be associated with the user profile. For each reminder of the one or more relevant reminders, the computing device 104 may further validate, via the embedded AI model, the reminder through a reminder generation criteria based on the contextual data. For each reminder of the one or more relevant reminders, the computing device 104 may further output, via the embedded AI model, the reminder in the vehicle in an audio format based on the validation.
[020] Further, the computing device 104 may include a processor 106 and a memory 108. In some embodiments, the processor 106 may be an edge processor. Additionally or alternatively, the processor 106 may include an AI accelerator (for example, a Google® Coral USB Accelerator). The memory 108 may store instructions that, when executed by the processor 106, cause the processor 106 to output relevant reminders in vehicles, in accordance with aspects of the present disclosure. The memory 108 may also store various data (for example, contextual data, a set of pre-defined user profiles, one or more predetermined travel profiles, a set of travel destinations, a set of user-defined reminders, a first similarity metric, a first predefined threshold value, a set of current patterns, a second similarity metric, a second predefined threshold value, a predefined threshold relevancy score, and the like) that may be captured, processed, and/or required by the system 100.
[021] The vehicle 102 may further include a display 110. The display may be a part of an infotainment system of the vehicle 102. A user may interact with the vehicle 102 via a user interface 112 accessible via the display 110. The system 100 may also include one or more external devices 114 and the computing device 104 may interact with the one or more external devices 114 over a communication network 116 for sending or receiving various data. The communication network 116, for example, may include, but may not be limited to, a Wireless Fidelity (Wi-Fi) network, a Light Fidelity (Li-Fi) network, a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a satellite network, the internet, a fiber optic network, a coaxial cable network, an infrared (IR) network, a Radio Frequency (RF) network, or a combination thereof. The one or more external devices 114 may include, but may not be limited to a remote server, a laptop, a netbook, a notebook, a smartphone, a mobile phone, a tablet, or any other computing device. Additionally, the computing device 104 may be communicatively connected to one or more devices within the vehicle 102. For example, the computing device 104 may be communicatively connected to an On-Board Diagnostics (OBD) port of the vehicle 102 (for example, an OBD-II port) to receive various sensor and diagnostics data of the vehicle 102. In embodiments where the computing device 104 is a separate device from the ECU of the vehicle 102, the computing device 104 may also be communicatively connected to the ECU.
[022] Referring now to FIG. 2, a functional block diagram of an exemplary system 200 for outputting relevant reminders in vehicles (such as the vehicle 102) is illustrated, in accordance with some embodiments of the present disclosure. FIG. 2 is explained in conjunction with FIG. 1. The system 200 may be analogous to the computing device 104 of the vehicle 102. .
[023] The system 200 may include, within the memory 108, a user profile module 202, a travel profile module 204, a reminder determination module 206, a reminder validation module 208, a modification module 210, an output module 212, and an AI module 214. The AI module 214 may include an embedded AI model 216. The embedded AI model 216 may be an offline AI model. The system 200 may also include a database 218 to store the data. The database 218 may be a local database (such as Structured Query Language Lite (SQLite) database) stored in the memory 108. In an embodiment, the database 218 may include a model repository of the embedded AI model 216. Additionally, the system 200 may be installed in the vehicle 102.
[024] The user profile module 202 may receive user voice input 220 and contextual data 222 from one or more data sources in the vehicle 102. The user voice input 220 may be received, via a voice interface (for example, the user interface 112), associated with the infotainment system in the vehicle 102. The contextual data 222 may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. The real-time vehicle data may include real-time vehicle diagnostics data and a real-time location of the vehicle. The real-time vehicle diagnostics data may be obtained from an OBD Port (such as an OBD-II port). The real-time vehicle diagnostics data may include ignition state, fuel level, speed, and the like. The real-time location (i.e., current location) of the vehicle 102 may be tracked using the Global Positioning System (GPS). The real-time user data may include real-time user behavioral data.
[025] Further, the user profile module 202 may determine, via the embedded AI model 216, a user profile from a set of pre-defined user profiles based on the user voice input 220. To determine the user profile, the user profile module 202 may compare, via the embedded AI model 216, the user voice input 220 with pre-stored voice information associated with each of the set of pre-defined user profiles based on a first similarity metric. The pre-stored voice information may be stored in the model repository in the database 218. Upon comparing, the user profile module 202 may determine, via the embedded AI model 216, the user profile when the first similarity metric for the user profile is greater than a first predefined threshold value, and when the first similarity metric for the user profile is greater than the first similarity metric for each of remaining of the set of pre-defined user profiles. Alternatively, the user profile module 202 may create, via the embedded AI model 216, a new user profile when the first similarity metric for each of the set of pre-defined user profiles is less than the first predefined threshold value.
[026] In other words, the embedded AI model 216 may perform voice recognition on the user voice input 220 to identify the user profile associated with the voice. In an embodiment, the embedded AI model 216 may include a set of offline lightweight AI models, each configured for predefined tasks. The set of offline lightweight AI models may include a wake word command detection model (such as Picovoice Porcupine) configured to detect a pre-configured wake word command (for example, “hello”, “hey”, etc.) that may activate further processing of the user voice input 220. Additionally, the set of offline AI models may include a speaker recognition model (such as Picovoice Eagle) configured to associate the voice in the user voice input 220 with one of the set of predefined user profiles. When the speaker recognition model fails to associate the voice with any of the set of predefined user profiles, a the speaker recognition model may initiate the creation of a new user profile.
[027] Upon determining the user profile, the travel profile module 204 may identify, via the embedded AI model 216, a travel profile from one or more predetermined travel profiles corresponding to the user profile based on at least one of the user voice input 220 or the contextual data 222. In an embodiment, the set of offline lightweight AI models may include an offline speech-to-text engine (such as Vosk API) to convert the user voice input 220 to text. Additionally, the set of offline lightweight AI models may include a Recurrent Neural Network (RNN) model to identify the travel profile based on pattern identification from the contextual data 222.
[028] Each of the one or more predetermined travel profiles may correspond to a set of travel destinations of the user. For example, the one or more predetermined travel profiles for a user profile may be ‘work’, ‘home’, ‘market’, ‘school’, and ‘doctor’. Further, for each travel profile, one or more locations up to a predefined number of locations (for example, up to 10 locations) may be stored. Additionally, for each location, one or more reminders up to a predefined number of reminders (for example, up to 10 reminders) may be stored.
[029] To identify the travel profile, the travel profile module 204 may identify, via the embedded AI model 216, a set of current patterns from the contextual data 222. The set of current patterns may include a time pattern and a location pattern of the vehicle 102 obtained from the real-time vehicle data. Further, the travel profile module 204 may compare, via the embedded AI model 216, the set of current patterns with pre-stored pattern information associated with each of the one or more predetermined travel profiles of the user profile, based on a second similarity metric. The pre-stored pattern information may be stored in the model repository in the database 218.
[030] Further, the travel profile module 204 may select, via the embedded AI model 216, the travel profile from the one or more predetermined travel profiles when the second similarity metric of the travel profile is greater than a second predefined threshold value, and when the second similarity metric of the travel profile is greater than the second similarity metric of each of remaining of the one or more predetermined travel profiles. In an exemplary scenario, for a given user profile, driving the vehicle 102 towards a particular route at 8:00 AM on a weekday may be a signature pattern (i.e., the pre-stored pattern information) of the ‘work’ travel profile. Thus, the travel profile module 204 may select the ‘work’ travel profile for the user profile.
[031] Alternatively, if a matching travel profile is not found (i.e., the second similarity metric of each of the one or more predetermined travel profiles is less than the second predefined threshold value), then the travel profile module 204 may prompt, via the embedded AI model 216, the user to provide a travel destination. In other words, when the embedded AI model 216 is unable to predict the destination or the travel profile, the travel profile module 204 may obtain the destination from the user. The travel profile module 204 may then identify, via the embedded AI model 216, the travel profile accordingly.
[032] When the embedded AI model 216 fails to identify the travel profile, the travel profile module 204 may initiate creation of a new profile. The travel profile module 204 may create, via the embedded AI model 216, a new travel profile for the user profile based on one of pattern identification or a user input. For creation of the new travel profile based on pattern identification, the travel profile module 204 may create, via the embedded AI model 216, a new travel profile for the user profile based on pattern identification from the historical vehicle data and the historical user data. For creation of the new travel profile based on the user input, the travel profile module 204 may create, via the embedded AI model 216, the new travel profile for the user profile based on a user input.
[033] Upon identifying the travel profile, the reminder determination module 206 may determine, via the embedded AI model 216, one or more relevant reminders from a set of user-defined reminders based on the travel profile. It should be noted that the set of user-defined reminders may be associated with the user profile. Some of the set of user-defined reminders may be general recurring reminders (i.e., defined for every vehicle journey associated with the travel profile). For example, for the travel profile corresponding to ‘work’, a general recurring reminder may be, “Reminder to take laptop and office ID card”. Similarly, for the travel profile corresponding to ‘doctor’, a general recurring reminder may be, “Reminder to take the test reports and prescription”. On the other hand, some of the set of user-defined reminders may be one-time specific reminders. For example, for the travel profile corresponding to ‘work’, a one-time specific reminder may be, “Reminder to buy stationary items on the way”.
[034] For each reminder 226 of the one or more relevant reminders, the reminder validation module 208 may validate, via the embedded AI model 216, the reminder 226 through a reminder generation criteria based on the contextual data 222. To validate the reminder, the reminder validation module 210 may determine, via the embedded AI model 216, a relevancy score corresponding to outputting of the reminder 226 at a current time based on the contextual data 222. In other words, it may not be apt to output all of the one or more relevant reminders of the travel profile to the user all at once. The relevancy score may help in determining the aptness of outputting the reminder 226. For example, a reminder corresponding to low fuel may only be relevant when the fuel level in the vehicle 102 is low regardless of the travel profile. Similarly, a reminder for the user to take essential items may be more relevant to be provided at the start of the journey. A reminder may be deferred for a later time instance in some scenarios, such as when the user is on a call.
[035] Further, the output module 212 may output, via the embedded AI model 216, the reminder 226 in the vehicle 102 in an audio format based on the validation. The output module 212 may output, via the embedded AI model 216, the reminder 226 in the vehicle 102 at the current time when the relevancy score is greater than a predefined threshold relevancy score. Alternatively, the output module 212 may determine, via the embedded AI model 216, an optimal time for outputting of the reminder when the relevancy score is less than the predefined threshold relevancy score. In other words, the output module 212 may use the relevancy score to decide what to say, when it may be safe or useful to say, whether to speak at all, and the like. Additionally, the relevancy score may determine whether or not the system 200 should engage in voice interaction at a given time. By way of an example, if the vehicle 102 is started every weekday at 8:30 AM, the travel profile module 204 predicts "Office" travel profile and asks for user confirmation. Upon confirmation, the output module 212 reminds the driver. The output module 212 may output “Hope you’ve taken your laptop, ID card, charger, and files. Is there anything you'd like me to remind you in the evening? Have a great drive!”
[036] In some embodiments, the modification module 210 may receive a modification request 224 corresponding to the travel profile. The modification request 224 may be an indicative of one of an addition of one or more new reminders to the travel profile, a deletion of the one or more reminders in the travel profile, or a modification of the one or more reminders in the travel profile. Upon receiving the modification request 224, the modification module 210 may modify, via the embedded AI model 216, the one or more reminders corresponding to the travel profile.
[037] It should be noted that all such aforementioned modules 202 – 214 may be represented as a single module or a combination of different modules. Further, as will be appreciated by those skilled in the art, each of the modules 202 – 214 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 202 – 214 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 202 – 214 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 202 – 214 may be implemented in software for execution by various types of processors (e.g., the processor 106). 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.
[038] As will be appreciated by one skilled in the art, a variety of processes may be employed for outputting relevant reminders in vehicles. For example, the exemplary system 100 and the associated computing device 104, may output the relevant reminders 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 associated 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 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 on the system 100.
[039] Referring now to FIG. 3, a flow diagram of an exemplary method 300 for outputting relevant reminders in vehicles, in accordance with some embodiments of the present disclosure. The method 300 may be implemented by the computing device 104 of the system 100. The method 300 may include receiving, by the user profile module 202, user voice input and contextual data 222 from one or more data sources in the vehicle, at step 302. The contextual data 222 may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. In other words, the contextual data 222 may include a vehicle telemetry, user history, environmental data and the like. Upon receiving, the method 300 may include determining, by the user profile module 202 via the embedded AI model 216, a user profile from a set of pre-defined user profiles based on the user voice input, at step 304.
[040] Further, the method 300 may include identifying, by the travel profile module 204 via the embedded AI model 216, a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data 222, at step 306. Each of the one or more predetermined travel profiles may correspond to a set of travel destinations of the user. Upon identifying, the method 300 may include determining, by the reminder determination module 206 via the embedded AI model 216, one or more relevant reminders from a set of user-defined reminders based on the travel profile, at step 308. The set of user-defined reminders may be associated with the user profile.
[041] For each reminder of the one or more relevant reminders, the method 300 may include validating, by the reminder validation module 208 via the embedded AI model 216, the reminder 226 through a reminder generation criteria based on the contextual data 222, at step, 310. Further, for each reminder of the one or more relevant reminders, the method 300 may include outputting, by the output module 212 via the embedded AI model 216, the reminder 226 in the vehicle in an audio format based on the validation, at step 312. The step 312 includes one of step 314 or step 316. The method may include 300 outputting, by the output module 212 via the embedded AI model 216, the reminder 226 in the vehicle at the current time when the relevancy score is greater than a predefined threshold relevancy score, at step 314. The method 300 may include determining, by the output module 212 via the embedded AI model 216, an optimal time for outputting of the reminder when the relevancy score is less than the predefined threshold relevancy score, at step 316.
[042] Referring now to FIG. 4, an exemplary method 400 for determining the user profile from the set of pre-defined user profiles is depicted via a flowchart, in accordance with some embodiments of the present disclosure. The user profile module 202 may perform steps 402-406 in order to determine the user profile from the set of pre-defined user profiles. The method 400 may include comparing, via the embedded AI model 216, the user voice input with pre-stored voice information associated with each of the set of pre-defined user profiles based on a first similarity metric, at step 402. In other words, the user may create an update in the user profile using the voice biometrics and the embedded AI model 216 may store contextual behavior patterns such as but are not limited to driving habits, frequently visited locations, and interaction preferences.
[043] Further, the method 400 may include determining, via the embedded AI model 216, the user profile when the first similarity metric for the user profile may be greater than a first predefined threshold value, and when the first similarity metric for the user profile may be greater than the first similarity metric for each of remaining of the set of pre-defined user profiles, at step 404. Further, the method 400 may include creating, via the embedded AI model 216, a new user profile when the first similarity metric for each of the set of pre-defined user profiles may be less than the first predefined threshold value, at step 406.
[044] Referring now to FIG. 5, an exemplary method 500 for identifying the travel profile is depicted via a flowchart, in accordance with some embodiments of the present disclosure. The travel profile module 204 may perform steps 502-508 in order to identify the travel profile. The method 500 may include identifying, via the embedded AI model 216, a set of current patterns from the contextual data 222, at step 502. Further, the method 500 may include comparing, via the embedded AI model 216, the set of current patterns with pre-stored pattern information associated with each of the one or more predetermined travel profiles of the user profile, based on a second similarity metric, at step 504.
[045] Further, the method 500 may include selecting, via the embedded AI model 216, the travel profile from the one or more predetermined travel profiles when the second similarity metric of the travel profile may be greater than a second predefined threshold value, and when the second similarity metric of the travel profile may be greater than the second similarity metric of each of remaining of the one or more predetermined travel profiles, at step 506. Further, the method 500 may include prompting, via the embedded AI model 216, the user to provide a travel destination when the second similarity metric may be less than the second predefined threshold value, at step 508.
[046] In some embodiments, the travel profile may not be presented in the database 218 corresponding to the prompted travel destination. Therefore, the method 500 may include creating, by the travel profile module 204 via the embedded AI model 216, a new travel profile for the user profile based on pattern identification from the historical vehicle data and the historical user data. Alternatively, the method 500 may include creating, by the travel profile module 204 via the embedded AI model 216, the new travel profile for the user profile based on a user input.
[047] Referring now to FIG. 6, an exemplary method 600 for modifying the travel profile is depicted via a flowchart, in accordance with some embodiments of the present disclosure. The method 600 may include receiving, by the system 200, a modification request 224 corresponding to the travel profile, at step 602. The modification request 224 may be indicative of one of: an addition of one or more new reminders to the travel profile, a deletion of the one or more reminders in the travel profile, or a modification of the one or more reminders in the travel profile. The method 600 may further include modifying, by the modification module 210 via the embedded AI model 216, the one or more reminders corresponding to the travel profile, at step 604.
[048] Referring now to FIG. 7, a flow diagram of a detailed exemplary method 700 for outputting relevant reminders in vehicles is illustrated, in accordance with some embodiments of the present disclosure. The method 700 may include starting ignition of a car, at step 702. The ignition status may be received by an embedded AI model (such as the embedded AI model 216) from an OBD-II port of the car. The OBD-II port may be a standardized diagnostic interface that may allow external devices (such as diagnostic tools) to communicate with the vehicle’s internal computer system (i.e., Electronic Control Unit). The OBD-II port may provide real-time vehicle data such as, but not limited to, ignition status (i.e., ON/OFF), vehicle speed, engine revolutions per minute (RPM), engine health, fuel level, GPS (if supported) and error codes.
[049] In some embodiments, the embedded AI model 216 may be embedded inside a micro-controller (i.e., the computing device 104), such as a Raspberry Pi®. The embedded AI model 216 may further include Natural Language Understanding (NLU) and pattern recognition modules. The Raspberry Pi® may store user data (for example, a user profile), run AI models (for example, the embedded AI model 216), connect all systems, and the like. The method 700 may include activating the embedded AI model 216 when the ignition status is ON, at step 704. Alternatively, the embedded AI model 216 may be activated upon receiving a wake word command from the user (for example, “hello”, “hey”, etc.). Upon activation, the embedded AI model 216 may greet, via an interface (such as the user interface 112), the user and may ask for a travel destination, at step 706. For example, the Raspberry Pi® via the offline voice system, may play a pre-programmed welcome message. The interface may include a screen and a speaker in the car to interact with the user and may display the reminders on the screen or play the reminders in audio format through the speaker.
[050] Once the pre-programmed welcome message is played, the method 700 may further include receiving user response with the travel destination, at step 708. In one example, the user may respond with “office”. Further, the method 700 may include reading, via the OBD-II port, the real-time vehicle data, at step 710. Upon reading, general reminders for each user related to the real-vehicle data may be announced. For example, if OBD-II detects low fuel, a reminder determination module (such as the reminder determination module 206) may determine one or more relevant reminders, then an output module (such as the output module 212) may output the reminder “You may need to refuel before heading to work.”
[051] Further, the method 700 may include processing the voice input provided by the user, at step 712. By way of an example, the Raspberry Pi® may use an offline voice system such as a Pico voice porcupine and a Vosk API to process the voice input. The Pico voice porcupine may be used to listen wake words and the Vosk API may convert the user voice input to text (for example, “Remind me to buy medicine”). Alternatively, a Wi-Fi module or Bluetooth may be used for wireless connection with a user device (such as a mobile phone) to sync customized reminders from phone to car.
[052] Further, the voice input is mapped, via a user profile module (such as the user profile module 202) to a user profile from a set of user profiles stored in the database 218. The method 700 may further include retrieving relevant reminders for a travel profile associated with the user profile based on running an AI logic from the database 218 (for example, the SQLite local database), at step 714. Further, the method 700 may include announcing a reminder to the user, at step 716. In one example, the reminder for the user on way back to home from work may be “Reminder to buy medicine”.
[053] In some embodiments, a chip (such as google coral USB accelerator) may be used along with the Raspberry Pi® to make the embedded AI model 216 faster and speed up the AI tasks. In other words, the chip may process AI models for learning user routines and voice faster. Based on pattern recognition of user routine, the system 200 may predict a relevant travel profile. By way of an example, when the user starts the car at 8:30 AM, the system 200 may automatically assume the travel destination as “office” and upon confirming routine, may remind the user: ‘Hope you’ve taken your ID card, laptop, charger. Need me to remind anything this evening?’ The user may add a new reminder or modify an already existing reminder for the evening.
[054] Referring now to FIG. 8, a flow diagram of a detailed exemplary method 800 for outputting relevant reminders in vehicles is illustrated, in accordance with some embodiments of the present disclosure. The method 800 may include monitoring by performing a check on the ignition status of the vehicle, at step 802. If the ignition is ON, then the method 800 may further include collecting contextual data 222, at step 804. The contextual data 222 may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. Further, the contextual data 222 may also include the time and location related information associated with the user profile for outputting reminder. If the ignition is OFF, then the system 200 may wait till the ignition turns ON.
[055] Further, the method 800 may include performing another check for pending reminders or suggestions, at step 806. If there are no pending reminders or suggestions, then the system 200 may wait until a predefined threshold may be achieved such as a particular time, situation, or the like. Further, if there may be any pending reminders or suggestions, the method 800 may include evaluating context match, at step 808. The evaluation may be performed by determining a relevancy score corresponding to an output reminder at a current time based on the contextual data 222. The real-time vehicle data may include the real-time vehicle diagnostics data. The real-time user data may include real-time user behavioral data.
[056] Upon evaluation, a check may be performed to determine if the context may be suitable, at step 810. If the context may not be suitable, then the pending reminders may be suppressed or deferred based on a user model. In other words, reminders may be suppressed if context may not be ideal. The non-ideal context may include several scenarios such as but is not limited to if the user is driving fast, then non-critical alerts may be suppressed. If the phone may be connected to the speaker of a vehicle and there is an ongoing call, then the reminder may be suppressed. If an alert may be repetitively ignored for more than three times, then the alert may be suppressed or rescheduled. If the context may be suitable, the method 800 may include triggering an alert or reminder via voice (such as in audio format), at step 812. By way of an example, the user model may be, but is not limited to, a behavioral learning model that may use a machine learning algorithm such as Recurrent Neural Networks (RNN) to track user behavior and predict travel destinations. Using RNN, the embedded AI model may continuously update the travel profile using voice commands given over time, frequently visited locations (such as home, office, school), type of reminders requested (such as travel, refueling, service) by a user, user reaction to past suggestions (such as accept, ignore, dismiss), prioritized reminders learned by usage frequency and urgency patterns, and the like. The behavioral learning model may allow automatic optimization of reminder priority, voice tone and timing.
[057] It is to be noted that the reminders may be delivered whey they are most useful, not just when conditions may be met. An output module (such as the output module 212) may trigger alerts or reminders based on real-time adaptive context evaluation using vehicle state via the OBD-II port, user history, learned behavior, time, place, activity patterns and the like. By way of an example, Low fuel” may be detected via the OBD-II port → Reminder 1: "Shall I guide you to your usual petrol pump? or Reminder 2: “You may need to refuel before heading to work.” In another example, frequent Monday 9AM start may be detected via the GPS route history → Reminder: "Your weekly meeting is soon. Do you want to review last week’s notes?"
[058] The method 800 may be explained in detail with the help of an exemplary embodiment,
User: Arjun
Pattern: Arjun usually leaves work at 6:30 PM and ignores alerts when he's on calls.
At 6:25 PM: the system 200 sees that Arjun's phone is on a call → suppresses reminder.
At 6:35 PM: Arjun disconnects, and engine is still on, speed < 10 km/h then, sends voice alert,
"Hi Arjun, your weekly expense report is due. Would you like me to note a reminder for tomorrow morning as well?
Response is positive → System logs it as evening time + idle + call completed = good trigger condition.
[059] Further, the method 800 may include logging outcome to the user profile, at step 814. In other words, the output may be stored in the historical user data in the database 218 in association with the user profile for future reference and may also store user feedback for the output in order to learn the user behavior (such as adaptive learning). The method 800 may be iteratively performed until there may be no more pending reminders or suggestions.
[060] 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, a 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).
[061] 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.
[062] The computing system 900 may also include 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, a magnetic tape, a 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.
[063] 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.
[064] 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 another 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.
[065] 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.
[066] 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.
[067] Various embodiments provide method and system for outputting relevant reminders in vehicles. The disclosed method and system may receive user voice input and contextual data from one or more data sources in the vehicle. The contextual data may include real-time vehicle data, real-time user data, historical vehicle data, and historical user data. Further, the disclosed method and system may determine, via an embedded AI model, a user profile from a set of pre-defined user profiles based on the user voice input. Further, the disclosed method and system may identify, via the embedded AI model, a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data. Each of the one or more predetermined travel profiles may correspond to a set of travel destinations of the user. Further, the disclosed method and system may determine, via the embedded AI model, one or more relevant reminders from a set of user-defined reminders based on the travel profile. The set of user-defined reminders may be associated with the user profile. Further, for each reminder of the one or more relevant reminders, the disclosed method and system may validate, via the embedded AI model, the reminder through a reminder generation criteria based on the contextual data. Further, for each reminder of the one or more relevant reminders, the disclosed method and system may output, via the embedded AI model, the reminder in the vehicle in an audio format based on the validation.
[068] Thus, the disclosed techniques try to overcome the problem for outputting relevant reminders in the vehicles. The techniques may cater to the requirement of outputting relevant vehicle in order to prevent forgetting important things before leaving. The techniques are capable of operating in offline mode, storing all data locally, while offering an optional mobile sync feature via Bluetooth®/Wi-Fi for enhanced usability. The techniques may provide voice-based reminders based on the user routine, selected destination, and past behavior ensuring a hands-free, distraction-free experience. The techniques may adapt when triggering the reminder based on historical user data. By way of an example, if the user may ignore the service reminders, then future alerts may be delayed or a tone or timing of delivering the reminder may be changed. If the user may respond promptly to early morning alerts or reminders, then the schedule may be adjusted accordingly. The techniques may further use offline storage, GPS, car ignition state detection that eliminates the need for the internet and make the system useful in the remote areas which possess low to no internet connection. With the help of local storage, the techniques may prevent latency that may happen due to server calls, ensures user privacy and data security simultaneously. The techniques may further learn from user routines and suggests smart reminders automatically. The techniques may further reduce user distraction while driving. The techniques may further allow users to update reminders via Bluetooth or Wi-Fi.
[069] 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.
[070] The specification has a described method and system for outputting relevant reminders in 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.
[071] 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.
[072] 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 (300) for outputting reminders in vehicles, the method (300) comprising:
receiving (302), by a processor (106) of a vehicle (102), user voice input (220) and contextual data (222) from one or more data sources in the vehicle (102), wherein the contextual data (222) comprises real-time vehicle data, real-time user data, historical vehicle data, and historical user data;
determining (304), by the processor (106) via an embedded Artificial Intelligence (AI) model (216), a user profile from a set of pre-defined user profiles based on the user voice input (220);
identifying (306), by the processor (106) via the embedded AI model (216), a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data (222), wherein each of the one or more predetermined travel profiles corresponds to a set of travel destinations of the user;
determining (308), by the processor (106) via the embedded AI model (216), one or more relevant reminders from a set of user-defined reminders based on the travel profile, wherein the set of user-defined reminders is associated with the user profile;
for each reminder of the one or more relevant reminders,
validating (310), by the processor (106) via the embedded AI model (216), the reminder (226) through a reminder generation criteria based on the contextual data (222); and
outputting (312), by the processor (106) via the embedded AI model (216), the reminder (226) in the vehicle in an audio format based on the validation.

2. The method (300) as claimed in claim 1, wherein determining, via the embedded AI model (216), the user profile from the set of pre-defined user profiles comprises:
comparing (402), via the embedded AI model (216), the user voice input (220) with pre-stored voice information associated with each of the set of pre-defined user profiles based on a first similarity metric;
determining (404), via the embedded AI model (216), the user profile when the first similarity metric for the user profile is greater than a first predefined threshold value, and when the first similarity metric for the user profile is greater than the first similarity metric for each of remaining of the set of pre-defined user profiles; and
creating (406), via the embedded AI model (216), a new user profile when the first similarity metric for each of the set of pre-defined user profiles is less than the first predefined threshold value.

3. The method (300) as claimed in claim 1, comprising, at least one of:
creating, via the embedded AI model (216), a new travel profile for the user profile based on pattern identification from the historical vehicle data and the historical user data; or
creating, via the embedded AI model (216), the new travel profile for the user profile based on a user input.

4. The method (300) as claimed in claim 1, wherein identifying, via the embedded AI model (216), the travel profile comprises:
identifying (502), via the embedded AI model (216), a set of current patterns from the contextual data (222);
comparing (504), via the embedded AI model (216), the set of current patterns with pre-stored pattern information associated with each of the one or more predetermined travel profiles of the user profile, based on a second similarity metric;
selecting (506), via the embedded AI model (216), the travel profile from the one or more predetermined travel profiles when the second similarity metric of the travel profile is greater than a second predefined threshold value, and when the second similarity metric of the travel profile is greater than the second similarity metric of each of remaining of the one or more predetermined travel profiles; and
prompting (508), via the embedded AI model (216), the user to provide the travel destination when the second similarity metric is less than the second predefined threshold value.

5. The method (300) as claimed in claim 1, wherein validating, via the embedded AI model (216), the reminder (226) through the reminder generation criteria comprises determining a relevancy score corresponding to outputting of the reminder (226) at a current time based on the contextual data (222), wherein the real-time vehicle data comprises real-time vehicle diagnostics data and a real-time location of the vehicle (102), and wherein the real-time user data comprises real-time user behavioral data.

6. The method (300) as claimed in claim 5, wherein outputting, via the embedded AI model (216), the reminder (226) in the vehicle (102) comprises, one of:
outputting (314), via the embedded AI model (216), the reminder (226) in the vehicle (102) at the current time when the relevancy score is greater than a predefined threshold relevancy score; or
determining (316), via the embedded AI model (216), an optimal time for outputting of the reminder (226) when the relevancy score is less than the predefined threshold relevancy score.

7. The method (300) as claimed in claim 1, comprising:
receiving (602) a modification request (224) corresponding to the travel profile, wherein the modification request (224) is indicative of one of:
an addition of one or more new reminders to the travel profile,
a deletion of the one or more reminders in the travel profile, or
a modification of the one or more reminders in the travel profile; and
modifying (604), via the embedded AI model (216), the one or more reminders corresponding to the travel profile.

8. A system (100) for outputting reminders in vehicles, the system (100) comprising:
a processor (106); and
a memory (108) communicatively coupled to the processor (106), wherein the memory (108) stores processor instructions, which when executed by the processor (106), cause the processor (106) to:
receive (302) user voice input (220) and contextual data (222) from one or more data sources in the vehicle (102), wherein the contextual data (222) comprises real-time vehicle data, real-time user data, historical vehicle data, and historical user data;
determine (304), via an embedded AI model (216), a user profile from a set of pre-defined user profiles based on the user voice input (220);
identify (306), via the embedded AI model (216), a travel profile from one or more predetermined travel profiles corresponding to the user profile based on the contextual data (222), wherein each of the one or more predetermined travel profiles corresponds to a set of travel destinations of the user;
determine (308), via the embedded AI model (216), one or more relevant reminders from a set of user-defined reminders based on the travel profile, wherein the set of user-defined reminders is associated with the user profile;
for each reminder of the one or more relevant reminders,
validate (310), via the embedded AI model (216), the reminder (226) through a reminder generation criteria based on the contextual data (222); and
output (312), via the embedded AI model (216), the reminder (226) in the vehicle in an audio format based on the validation.

9. The system (100) as claimed in claim 8, wherein to determine the user profile from the set of pre-defined user profiles, the processor instructions, on execution, cause the processor (106) to:
compare (402), via the embedded AI model (216), the user voice input (220) with pre-stored voice information associated with each of the set of pre-defined user profiles based on a first similarity metric;
determine (404), via the embedded AI model (216), the user profile when the first similarity metric for the user profile is greater than a first predefined threshold value, and when the first similarity metric for the user profile is greater than the first similarity metric for each of remaining of the set of pre-defined user profiles; and
create (406), via the embedded AI model (216), a new user profile when the first similarity metric for each of the set of pre-defined user profiles is less than the first predefined threshold value.

10. The system (100) as claimed in claim 8, wherein the processor instructions, on execution, cause the processor (106) to, at least one of:
create, by the embedded AI model (216), a new travel profile for the user profile based on pattern identification from the historical vehicle data and the historical user data; or
create, by the embedded AI model (216), the new travel profile for the user profile based on a user input.

11. The system (100) as claimed in claim 8, wherein to identify, via the embedded AI model (216), the travel profile, the processor instructions, on execution, cause the processor (106) to:
identify (502), via the embedded AI model (216), a set of current patterns from the contextual data (222);
compare (504), via the embedded AI model (216), the set of current patterns with pre-stored pattern information associated with each of the one or more predetermined travel profiles of the user profile, based on a second similarity metric;
select (506), via the embedded AI model (216), the travel profile from the one or more predetermined travel profiles when the second similarity metric of the travel profile is greater than a second predefined threshold value, and when the second similarity metric of the travel profile is greater than the second similarity metric of each of remaining of the one or more predetermined travel profiles; and
prompt (508), via the embedded AI model (216), the user to provide a travel destination when the second similarity metric is less than the second predefined threshold value.

12. The system (100) as claimed in claim 8, wherein to validate, via the embedded AI model (216), the reminder (226) through the reminder generation criteria, the processor instructions, on execution, cause the processor (106) to determine a relevancy score corresponding to outputting of the reminder (226) at a current time based on the contextual data (222), wherein the real-time vehicle data comprises real-time vehicle diagnostics data, and a real-time location of the vehicle (102), and wherein the real-time user data comprises real-time user behavioral data.

13. The system (100) as claimed in claim 12, wherein to output, via the embedded AI model (216), the reminder (226) in the vehicle (102), the processor instructions, on execution, cause the processor (106) to, one of:
output (314), via the embedded AI model (216), the reminder (226) in the vehicle (102) at the current time when the relevancy score is greater than a predefined threshold relevancy score; or
determine (316), via the embedded AI model (216), an optimal time for outputting of the reminder (226) when the relevancy score is less than the predefined threshold relevancy score.

14. The system (100) as claimed in claim 8, wherein the processor instructions, on execution, cause the processor (106) to:
receive (602) a modification request (224) corresponding to the travel profile, wherein the modification request (224) is indicative of one of:
an addition of one or more new reminders to the travel profile,
a deletion of the one or more reminders in the travel profile, or
a modification of the one or more reminders in the travel profile; and
modify (604), via the embedded AI model (216), the one or more reminders corresponding to the travel profile.