WO2023007515A1

WO2023007515A1 - Automatic locking and unlocking of vehicles

Info

Publication number: WO2023007515A1
Application number: PCT/IN2022/050675
Authority: WO
Inventors: Bhavish Aggarwal; Shravanthi Majji; Gaurav Agarwal; Nishit Jain; Vijayanand Jayaraman
Original assignee: Ola Electric Mobility Private Limited
Priority date: 2021-07-27
Filing date: 2022-07-26
Publication date: 2023-02-02

Abstract

A method for automatic locking and unlocking a vehicle is provided. The method includes learning, over a first time-interval, a speed pattern of a user device registered with the vehicle. The speed pattern is learnt based on a relationship between a plurality of unlocking events of the vehicle during the first time-interval and speed data with which the user device progressed towards the vehicle at the plurality of unlocking events. A speed with which the user device progresses towards the vehicle is determined based on first data associated with the user device and a first unlocking event is detected based on a comparison of the learnt speed pattern with the determined speed. Lock and unlock circuitry of the vehicle is controlled based on the detected first unlocking event to unlock one or more components of the vehicle.

Description

AUTOMATIC LOCKING AND UNLOCKING OF VEHICLES

BACKGROUND

FIELD OF THE DISCLOSURE

Various embodiments of the disclosure relate generally to vehicle locking and unlocking. More specifically, various embodiments of the disclosure relate to methods and systems for automatic locking and unlocking of vehicles.

DESCRIPTION OF THE RELATED ART

Vehicle locking and unlocking systems are used to prevent unauthorized access to vehicles. Typically, a vehicle, when not in use, remains locked and is unlocked before it is put to use. Conventionally, vehicles can be locked or unlocked using physical keys. However, under some circumstances, dependency on a physical key for locking and/or unlocking a vehicle may be inconvenient to an individual who is a user of the vehicle. For example, the individual may forget or loose the key, and is therefore unable to access the vehicle.

A known solution that facilitates keyless vehicle access involves registering a user device (e.g., a smartphone, a smart watch, or the like) of the individual with the vehicle. The registered user device, when present within a vicinity of the vehicle, pairs with the vehicle. Based on such pairing between the vehicle and the user device, the vehicle gets unlocked. However, the aforementioned solution suffers from multiple challenges. In one example, a user may be using the user device while being in the vicinity of the vehicle, without any intention to travel. In such a scenario, the vehicle may get unlocked due to the presence of the user device in the vicinity. In another example, the user device may get stolen or cloned by a malicious entity for gaining access to the vehicle. Besides, the aforementioned solution works on a principle of identification of the user device. However, an identity of the user device may be prone to compromise and theft, thereby rendering the solution inefficient. Therefore, there exists a need for a technical and reliable solution that overcomes the abovementioned problems and enables secure automatic locking and unlocking of vehicles.

Limitations and disadvantages of conventional and traditional approaches will become apparent to one of skill in the art, through comparison of described systems with some aspects of the present disclosure, as set forth in the remainder of the present application and with reference to the drawings.

SUMMARY Systems and methods for automatic locking and unlocking of a vehicle are provided substantially as shown in, and described in connection with, at least one of the figures, as set forth more completely in the claims.

These and other features and advantages of the present disclosure may be appreciated from a review of the following detailed description of the present disclosure, along with the accompanying figures in which like reference numerals refer to like parts throughout.

BRIEF DESCRIPTION OF DRAWINGS

FIG. 1A is a diagram that illustrates a system environment for automatic locking and unlocking of a vehicle, in accordance with an exemplary embodiment of the disclosure; FIG. IB is another diagram that illustrates another system environment for automatic locking and unlocking of a vehicle, in accordance with another exemplary embodiment of the disclosure;

FIG. 2 is a block diagram of a vehicle, in accordance with an exemplary embodiment of the disclosure;

FIG. 3 is a diagram that represents a learning phase executed by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure; FIG. 4 is a diagram that represents an exemplary scenario for learning of path profiles by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure;

FIGS. 5A, 5B, and 5C, collectively, illustrate diagrams that represent an exemplary scenario for learning a speed pattern of a user device by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure;

FIG. 6 is a diagram that illustrates a system environment for automatic locking and unlocking of a locking system associated with a facility, in accordance with another exemplary embodiment of the disclosure; FIG. 7 is a block diagram that illustrates a system architecture of a computer system for performing automatic locking and unlocking of a vehicle, in accordance with an exemplary embodiment of the disclosure;

FIG. 8 is a flow chart that illustrates a method for detecting an unlocking event for a vehicle, in accordance with an exemplary embodiment of the disclosure; FIG. 9 is a flow chart that illustrates a method for executing a learning phase by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure; and

FIGS. 10- IOC, collectively, illustrate a method for automatic locking and unlocking of a vehicle, in accordance with an exemplary embodiment of the disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

Certain embodiments of the disclosure may be found in the disclosed systems and methods for automatic locking and unlocking of a vehicle. Exemplary aspects of the disclosure provide methods for automatic locking and unlocking of a vehicle. The methods include various operations executed by the processing circuitry of the vehicle for automatic locking and unlocking of the vehicle. In an embodiment, the processing circuitry is configured to learn, over a first time-interval, a speed pattern of a user device registered with the vehicle. The speed pattern may be learnt based on a relationship between a plurality of unlocking events of the vehicle in the first time-interval and speed data with which the user device progressed towards the vehicle at the plurality of unlocking events in the first time-interval. The processing circuitry is further configured to determine, based on first data associated with the user device, a speed with which the user device progresses towards the vehicle. The first data is received after the first time-interval. The processing circuitry is further configured to compare the learnt speed pattern with the determined speed. The processing circuitry is further configured to detect a first unlocking event based on the comparison between the leamt speed pattern and the determined speed. The vehicle may include lock and unlocking circuitry and the processing circuitry is further configured to the control lock and unlock circuitry to unlock one or more components of the vehicle based on the detected first unlocking event.

In an embodiment, the processing circuitry is further configured to determine a distance of the user device from the vehicle after the one or more components are unlocked. The processing circuitry is further configured to grant a user, driving access to the vehicle based on the distance being less than a preset distance.

In an embodiment, the processing circuitry is further configured to determine one or more driving parameters of a user while the vehicle is being driven by the user. The processing circuitry is further configured to revoke the granted driving access to the vehicle based on a mismatch between a driving profile associated with the vehicle and the determined one or more driving parameters.

In an embodiment, the processing circuitry is further configured to learn a plurality of path profiles of the user device over the first time-interval. The plurality of path profiles is learnt based on a relationship between the plurality of unlocking events in the first time-interval and time-series location data of the user device at the plurality of unlocking events. In an embodiment, the processing circuitry is further configured to determine, based on second data received from the user device, a path trajectory followed by the user device to progress towards the vehicle. The processing circuitry is further configured to compare the determine path trajectory with the plurality of path profiles. The processing circuitry is further configured to detect the first unlocking event based on the comparison of the determined path trajectory with at least one of the plurality of path profiles.

In an embodiment, the speed data includes a time series of speed values with which the user device progressed towards the vehicle at the plurality of unlocking events. The first data is indicative of at least one of a signal strength of a wireless signal received from the user device, time-series speed measurements sensed by one or more sensors of the user device, and time- series location data of the user device.

In an embodiment, the processing circuitry is further configured to determine, based on the first data, a first distance gradient with which the user device progresses towards the vehicle. The processing circuitry is further configured to detect the first unlocking event based on the first distance gradient being greater than or equal to a first preset value. The first distance gradient is indicative of a rate of change of distance between the user device and the vehicle while the user device progresses towards the vehicle.

In an embodiment, the processing circuitry is further configured to determine a second distance gradient with which the user device progresses away from the vehicle. The second distance gradient is indicative of a rate of change of distance between the user device and the vehicle while the user device progresses away from the vehicle. The processing circuitry is further configured to detect a locking event based on the second distance gradient being greater than or equal to a second preset value. The processing circuitry is further configured to control the lock and unlock circuitry to lock the one or more components of the vehicle based on the detected locking event.

In an embodiment, the processing circuitry is further configured to learn a temporal routine associated with the plurality of unlocking events.

In an embodiment, the processing circuitry is further configured to determine, based on the first data, a timestamp while the user device progresses towards the vehicle. The processing circuitry is further configured to compare the determined timestamp with the learnt temporal routine and detect the first unlocking event based on the comparison of the timestamp with the learnt temporal routine. In an embodiment, the processing circuitry is further configured to re-leam the speed pattern based on the detected first unlocking event. The processing circuitry is further configured to detect a second unlocking event subsequent to the first unlocking event based on the re-learnt speed pattern. The methods and systems of the disclosure provide a solution for automatic locking and unlocking of a vehicle. The disclosed methods and systems further provide unlocking of the vehicle based on an authentication of a user device as well as a user associated with the vehicle. The disclosed methods and systems allow for a fool-proof authentication of the user device and the user. Therefore, the disclosed methods and systems significantly reduce a probability of unlocking the vehicle based on a false-positive identification of the user device and the user. The disclosed methods and systems also significantly reduce requirement of carrying a physical key (for example, a key fob) of the vehicle each time the vehicle has to be unlocked. The disclosed methods and systems are artificial intelligence (AI) enabled. Hence, the methods and systems continuously improve accuracy for identification and authentication of the user device and the user for locking and/or unlocking of the vehicle.

FIG. 1A is a diagram that illustrates a system environment for automatic locking and unlocking of a vehicle, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 1A, a system environment 100A is shown that includes a first vehicle 102a and a first user device 104a. The first vehicle 102a and the first user device 104a may be associated with a first user 103a. The first vehicle 102a and the first user device 104a are communicatively coupled via a communication network 106. Examples of the communication network 106 may include, but are not limited to, a wireless fidelity (Wi-Fi) network, a light fidelity (Li-Fi) network, a wide area network (WAN), a metropolitan area network (MAN), the Internet, an infrared (IR) network, a radio frequency (RF) network, a near field communication (NFC) network, a Bluetooth network, a Zigbee network, and a combination thereof. Various entities (such as the first vehicle 102a and the first user device 104a) in the system environment 100A may be coupled to the communication network 106 in accordance with various wired and wireless communication protocols, such as Transmission Control Protocol and Internet Protocol (TCP/IP), User Datagram Protocol (UDP), Long Term Evolution (LTE) communication protocols, an IEEE 802.11 standard protocol, an IEEE 802.15 standard protocol, an IEEE 802.15.4 standard protocol, or any combination thereof.

The first user device 104a may refer to a personal device of the first user 103a such as a phone, a tablet, a phablet, a laptop, a smart phone, a wearable device (such as a smartwatch), a key fob, or the like. The first user device 104a may include one or more sensors configured to detect one or more parameters associated with the first user device 104a. The one or more sensors may include a speed sensor, a global positioning sensor (GPS), a signal sensor, or the like. The first user device 104a may be registered with the first vehicle 102a based on an authentication performed therebetween. The authentication between the first user device 104a and the first vehicle 102a may be performed by exchange of at least one of a one-time password (OTP), a user account information (an account identifier and password), or the like. The first user device 104a may have a web-based application or a mobile application (for example, a service application) that may be accessed by the first user 103a to control one or more operations (such as locking, unlocking, or the like) of the first vehicle 102a. The first vehicle 102a refers to a two-wheeler vehicle (for example, a motorbike, a scooter, an electronic bike, a hybrid bike, or the like). The first vehicle 102a may have an automatic locking and unlocking capability and may be locked or unlocked based on an interaction with the first user device 104a. As shown in FIG. 1A, the first vehicle 102a includes first lock and unlock circuitry 108a, first control circuitry 110a (e.g., processing circuitry), and a first memory 112a. The first control circuitry 110a may be coupled to the first lock and unlock circuitry 108a and the first memory 112a. Various components of the first vehicle 102a are described in detail in conjunction with FIG. 2.

The first vehicle 102a may be configured to operate in two phases, for example, a learning phase and an implementation phase. During the learning phase, the first vehicle 102a may be configured to learn one or more parameters associated with the first user device 104a. The one or more parameters may include a speed pattern, a plurality of path profiles, a driving profile, and a temporal routine associated with the first user device 104a. The first vehicle 102a may be configured to operate in the learning phase for a first time-interval. During the implementation phase, the first vehicle 102a may be configured to utilize the learnt one or more parameters for automatic locking and unlocking thereof. The first vehicle 102a may be configured to operate in the implementation phase upon completion of the learning phase, for example, after the first time- interval.

The first vehicle 102a may be configured to initiate the learning phase upon registration of the first user device 104a with the first vehicle 102a. In other words, the first vehicle 102a may be configured to initiate the learning phase when a new device of a new user is registered with the first vehicle 102a. The first time-interval for which the learning phase is executed may refer to an initial period of use of the first vehicle 102a by the first user 103a. In an embodiment, the first time- interval may refer to a configuration time-interval during which the first vehicle 102a is personalized for the first user device 104a. Examples of the first time-interval may include 1 hour, 2 hours, 1 day, 2 days, 3 days, one week, two weeks, one month, or the like.

During the first time-interval, the first vehicle 102a may be required to be locked and/or unlocked for a predefined number of times using the first user device 104a for collection of data associated with the first user device 104a. In one example, during the first time- interval, the first vehicle 102a may be automatically unlocked (for example, an unlocking event) when a rate of progression of the first user 103a holding the registered first user device 104a towards the first vehicle 102a is greater than or equal to a first preset value. Since the first user 103a is holding the first user device 104a, movement parameters (e.g., speed, velocity, acceleration, path trajectory, or the like) of the first user device 104a may be used as a proxy for the first user 103a. Therefore, when the first vehicle 102a detects that a distance between the first user device 104a and the first vehicle 102a is continuously decreasing with time at a rate greater than or equal to the first preset value, the first vehicle 102a may get auto-unlocked. The rate of change of distance between the first user device 104a and the first vehicle 102a with respect to time may be referred to as a distance gradient. In other words, during the first time-interval, the first vehicle 102a may be automatically unlocked (auto-unlocked) when the first vehicle 102a detects that a distance gradient with which the first user device 104a is progressing towards the first vehicle 102a is greater than or equal to the first preset value. The first vehicle 102a may detect the distance gradient of the first user device 104a based on a signal strength of a wireless signal received from the first user device 104a, time-series speed measurements sensed by one or more sensors of the first user device 104a, and time-series location data of the first user device 104a while the first user device 104a is progressing towards the first vehicle 102a.

The first vehicle 102a may be configured to receive and/or collect data from the registered first user device 104a for every locking or unlocking instance during the first time-interval. In an example, the data collected by the first vehicle 102a from the registered first user device 104a for every locking or unlocking instance may include the time-series speed measurements, the time- series location data, identification data, or the like. In another embodiment, the first vehicle 102a may be configured to receive the data from a server (not shown) associated with the first user device 104a. The server may be responsible for hosting the mobile or web application executed on the first user device 104a for accessing the first vehicle 102a.

The first control circuitry 110a may be configured to learn, over the first time- interval, the speed pattern of the first user device 104a registered with the first vehicle 102a using the collected data. The speed pattern of the first user device 104a may capture a trend in velocity (or speed) with which the first user device 104a has progressed towards the first vehicle 102a during the first time-interval at different instances of unlocking the first vehicle 102a. Each instance of unlocking the first vehicle 102a may be referred to as an unlocking event of the first vehicle 102a. In other words, the first vehicle 102a may leam the speed pattern based on a relationship between a plurality of unlocking events of the first vehicle 102a in the first time-interval and speed (or velocity) data with which the first user device 104a progressed towards the first vehicle 102a at the plurality of unlocking events. In an embodiment, the speed pattern may include a range of speed (or velocity) learnt based on various speed values with which the first user device 104a has progressed towards the first vehicle 102a at the plurality of unlocking events during the first time- interval.

The first control circuitry 110a may be further configured to learn the plurality of path profiles associated with the first user device 104a over the first time-interval using the collected data. The plurality of path profiles may be learnt based on a relationship between the plurality of unlocking events in the first time- interval and time-series location data of the first user device 104a at the plurality of unlocking events. The plurality of path profiles may refer to a collection of absolute paths traversed by the first user 103 a to progress towards the first vehicle 102a during the first time-interval at the plurality of unlocking events. In an embodiment, each path profile may be associated with a specific location of the first vehicle 102a. For example, a first path profile may include a plurality of path trajectories that the first user device 104a has traversed to progress towards the first vehicle 102a parked at a location “A”. Each path trajectory may be represented as time-series location data of the first user device 104a while the first user device 104a was progressing towards the first vehicle 102a.

In an embodiment, the first control circuitry 110a may be configured to leam the temporal routine associated with the plurality of unlocking events using the collected data. The temporal routine may refer to a temporal pattern or trend in occurrence of the plurality of unlocking events associated with the first vehicle 102a. A repetition or similarity in time and/or day and/or date of the plurality of unlocking events may be used to determine the temporal routine associated with the plurality of unlocking events.

The first control circuitry 110a may be further configured to leam the driving profile associated with the first user device 104a. The driving profile may include a collection of driving parameters that are recorded by the first control circuitry 110a over the first time-interval while the first vehicle 102a was being driven by the first user 103 a. The first control circuitry 110a may be configured to store the learnt speed pattern, the plurality of path profiles, the temporal routine, and the driving profile in the first memory 112a.

In an embodiment, the first vehicle 102a may have a threshold zone 105a (shown by way of area enclosed within a dotted boundary 105a) associated therewith. The threshold zone 105a may be predefined or manually defined by the first user 103a. In another embodiment, the threshold zone 105a may be defined based on a communication range (for example, a signal range) of at least one of the first vehicle 102a, the first user device 104a, and the communication network 106. Once the registration of the first user device 104a with the first vehicle 102a is complete, the first user device 104a may automatically get paired with the first vehicle 102a, via the communication network 106, when the first user device 104a enters the threshold zone 105a. The first user device 104a may send and/or receive a signal (e.g., a pairing request) to and/or from the first vehicle 102a upon entering the threshold zone 105a. In an embodiment, the first user device 104a, upon receiving the signal from the first vehicle 102a, may respond to the first vehicle 102a with a user device identifier, an ID-Password combination, a user profile identifier, or the like to initiate pairing with the first vehicle 102a. In another embodiment, based on reception of the signal from the first user device 104a, the first vehicle 102a may respond with one of a vehicle identifier, an ID-password, or the like to initiate the pairing.

After the first time-interval, the first vehicle 102a may be configured to operate in the implementation phase. During the implementation phase, the first control circuitry 110a may be configured to determine, based on first data associated with the first user device 104a, a speed with which the first user device 104a progresses towards the first vehicle 102a. The first data is received after the first the first time-interval and may be indicative of at least one of signal strength of a wireless signal received from the first user device 104a, time-series speed measurements sensed by one or more sensors of the first user device 104a, and time-series location data of the first user device 104a. The first control circuitry 110a may be further configured to compare the leamt speed pattern with the determined speed and detect a first unlocking event based on the comparison of the leamt speed pattern with the determined speed. The comparison between the leamt speed pattern and the determined speed is performed to determine whether the determined speed matches the learnt speed pattern. In other words, the first control circuitry 110a compares the learnt speed pattern with the determined speed and detects the first unlocking event when the learnt speed pattern matches the determined speed. The first control circuitry 110a may be further configured to control the first lock and unlock circuitry 108a to unlock one or more components of the first vehicle 102a based on the detected first unlocking event.

The first control circuitry 110a may be further configured to determine, based on the first data, a first distance gradient with which the first user device 104a progresses towards the first vehicle 102a. The first distance gradient associated with the first user device 104a may be determined once the first user device 104a gets paired with the first vehicle 102a. The first control circuitry 110a may be configured to detect the first unlocking event based on the first distance gradient being greater than or equal to the first preset value. The first distance gradient may refer to a rate of change of distance of the first user device 104a with respect to the first vehicle 102a while the first user device 104a is progressing towards the first vehicle 102a. The first distance gradient may be measured based on the time-series location data received from the first user device 104a, the signal strength of the wireless signal received from the first user device 104a, or the like. The first distance gradient may indicate whether the first user 103a is progressing towards the first vehicle 102a with an intent to unlock the first vehicle 102a. The first preset value may be compared with the first distance gradient to determine if the first user 103a progressing towards the first vehicle 102a intends to unlock the first vehicle 102a. The first preset value may be predefined or manually defined by the first user 103a.

In an embodiment, the first control circuitry 110a may be further configured to determine, based on second data received from the first user device 104a, a path trajectory followed by the first user device 104a to progress towards the first vehicle 102a. The second data may include time- series location data associated with the first user device 104a. The first control circuitry 110a may be further configured to compare the determined path trajectory with the plurality of path profiles and detect the first unlocking event based on the comparison of the determined path trajectory with the plurality of path profiles. The comparison between the determined path trajectory with the plurality of path profiles is performed to determine whether the determined path trajectory matches with at least one of the plurality of path profiles. In other words, the first control circuitry 110a compares the determined path trajectory with the plurality of path profiles and detects the first unlocking event when the determined path trajectory matches the plurality of path profiles. The path trajectory may refer to time-series location of the first user device 104a while the first user device 104a progresses towards the first vehicle 102a. A malicious user having the first user device 104a may follow a different path trajectory that is not included in the plurality of path profiles. Therefore, the path trajectory may not match the learnt path profiles. As a result, the one or more components of the first vehicle 102a remain locked.

The first control circuitry 110a may be further configured to determine, based on the first data, a timestamp while the first user device 104a is progressing towards the first vehicle 102a. The timestamp may refer to a date and time marker associated with an ongoing detection of the first unlocking event. The first control circuitry 110a may be further configured to compare the timestamp with the learnt temporal routine and detect the first unlocking event based on the comparison of the timestamp with the leamt temporal routine., The comparison between the timestamp and the learnt temporal routine is performed to determine whether the timestamp matches the learnt temporal routine. In other words, the first control circuitry 110a compares the timestamp with the learnt temporal routine and detects the first unlocking event when the timestamp matches the learnt temporal routine.

Thus, the first control circuitry 110a may be configured to compare a determined parameter with a learnt parameter (for example, determined speed with learnt speed pattern, the timestamp with the temporal routine, the determined path trajectory with the plurality of path profiles, or the like) to determine whether the determined parameter matches the learnt parameter and detect an unlocking event upon successful match.

The first control circuitry 110a may be further configured to determine a distance of the first user device 104a from the first vehicle 102a after the one or more components are unlocked as a second layer (or double layer) of authentication. The first control circuitry 110a may be further configured to grant the first user 103 a, driving access to the first vehicle 102a based on the determined distance being less than a preset distance. For the granting of the driving access, the first control circuitry 110a may be configured to turn on the power of the first vehicle 102a.

The first control circuitry 110a may be further configured to determine one or more driving parameters of the first user 103a while the first vehicle 102a is being driven by the first user 103a. The first control circuitry 110a may be further configured to revoke the granted driving access, for example, by turning off the power, to the first vehicle 102a based on a mismatch between the driving profile associated with the first vehicle 102a and the determined one or more driving parameters. The driving parameters may refer to one or more driving characteristics associated with a current user of the first vehicle 102a. The one or more driving characteristics may be indicative of a manner, a pattern, a habit, or a trend in a driving style of the current user. Examples of the driving parameters may include, but are not limited to, acceleration and/or deacceleration trend, harsh braking events, harsh acceleration events, speeding trend, accelerating the first vehicle 102a to a certain speed before starting to move the first vehicle 102a, applying breaks and acceleration simultaneously, turning the first vehicle 102a to follow a semi-circular path after releasing breaks, or the like. The driving parameters of the current user are matched with the driving profile of the first user 103a to authenticate the current user. Based on a successful match of the one or more driving parameters with the driving profile, no action is taken and the first vehicle 102a continues to be driven by the first user 103a. However, when the one or more driving parameters do not comply with the driving profile (or do not match the driving profile), the driving access to the first vehicle 102a is revoked. For example, a park mode of the first vehicle 102a may be activated to revoke the driving access to the vehicle 102a. The park mode may refer to a mode of operation of the first vehicle 102a during which the first vehicle 102a gets locked and couldn’t be unlocked and/or driven without at least one of using a physical key of the first vehicle 102a, authenticating or unlocking the first vehicle 102a via the first user device 104a.

The first control circuitry 110a may be further configured to re-learn the speed pattern, the plurality of path profiles, and the temporal routine based on the detected first unlocking event during the implementation phase. For example, the determined speed data may not match the learnt speed pattern. However, the first user 103a may unlock the first vehicle 102a using the physical key or the service application of the first user device 104a. Therefore, the speed pattern is re-learnt by the first control circuitry 110a using the determined speed. The first control circuitry 110a may be configured to detect a second unlocking event subsequent to the first unlocking event based on the re-leamt speed pattern, plurality of path profiles, and temporal routine.

In an embodiment, the first control circuitry 110a may be configured to detect the first unlocking event and unlock the first vehicle 102a based on the match between the leamt speed pattern and the determined speed, and at least one of the match of the determined path trajectory with at least one of the plurality of path profiles and a match of the timestamp with the leamt temporal routine.

The first control circuitry 110a may be further configured to determine a second distance gradient with which the first user device 104a progresses away from the first vehicle 102a. The second distance gradient may refer to a change in distance of the first user device 104a with respect to the first vehicle 102a while the first user device 104a is progressing away from the first vehicle 102a. The second distance gradient may be determined based on time-series location data received from the first user device 104a. In an embodiment, the second distance gradient may be indicative of a speed with which the first user device 104a is moving away from the first vehicle 102a. The first control circuitry 110a may be further configured to detect a locking event based on the second distance gradient being greater than or equal to a second preset value. The second preset value may be predefined or dynamically defined by the first user 103a. The first control circuitry 110a may be further configured to control the first lock and unlock circuitry 108a to lock the one or more components of the first vehicle 102a based on the detected locking event.

In an embodiment, the first vehicle 102a may have a plurality of users and a plurality of user devices associated therewith. The first control circuitry 110a may be configured to detect an unlocking or locking event based on at least one of the plurality of users and corresponding user devices. In operation, the first vehicle 102a may be configured to continuously broadcast a signal (e.g., the pairing request) for pairing with the first user device 104a. In another embodiment, the first vehicle 102a may be configured to periodically broadcast the signal for pairing with the first user device 104a. Alternatively, the first vehicle 102a may be configured to communicate the signal for pairing with the first user device 104a upon being prompted by the first user device 104a. The first user 103a holding the first user device 104a may be progressing towards the first vehicle 102a. Thus, when the first user device 104a enters the threshold zone 105a, the first user device 104a may be paired with the first vehicle 102a based on the signal communicated by the first vehicle 102a. The first user device 104a may pair with the first vehicle 102a based on the OTP, a first user device identifier, the account information, or the like. Upon pairing, the first user device 104a may be configured to communicate the first data to the first vehicle 102a. The first control circuitry 110a may be configured to determine, based on the first data, the first distance gradient for the first user device 104a. In instances where the first distance gradient is greater than or equal to the first preset value, this may indicate that the first user device 104a is progressing towards the first vehicle 102a. Subsequently, the first control circuitry 110a may determine the speed, based on the first data, with which the first user device 104a is progressing towards the first vehicle 102a. The first data may be indicative of signal strength of a wireless signal (for example, a Bluetooth signal) being received from the first user device 104a, time- series speed measurements sensed by one or more sensors (for example, a speed sensor, an accelerometer, a motion sensor, or the like) of the first user device 104a, time-series location data of the first user device 104a. The time-series location data may be used to determine the speed by calculating a distance progressed by the first user device 104a per unit time. The first control circuitry 110a may compare the determined speed with the learnt speed pattern and detect the first unlocking event based on the comparison of the determined speed with the learnt speed pattern.

The first control circuitry 110a may determine, based on the second data received from the first user device 104a, the path trajectory followed by the first user device 104a. The second data may be time-series GPS data associated with the first user device 104a. The first control circuitry 110a may be configured to compare the determined path trajectory with a path profile associated with a current location of the first vehicle 102a. The first control circuitry 110a may further detect the first unlocking event based on a successful match of the determined path trajectory with one or more path trajectories included in the path profile associated with the current location of the first vehicle 102a.

The first control circuitry 110a may further determine a timestamp while the first user device 104a is progressing towards the first vehicle 102a. The first control circuitry 110a may be further compare the determined timestamp with the learnt temporal routine and detect the first unlocking event based on the comparison of the determined timestamp with the leamt temporal routine, for example when the determined timestamp successfully matches the learnt temporal routine of the plurality of unlocking events. Upon detecting the first unlocking event, the first control circuitry 110a may be configured to unlock the one or more components of the first vehicle 102a by controlling the first lock and unlock circuitry 108a. The first control circuitry 110a may be further configured to determine a distance of the first user device 104a from the first vehicle 102a. The first control circuitry 110a may grant the first user 103 a the driving access to the first vehicle 102a based on the determined distance being less than the preset distance. In an example, the present distance may be 0.5 meter, 1 meter, 2 meters, or the like. The preset distance may be indicative of a fact that the first user device 104a is close to the first vehicle 102a. Therefore, the first control circuitry 110a may establish that the first vehicle 102a is being unlocked by the first user device 104a and/or the detected first unlocking event is authentic and not a false positive detection of unlocking event. Subsequently, the first control circuitry 110a may determine one or more driving parameters of the first user 103a while the first vehicle 102a is being driven by the first user. When the determined driving parameters do not match the driving profile associated with the first vehicle 102a, the first control circuitry 110a may revoke the granted driving access to the first vehicle 102a. In an embodiment, when the determined driving parameters do not match the driving profile associated with the first vehicle 102a, the first control circuitry 110a may again determine the distance of the first user device 104a from the first vehicle 102a. Upon failing to detect the distance, the first control circuitry 110a may be configured to determine that the current use of the first vehicle 102a may be unauthorized. Subsequently, the first control circuitry 110a may communicate an alert notification to the first user device 104a indicating the unauthorized use of the first vehicle 102a. Based on reception of the alert notification, the first user device 104a may receive an approval or a rejection of use of the first vehicle 102a. In an example, when the use of the first vehicle 102a is approved via the first user device 104a, the first vehicle 102a remains mobilized. In another example, when the use of the first vehicle 102a is rejected via the first user device 104a, the first control circuitry 110a may activate an alert mode (or a theft mode) on the first vehicle 102a. While operating in the alert mode, the first control circuitry 110a may be configured to communicate a real-time location of the first vehicle 102a to the first user device 104a. Subsequently, the first control circuitry 110a may cause the speed of the first vehicle 102a to gradually reduce, eventually immobilizing the first vehicle 102a. In an example, the first control circuitry 110a may be configured to determine a location of a nearest security personnel (such as a security guard, a policeman, or the like), a police station, or the like, and may cause the first vehicle 102a to halt in a proximity to determine location of the security personnel, the police station, or the like.

In an embodiment, the first user device 104a may be configured to activate or deactivate one or more parameters based on which the first unlocking event is detected by the first vehicle 102a. The first user device 104a may be configured to acquire a parameter activation or deactivation input from the first user 103a and perform the activation and/or the deactivation of the one or more parameters. In one example, the parameter activation input may indicate activation of the first gradient and the plurality of speed profiles for automatic locking and unlocking. In such a scenario, the first unlocking event may be detected based on the first gradient and the speed associated with the first user device 104a. In another example, the first unlocking event may be detected based on the speed and path trajectory of the first user device 104a. In another example, the first unlocking event may be detected based on the speed and the timestamp while the first user device 104a is progressing towards the first vehicle 102a.

In another embodiment, the first control circuitry 110a may be configured to receive an input that defines one or more safe spaces associated with the first vehicle 102a. The input may be received from the first user device 104a or an input/output (I/O) interface of the first vehicle 102a. The one or more safe spaces may refer to various parking spaces that may be defined as secure parking locations for the first vehicle 102a by the first user 103a (e.g., an owner of the first vehicle 102a). Examples of the safe spaces may include a home location, an office parking location, or the like. The first control circuitry 110a may further receive another input to enable automatic detection of the unlocking events and/or locking events only when a current location of the first vehicle 102a is one of the safe spaces. In other words, when the safe spaces are defined for the first vehicle 102a, the first control circuitry 110a may only attempt to automatically unlock the first vehicle 102a (or one or more components of the first vehicle 102a) when the current location of the first vehicle 102a is one of the safe spaces. Thus, if the first vehicle 102a is not parked at one of the safe spaces, the first control circuitry 110a may not attempt to automatically unlock the first vehicle 102a.

It will be apparent to a person skilled in the art that the first unlocking event may be detected based on at least one of the one or more parameters described throughout the description. In an embodiment, the first control circuitry 110a may be external to the first vehicle 102a, for example, a server (not shown). In such a scenario, the server may be trained to learn to automatic locking and unlocking criteria for the first vehicle 102a based on the interaction with the first user device 104a.

FIG. IB is another diagram that illustrates a system environment for automatic locking and unlocking of a vehicle, in accordance with another exemplary embodiment of the disclosure. Referring to FIG. IB, a system environment 100B is shown that includes a second vehicle 102b and a second user device 104b associated with a second user 103b. The second vehicle 102b and the second user device 104b may be communicatively coupled via the communication network 106. A threshold zone associated with the second vehicle 102b is represented by way of an area enclosed within a boundary 105b. As shown in FIG. IB, the second vehicle 102b includes second lock and unlock circuitry 108b, second control circuitry 110b, and a second memory 112b. The second control circuitry 110b may be coupled to the second lock and unlock circuitry 108b and the second memory 112b. The second vehicle 102b shown in the FIG. IB is a four- wheeler. Therefore, the second lock and unlock circuitry 108b may be controlled by the second control circuitry 110b to lock or unlock at least one of a door, an engine, a steering column, or any other vehicular sub-system of the second vehicle 102b.

It will be apparent to a person skilled in the art that the first vehicle 102a and the second vehicle 102b shown in FIGS. 1A and IB respectively are exemplary. In other embodiments, the system environments 100A and 100B may include any other vehicle such as a three-wheeler, a six wheeler, or the like.

For the sake of brevity, the ongoing description is described with respect to the first vehicle 102a. It will be apparent to a person skilled in the art that the description related to the first vehicle 102a and its components is also applicable to the second vehicle 102b and its corresponding components without deviating from the scope of the disclosure.

FIG. 2 is a block diagram of a vehicle, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 2, the vehicle is shown to be the first vehicle 102a. However, the scope of the disclosure is not limited to the vehicle being the first vehicle 102a. In another embodiment, the vehicle in FIG. 2 may correspond to the second vehicle 102b. The first vehicle 102a may include the first lock and unlock circuitry 108a, the first control circuitry 110a including a first processor 202 and an artificial intelligence (Al)-based processor 204, the first memory 112a, a network interface 206, a human-machine interface (HMI) 208, a power supply system 210, and vehicular sub-systems 212.

The first lock and unlock circuitry 108a may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, to lock and unlock one or more components of the first vehicle 102a. The one or more components may include a steering column, a brake, an accelerator, wheels, a standing gear, or the like of the first vehicle 102a. The first lock and unlock circuitry 108a may include mechanical and electromechanical components configured to physically and/or operationally lock and unlock the one or more components of the first vehicle 102a. The first lock and unlock circuitry 108a may be configured to prevent the one or more components from being operational when the one or more components are locked. In an embodiment, the first lock and unlock circuitry 108a may be controlled via the service application of the first user device 104a to lock or unlock the one or more components of the first vehicle 102a.

The first control circuitry 110a may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, to control functionalities of a plurality of components of the first vehicle 102a. The first control circuitry 110a may receive one or more instructions and data via the first user device 104a for performing one or more operations associated with the first vehicle 102a. The first control circuitry 110a may be further configured to perform various operations for identification and authentication of the first user device 104a and the first user 103a. The first control circuitry 110a may be configured to receive one or more signals from the first user device 104a. The first control circuitry 110a may be further configured to analyze the received signals to determine a live location, a speed, a trajectory, and a timestamp associated with the first vehicle 102a. Although the first control circuitry 110a is shown to include the first processor 202 and the

AI-based processor 204 as two standalone processors, in other embodiments, the functionalities of the first processor 202 and the AI-based processor 204 may be implemented by a single processor without limiting the scope of the disclosure.

The first processor 202 may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, to perform automatic locking and unlocking of the one or more components of the first vehicle 102a. The first processor 202 may be configured to receive the first data from the first user device 104a. The first data may be indicative of the signal strength of a wireless signal received from the first user device 104a, the time-series speed data sensed by the plurality of sensors of the first user device 104a, and the time-series location data (e.g., GPS data) of the first user device 104a. The first processor 202 may be configured to determine the first distance gradient for the first user device 104a based on the first data. The first processor 202 may be further configured to determine the speed with which the first user device 104a progresses towards the first vehicle 102a based on the first data. In an exemplary scenario, the time-series GPS data received by the first processor 202 from the first user device 104a may indicate that the first user device 104a was present at a first location A at time instance ti (e.g., 4 PM) and at a second location B at time instance t2 (e.g., 4:01 PM). The time-series GPS data may further indicate that a distance between the first location A and the second location B is “50 meters”. Therefore, a speed of movement of the first user device 104a may be 50 meters/minute or 0.83 meters/second. In an embodiment, when the second location B is nearer to a location of the first vehicle 102a than the first location A, the first processor 202 may determine that the speed with which the first user device 104a is progressing towards the first vehicle 102a is 50 meters/minute or 0.83 meters/second. In another embodiment, when the first location A is nearer to a location of the first vehicle 102a than the second location B, the first processor 202 may determine that the speed with which the first user device 104a is progressing away from the first vehicle 102a is 50 meters/minute or 0.83 meters/second.

In another exemplary scenario, the first processor 202 may be configured to continuously monitor a rate of change of the signal strength of the wireless signal received from the first user device 104a. The signal strength may get stronger as the first user device 104a progresses towards the first vehicle 102a. Therefore, the first processor 202 may correlate the rate of change of the signal strength with a distance of the first user device 104a from the first vehicle 102a. A change in the signal strength with respect to time may be utilized by the first processor 202 to determine the speed with which the first user device 104a progresses towards the first vehicle 102a. For example, a signal strength of a first wireless signal received from the first user device

104a may be SSi when the first user device 104a is positioned at a distance of 200 meters from the first vehicle 102a. The signal strength may change to SS2 when the first user device 104a is positioned at a distance of 100 meters from the first vehicle 102a. If the first wireless signal is received at 5 PM and the second wireless signal is received at 5:01 PM, the first processor 202 may determine that the speed with which the first user device 104a is progressing towards the first vehicle 102a is 100 meters per minute or 1.67 meters/second. However, if the first wireless signal is received at 5:01 PM and the second wireless signal is received at 5:00 PM, the first processor 202 may determine that the speed with which the first user device 104a is progressing away from the first vehicle 102a is 100 meters per minute or 1.67 meters/second. The first processor 202 may be further configured to detect the first unlocking event based on the match between the determined speed and the leamt speed pattern. One or more concepts of learning the speed pattern and detecting the first unlocking event based on the match of the determined speed and the learnt speed pattern are described in detail in conjunction with FIGS. 5A, 5B, and 5C.

In another embodiment, the first processor 202 may be further configured to determine the path trajectory followed by the first user device 104a to progress towards the first vehicle 102a. The first processor 202 may determine the path trajectory based on the second data received from the first user device 104a. The second data may be indicative of a time-series location of the first user device 104a. The path trajectory may be defined as a curve or a line that is being followed by the first user device 104a while progressing towards the first vehicle 102a. In an embodiment, the first processor 202 may be further configured to detect the first unlocking event based on the match between the determined path trajectory with at least one of the plurality of path profiles. One or more concepts of learning the plurality of path profiles and detecting the first unlocking event based on the match of the determined path trajectory with at least one of the plurality of path profiles are described in detail in conjunction with FIG. 4.

In another embodiment, the first processor 202 may be further configured to determine the timestamp while the first user device 104a progresses towards the first vehicle 102a. The first processor 202 may be configured to determine the timestamp based on at least one of time data received from the first user device 104a, the wireless signal received from the first user device

104a, or the like. The first processor 202 may be configured to determine the first unlocking event based on the match of the timestamp with the learnt temporal routine.

In another embodiment, the first processor 202 may be further configured to determine the second distance gradient for the first user device 104a when the first user device 104a is progressing away from the first vehicle 102a. The first processor 202 may be configured to detect the locking event based on the second distance gradient being greater than or equal to the second preset value. The first processor 202 may be further configured to communicate with the AI-based processor 204 to acquire learnings of the AI-based processor 204 to detect locking and unlocking events. In another embodiment, the first processor 202 may be further configured to determine the distance of the first user device 104a from the first vehicle 102a after the one or more components are unlocked by the first lock and unlock circuitry 108a. The first processor 202 may be configured to grant the first user 103 a the driving access to the first vehicle 102a when the first user device 104a is within the preset distance, for example, when the determined distance of the first user device 104a from the first vehicle 102a is less than the preset distance. Alternatively, the first processor 202 may be configured to enable the park mode of the first vehicle 102a and disable driving access to the first vehicle 102a when the determined distance is greater than the preset distance. In another embodiment, the first processor 202 may be further configured to determine the one or more driving parameters associated with the first vehicle 102a. The first processor 202 may be configured to determine the one or more driving parameters by monitoring a plurality of components of the first vehicle 102a while the first vehicle 102a is being driven. The first processor 202 may be configured to revoke the driving access to the first vehicle 102a when the one or more driving parameters do not match the learnt driving profile associated with the first vehicle 102a.

The AI-based processor 204 may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, to leam during the first time-interval various parameters for detecting unlocking events for the first vehicle 102a. The AI-based processor 204 may apply one or more machine learning algorithms to learn and re-learn the one or more parameters for detecting the unlocking events. The AI-based processor 204 may learn the speed pattern, the plurality of path profiles, and the temporal routine associated with the first vehicle 102a during the first time- interval. The AI-based processor 204 may be further configured to learn the one or more parameters based on day-to-day operations of the first vehicle 102a. Such learnings from day-to- day operations may be used by the first processor 202 to adapt to changing routines and habits associated with the first user device 104a and/or the first vehicle 102a. One or more operations of the AI-based processor 204 are described in detail in conjunction with FIG. 3.

Examples of the first processor 202 and the AI-based processor 204 may include, but are not limited to, an application-specific integrated circuit (ASIC) processor, a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a field- programmable gate array (FPGA) processor, a central processing unit (CPU), a graphics processing unit (GPU), a network processing unit (NPU), a digital signal processor (DSP), or the like. It will be apparent to a person of ordinary skill in the art that the first processor 202 and the AI-based processor 204 may be compatible with multiple operating systems without departing from the scope of the disclosure.

The network interface 206 may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, for facilitating communication using one or more communication protocols. For example, the network interface 206 may facilitate communication between the first control circuitry 110a and the first user device 104a. Examples of the network interface 206 may include, but are not limited to, an antenna, a radio frequency transceiver, a wireless transceiver, a Bluetooth transceiver, an ethernet based transceiver, a universal serial bus (USB) transceiver, an NFC-based transceiver, or any other device configured to transmit and receive data. The HMI 208 may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, for facilitating interaction between the first user 103a and the first vehicle 102a. The HMI 208 may include at least one of a touch screen, a voice-enabled input interface, a physical input interface (such as a keyboard), or the like. The HMI 208 may be configured to receive (or acquire) inputs from the first user 103a. The HMI 208 may be communicatively coupled to the first control circuitry 110a and may communicate inputs received from the first user 103a to the first control circuitry 110a. In an embodiment, the HMI 208 may be used by the first user 103a to control the first vehicle 102a (e.g., manually lock or unlock the one or more components of the first vehicle 102a), define thresholds and preset values, activate and deactivate various parameters for automatic locking and unlocking. The power supply system 210 may include suitable logic, circuitry, interfaces, and/or code, executable by the circuitry, for powering the one or more components (for example, engine) of the first vehicle 102a. The power supply system 210 may include one or more batteries, capacitors, or the like configured to power the one or more components of the first vehicle 102a. The power supply system 210 may be controlled by the first control circuitry 110a or the first lock and unlock circuitry 108a to power or depower the one or more components of the first vehicle 102a. In an embodiment, the power supply system 210 may be controlled via the HMI 208 or the first user device 104a to power or depower the one or more components of the first vehicle 102a. In an embodiment, the first vehicle 102a may operate in a low power mode or a power saver mode prior to and/or while detecting the first unlocking event. During the power saver mode, the first vehicle 102a may consume energy less than a threshold energy value. The first vehicle 102a, while in the power saver mode, may activate only those components and features that are essential for detecting the first unlocking event. Further, the first vehicle 102a may include a backup power supply (for example, a battery pack, a supercapacitor, or the like). When a state of charge (SoC) of the power supply system 210 is less than a threshold SoC, the backup power supply may facilitate detection of the first unlocking event by the first vehicle 102a. In an embodiment, the low power mode may be customizable or configurable such that the components and features that are to remain active prior to and during the detection of the first unlocking event may be selected based on a selection input received by the first control circuitry 110a. The selection input may be received via the first user device 104a or an I/O interface of the first vehicle 102a.

The vehicular sub-systems 212 of the first vehicle 102a may include the one or more components of the first vehicle 102a that are responsible for the functioning of the first vehicle 102a. The vehicular sub-systems 212 may be controlled by the first lock and unlock circuitry 108a and/or the first control circuitry 110a. Examples of the vehicular sub-systems 212 may include, but are not limited to, a battery pack, a steering column, a braking system, or the like.

In an embodiment, the first vehicle 102a may further include an intra-vehicle network 214 for facilitating communication among various components of the first vehicle 102a. Examples of the intra-vehicle network 214 may include a controlled area network (CAN), a FlexRay network, an Automotive Ethernet, a Media Oriented System Transport (MOST) network, or the like. It will be apparent to a person of ordinary skill in the art that the first vehicle 102a may implement various other protocols for communication among vehicular components without deviating from the scope of the disclosure. It will be apparent to a person skilled in the art that FIG. 2 is an exemplary illustration of the first vehicle 102a. In other embodiments, the first vehicle 102a may include additional or different components.

FIG. 3 is a diagram that represents a learning phase executed by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 3, the first vehicle 102a is shown to execute the learning phase for automatic locking and unlocking.

The first vehicle 102a may be configured to execute the learning phase during the first time- interval. The first time-interval may start (or begin) when a new device is registered with the first vehicle 102a. For example, the first time-interval may begin when the first user device 104a is registered with the first vehicle 102a. Registering of the first user device 104a with the first vehicle 102a may include an exchange of a one time password, a user account- password combination, or the like. In an embodiment, the first vehicle 102a may be locked or unlocked manually by the first user 103 a during the first time-interval. For example, during the first time- interval, the first user 103a may take a path that is different from paths learnt by the first vehicle 102a. Therefore, the first vehicle 102a may not detect an unlocking event hence the first user 103a may manually unlock the first vehicle 102a using the physical key or the first user device 104a. Subsequently, the new path is learnt by the AI-based processor 204. In another embodiment, the first vehicle 102a may be locked or unlocked automatically based on a distance gradient of the registered first user device 104a with respect to the first vehicle 102a during the first time-interval. The first vehicle 102a may be configured to observe and record various parameters of the first user device 104a with regard to various locking and unlocking events of the first vehicle 102a during the first time- interval.

The first control circuitry 110a may be configured to receive speed data and time-series location data from the first user device 104a every time the first vehicle 102a is unlocked during the first time- interval. The speed data received from the first user device 104a may refer to a time-series speed data of the first user device 104a that was recorded (measured or sensed) while the first user device 104a was progressing towards the first vehicle 102a, for each of the unlocking event during the first time-interval. The AI-based processor 204 may be configured to utilize the speed data associated with the unlocking events of the first time-interval to learn a speed pattern of the first user device 104a. In an embodiment, the speed pattern may be indicative of a maximum speed range, a minimum speed range, and/or a median speed with which the first user device 104a progressed towards the first vehicle 102a at the unlocking events during the first time- interval. The AI-based processor 204 may be configured to determine the maximum speed range by aggregating maximum speeds of the first user device 104a at multiple unlocking events of the first time-interval. For example, for five unlocking events of the first time-interval, the maximum speed of the first user device 104a may be recorded as 1 meter/second (m/s), 1.5 m/s, 1.45 m/s, 1.78 m/s, and 1.85 m/s. In such a scenario, the AI-based processor 204 may be configured to determine the maximum speed range as 1.85m/s - 1.5 m/s. In another exemplary scenario, the AI-based processor 204 may learn a deviation in the maximum speed of the first user device 104a across different unlocking events and determine the maximum speed range based on the deviation. The AI-based processor 204 may be configured to determine the minimum speed range by aggregating minimum speeds of the first user device 104a at multiple unlocking events of the first time-interval. For example, for five unlocking events of the first time-interval, the minimum speed of the first user device 104a may be recorded as 0.5 m/s, 0.55 m/s, 0.45 m/s, 0.78 m/s, and 0.85 m/s. In such a scenario, the AI-based processor 204 may be configured to determine the minimum speed range as 0.85m/s - 0.5 m/s. In another exemplary scenario, the AI-based processor 204 may learn a deviation in the minimum speed of the first user device 104a across different unlocking events and determine the minimum speed range based on the deviation. The median speed is a magnitude of speed that is positioned at a middle position in the time-series speed data. In an example, the time-series speed data may include 1 meter/second (m/s), 0.5 m/s, 1.5 m/s, 2 m/s, and 2.5 m/s. Here, the median speed is 1.5 m/s. In an embodiment, the AI-based processor 204 may be configured to learn multiple speed patterns for the first user device 104a based on multiple parking locations of the first vehicle 102a. In such a scenario, each speed pattern may be associated with a different location and may be learnt based on speed data corresponding to unlocking events at the corresponding location. An exemplary scenario for learning the speed pattern of the first user device 104a by the first vehicle 102a is described in detail in conjunction with FIGS. 5A-5C. The AI-based processor 204 may be configured to store the learnt speed pattern in the first memory 112a. The stored speed pattern may be utilized by the first control circuitry 110a for detecting a future unlocking event (for example, after the first time- interval) for the first vehicle 102a.

The AI-based processor 204 may be further configured to learn the plurality of path profiles based on the second data including at least the time-series location data received from the first user device 104a. Each path profile may be associated with at least one of a location and time associated with at least one of the first vehicle 102a and the first user device 104a. Each path profile may include a plurality of path trajectories followed by the first user device 104a, at multiple unlocking events during the first time-interval, to progress towards the first vehicle 102a that is parked at a corresponding location. In an example, the first vehicle 102a may be parked in a parking area. The parking area may have three entry gates, e.g., a first gate, a second gate, and a third gate. In the first time-interval, the first user 103a holding the first user device 104a may have used the three entry gates to enter the parking area at three different unlocking events of the first vehicle 102a, respectively. Therefore, a path profile associated with the parking area may include three path trajectories corresponding to the first, second, and third gates to the parking area. In another example, the AI-based processor 204 may learn a path profile by correlating each path trajectory with its corresponding time of unlocking event. For example, the first user 103a may progress towards the first vehicle 102a via the first gate in morning, the second gate at noon, and the third gate at night. Therefore, the path profile associated with the parking area may include three path trajectories that are correlated with a routine of the first user device 104a. An exemplary scenario for learning the plurality of path profiles of the first user device 104a by the first vehicle 102a is described in detail in conjunction with FIG. 4. The AI-based processor 204 may be configured to store the learnt plurality of path profiles in the first memory 112a. The stored plurality of path profiles may be utilized by the first control circuitry 110a for detecting a future unlocking event (for example, after the first time-interval) for the first vehicle 102a.

The AI-based processor 204 may be further configured to learn the temporal routine associated with the plurality of unlocking events. The AI-based processor 204 may be configured to determine a temporal trend or a temporal pattern in the plurality of unlocking events of the first vehicle 102a. For example, the AI-based processor 204 may determine that the first vehicle 102a was unlocked between 9-10 AM and 4-5 PM on Monday-Friday for two consecutive weeks (e.g., the first time-interval). Therefore, the AI-based processor 204 may learn a temporal routine that indicates unlocking of the first vehicle 102a between 9-10 AM and 4-5 PM on Mondays-Fridays. In another example, the AI-based processor 204 may leam a pattern that the first vehicle 102a is being unlocked at 6 AM, 2 PM, and 8 PM every day. Therefore, the AI-based processor 204 may learn a temporal routine that the plurality of unlocking events associated with the first vehicle 102a occur at 6 AM, 2 PM, and 8 PM every day. In another example, the AI-based processor 204 may leam that the first vehicle 102a, when parked at a specific location (e.g., home parking), does not get unlocked for at least 12 hours, e.g., between 8PM - 6AM. Therefore, the AI-based processor 204 may learn to not detect an unlocking event in an instance when the first vehicle 102a is parked at the specific location and the first user device 104a pairs within 2 hours of the first vehicle 102a being parked. The AI-based processor 204 may be configured to store the learnt temporal routine in the first memory 112a.

The AI-based processor 204 may be further configured to leam the driving profile associated with the first vehicle 102a. The driving profile may include one or more driving parameters associated with the first vehicle 102a. The AI-based processor 204 may determine the one or more driving parameters associated with the first vehicle 102a. In an example, the AI-based processor 204 may learn that the first vehicle 102a is moved in a to-and-fro direction before starting the engine of the first vehicle 102a. In another example, the AI-based processor 204 may observe that the first vehicle 102a is driven maximum at a speed of 60 kilometers per hour. Therefore, the AI-based processor 204 may learn a driving parameter that the first vehicle 102a is driven maximum at the speed of 60 kilometers per hour. As shown in FIG. 3, the driving profile learnt by the AI-based processor 204 may be stored in the first memory 112a.

In an embodiment, the AI-based processor 204 may be configured to deduce one or more rules for detecting unlocking events. In an example, after a locking event, the first user 103a may approach the first vehicle 102a to retrieve an article stored in a storage of the first vehicle 102a. In this scenario, the first processor 202 may detect an unlocking event based on comparison of speed and path trajectory of the first user device 104a with the learnt speed pattern and path profile, respectively. However, the first user 103a may manually lock the first vehicle 102a using the first user device 104a after the first vehicle 102a was automatically unlocked. Therefore, the AI-based processor 204 may leam that, upon detection of a locking event, if the first user 103a rushes back to the first vehicle 102a it may not be associated with the intent of unlocking the first vehicle 102a. The one or more rules for detecting the unlocking events learnt by the AI-based processor 204 are stored in the first memory 112a. As shown, the first memory 112a, further stores the first preset value and the second preset value. The first and second preset values may be predefined values. In an embodiment, the first and second preset values may be defined by the first user. In an example, the first user 103 a may define the first and second preset values using the HMI 208 based on a geographical region associated with the first vehicle 102a.

FIG. 4 is a diagram that represents an exemplary scenario for learning of path profiles by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 4, illustrated in the exemplary scenario 400 is the first vehicle 102a and a residence 402 of the first user 103a. The exemplary scenario 400 further illustrates the first user device 104a associated with the first vehicle 102a and the first user 103a. During the first time-interval the AI-based processor 204 may be configured to learn a plurality of path profiles for the first vehicle 102a. The exemplary scenario 400 illustrates learning of one such path profile by the first vehicle 102a. At a first time-instance during the first time-interval, the first vehicle 102a may be parked at the location LI by the first user 103a. The AI-based processor 204 may detect the location LI of the first vehicle 102a based on a GPS sensor in the first vehicle 102a. When the first user device 104a enters the threshold zone 105a of the first vehicle 102a, the first user device 104a may get paired with the first vehicle 102a. The first user 103a possessing the first user device 104a may follow a first path PI to reach the location LI from the residence 402. The first vehicle 102a may detect an unlocking event EL In one example, the unlocking event El may be detected due to a manual unlocking of the first vehicle 102a by the first user 103a using the service application on the first user device 104a, a key fob of the first vehicle 102a, or the like. In another example, the unlocking event El may be detected automatically by the first vehicle 102a due to a progression of the first user device 104a towards the first vehicle 102a with a distance gradient being greater than the first preset value. Determination of the distance gradient has been described in the foregoing description of FIGS. 1A-1B, 2, and 3.

While the first user device 104a was progressing towards the first vehicle 102a, the first vehicle 102a may continuously receive time-series location data from the first user device 104a indicating an absolute path PI followed by the first user device 104a to reach the location LI. When the unlocking event El is detected, the AI-based processor 204 may be configured to correlate the time-series location data of the first path PI with the unlocking event El, and leam a path profile 404 associated with the location LI . The path profile 404 may include the first path PI and a first region (e.g., a residual region added to the first path PI) that is within a predetermined threshold (e.g., within 3 meters) from the first path PI. The AI-based processor 204 may be further configured to store the path profile 404 in the first memory 112a.

At a second time-instance during the first time- interval, the first vehicle 102a may be parked at the location LI again and the first vehicle 102a may detect another unlocking event E2. When the unlocking event E2 is detected, the AI-based processor 204 may be configured to correlate time-series location data of a second path P2 followed by the first user device 104a to reach the location LI at the unlocking event E2 with the unlocking event E2, and update the path profile 404 associated with the location LI. The updated path profile 404 may now include the first path PI, the first region, the second path P2, and a second region that is within a predetermined threshold (e.g., within 3 meters) from the second path P2. The AI-based processor 204 may be further configured to store the updated path profile 404 in the first memory 112a.

Similarly, the AI-based processor 204 may be further configured to update the path profile 404 based on other unlocking events that occur during the first time-interval at the location LI. Additionally, the AI-based processor 204 may learn additional path profiles for other locations where the first vehicle 102a was parked. Each path profile may include a plurality of paths followed by the first user device 104a to reach the first vehicle 102a parked at the corresponding location and a residual region associated with the plurality of paths. Lor example, the AI-based processor 204 may leam another path profile associated with an office parking location of the first user 103a. During the implementation phase that is to say after the AI-based processor 204 has successfully learnt the path profile 404 associated with the location LI, the first vehicle 102a may be parked at the location LI and the first user device 104a may follow a path P3 to reach the location LI from the residence 402. In one example, the path P3 may be the same as one of the paths previously followed by the first user device 104a during the first time- interval. In another example, the path P3 may be different from the paths previously followed by the first user device 104a during the first time-interval.

The first user device 104a may be paired with the first vehicle 102a as the path P3 is within the threshold zone 105a. Therefore, while the first user device 104a is following the path P3, the first vehicle 102a may continue to receive time-series location data from the first user device 104a. The first processor 202 may be configured to determine a path trajectory associated with the path P3 based on the time-series location data received from the first user device 104a. The first processor 202 may be further configured to select one of the path profiles (e.g., the path profile 404 stored in the first memory 112a that corresponds to the current location (e.g., the location LI) of the first vehicle 102a. The first processor 202 may be configured to match the path trajectory associated with the path P3 with the path profile 404. In one example, the first processor 202 may determine that the path P3 is same as one of the paths included in the path profile 404. In such a scenario, the first processor 202 determines that the path P3 matches the path profile 404. In another example, the first processor 202 may determine that the path P3 is different from the paths included in the path profile 404 but a region associated with the path P3 is included in the path profile 404. In such a scenario, the first processor 202 determines that the path P3 matches the path profile 404. When the first processor 202 determines that the path P3 matches the path profile 404, the first processor 202 detects it as an unlocking event E3. As a result, the first processor 202 may control the first lock and unlock circuitry 108a to unlock the one or more components of the first vehicle 102a.

The first vehicle 102a may be parked at the location LI again and the first user device 104a may follow another path P4 to reach the location LI from the residence 402. In a non-limiting example, it is assumed that the path P4 is different from the paths previously followed by the first user device 104a during the first time-interval. While the first user device 104a is following the path P4, the first vehicle 102a may continue to receive time-series location data from the first user device 104a. The first processor 202 may determine a path trajectory associated with the path P4 based on the time-series location data. The first processor 202 may select the path profile 404 stored in the first memory 112a that corresponds to the current location (e.g., the location LI) of the first vehicle 102a. The first processor 202 may then match the path P4 with the path profile 404. In the current example, the first processor 202 may determine that the path P4 is different from the paths included in the path profile 404. The first processor 202 may further determine that at least a portion of the path P4 is not included in the path profile 404. In such a scenario, the first processor 202 determines that the path P4 does not match the path profile 404. When the first processor 202 determines that the path P4 does not match the path profile 404, the first processor 202 may not detect any unlocking event and the one or more components of the first vehicle 102a may remain locked.

In a scenario where the first vehicle 102a detects a manual unlocking event E4 after the determination that the path P4 does not match the path profile 404, the AI-based processor 204 may correlate the time-series location data of the path P4 with the unlocking event E4, and update the path profile 404 associated with the location LI to include the path P4. The AI-based processor 204 may then store the updated path profile 404 in the first memory 112a such that any subsequent unlocking event at the location LI is detected based on the updated path profile 404. In a case where the first vehicle 102a visits a new location, a new path profile may be added to the plurality of path profiles for the new location.

In another embodiment, the first processor 202 may be configured to detect a percentage of match between the determined path trajectory of the path P4 and the path profile 404. The first processor 202 may determine that the path P4 matches the path profile 404 when the determined percentage of match between the path P4 and the path profile 404 equals or exceeds a threshold match percentage. For example, the threshold match percentage may be “90 percent”. Therefore, 90 percent of time-series location data should fall within the path profile 404 for a path to be a successful match to the path profile 404. The path P4 followed by the first user device 104a may have “95 percent” time-series location data that is included within the path profile 404. Therefore, the first processor 202 may be configured to determine the path P4 matches the corresponding path profile. In an embodiment, the first processor 202 may be configured to determine the threshold match percentage required for matching a path with the path profile 404. In another embodiment, the threshold match percentage required may be defined by the first user 103a using the HMI 208 or the service application running on the first user device 104a. The AI-based processor 204 may be further configured to learn a temporal routine associated with the first user device 104a. In one embodiment, the AI-based processor 204 may leam the temporal routine by correlating a time of an unlocking event and a location of the unlocking event. For example, the AI-based processor 204 may determine that the first user device 104a has progressed towards the first vehicle 102a between 9:00 AM - 9:30 AM on weekdays to unlock the first vehicle 102a parked at the location LI. Therefore, the AI-based processor 204 may learn a temporal routine that the first user device 104a progresses towards the first vehicle 102a between 9:00 AM - 9:30 AM on weekdays for unlocking. The learnt temporal routine may be utilized to detect unlocking events for the first vehicle 102a in the future. For example, the first processor 202 may determine that the first user device 104a is progressing towards the first vehicle 102a at 9: 15 AM on a Monday. In such a scenario, the first processor 202 may determine that the timestamp (e.g., 9:15 AM on a Monday) while the first user device 104a progresses towards the first vehicle 102a matches the temporal routine. Thus, the first processor 202 may detect an unlocking event and control the first lock and unlock circuitry 108a to unlock one or more components of the first vehicle 102a. However, if the first processor 202 determines that a timestamp (e.g.., 10:15 AM on a Monday) while the first user device 104a progresses towards the first vehicle 102a does not match the temporal routine, the first processor 202 does not detect an unlocking event and the one or more components of the first vehicle 102a remain locked.

In another embodiment, the AI-based processor 204 may further leam the temporal routine by correlating a time of an unlocking event, a location of the unlocking event, and a path associated with the unlocking event. For example, the AI-based processor 204 may determine that the first user device 104a progresses towards the first vehicle 102a between 9:00 AM - 9:30 AM on weekdays when the first vehicle 102a is parked at the location LI. The AI-based processor 204 may further determine that the first user device 104a always follow the path PI or P2 while progressing towards the first vehicle 102a between 9:00 AM - 9:30 AM on weekdays. Therefore, the AI-based processor 204 may learn a temporal routine that the first user device 104a progresses towards the first vehicle 102a between 9:00 AM - 9:30 AM on weekdays following the path PI or P2. The leamt temporal routine may be utilized to detect unlocking events for the first vehicle 102a in the future. For example, the first processor 202 may determine that the first user device 104a is progressing towards the first vehicle 102a at 9:15 AM on a Monday. Based on the time-series location data received from the first user device 104a, the first processor 202 may determine that the first user device 104a is following a path that is included in the path profile 404 but is different from the paths PI or P2 and is also outside the residual regions associated with the paths PI or P2. In such a scenario, the first processor 202 may determine that the temporal routine and the path profile 404 are not satisfied. Thus, the first processor 202 may not detect any unlocking event and the one or more components of the first vehicle 102a may remain locked. However, if the first processor 202 determines that the first user device 104a is following one the paths PI or P2 to progress towards the first vehicle 102a at 9:15 AM on a Tuesday, the first processor 202 may determine that the temporal routine and the path profile 404 are satisfied by the current timestamp. Thus, the first processor 202 may detect an unlocking event and the one or more components of the first vehicle 102a may be unlocked.

FIGS. 5A, 5B, and 5C, collectively, illustrate diagrams that represent an exemplary scenario for learning a speed pattern of a user device by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure. Referring to FIGS. 5A, 5B, and 5C, the exemplary scenario 500 illustrates learning of the speed pattern of the first user device 104a by the first vehicle 102a for automatic locking and unlocking. For the sake of brevity, the first vehicle 102a is assumed to be parked at the location LI and the first vehicle 102a is aware of its current location LI based on the location data from the GPS sensor.

Referring to FIG. 5A, at the first unlocking event El during the first time-interval, the first user device 104a may have progressed towards the first vehicle 102a with a first speed. The first processor 202 may be configured to determine the first speed based on first speed data SI associated with the first unlocking event EL The first speed data SI may include a time series of speed values with which the first user device 104a progressed towards the first vehicle 102a at the first unlocking event EL As described in the foregoing description of FIGS. 1A-3, the first processor 202 may obtain the first speed data SI using the wireless signal strength of the wireless signal (such as a Wi-Fi signal, a Bluetooth signal, a radio signal, or the like) received by the first vehicle 102a from the first user device 104a, the time-series location data received from the first user device 104a, the sensor data of the one or more sensors (for example, an accelerometer, a speed sensor, or the like) of the first user device 104a. Based on the first speed data SI, the AI-based processor 204 may be configured to determine a maximum speed SI, a minimum speed SI, and a median speed SI corresponding to the first speed data SI associated with the first unlocking event El. The maximum speed SI may correspond to the highest magnitude of speed within the first speed data SI associated with the first unlocking event El. The minimum speed SI may correspond to the lowest magnitude of speed within the first speed data SI associated with the first unlocking event El. The median speed SI may correspond to a middle value (e.g., a centermost value) of the first speed data SI associated with the first user device 104a during the first unlocking event El. The AI-based processor 204 may be configured to learn the speed pattern that includes the maximum speed SI, the minimum speed S 1 , and the median speed S 1.

Referring to FIG. 5B, at the second unlocking event E2 during the first time-interval, the first user device 104a may progress towards the first vehicle 102a with a second speed that is different from the first speed. The first processor 202 may be configured to determine the second speed based on second speed data S2 associated with the second unlocking event E2. The second speed data S2 may include a time series of speed values with which the first user device 104a progressed towards the first vehicle 102a at the second unlocking event E2. Based on the second speed data S2, the AI-based processor 204 may be configured to determine a maximum speed S2, a minimum speed S2, and a median speed S2 corresponding to the second speed data S2. The AI-based processor 204 may be further configured to update the learnt speed pattern based on the maximum speed S2, the minimum speed S2, and the median speed S2. For example, the AI- based processor 204 may update the learnt speed pattern to include a maximum speed range, a minimum speed range, and a median speed range based on the maximum speeds SI and S2, the minimum speeds SI and S2, and the median speeds SI and S2.

Subsequently, the AI-based processor 204 may continue to leam and update the speed pattern based on speed data received during subsequent unlocking events in the first time-interval. The learnt speed pattern may define upper and lower boundaries of speed with which the first user device 104a may progress towards the first vehicle 102a with an intent to unlock the first vehicle 102a. Referring to FIG. 5C, after the first time- interval, the first user device 104a may get paired with the first vehicle 102a when the first user device 104a enters the threshold zone 105a (as shown in FIG. 1A). The first processor 202 may be configured to obtain time-series speed data associated with the first user device 104a when the first user device 104a is determined to be progressing towards the first vehicle 102a. The first processor 202 may obtain time-series speed data based on the signal strength of the wireless signal received from the first user device 104a, time-series speed measurements sensed by the sensors of the first user device 104a, and time-series location data of the first user device 104a (as described in the foregoing description of FIGS. 1A, 2, and 3). The first processor 202 may be further configured to determine a maximum speed S3, a minimum speed S3, and/or a median speed S3 based on the obtained time-series speed data. The first processor 202 may match the maximum speed S3, the minimum speed S3, and/or the median speed S3 with the speed pattern learnt by the AI-based processor 204.

In an embodiment, the maximum speed S3, the minimum speed S3, and the median speed S3 may not match the learnt speed pattern. In other words, the maximum speed S3 may be outside the maximum speed range defined in the learnt speed pattern, the minimum speed S3 may be outside the minimum speed range defined in the learnt speed pattern, and/or the median speed S3 may be outside the median speed range defined in the leamt speed pattern. When the first processor 202 determines that the current speed (maximum speed, minimum speed, and/or median speed) does not match the learnt speed pattern, the first processor 202 may not detect any unlocking event and the one or more components of the first vehicle 102a may remain locked.

In another embodiment, the maximum speed S3, the minimum speed S3, and the median speed S3 may match the learnt speed pattern. In other words, the maximum speed S3 may be within the maximum speed range defined in the leamt speed pattern, the minimum speed S3 may be within the minimum speed range defined in the learnt speed pattern, and/or the median speed S3 may be within the median speed range defined in the learnt speed pattern. When the first processor 202 determines that the current speed (maximum speed, minimum speed, and/or median speed) matches the learnt speed pattern, the first processor 202 may detect an unlocking event and the one or more components of the first vehicle 102a may be unlocked by the first lock and unlock circuitry 108a. In another embodiment, the speed pattern leamt by the AI-based processor 204 may define a range of speed within which a current speed of the first user device 104a progressing towards the first vehicle 102a should lie for automatic unlocking. For example, the range of speed may include an upper limit (e.g., maxima) of 5 kilometers per hour and a lower limit (e.g., minima) of 0.5 kilometers per hour. Therefore, the first user device 104a progressing towards the first vehicle 102a with a speed of 6 kilometers per hour may be detected as an intruder trying to unlock the first vehicle 102a. However, when the first user device 104a progresses towards the first vehicle 102a with a speed of 4.5 kilometers per hour that matches the leamt speed pattern, the first processor 202 may detect it as an unlocking event. As a result, the first processor 202 may control the first lock and unlock circuitry 108a to unlock the one or more components of the first vehicle 102a. In an embodiment, the AI-based processor 204 may determine an offset that may be added or subtracted from the determined speed to normalize the determined speed. For example, the range may be 5 km/h to 9 km/h, and the determined speed may be 4.8 km/h. Therefore, an offset of 0.2 km/h may be added to the determined speed and the determined speed may match the learnt speed pattern.

In another embodiment, the first processor 202 may determine that the current speed (maximum speed, minimum speed, and/or median speed) matches the leamt speed pattern, when the deviation in the current speed and the leamt speed pattern is less than a speed threshold value. In other words, the first processor 202 may determine that the current speed matches the learnt speed pattern, when a deviation in the pluralities maximum speed S3 and the maximum speed range defined in the learnt speed pattern is less than the speed threshold value, when a deviation in the pluralities minimum speed S3 and the minimum speed range defined in the learnt speed pattern is less than the speed threshold value, and/or when a deviation in the pluralities median speed S3 and the median speed range defined in the learnt speed pattern is less than the speed threshold value. For example, the maximum speed range defined in the learnt speed pattern may be 6-10 km/hr and the speed threshold value may be 2 km/hr. In such a scenario, if the maximum speed S3 is within 4-12 km/hr may determine the maximum speed S3 to match the maximum speed range defined in the leamt speed pattern. In other words, the speed threshold value of 2 km/hr is added to an upper bound of the maximum speed range and subtracted from a lower bound of the maximum speed range. In an embodiment, the AI-based processor 204 may be configured to learn the speed pattern by plotting the speed data pertaining to the plurality of unlocking events in the first time-interval on a graph (e.g., a time versus speed graph).

In another embodiment, the AI-based processor 204 may be configured to learn a new speed pattern as an anomaly. For example, the first user 103a may be getting late for his/her office and may have run towards the first vehicle 102a. Therefore, a speed of the first user device 104a while progressing towards the first vehicle 102a may not match the leamt speed pattern. In such a scenario, the first processor 202 may not detect an unlocking event. However, based on a manual unlocking event associated with the first vehicle 102a, the AI-based processor 204 may be configured to learn the determined speed as an anomaly pattern.

In a scenario where the first vehicle 102a detects a manual unlocking event after the determination that the current speed of the first user device 104a does not match the leamt speed pattern, the AI-based processor 204 may correlate the time-series speed data of the current speed with the manual unlocking event, and re-learn the speed pattern. Re-learning of the speed pattern may include updating the speed pattern based on the time-series speed data of the current speed. The AI-based processor 204 may then store the re-learnt speed pattern in the first memory 112a such that any subsequent unlocking event is detected based on the re-learnt speed pattern.

FIG. 6 is a diagram that illustrates a system environment for automatic locking and unlocking of a locking system associated with a facility, in accordance with another exemplary embodiment of the disclosure. Referring to FIG. 6, a system environment 600 is shown that includes a locking system 602 for controlling an access to a facility 604. The system environment 600 further includes the first user device 104a of the first user 103a. The locking system 602 may include a third lock and unlock circuitry 606, a control circuitry 608, and a third memory 610. The locking system 602 may get paired with the first user device 104a when the first user device 104a enters a threshold region 612 of the locking system 602. The control circuitry 608 may be functionally similar to the first processor 202 and the AI-based processor 204 and may execute the learning phase and implementation phase for automatic locking and unlocking as described in the foregoing description. The third lock and unlock circuitry 606 may be functionally similar to the first lock and unlock circuitry 108a and the third memory 610 may be functionally similar to the first memory 112a described in the foregoing description.

It will be apparent to a person of ordinary skill in the art that the automatic locking and unlocking is not limited to vehicles. In another embodiment, the locking system 602 associated with the facility 604 may also implement automatic locking and unlocking of the facility 604 based on an interaction with the first user device 104a. In such an embodiment, the locking system 602 may be configured to automatically lock or unlock a door to an enclosed space, a locker, a safe, a warehouse, a housing society, or the like based on the interaction with the first user device 104a. FIG. 7 is a block diagram that illustrates a system architecture of a computer system for performing automatic locking and unlocking of a vehicle, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 7, a computer system 700 is shown for performing automatic locking and unlocking of the first vehicle 102a. The computer system 700 may include a processor 702, a communication infrastructure 704, a main memory 706, a secondary memory 708, an input/output (I/O) port 710, and a communication interface 712. An embodiment of the disclosure, or portions thereof, may be implemented as computer readable code on the computer system 700. In one example, the first control circuitry 110a of FIG. 1 may be implemented in the computer system 700 using hardware, software, firmware, non-transitory computer readable media having instructions stored thereon, or a combination thereof and may be implemented in one or more computer systems or other processing systems. Hardware, software, or any combination thereof may embody modules and components used to implement the methods of FIGS. 8, 9, and 10A-10C.

The processor 702 may be a special purpose or a general-purpose processing device. The processor 702 may be a single processor or multiple processors. The processor 702 may have one or more processor “cores.” Further, the processor 702 may be coupled to the communication infrastructure 704, such as a bus, a bridge, a message queue, the communication network 106, multi-core message-passing scheme, or the like.

Examples of the main memory 706 may include RAM, ROM, and the like. The secondary memory 708 may include a hard disk drive or a removable storage drive (not shown), such as a floppy disk drive, a magnetic tape drive, a compact disc, an optical disk drive, a flash memory, or the like. Further, the removable storage drive may read from and/or write to a removable storage device in a manner known in the art. In an embodiment, the removable storage unit may be a non-transitory computer readable recording media. The I/O port 710 may include various input and output devices that are configured to communicate with the processor 702. Examples of the input devices may include a keyboard, a mouse, a joystick, a touchscreen, a microphone, and the like. Examples of the output devices may include a display screen, a speaker, headphones, and the like. The communication interface 712 may be configured to allow data to be transferred between the computer system 700 and various devices that are communicatively coupled to the computer system 700. Examples of the communication interface 712 may include a modem, a network interface, for example, an Ethernet card, a communication port, and the like. Data transferred via the communication interface 712 may be signals, such as electronic, electromagnetic, optical, or other signals as will be apparent to a person skilled in the art. The signals may travel via a communications channel, such as the communication network 106, which may be configured to transmit the signals to the various devices that are communicatively coupled to the computer system 700. Examples of the communication channel may include a wireless medium such as a phone line, a cellular phone link, a radio frequency link, and the like. The main memory 706 and the secondary memory 708 may refer to non-transitory computer readable mediums that may provide data that enables the computer system 700 to implement the methods illustrated in FIGS. 8, 9, and 10A-10C.

FIG. 8 is a flow chart that illustrates a method for detecting an unlocking event for a vehicle, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 8, illustrated is a flow chart 800 of the method for detecting the first unlocking event for the first vehicle 102a.

At 802, the speed pattern of the first user device 104a registered with the first vehicle 102a is learnt. The AI-based processor 204 may be configured to learn the speed pattern of the first user device 104a registered with the first vehicle 102a. The AI-based processor 204 may learn the speed pattern of the first user device 104a based on the relationship between the plurality of unlocking events of the first vehicle 102a in the first time-interval and speed data with which the first user device 104a progressed towards the first vehicle 102a at the plurality of unlocking events.

At 804, the speed with which the first user device 104a progresses towards the first vehicle 102a is determined based on the first data associated with the first user device 104a. The first processor 202 may be configured to determine the speed with which the first user device 104a progresses towards the first vehicle 102a based on the first data associated with the first user device 104a.

At 805, the determined speed is compared with the learnt speed pattern. The first processor 202 may be configured to compare the learnt speed pattern with the determined speed. At 806, the first unlocking event is detected based on the comparison of the learnt speed pattern with the determined speed. The first processor 202 may be configured to detect the first unlocking event based on the comparison of the leamt speed pattern with the determined speed, for example, when the determined speed successfully matches the learnt speed pattern.

At 808, the first lock and unlock circuitry 108a is controlled to unlock the one or more components of the first vehicle 102a. The first processor 202 may be configured to control the first lock and unlock circuitry 108a to unlock the one or more components of the first vehicle 102a.

FIG. 9 is a flow chart that illustrates a method for executing a learning phase by a vehicle for automatic locking and unlocking, in accordance with an exemplary embodiment of the disclosure. Referring to FIG. 9, illustrated is a flow chart 900 of the method to execute the learning phase by the first vehicle 102a for automatic locking and unlocking.

At 902, the speed pattern of the first user device 104a registered with the first vehicle 102a is learnt. The AI-based processor 204 may be configured to learn the speed pattern of the first user device 104a registered with the first vehicle 102a. The first processor 202 may learn the speed pattern of the first user device 104a based on the relationship between the plurality of unlocking events of the first vehicle 102a in the first time- interval and speed data with which the first user device 104a progressed towards the first vehicle 102a at the plurality of unlocking events (as described in the foregoing conjunction FIGS. 1 A, 2, 3, and 5A-5C). At 904, the plurality of path profiles of the first user device 104a are learnt over the first time- interval. The AI-based processor 204 may be configured to learn the plurality of path profiles of the first user device 104a over the first time-interval.

At 906, the temporal routine associated with the plurality of unlocking events is learnt. The AI- based processor 204 may be configured to learn the temporal routine associated with the plurality of unlocking events.

At 908, the driving profile associated with the first user 103a of the first vehicle 102a is leamt. The AI-based processor 204 may be configured to learn the driving profile associated with the first user 103a of the first vehicle 102a. At 910, the learnt data is stored in the first memory 112a. The AI-based processor 204 may be configured to store the learnt speed pattern, the plurality of path profiles, and the driving profile in the first memory 112a.

FIGS. 10A, 10B, and IOC, collectively, illustrate a method for automatic locking and unlocking of a vehicle, in accordance with an exemplary embodiment of the disclosure. Referring to FIGS. 10A, 10B, and IOC, illustrated is a flowchart 1000 of the method for automatic locking and unlocking of the first vehicle 102a.

Referring to FIG. 10A, at 1002, the speed with which the first user device 104a progresses towards the first vehicle 102a is determined based on the first data associated with the first user device 104a. The first processor 202 may be configured to determine the speed with which the first user device 104a progresses towards the first vehicle 102a based on the first data associated with the first user device 104a.

At 1004, the path trajectory followed by the first user device 104a to progress towards the first vehicle 102a is determined based on the second data associated with the first user device 104a. The first processor 202 may be configured to determine the path trajectory followed by the first user device 104a to progress towards the first vehicle 102a based on the second data associated with the first user device 104a. At 1006, the timestamp while the first user device 104a progresses towards the first vehicle 102a is determined based on the first data. The first processor 202 may be configured to determine, based on the first data, the timestamp while the first user device 104a progresses towards the first vehicle 102a. At 1008, the first distance gradient with which the paired user device (e.g., the first user device 104a) progresses towards the first vehicle 102a is determined. The first processor 202 may be configured to determine, based on the first data, the first distance gradient with which the paired user device (e.g., the first user device 104a) progresses towards the first vehicle 102a.

At 1010, it is determined whether the first distance gradient is greater than or equal to the first preset value. The first processor 202 may be configured to determine whether the first distance gradient is greater than or equal to the first preset value.

If at 1010, the first processor 202 determines that the first distance gradient is not greater than or equal to the first preset value, 1012 is executed. At 1012, no action is performed. In other words, the one or more components of the first vehicle 102a remain locked. If at 1010, the first processor 202 determines that the first distance gradient is greater than or equal to the first preset value, 1013 is executed.

Referring to FIG. 10B, at 1013, the determined data is compared with the learnt data. The first processor 202 compares the determined data with the learnt data. The determined data may refer to the determined speed, the path trajectory, and the timestamp. For example, the first processor 202 may compare the determined speed with the learnt speed pattern, the path trajectory with the plurality of path profiles, and/or the timestamp with the learnt temporal routine.

At 1014, it is determined whether the determined data matches with the learnt data based on the comparison. The determined data may refer to the determined speed, the path trajectory, and the timestamp. If at 1014, the first processor 202 determines that the determined data does not match the learnt data, 1016 is executed. At 1016, no action is performed. In other words, the one or more components of the first vehicle 102a remain locked. If at 1014, the first processor 202 determines that the determined data matches the leamt data, 1018 is executed. At 1018, the first unlocking event is detected. The first processor 202 may be configured to detect the first unlocking event based on the match of the determined data with the leamt data.

At 1020, the one or more components of the first vehicle 102a are unlocked. The first processor 202 may be configured to control the first lock and unlock circuitry 108a to unlock the one or more components of the first vehicle 102a.

At 1022, the distance of the first user device 104a from the first vehicle 102a is determined after the one or more components are unlocked. The first processor 202 may be configured to determine the distance of the first user device 104a from the first vehicle 102a after the one or more components are unlocked. At 1024, it is determined whether the distance is less than the preset distance. If at 1024, the first processor 202 determines that the distance is greater than the preset distance, 1026 is executed. At 1026, the park mode of the first vehicle 102a is enabled by the first processor 202. In other words, no driving access is granted to the first user 103a for driving the first vehicle 102a based on the determined distance being greater than the preset distance. If at 1024, the first processor 202 determines that the distance is less than the preset distance, 1028 is executed.

Referring to FIG. IOC, at 1028, the driving access to the first vehicle 102a is granted to the first user 103a. The first processor 202 may be configured to grant the driving access to the first vehicle 102a to the first user 103 a.

At 1030, the one or more driving parameters of a current user are determined while the first vehicle 102a is being driven by the current user. The first processor 202 may be configured to determine the driving parameters of the current user while the first vehicle 102a is being driven.

At 1032, it is determined whether the one or more driving parameters match the leamt driving profile associated with the first vehicle 102a. The first processor 202 may be configured to determine whether the driving parameters match the learnt driving profile of the first vehicle 102a.

If at 1032, the first processor 202 determines that the driving parameters match the leamt driving profile, 1034 is executed. At 1034, no action is performed. If at 1032, the first processor 202 determines that the driving parameters do not match the learnt driving profile, 1036 is executed. At 1036, the granted driving access to the first vehicle 102a is revoked. The first processor 202 may be configured to revoke the granted driving access to the first vehicle 102a. In an embodiment, if it is determined the driving parameters do not match the learnt driving profile, the park mode of the first vehicle 102a may be enabled.

Various embodiments of the disclosure provide the first control circuitry 110a for automatic locking and unlocking the first vehicle 102a. The first control circuitry 110a may be configured to learn, over the first time-interval, the speed pattern of the first user device 104a registered with the first vehicle 102a. The speed pattern is learnt based on the relationship between a plurality of unlocking events of the first vehicle 102a in the first time-interval and the speed data with which the first user device 104a progressed towards the first vehicle 102a at the plurality of unlocking events in the first time-interval. The first control circuitry 110a may be further configured to learn, over the first time- interval, the driving profile associated with the first vehicle 102a, the plurality of path profiles associated with the first vehicle 102a, and the temporal routine of the first vehicle 102a. The first control circuitry 110a may be further configured to determine, based on the first data received from the first user device 104a, the first distance gradient and may further determine the speed with which the first user device 104a progresses towards the first vehicle 102a based on the first distance gradient being greater than or equal to the first preset value. The first data is received after the first time- interval. The first control circuitry 110a may be further configured to determine the path trajectory and the timestamp based on the first data. The first control circuitry 110a may be further configured to compare the determined speed with the leamt speed profile, the path trajectory with the plurality of path profiles, and/or the timestamp with the learnt temporal routine and detect the first unlocking event based on the comparison of the determined speed with the learnt speed profile, the path trajectory with the plurality of path profiles, and./or the timestamp with the learnt temporal routine. The first control circuitry 110a may be further configured to control the first lock and unlock circuitry 108a to unlock the one or more components of the first vehicle 102a based on the detected first unlocking event.

Various embodiments of the disclosure provide a non-transitory computer readable medium having stored thereon, computer executable instructions, which when executed by a computer, cause the computer to execute one or more operations for automatic locking and unlocking of the first vehicle 102a. The one or more operations include learning, over the first time- interval, the speed pattern of the first user device 104a registered with the first vehicle 102a. The speed pattern is learnt based on the relationship between the plurality of unlocking events of the first vehicle 102a in the first time-interval and the speed data with which the first user device 104a progressed towards the first vehicle 102a at the plurality of unlocking events in the first time- interval. The one or more operations further include learning, over the first time-interval, the driving profile associated with the first vehicle 102a, the plurality of path profiles associated with the first vehicle 102a, and the temporal routine of the first vehicle 102a. The one or more operations further include determining, based on the first data received from the first user device 104a, the first distance gradient. The first data is received after the first time-interval. The one or more operations further include determining, based on the first data, the speed with which the first user device 104a progresses towards the first vehicle 102a based on the first distance gradient being greater than or equal to the first preset value. The one or more operations further include comparing the determined speed with the learnt speed profile, the path trajectory with the plurality of path profiles, and/or the timestamp with the learnt temporal routine and detecting the first unlocking event based on the comparison of the determined speed with the learnt speed profile, the path trajectory with one of the plurality of path profiles, and/or the timestamp with the leamt temporal routine. The one or more operations further include controlling, based on the detected first unlocking event, the first lock and unlock circuitry 108a of the first vehicle 102a to unlock one or more components of the first vehicle 102a.

The disclosed embodiments encompass numerous advantages. Exemplary advantages of the disclosed methods include, but are not limited to, providing a passive keyless entry (PKE) to vehicles or facilities (e.g., the first vehicle 102a or the facility 604). The methods and systems disclosed herein provide a seamless and intelligent approach for locking and unlocking the first vehicle 102a. The disclosed methods ensure that the first vehicle 102a is unlocked only when an authentic user having the first user device 104a progresses towards the first vehicle 102a. The methods and systems disclosed herein significantly reduce a probability of unlocking the first vehicle 102a based on a false-positive detection of the registered first user device 104a. The disclosed methods and systems are AI-enabled and hence continue to improve based on a change in routine and state of the first vehicle 102a. Further, the disclosed methods and systems significantly reduce a requirement for carrying or looking for the physical key to unlock the first vehicle 102a. Technical improvements in the first vehicle 102a or the locking system 602 has enabled quick access to the first vehicle 102a or the facility 604 at all times. The unlocking events are detected based on multiple parameters hence eliminating a chance of false-positive detection of the unlocking events. Further, each parameter is updated (or re-learnt) in real-time based on detection of unlocking events. Further, the methods and systems disclosed herein do not need any modification in a physical structure of the first vehicle 102a and are flexible to be accommodated in any kind of vehicle. The disclosed methods and systems may be incorporated to operate with any vehicle such as a two-wheeled vehicle, a three-wheeled vehicle, a four- wheeled vehicle, or the like.

A person of ordinary skill in the art will appreciate that embodiments and exemplary scenarios of the disclosed subject matter may be practiced with various computer system configurations, including multi-core multiprocessor systems, minicomputers, mainframe computers, computers linked or clustered with distributed functions, as well as pervasive or miniature computers that may be embedded into virtually any device. Further, the operations may be described as a sequential process, however some of the operations may in fact be performed in parallel, concurrently, and/or in a distributed environment, and with program code stored locally or remotely for access by single or multiprocessor machines. In addition, in some embodiments, the order of operations may be rearranged without departing from the scope of the disclosed subject matter.

Techniques consistent with the disclosure provide, among other features, systems and methods for automatic locking and unlocking of a vehicle. While various exemplary embodiments of the disclosed systems and methods have been described above, it should be understood that they have been presented for purposes of example only, and not limitations. It is not exhaustive and does not limit the disclosure to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practicing of the disclosure, without departing from the breadth or scope.

While various embodiments of the disclosure have been illustrated and described, it will be clear that the disclosure is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the scope of the disclosure, as described in the claims.

Claims

I/WE CLAIM:

1. A vehicle, comprising: lock and unlock circuitry; and processing circuitry coupled to the lock and unlock circuitry, wherein the processing circuitry is configured to: learn, over a first time-interval, a speed pattern of a user device registered with the vehicle, wherein the speed pattern is learnt based on a relationship between a plurality of unlocking events of the vehicle in the first time-interval and speed data with which the user device progressed towards the vehicle at the plurality of unlocking events of the vehicle in the first time-interval; determine, based on first data received from the user device, a speed with which the user device progresses towards the vehicle, wherein the first data is received after the first time- interval; compare the learnt speed pattern with the determined speed; detect a first unlocking event based on the comparison of the learnt speed pattern with the determined speed; and control the lock and unlock circuitry to unlock one or more components of the vehicle based on the detected first unlocking event.

2. The vehicle of claim 1, wherein the processing circuitry is further configured to: determine a distance of the user device from the vehicle after the one or more components are unlocked; and grant a user, driving access to the vehicle based on the distance being less than a preset distance.

3. The vehicle of claim 2, wherein the processing circuitry is further configured to: determine one or more driving parameters of a user while the vehicle is being driven by the user; and revoke the granted driving access to the vehicle based on a mismatch between a driving profile associated with the vehicle and the determined one or more driving parameters.

4. The vehicle of claim 1, wherein the processing circuitry is further configured to learn a plurality of path profiles of the user device over the first time-interval, wherein the plurality of path profiles is learnt based on a relationship between the plurality of unlocking events in the first time-interval and time-series location data of the user device at the plurality of unlocking events.

5. The vehicle of claim 4, wherein the processing circuitry is further configured to: determine, based on second data received from the user device, a path trajectory followed by the user device to progress towards the vehicle; compare the determined path trajectory with the plurality of path profiles; and detect the first unlocking event based on the comparison of the determined path trajectory with the plurality of path profiles.

6. The vehicle of claim 1, wherein the speed data includes a time series of speed values with which the user device progressed towards the vehicle at the plurality of unlocking events, and wherein the first data is indicative of at least one of a signal strength of a wireless signal received from the user device, time-series speed measurements sensed by one or more sensors of the user device, and time-series location data of the user device.

7. The vehicle of claim 1 , wherein the processing circuitry is further configured to determine, based on the first data, a first distance gradient with which the user device progresses towards the vehicle, wherein the processing circuitry is further configured to detect the first unlocking event based on the first distance gradient being greater than or equal to a first preset value, and wherein the first distance gradient is indicative of a rate of change of distance between the user device and the vehicle while the user device progresses towards the vehicle.

8. The vehicle of claim 1, wherein the processing circuitry is further configured to: determine a second distance gradient with which the user device progresses away from the vehicle, wherein the second distance gradient is indicative of a rate of change of distance between the user device and the vehicle while the user device progresses away from the vehicle; detect a locking event based on the second distance gradient being greater than or equal to a second preset value; and control the lock and unlock circuitry to lock the one or more components of the vehicle based on the detected locking event.

9. The vehicle of claim 1, wherein the processing circuitry is further configured to learn a temporal routine associated with the plurality of unlocking events.

10. The vehicle of claim 9, wherein the processing circuitry is further configured to: determine, based on the first data, a timestamp while the user device progresses towards the vehicle; compare the determined timestamp with the learnt temporal routine; and detect the first unlocking event based on the comparison of the timestamp with the leamt temporal routine.

11. The vehicle of claim 1, wherein the processing circuitry is further configured to: re-leam the speed pattern based on the detected first unlocking event; and detect a second unlocking event subsequent to the first unlocking event based on the re learnt speed pattern.

12. A method, comprising: learning, by processing circuitry of a vehicle, over a first time-interval, a speed pattern of a user device registered with the vehicle, wherein the speed pattern is learnt based on a relationship between a plurality of unlocking events of the vehicle in the first time-interval and speed data with which the user device progressed towards the vehicle at the plurality of unlocking events of the vehicle in the first time-interval; determining, by the processing circuitry, a speed with which the user device progresses towards the vehicle based on first data received from the user device, wherein the first data is received after the first time-interval; comparing, by the processing circuitry, the learnt speed pattern with the determined speed; detecting, by the processing circuitry, a first unlocking event based on the comparison of the leamt speed pattern with the determined speed; and controlling, by the processing circuitry, based on the detected first unlocking event, lock and unlock circuitry of the vehicle to unlock one or more components of the vehicle.

13. The method of claim 12, further comprising: determining, by the processing circuitry, a distance of the user device from the vehicle after the one or more components are unlocked; and granting a user, by the processing circuitry, driving access to the vehicle based on the distance being less than a preset distance.

14. The method of claim 13, further comprising: determining, by the processing circuitry, one or more driving parameters of a user while the vehicle is being driven by the user; and revoking, by the processing circuitry, the granted driving access to the vehicle based on a mismatch between a driving profile associated with the vehicle and the determined one or more driving parameters.

15. The method of claim 12, further comprising: learning, by the processing circuitry, a plurality of path profiles of the user device over the first time-interval, wherein the plurality of path profiles is learnt based on a relationship between the plurality of unlocking events in the first time-interval and time-series location data of the user device at the plurality of unlocking events; and determining, by the processing circuitry, a path trajectory followed by the user device to progress towards the vehicle based on second data received from the user device; comparing, by the processing circuitry, the determined path trajectory with the plurality of path profiles; and detecting, by the processing circuitry, the first unlocking event based on the comparison of the determined path trajectory with the plurality of path profiles.

16. The method of claim 12, further comprising determining, by the processing circuitry, based on the first data, a first distance gradient with which the user device progresses towards the vehicle, wherein the first unlocking event is further detected based on the first distance gradient being greater than or equal to a first preset value, and wherein the first distance gradient is indicative of a rate of change of distance between the user device and the vehicle while the user device progresses towards the vehicle.

17. The method of claim 12, further comprising: learning, by the processing circuitry, a temporal routine associated with the plurality of unlocking events; and determining, by the processing circuitry, based on the first data, a timestamp while the user device progresses towards the vehicle; comparing, by the processing circuitry, the determined timestamp with the learnt temporal routine; and detecting, by the processing circuitry, the first unlocking event based on the comparison of the timestamp with the leamt temporal routine.

18. The method of claim 12, further comprising: determining, by the processing circuitry, a second distance gradient with which the user device progresses away from the vehicle, wherein the second distance gradient is indicative of a rate of change of distance between the user device and the vehicle while the user device progresses away from the vehicle; detecting, by the processing circuitry, a locking event based on the second distance gradient being greater than or equal to a second preset value; and controlling, by the processing circuitry, based on the detected locking event, the lock and unlock circuitry to lock the one or more components of the vehicle.

19. The method of claim 12, further comprising: re-leaming, by the processing circuitry, the speed pattern based on the detected first unlocking event; and detecting, by the processing circuitry, a second unlocking event subsequent to the first unlocking event based on the re-learnt speed pattern.

20. A method, comprising: learning, by processing circuitry, over a first time- interval, a speed pattern of a user device registered with a locking system, wherein the speed pattern is learnt based on a relationship between a plurality of unlocking events of the locking system in the first time-interval and speed data with which the user device progressed towards the locking system at the plurality of unlocking events of the locking system in the first time-interval; determining, by the processing circuitry, a speed with which the user device progresses towards the locking system based on first data received from the user device, wherein the first data is received after the first time-interval; comparing, by the processing circuitry, the learnt speed pattern with the determined speed; detecting, by the processing circuitry, an unlocking event based on the comparison of the learnt speed pattern with the determined speed; and unlocking, by the processing circuitry, the locking system automatically based on the detected unlocking event.