Electronically controlled lock and scanning arrangements

Abstract

An installation comprising an electronically controlled lock mounted on a door, the electronically controlled lock including a first sensing arrangement in the form of an accelerometer or a magnetometer, the installation comprising a unit distinct from the lock mounted on the door or on a door frame receiving the door, the unit including a second sensing arrangement, the second sensing arrangement including an accelerometer or a magnetometer, the installation including digital processor circuitry configured to receive signals from the first and second sensing assemblies and process the signals to detect a possible intrusion attempt based on sensor data simultaneously sampled from different sensing positions relative to the door and / or the door frame.

Description

Technical area

[0001] The present invention relates to electronically controlled locks and scanning assemblies for a door to premises, to associated security monitoring installations incorporating one or more such locks, and to associated systems and subsystems. The electronically controlled lock may be in the form of an electronic lock driver with, or include, an electric motor or solenoid to drive the mechanism of a mechanical lock, rather than being a fully integrated smart lock. background

[0002] Locks used to protect doors to premises, preventing unauthorized opening and access to the interior of the premises (access control), have been known for hundreds, if not thousands, of years. The basic idea is to prevent anyone without a suitable key from gaining access to the protected premises secured by the door. But ever since locks have existed, there have also been criminals attempting to open the lock without a suitable key, for example, using a lock pick or a picking key. In the last decade, electromechanical locks, known as smart locks, have been introduced to improve security and potentially user convenience.Such smart locks typically respond to the presentation of an electronic token or an electromagnetically signaled command, replacing the usual key and keyhole mechanism, to effect locking or unlocking via a latching mechanism. Such locks can operate with access cards or other tokens, or active devices such as phones that generate or can be read by RF signals (e.g., Bluetooth, NFC, RFID, or the like), or magnetically and / or via a biometric interface (such as an iris, fingerprint, or facial recognition interface).Many smart lock designs do not have a keyhole, so lock activation is only feasible using electromagnetic means, but many home users seem to be reassured by the presence of a keyhole that interacts with a tangible key that can be carried by the user.

[0003] Smart locks can be used as standalone security measures, and such a lock may include an alarm sounder that is activated if the lock detects a tamper attempt. However, smart locks can also be used as part of or in conjunction with security monitoring systems for premises and also in conjunction with smart home installations, often with the option of signaling a detected tamper or interference attempt. One such smart lock, which may also be referred to as an electronically controlled lock, is described in the applicant's previous patent application, first published as WO2023 / 227258. This smart lock is designed to meet the requirements of EN50131 Grade 2, allowing the smart lock to be integrated into a security monitoring system that otherwise meets the requirements of EN50131 Grade 2 or higher.

[0004] Some smart locks are designed for use with traditional cylinder lock hardware, providing either a convenient upgrade for an existing lock installation or a way to enjoy both the convenience of electronic lock control and the ability to continue using mechanical keys. However, such smart locks can be just as vulnerable to "picking" attacks as the mechanical cylinder locks on which they are based.

[0005] In this utility model application, the terms "smart lock" and "electronically controlled lock" should be interpreted to encompass conventional (mechanical) locks to which an electronic lock driver has been added. Such electronic lock drivers may include an electric motor or solenoid mechanically coupled to a mechanical lock, allowing the electronics in the lock driver to be used to control ("manipulate") the operation of the lock. The terms "smart lock" and "electronically controlled lock" also encompass an electronic lock driver for incorporation into a mechanical lock assembly.

[0006] While there are many smart lock designs available, there is a need for an improved smart lock, especially one suitable for installation in residential premises. It would also be desirable for such a smart lock to meet the requirements of EN50131 Grade 2, allowing the smart lock to be integrated into a security monitoring system that otherwise meets the requirements of EN50131 Grade 2 or higher. Summary

[0007] Various aspects of the invention are disclosed herein. These aspects may be used independently, or two or more aspects may be used together.

[0008] According to a first aspect, there is provided an electronically controlled lock for a door of premises, the lock comprising a processor and an accelerometer or magnetometer coupled to the processor, wherein: the accelerometer or magnetometer is configured to operate as a vibration sensor, the processor and the accelerometer or magnetometer together functioning as a vibration detector to generate a warning signal in the event of an attempt to pick or interfere with the lock;and the processor is configured to first execute a first classifier to detect anomalies in signals received from the accelerometer or magnetometer during or as a result of an event, and upon detection of an anomaly, execute a second classifier to classify the anomaly as belonging to an identified one of a plurality of event classes, and wherein the processor is optionally configured to send a warning signal using a transceiver of the lock if an attempt is made to pick or disrupt the lock;

[0009] According to a second aspect, a smart lock is provided, comprising: an accelerometer or a magnetometer configured as a shock detector; a processor configured to detect an anomaly in a signal received from the accelerometer or magnetometer, the processor configured to implement an autoencoder, the autoencoder configured to classify the received signal according to pre-trained non-anomalous signal data and re-score the signal therefrom; and the processor configured to detect an anomaly depending on a difference between the received signal and the re-score signal. Optionally, the processor may be configured (e.g., programmed) to detect an anomaly according to an energy difference between the received signal and the re-score signal.

[0010] According to a third aspect, there is provided an electronically controlled smart lock for a door of premises, the lock comprising an accelerometer or a magnetometer, a processor coupled to the accelerometer or magnetometer and configured to execute a first classifier to detect anomalies in signals received from the accelerometer relating to an event, and upon detection of an anomaly, execute a second classifier to attempt to classify the event into one of a plurality of event classes, at least one of the classes indicating an alarm event and at least one of the classes corresponding to a non-alarm event, the processor being configured to signal an alarm event if the classifier determines that an event is an alarm event, and optionally also if an event is not classifiable as a non-alarm event.

[0011] A fourth aspect of the invention provides a vibration sensor (e.g., for a door or window and configured for intrusion detection), wherein the vibration sensor includes a processor configured to apply a machine learning model to process sensor data to determine the presence of anomalies in the data and generate an output if an anomaly is detected. The vibration sensor may comprise an accelerometer and / or a magnetometer, and optionally a microphone. The microphone may be located in the lock and arranged to detect sounds of attacks on the lock, such as lock picking.A further microphone may be provided in the lock or in a second sensing arrangement to detect ambient noise, and particularly ambient noise on the exposed or vulnerable side of the door - these noises can be used to aid in distinguishing between false alarms and genuine alarm events (e.g., as a result of signals representative of such sounds provided and processed by a unit monitoring the installation of which the lock and / or the second sensing arrangement is a part).

[0012] Any microphone forming part of the lock or the second sensing arrangement is preferably located within the housing of the lock or the second sensing arrangement in such a way that the microphone is protected from direct attack by an aperture, port, or grille through which ambient noise reaches the microphone - e.g., by displacing the microphone with respect to such port, aperture, or grille, for example, by mounting it perpendicular to it, so that the microphone is not exposed to damage if a foreign object (such as a screwdriver or drill) is inserted through the aperture, opening, or grille. A microphone intended to detect the sound of lock picking may be coupled to a keyhole of the lock through an open passage, but is preferably displaced again, e.g.,mounted perpendicular to the axis of the keyhole hole so that the microphone cannot easily be attacked through the keyhole.

[0013] In some embodiments, the processor is programmed to operate as an autoencoder to process the sensor data.

[0014] For example, in some embodiments, the autoencoder is configured to adapt and / or classify a received signal according to pre-trained non-anomalous signal data and re-score the signal therefrom, and the processor is configured to detect an anomaly based on a difference between the received signal and the re-score signal. The processor may be configured to detect an anomaly based on an energy difference between the received signal and the re-score signal.

[0015] In some embodiments, if the processor detects the presence of an anomaly, the processor is programmed to analyze the sensor data or processed sensor data to assign a detected event to one of a plurality of event types, wherein the event types include at least one threat class and at least one non-threat class. The threat class may include at least one of lock picking, lock picking, and lock picking.

[0016] A fifth aspect of the invention provides an electronically controlled lock including a vibration sensor as described above, and wherein the smart lock optionally includes a smart electronic lock driver operatively coupled to a mechanical lock.

[0017] The lock may include a keyhole, and the machine learning model may be trained to identify at least one of lock picking, lock picking, and lock picking as an anomalous event. A lock with a keyhole may include a microphone, for example, arranged to preferentially capture sound from a keyhole of the lock and / or from the vicinity of a lock cylinder, and the digital processor circuit may be arranged to receive signals or data from the microphone in addition to the signals received from the accelerometer or magnetometer.Optionally, the lock may additionally or alternatively include a pressure sensor and / or an insertion detector (possibly based on the mechanical displacement of a sensing element) to detect the insertion of an element (such as a key, picking key or lock pick) into an external keyhole of the lock, and the digital processor circuit (or a processor located at a remote location) may be arranged to receive signals or data from one or more such sensors in addition to those received from the accelerometer or magnetometer, or merely as a further sensor whose signals may contribute to the detection of an anomalous event and possibly to its classification.

[0018] The lock may further comprise one or more electronic sensing assemblies to perform hand-on-handle or hand-on-lock detection, for example, capacitive sensing, and / or key-in-lock detection (e.g., using impedance sensing), and the digital processor circuitry is configured to use data from the one or more electronic sensing assemblies in classifying events into particular attack modes such as lock picking, lock picking, and lock picking.

[0019] A sixth aspect of the invention provides an electronically controlled lock including a vibration sensor as described above, wherein the processor is configured to implement an autoencoder, the autoencoder being configured to classify a signal received from the accelerometer or magnetometer according to pre-trained non-anomalous signal data and re-evaluate the signal therefrom, and the processor is further configured to detect an anomaly depending on a difference between the received signal and the re-evaluated signal. The processor may be configured to detect an anomaly according to an energy difference between the received signal and the re-evaluated signal.

[0020] According to a seventh aspect, there is provided an electronically controlled lock for a door of premises, the lock comprising a processor and an accelerometer or magnetometer coupled to the processor, wherein: the accelerometer or magnetometer is configured to operate as a vibration sensor, the processor and the accelerometer or magnetometer together functioning as a vibration detector to generate a warning signal in the event of an attempt to pick or interfere with the lock;wherein the processor is configured to first detect anomalies in signals received from the accelerometer or magnetometer during or as a result of an event, and, upon detection of an anomaly, is configured to execute a classifier to classify the anomaly as belonging to an identified one of a plurality of event classes, and wherein the processor is optionally configured to transmit a warning signal using a transceiver of the lock if an attempt is made to pick or disrupt the lock;

[0021] Locks according to the seventh aspect may include a keyhole and may further comprise one or more additional sensors in the form of: (i) a microphone, for example arranged to preferentially pick up the sound from a keyhole of the lock and / or from the vicinity of a lock cylinder, and the digital processor circuit may be arranged to receive signals or data from the microphone in addition to the signals received from the accelerometer or magnetometer; (ii) a pressure sensor; and / or (ii) an insertion detector (possibly based on the mechanical displacement of a sensing element) to detect the insertion of an element (such as a key, picking key or lock pick) into an external keyhole of the lock: and the processor (or a remote processor) may be arranged to receive signals or data from each such additional sensor in addition to the signals received from the accelerometer or magnetometer, wherein the digital processor circuit (or a remote processor) is programmed or configured to use signals or data from each such additional sensor in detecting and / or classifying an anomalous event.

[0022] According to an eighth aspect, there is provided a security monitoring installation for premises, comprising a control unit for controlling the operation of the security monitoring installation, the installation including: a window or door vibration sensor integrating a first detector, the first detector comprising an accelerometer or a magnetometer; an electronically controlled lock according to any variant of the seventh aspect integrating a second detector, the second detector comprising an accelerometer or a magnetometer; wherein the window or door vibration sensor and the smart lock are configured to transmit signal data from the first and second detectors to the control unit;and wherein the control unit is configured / programmed to classify an event based on the signal data received from the first and second detectors and optionally based on signal data from one or more of the aforementioned additional sensors of the lock;

[0023] A ninth aspect of the invention provides a security monitoring installation for premises, comprising a control unit for controlling the operation of the security monitoring installation, the installation including: an electronically controlled lock according to any variant of the seventh aspect, coupled to a door of the premises, the electronically controlled lock integrating a first detector, the first detector comprising an accelerometer or a magnetometer; a door vibration sensor integrating a second detector, the second detector comprising an accelerometer or a magnetometer, coupled to the same door at a position remote from the lock; the door vibration sensor and the smart lock being configured to transmit signal data from the first and second detectors to the control unit;and wherein the control unit is configured / programmed to classify an event based on the signal data received from the first and second detectors and optionally based on signal data from one or more of the aforementioned additional sensors of the lock;

[0024] A tenth aspect of the invention provides an installation including an electronically controlled lock mounted on a door, wherein the electronically controlled lock is according to any variant of the seventh aspect and includes a first sensing arrangement in the form of a first accelerometer and / or magnetometer, the installation comprising a unit separate from the lock and mounted on the door or on a door frame receiving the door, the unit including a second sensing arrangement separate from the first sensing arrangement, the second sensing arrangement comprising one or more accelerometers, a magnetometer, the installation including a digital processor circuit configured to receive signals from the first and second sensing arrangements and optionally from one or more of the aforementioned additional sensors of the lock and for processing the signals,to detect a possible intrusion attempt based on data simultaneously perceived from different scanning positions relative to the door and / or door frame.

[0025] An eleventh aspect of the invention provides an electronically controlled lock incorporating a vibration sensor as previously described, wherein the processor is configured to execute a first classifier to detect anomalies in signals received from the accelerometer or magnetometer relating to an event, and upon detection of an anomaly, execute a second classifier to attempt to classify the event into one of a plurality of event classes, at least one of the classes indicating an alarm event and at least one of the classes corresponding to a non-alarm event, wherein the processor is configured to signal an alarm event if the classifier determines that an event is an alarm event, and optionally also in the event that an event is not classifiable as a non-alarm event.

[0026] A twelfth aspect of the invention provides a security monitoring installation for premises including at least one vibration sensor having any of the features described above and / or an electronically controlled lock as described above.

[0027] A thirteenth aspect of the invention provides a security monitoring installation for premises, optionally as above, comprising a control unit for controlling the operation of the security monitoring installation, the installation comprising: a window or door vibration sensor integrating a first detector, the first detector comprising an accelerometer or a magnetometer; an electronically controlled lock, optionally as defined with any of the above features, incorporating a second detector, wherein the second detector comprises an accelerometer or a magnetometer; the window or door vibration sensor and the smart lock are configured to transmit signal data from the first and second detectors to the control unit; and wherein the control unit is configured / programmed to classify an event based on the signal data received from the first and second detectors.

[0028] A fourteenth aspect of the invention provides a security monitoring installation for premises optionally as defined above, comprising a control unit for controlling the operation of the security monitoring installation, the installation comprising: an electronically controlled lock, optionally defined with any of the above features, coupled to a door of the premises, the electronically controlled lock incorporating a first detector, the first detector comprising an accelerometer or a magnetometer; a door vibration sensor incorporating a second detector, the second detector comprising an accelerometer or a magnetometer, coupled to the same door at a position remote from the lock; wherein the door vibration sensor and the smart lock are configured to transmit signal data from the first and second detectors to the control unit; and wherein the control unit is configured / programmed to classify an event based on the signal data received from the first and second detectors.

[0029] A fifteenth further aspect of the invention provides a security monitoring installation for premises, optionally as previously described, wherein the control unit includes a processor configured to apply a machine learning model, such as an autoencoder, to process received signal data to determine the presence of anomalies in the received signal data.

[0030] A sixteenth aspect of the invention provides an installation including an electronically controlled lock mounted on a door, the electronically controlled lock including a first sensing arrangement in the form of an accelerometer and / or a magnetometer, the installation comprising a unit separate from the lock and mounted on the door or on a door frame receiving the door, the unit including a second sensing arrangement separate from the first sensing arrangement, the second sensing arrangement comprising an accelerometer and / or a magnetometer (such that the first and second sensing arrangements may each comprise the same or different types of detectors in any order), the installation including digital processor circuitry configured to receive signals from the first and second sensing arrangements and to process the signals,to detect a possible intrusion attempt based on data simultaneously sampled from different scanning positions relative to the door and / or door frame.

[0031] The processor circuit may comprise a processor programmed to operate as an autoencoder for processing data from the first and second sampling arrangements.

[0032] In some embodiments, if the processor detects the presence of an anomaly, the processor circuit is programmed to analyze the sensor data or processed sensor data to assign a detected event to one of several event types, wherein the event types include at least one threat class and at least one non-threat class. The threat class may optionally include at least one of lock picking, lock picking, and lock picking.

[0033] In some embodiments, the processor circuit includes a processor that is a component of the electronically controlled lock.

[0034] The installation may further comprise a security monitoring system for premises of which the door forms a part, and optionally, at least a portion of the processor circuit may comprise a processor of a controller of the security monitoring system. Control of the security monitoring system may optionally be provided by a video doorbell arrangement.

[0035] The security monitoring system may have at least one operating mode in which it is arranged to notify a remote monitoring unit of alarm events. For example, the security monitoring system may have at least one operating mode in which it is arranged to notify the remote monitoring unit of anomalous events detected in the sensor data.

[0036] A seventeenth aspect of the invention provides a security monitoring installation for premises including a control unit for controlling the operation of the security monitoring installation, the security monitoring installation further comprising: a door vibration sensor integrating a first accelerometer and / or a magnetometer, the vibration sensor being coupled to a door of the premises; an electronically controlled lock integrating a second accelerometer, wherein the electronically controlled lock is coupled to the door of the premises; wherein the vibration sensor and the electronically controlled lock are configured to transmit signal data derived from their accelerometer(s) and / or magnetometer(s) to the control unit; and wherein the control unit is configured / programmed to classify an event based on the signal data derived from the first and second vibration sensors.

[0037] The control unit may include a processor configured to apply a machine learning model, such as an autoencoder, to process received signal data to determine the presence of anomalies in the received signal data.

[0038] The control unit may be configured / programmed to provide a quantized output signal whose value is selected from at least three levels (i.e., a non-binary output).

[0039] Non-limiting features and advantages of the invention include the ability to detect anomalous vibrations, for example, compared to vibrations detectable under normal operating conditions of the smart lock and door. When using a machine learning algorithm trained only on, or by prioritizing training data for, "normal" conditions, it is possible to detect suspicious vibrations as an anomaly, even if they correspond to a break-in attempt or lock attack that the system has not been specifically trained to detect (e.g., a new type of break-in attempt or lock attack). When using multiple sensing arrays, one at the lock and another at a different position spaced from the lock, it is possible to derive additional context by sampling the same vibration event substantially simultaneously from or at multiple sampling positions.This can facilitate automatic differentiation between a break-in attempt focused on the lock and another attempt focused on a different part of the door. It can also help reduce the occurrence of false alarms compared to using only a single sensing array on the door.

[0040] Additional aspects of the invention are defined in the claims. Independent protection is also claimed for each novel feature and / or idea disclosed herein and / or in the drawings, regardless of whether emphasis has been placed thereon or not. Short description of the characters

[0041] The embodiments of the invention will now be described by way of example only with reference to the accompanying figures in which: Fig. 1 schematically shows premises with a Smart Lock installation, which may include video surveillance of access to the Smart Lock. Fig. Figure 2 schematically illustrates the main components of a smart lock according to one aspect of the invention; Fig. 3A illustrates a mortise lock with which aspects of the invention may be used, installed in a door; Fig. 3B illustrates an assembly incorporating the mechanism and electronics of an electronic lock according to aspects of the invention; Fig. 3C schematically shows a longitudinal section through the assembly of Fig. 3B; Fig. Figure 4 schematically illustrates the elements forming an autoencoder as may be used in aspects of the invention; Fig. 5 schematically illustrates how a trained autoencoder can distinguish between routine events and outlier events according to aspects of the invention; Fig. 6 schematically illustrates how an autoencoder according to one aspect of the invention can be integrated into a smart lock; Fig. Figure 7 schematically illustrates the main components of a video doorbell according to one aspect of the invention; Fig. Figure 8 schematically illustrates a home security monitoring system built around a video doorbell; and Fig. 9 in general Fig. 8, but also includes the benefit of professional monitoring by a remote alarm receiving center. Special description

[0042] Fig. Figure 1 schematically illustrates a home ("premises") with a smart lock installation, which may include video surveillance of access to the smart lock. In this case, a video doorbell 100 may be provided adjacent to the main entrance door 102, in this case the front door, of the house 104. The front door 102 is equipped with a "smart lock" 106 that can be locked and unlocked by electrical control signals received, for example, from a homeowner's personal communications device 108. For example, the video doorbell 100 may interact with a backend service 110 that sends push notifications to a user's personal communications device 108 when the doorbell is pressed (or optionally, when someone approaches the doorbell 100 or other video surveillance device).To support such communications, the video doorbell may use Wi-Fi to connect to a Wi-Fi router 112 (or a controller of a premises security monitoring installation) having a broadband 114 connection to the Internet 115, with the backend service 110 sending push notifications to a public mobile network (PLMN) 116, over which notifications may be delivered to the user's personal communication device 108. The same communication path may be used to stream live video (and audio) from the video doorbell 100 to the user. A reverse communication path may also be supported to allow the user to speak to a person at the doorbell 100 and also to allow the user to activate (i.e., release) the lock 106 to allow the person at the door to open the door 102.The signals to activate (unlock) the lock can be passed directly from the router 112 (or the security monitoring system controller) to the lock 106, or they can be passed through the video doorbell 100, which in turn communicates with the smart lock 106. The smart lock 106 is designed to comply with Level 2 of EN50131 by incorporating a shock sensor (more generally, a vibration sensor) with tamper detection capability.

[0043] Some or all of the smart lock, video doorbell, and security surveillance system controller may additionally or alternatively be equipped with at least one transceiver supporting NB-IOT (Narrowband IoT, supported by 3GPP), LTE-M (LTE Machine Type Communication), or the like, which are LPWAN technologies that provide secure connections using licensed spectrum in operator-managed networks.

[0044] Fig. Figure 2 schematically illustrates the main components of a Smart Lock 106, as shown in Fig. 1, according to embodiments of the invention. The lock 106 is shown installed in a door 102, wherein a door frame 240 houses a cooperating strike plate 242 receiving at least one bolt 244. The lock 106 may be configured as a mortise lock, in which case the lock typically includes a mortise lock set or latch (not shown) in addition to the bolt 244.

[0045] Providing the lock 106 as a mortise lock is particularly attractive when the lock is to be pre-installed in a door (or when the door is to be manufactured with slots provided for ready-to-install the lock on site), rather than retrofitting it to a pre-hung door as a replacement for an existing lock. However, there is often a desire, especially when replacing a surface-mounted lock, to surface-mount the lock 106 (on the protected, typically interior, side of the door 102), since installation is typically much easier and faster without having to create a cavity (slot) in the door to accommodate the new lock. In both cases, the bolt 224 can be received in a cavity in the door, but with a surface-mounted lock, the bolt can also be external to the door.The lock 106 is provided with an actuator 246, which may be a solenoid or a motor, which either drives the bolt to the locked or unlocked position, or engages or disengages a clutch that couples or uncouples a knob or handle 248 on the exposed side of the door, allowing the bolt to be retracted to the unlocked position, allowing the door to be opened from the exposed (unprotected) side. Typically, when the lock 106 is provided with a clutch handle, the actuator is a solenoid rather than a motor. The lock 106 may, of course, be provided with another handle or knob (not shown) on the protected side of the door 102 to operate the bolt 244 to allow the door 102 to be opened and locked from the protected (generally the inside) side of the door 102.

[0046] While Fig. 2 illustrates a lock installation having only a single bolt 244 and a corresponding single strike plate 242 for ease of illustration and explanation, locks according to embodiments of the invention may include, be integrated into, or be used with multi-point lock installations / doors where, in fact, more than one bolt is used to secure a door.

[0047] The lock 106 includes a power supply 250, which preferably includes a rechargeable battery 252, and preferably also a charging assembly 254 to facilitate charging the rechargeable battery 252 in the field. The charging assembly may be coupled to a mains power supply, but for ease and simplicity, it may be preferred that it include an interface 256 (such as a micro-USB port, a USB-C port, a Lightning connector, or the like) to receive a low-voltage supply (e.g., 5 V or 20 V) (e.g., from a power bank or external charger) that can be used to charge the rechargeable battery 252 in the field in the absence of a mains power supply (or in the event of a mains power failure), rather than having to remove the battery for charging, so that the lock 106 can always be powered.In an alternative embodiment, the lock may include a coil or other arrangement to enable inductive charging from a suitably placed transmitter connected to an external power source (such as a power bank or mains power supply).

[0048] The actuator 246 is operatively coupled to and controlled by a processor 258 having an associated memory 260 storing program instructions ("software") that, when executed on the processor 258, control the operation of the lock 106. The processor 258 may be, for example, a microcontroller or a microprocessor. Also coupled to and controlled by the processor 258 is at least one transceiver 262 that is configured to receive control signals from a controller of the security monitoring system (e.g., from the video doorbell 100 or the controller of the security monitoring installation in the Fig. 1) and transmits event information to it. These may be relatively low-bandwidth transmissions (e.g., compared to video transmissions from video doorbell 100), so a low-bandwidth channel is suitable—meaning a low-power transceiver can be used, facilitating acceptably long battery life. For example, transceiver 262 may be configured to operate using a suitable allocated frequency in the Industrial, Scientific, and Medical (ISM) bands—such as (in Europe) 868 MHz. Preferably, communication to and from the lock is encrypted.As previously mentioned, the transceiver 262 may additionally or alternatively support an LPWAN technology such as NB-IOT or LTE-M, in which it communicates with one or more user devices (WTRUs) 108 and / or a remote system backend or remote monitoring station or alarm receiving center (ARC).

[0049] The lock 106 may also include a chime or speaker (generally a sound output device, such as an electromechanical chime or buzzer) 263 operatively coupled to the processor 258. This speaker may be used instead of or in addition to a separate chime (located, for example, in an entryway or elsewhere in the premises) that sounds when a chime triggering device of the video doorbell 100 is activated. A processor of the video doorbell 100 may optionally be configured to use a transceiver to transmit a chime activation signal identified by a marker, to which the lock processor 258 and / or the processor of a separate chime sounding device (not shown) is responsive using an internal sound output device to ring in response to activation of the chime triggering device.

[0050] The lock 106 may be provided with a housing 259 through which the bolt 244 and a mortise lock set can freely protrude, with the knob or handle 248, of course, being outside the housing 259. Preferably, the housing is made of an engineering plastic material or a non-ferromagnetic material so that it does not interfere with the function of one or more magnetometers optionally provided as part of the lock 106.

[0051] The lock 106 may further include a magnetometer 264, which may be configured to sense and monitor a first magnetic field provided by an optional first magnet 266, which may be fixedly mounted with respect to the frame 240 or other abutment surface against which the door 102 closes. The same magnetometer 264 or an additional magnetometer (not shown) may also be configured to sense and monitor a second magnetic field provided by a second magnet 270, which may be attached to the door, preferably mounted inside the door, i.e., between the protected side and the unprotected side of the door, although it is also possible to attach a magnet 270 to the side of the door (the side on the inside (e.g., inside) of the door) (e.g., with adhesive and / or using a mechanical fastener such as a screw).This second magnet 270, if present, is located outside the lock 106 and is provided such that a magnetometer configured to sense the magnetic field of the second magnet 270 can generate a tamper signal to indicate an attempt to remove the lock 106 from the door 102. Meanwhile, a magnetometer 264 can sense and monitor the first magnetic field provided by a first magnet 266 and can provide a signal indicative of the state of the door, e.g., whether the door 102 is open or closed.The processor 258 may be configured to generate an alarm signal that is transmitted to a controller of the security monitoring system, such as a video doorbell enhanced according to some aspects of the invention, to forward a report to a monitoring service and / or the owner / occupant of the home if it is detected that the door has been opened without the lock being unlocked and / or the alarm being disarmed - since such a combination of circumstances may indicate that the door 102 has been forced open.It is understood that a magnetometer can function as a shock or vibration sensor because it may be able to respond to short-term disturbances or degradations of the magnetic field, for example, from an associated magnet, due to the magnetometer being displaced relative to the source of the magnetic field. For example, a magnetometer mounted on or inside a door may detect a shock caused by anything striking the door (e.g., a criminal attempting to gain entry or a football violently striking the door) as a result of small changes in the distance between the magnetometer and the source of the magnetic field. This may make it possible to use a magnetometer instead of an accelerometer in the design of a vibration sensor.In general, embodiments of the present invention can be implemented using an accelerometer or a magnetometer, or both. Depending on the application and the precise details of an installation, an accelerometer may be more sensitive to subtle perturbations, and therefore, it may be preferable to use an accelerometer rather than a magnetometer. In other situations, however, a magnetometer may be preferred due to its relative insensitivity to small perturbations.

[0052] The lock 106 may further include an accelerometer 275, also coupled to the processor 258, and configured to function as a shock sensor (or more generally, a vibration sensor) for providing signals to the processor to enable the processor to detect attempts to "pick" or "break" the lock, drill the lock cylinder, and other mechanical attacks on the lock, as well as providing signals in the event of attempts to break down the door (or force the lock) with, for example, a sledgehammer or battering ram. The processor 258 preferably uses machine learning, e.g., deep learning, and / or other AI approaches to detect accelerometer signals caused by "everyday events" such asDistinguishing anomalous signals generated by a normal "Here I am!" knock on the door, the unlocking of the lock with the corresponding key, the slamming of an unlocked door, the accidental impact of a soccer ball, or the like, from anomalous signals generated as a result of malicious activities such as attempted lock picking or forcing, or attempts to force open or destroy the lock. The application of AI techniques to this problem of distinguishing between signals representing anomalous events and "everyday" or "non-anomalous" or "ordinary" events is described and discussed later in this utility model application. Providing the accelerometer 275 also provides a potential basis for certifying the lock as a shock detector (for an alarm system of at least Grade 2 or Grade 3) according to EN 50131-2-8 (also referred to herein as an "alarm peripheral").The accelerometer can be a three-axis device, although a simpler device can also be used to provide satisfactory results. As mentioned above, in some situations, the relevant sensor may be a magnetometer rather than an accelerometer.

[0053] A suitable accelerometer is available from STMicroelectronics as the LIS2DTW12, although there are of course many similar alternative devices available from other manufacturers.

[0054] Conveniently, the accelerometer can be configured to enter standby mode if it is not subject to a certain level of activity for more than a predetermined period of time (to reduce power consumption and thus extend battery life in battery-powered devices), and the accelerometer can be further configured to wake up quickly when subjected to a specific stimulus—such as an RMS signal value of a threshold or greater (for example, on one of the sensing axes) (possibly an increasing activity level). The STMicro device mentioned is an "always-on" device, but has a sampling rate of 12.5 Hz in standby mode, meaning a sample is taken every 80 ms.Wake-up occurs quickly, and the device can switch to a sampling rate of up to 1600 Hz upon wake-up (although the optional 800 Hz sampling rate is likely fast enough for this application), so it is generally expected that an accelerometer that has been woken up will likely continue to experience stimulation triggered by the wake-up event. This stimulation evokes an analyzable output signal. The STMicro device mentioned (and likely its counterparts from other manufacturers) can also generate an interrupt signal upon wake-up, so the processor can also be notified of the activity.

[0055] Processor 258 may thus be configured to first process the sensor data from at least a first sensor, for example, a first sensor such as accelerometer 275 or a magnetometer, to determine the presence of any anomalies represented by the data and to generate an output in the event that an anomaly is detected. When a sensing device has a standby mode, such as the STMicro accelerometer just mentioned, it may be preferable that the fact of the device waking up not be considered an anomalous event in itself—although the activity following the device waking up may well constitute an anomalous event and should be treated as such by the processor.As a result, an attack event that awakens a sensing device may constitute an anomalous event, even though the simple act of the sensing device being awakened would not in itself be considered an anomalous event.

[0056] The processor 258 may also be arranged to process the second sensor data provided by at least one second sensor (e.g., a magnetometer 264 or another accelerometer or magnetometer, optionally located at a different location (i.e., outside the lock and optionally remote from the lock) on the door 102 and / or the door frame 240) and consider both the first sensor data and the second sensor data in determining whether the data indicates the presence of an anomaly, and if so, provide an output. In either case, the output signal provided by the processor 258 may be transmitted to a remote receiver (such as a user device, e.g.,WTRU, a system backend, a remote monitoring station or an ARC, a control unit of a security monitoring installation for the premises, a "smart doorbell" as described elsewhere in this application). Additionally or alternatively, the output provided by processor 258 may be subjected to a classification process (e.g., using a classifier (or autoencoder) running on processor 258 or on other processing device in the lock or elsewhere) to classify events into particular threat types (e.g., lock picking, lock picking, lock tampering, lock striking, door tampering, etc.), and optionally classify events into particular everyday categories, and optionally classify an event as being intermediate between a threat and an everyday event.

[0057] Based on such classification, the processor can, for example, be configured to indicate, in warning messages and "tamper detection" signals, the type of attack that triggered the signal's transmission. For example, it is desirable to distinguish between signals resulting from mechanical impacts resulting from a violent attack on the door or door frame, and those resulting from attempts to pick the lock, and those resulting from attempts to remove the lock from the door (removing the lock from its mounting surface). Such information can be useful in distinguishing between genuine attacks (genuine break-ins), tampering, and false alarms, i.e., in verifying whether a security alarm can be forwarded to the police for action.

[0058] Optionally, the lock may include a microphone 276, which is arranged, for example, to preferentially pick up sounds from the keyhole and / or from the surroundings of the lock cylinder, and the processor 258 may be arranged to receive signals or data from the microphone as the or one of the second sensors. As previously described, the microphone is preferably shielded from direct attack through the keyhole, for example, by being offset from the keyhole or arranged orthogonally to the keyhole axis.Optionally, the lock may additionally or alternatively include a pressure sensor 278 and / or an insertion detector 279 (possibly based on mechanical displacement of a sensing element) to detect the insertion of an element (such as a key, picking key, or lock pick) into an external keyhole of the lock, and the processor 258 (or a remotely located processor) may be arranged to receive signals or data from such a sensor or one of the second sensors, or merely as another sensor whose signals may contribute to the detection of an anomalous event and possibly its classification. Furthermore, the lock may optionally include a microphone to detect ambient noise, particularly that from the vulnerable side of the door.An aperture or opening may be provided in the lock body to allow the microphone to detect such ambient noise, and the aperture or opening may be provided with a grille or the like to protect the microphone from attack. As previously described, the microphone is preferably further protected from attack through the aperture or opening (e.g., from attack by inserting an object through the aperture or opening by being offset from or mounted orthogonally to an axis of the aperture / opening).

[0059] Optionally, the processor may be configured to indicate in the signal reporting an event the identity of the sensor(s) that caused the transmission of the signal, i.e., whether it was the accelerometer 275 or the magnetometer 264 (indicating which magnetometer if the lock includes more than one), the external accelerometer, the external magnetometer, the microphone, the pressure sensor, the displacement sensor, or a combination of these - and at least, if a single magnetometer is provided, the nature of the change in the observed magnetic environment, e.g.Whether the magnetometer detects a change in the magnetic field caused by a door magnet 270 or a frame magnet, and whether the change is a decrease in magnetic field strength, an increase in magnetic field strength, or a change in polarity—both indicate a possible attempt to deceive the system by adding a fake magnet to trick the magnetometer ("masking"). This information can also be useful in distinguishing between genuine intrusion attacks, tampering, and false alarms, for example, distinguishing between vibrations caused by a break-in and vibrations caused by road or rail traffic, or by impacts from a kicked soccer ball.

[0060] While the foregoing description has been in the context of the lock's electronics being provided in a lock case along with the main mechanical elements of the lock, the invention also contemplates alternative arrangements where the smart lock's electronics are provided in a separate unit than the lock case. For example, in a mortise lock where the main mechanical parts of the lock are provided in a slot in a door (preferably contained in a lock case within the door), a separate unit (preferably) may be provided on the protected (e.g., interior) side of the door to house the smart lock's electronics, with the separate unit being mechanically coupled to the mechanical parts of the lock within the door.Such an arrangement can be used to allow the functionality of a smart lock to be 'retrofitted' to a previously installed lock, for example, by removing the existing lock cylinder and replacing it with a new cylinder that provides a mechanical connection to the new separate unit, allowing the lock to be locked or unlocked remotely. If the lock assembly provides a deadbolt arrangement, this can also be coupled to the new separate unit to allow a motor or other actuator (e.g., a solenoid) to operate both the locking bolt and deadbolt, potentially enabling contactless door opening. This approach is perhaps best explained with reference to . Fig. 3 understood.

[0061] Fig. Figure 3A illustrates a mortise lock 300 installed in a slot (cavity) formed in a door 302, viewed from the protected, e.g., inner side of the door. The lock includes a lock case 304, shown in phantom, in which the bolt 306 and a latch 308 are received. The bolt 306 is shown retracted here so that only the free end of the bolt is visible in the forend 310 of the lock, under which condition the door 302 can be opened from the closed position. The lock 300 is secured in the slot by screws 312, 312' that are passed through the forend 310 into the material of the door. In the illustrated example, the lock is lockable and unlockable by the key cylinder 314, which is shown removed from its bore 315 in the lock toward the inner (protected) side of the door.The cylinder illustrated here is a Euro cylinder in which a key operates a pin and tumbler arrangement (of course, other types of cylinders are used, and the invention is equally applicable to locks utilizing such other types of cylinders, as well as to other lock and locking arrangements, such as multi-point and other single-point locking arrangements). A keyhole 316 is provided at each end of the conventional cylinder, and by inserting a correctly coded key into a keyhole 316 at one end of the cylinder, it is possible to rotate a rotatable cam 318 having an integral tongue 320 which, when installed in the lock, effectively moves the bolt 306 in and out of the lock case 304, thereby unlocking and locking the door 302 in an associated door frame 240 (not shown).The free end of the bolt penetrates an aperture or “retainer” in the door frame 240 to lock the door in the closed position.

[0062] The cylinder 314 is fixed in position in the lock using a locking screw (not shown), which, in use, is passed through an aperture 322 in the lock face. It should be understood that the lock is shown without the usual cover plate that might normally cover the lock face 310 and the screws 322 and aperture 322. The bolt 308 can be opened and closed by a bolt drive that engages a typically square aperture 324 in the bolt (or a bolt drive in the lock). The bolt may be coupled to a handle or knob (one on each side of the door) by which the bolt can be retracted. Bolts are often spring-loaded so that when pressure on the handle or knob is released, they return to the position shown with the bolt tongue extending from the lock.Sometimes the deadbolt is coupled to be driven by the cylinder, so that additional rotation of the cylinder in one direction retracts the deadbolt and rotation in the opposite direction does the opposite - in this case no deadbolt handle may be provided or a deadbolt handle may only be provided on the protected side of the door.

[0063] In Fig. Figure 3A shows two Euro cylinders: on the left, a conventional cylinder 314 with a keyhole 316 at each end; on the right, a new cylinder 314' in which, instead of the keyhole on the protected side of the door, an elongated tongue 326 protrudes. The tongue 326 engages the mechanism of an assembly containing the mechanism and electronics of an electronic lock. This assembly, which is described with reference to Fig. 3B and Fig. 3C is fitted in place of the shield 328 surrounding the bore 315 for the cylinder 314'.

[0064] The modified cylinder 314' is also schematically illustrated as including a pressure sensor 278 coupled to a bore communicating with the keyhole at the exposed outer end of the cylinder. The pressure sensor is arranged to detect pressure changes resulting from the insertion of a key (or the like) into the keyhole. Also schematically illustrated is a displacement sensor 279, which may be provided in addition to or in place of the pressure sensor 278 and which is coupled to a displaceable element that is displaced by the insertion of an elongated object (such as a key or lock pick) into the keyhole. Additionally or alternatively, a microphone 276 may be provided at a suitable location on the cylinder 314 to detect sounds of interaction with the lock, e.g., sounds from key insertion, lock pick insertion, hack key insertion, etc.

[0065] In Fig. 3B is an assembly incorporating the mechanism and electronics of an electronic lock, housed in a knob, or more generally, a handle 330, which is attached to the door 302 by a mounting plate 332, which in turn is mounted on the door in place of the escutcheon 328. The mounting plate 332 is secured to the inside of the door with a pair of mounting screws 334. The mounting plate includes engaging portions, shown here as projections 336, which may be in the form of flanges that engage and lock corresponding formations in the knob 330. The mounting plate 332 and the knob may be locked together by one or more hidden threaded pins, each concealed in corresponding bores 338 through the (here) curved surface of a first portion 340 of the knob 330.In the example shown, most of the length of the button forms a body 339 which here extends over and receives the first (or inner) part 340, although of course other arrangements are possible within the scope of the invention.

[0066] In Fig. 3B also shows a set of one or more visual indicators 341, for example in the form of RGB LEDs, by which a state of the electronic lock and / or a mode or condition of the electronic lock can be indicated. Finally, Fig. 3B shows one or more apertures 342 formed in the major surface of the mounting plate 332. Each aperture 342 provides a window through which the magnetic field of a magnet 270 can pass unobstructed. The magnet(s) 270, if used, can be surface-mounted on the door in the window provided by an aperture 342, or the mounting plate can be used as a template (or template) to allow a recess or hole to be formed (e.g., drilled, machined, or cut) in the structure of the door so that a magnet can be inserted into the body of the door. If the recess or hole is deep enough, a magnet can be embedded in the door and concealed under a wooden or plastic cap, possibly prior to securing the mounting plate to the door.As mentioned, one or more magnets 270 may be mounted on the door in this manner to cooperate with the magnetometer(s) 264 of the electronic lock, as described with reference to FIG. Fig. 2. It is understood that the position of the aperture(s) 342 relative to the engagement portions 336 and the position of the complementary features of the assembly relative to the accelerometer used to detect the magnetic field of the magnet 270 are selected so that when the assembly is mounted on the door, the magnetometer 264 and the magnet 270 (positioned using the mounting plate used as a template) are aligned for optimal sensitivity.

[0067] Fig. Figure 3C schematically illustrates a longitudinal section through the assembly 330, the mounting plate 332, the lock case 304, the door 302, and the door frame 240. The assembly includes the knob 330 fitted over an inner portion 340. The inner portion 340 includes engagement portions 350 that engage and lock the engagement portions 336 of the mounting plate 332. As illustrated, approximately half the length of the knob overlaps the inner portion 340, with the inner portion effectively providing a shroud or housing for the smart lock electronics, although it is understood that many other possible configurations are within the scope of the invention.The tongue 326 of the cylinder 314' extends through an aperture in a PCB 251 (or between a pair of PCBs) that carries the majority of the smart lock's electronic components, including the processor 258, the memory 260, the RF transceiver 262, the magnetometers 264, and the accelerometer 275. As illustrated here, two magnetometers may be used, one for tamper detection using a magnetic field from a door-mounted magnet 270, and the other 264' for sensing the door open state (and thus a possible break-in) using a magnetic field from a frame-mounted magnet 266, although the same functionality can also be provided using only a single magnetometer. Connected to the processor, but optionally mounted external to the PCB 251, are the speaker / sounder 263 and the indicators 341.

[0068] The assembly includes a battery power supply including batteries 252, a charging assembly 254, optionally together with a charging socket 256 (preferably on the underside of the button so that it is hidden from view under normal circumstances).

[0069] In the Fig. 3C, the locking mechanism includes an electrically controlled actuator 246 (e.g., a motor or solenoid) and optionally an associated mechanism 352, which together are configured to apply torque between the inner portion 340 of the knob and the tongue 326 to rotate the cylinder 314' within the lock—to retract the bolt 244 into the lock case 304 or to extend the bolt 244 from the lock case 304. A force transmission arrangement 354 may be provided between the cam tongue 320 and the bolt. Likewise, the lock may be configured so that rotation (e.g., over-rotation) of the cam 318 also operates the latch 308.

[0070] Although Fig. While the above three arrangements represent arrangements suitable for a conventional door, those skilled in the art will appreciate that the same assembly and modified cylinder can be used equally well in conjunction with a door (or French window, patio door, etc.) with a multi-point locking system (typically having at least three locking points, all of which lock simultaneously when the mechanism is engaged). These typically work in conjunction with a cylinder lock (e.g., a Euro cylinder lock), although locking typically involves manually activating a door handle to engage the various locking points with their counterparts before the lock engages.Although this engagement phase may require the application of too much torque for a meaningful application of the described electronic lock complement (if only due to short battery life), the locking and unlocking step, which is different from the engagement / disengagement operations, could potentially be handled using the system just described.

[0071] In an alternative arrangement, the smart lock is provided with a clutch handle or knob on each side of the door, with the smart lock mechanism configured to control the clutch assembly so that, in the unlocked condition, the bolt can be retracted, and in the locked position, the handles / knobs are decoupled from the bolt, rendering them unable to retract the bolt to unlock the door. It is also understood that instead of providing the additional assembly in the form of a knob, a larger body that does not take the form of a knob or other handle (although it may incorporate a knob or other handle to facilitate pulling the door open) may be used to house the added mechanism—and such an arrangement may be configured to include a powered deadbolt actuator.

[0072] The Smart Lock from Fig. 3 and its developments as described with reference to the Fig. 4 to 7 may be designed and configured as an EN-certifiable shock sensor for use with EN-certified premises security systems (burglar alarm systems) of Grade 2 or higher (EN50131), including the required tamper detection function that triggers a tamper alarm if an attempt is made to open the device, remove its battery, or remove the lock from the door to which it is mounted.

[0073] Using a two-step process, where a separate anomaly detection step 406 is performed before an (optional) classification step, rather than attempting to classify the input 402 directly, has the advantage that an input 402 that represents an outlier compared to "normal" behavior can be identified as a potentially suspicious event, even if it is a type that has not been encountered or modeled before. This allows new types of attacks to be detected, even if they have not been specifically modeled. They may be difficult to classify retrospectively, but the system can at least detect the occurrence of something unusual. This could add future-proofing to the system, making it more robust than a one-step classification.

[0074] The anomaly detection process 404 may be based solely on the output provided by a shock or vibration sensing arrangement of the smart lock, such that the output 412 is derived only from the output provided by the shock or vibration sensing arrangement of the smart lock. Alternatively, the output 412 may be the result of processing the input 402 provided by the shock or vibration sensing arrangement of the smart lock, along with one or more optional additional inputs 414. Such optional additional inputs 414 may be provided by one or more sensors optionally external to the smart lock, but coupled to the door or door frame, optionally at one or more locations remote from the smart lock.For example, a sensor, such as a magnetic opening / closing detector, positioned to detect the opening / closing state of the door on which the smart lock is mounted. Also, a sensor capable of detecting the opening / closing state of the door by detecting the rotation of the door relative to an axis (e.g., capable of encoding the closed, opening, and open states, e.g., as -1 / 0 / 1), or detecting the rotation rate (normalized or not) or angular change of orientation (e.g., using an accelerometer or a magnetometer, or the like).

[0075] An additional input 414 may also be provided by another sensor in or associated with the smart lock, such as a microphone in or coupled to the lock, for example coupled to a cylinder of the lock, an inductive or capacitive sensor coupled to the lock or cylinder to detect human interaction with the lock (e.g., touch or close contact), or an insertion detector (such as a microswitch) to detect the insertion of a key or lock pick into the keyhole of the smart lock.

[0076] Anomaly detection 404 or 406 can be performed using a machine learning algorithm.

[0077] The machine learning algorithm can be trained with training data containing numerous examples (e.g., at least 1,000, at least 5,000, at least 10,000, or more) of sensor output data for "normal" events (such as inserting a key, opening a door, closing a door, unlocking a door, knocking on the door, slamming a door, etc.) and, optionally, for each class of "abusive" or "attack" behavior (e.g., lock picking, lock picking, drilling, lock or cylinder picking, cylinder extraction or removal, break-in attempts). The training data is labeled according to its "abusive" class. Training data for "normal" events can be labeled to indicate "normality," or they can be unlabeled, thus distinguishing them from data representing "abusive" events.Preferably, the training data includes data collected in-situ rather than exclusively "lab-collected" data, although it may be necessary to obtain a large amount of "abusive" data from attacks executed on test benches set up in labs or other environments that simulate the real world. The training dataset does not need to be a balanced dataset, meaning it is not required that the number of data samples for normal events be the same as for "abusive" elements.

[0078] Optionally, for two-stage anomaly detection, the autoencoder can be trained only on, and / or prioritized, normal data (by omitting and / or penalizing "attack" type data). When the signal is regenerated by the autoencoder, anomaly detection depends on how well the autoencoder was able to "adapt" the original input signal to a "normal" state and regenerate it. A large error (measured in energy) means that the autoencoder did a poor job of adapting the signal to one of the normal states, thus implying an anomaly compared to the "normal" training data. This generates detection. However, the "abusive" (or "attack") data can be used to train a classifier, which can then "flag" or categorize an abusive event—for example, labeling an event as a lockpicking or lockpicking attack.

[0079] The anomaly detection process can be performed using unsupervised learning with Gaussian mixture models (GMMs) or, alternatively, using an autoencoder. Autoencoders are neural network-based models trained through unsupervised learning to efficiently compress input data to form an encoded representation and then reconstruct the compressed representation to produce an output as close as possible to the original input. An autoencoder can be thought of as a multilayer perceptron (MLP).

[0080] The classification can be performed using any suitable classifier, such as a Convolutional Recurrent Neural Network (CRNN) architecture, which can be based on the combination of a CNN (Convolutional Neural Network) architecture with a GRU (Gated Recurrent Unit) architecture.

[0081] Fig. Figure 4B schematically illustrates the principle of a processor 450 making a determination based on data received from a sensor 452, e.g., a shock or vibration sensor such as an accelerometer or a magnetometer, of a smart lock such as 106, and from another sensor 454 that is not part of the smart lock. The processor may also be part of the smart lock.

[0082] The additional sensor 454 may, for example, be a door contact sensor that senses the state (open, closed, opening or closing, degree of rotation, etc.) of the door to which the smart lock 106 is attached, e.g., a magnetic sensing-based door contact sensor such as a magnetometer, a Hall sensor, or other magnetically switched device. Alternatively, the additional sensor 454 may be an accelerometer (single-, dual-, or tri-axis) that is not included or part of the smart lock, wherein the additional sensor is coupled to (e.g., mounted on or within) the door or door frame in which the door is mounted. Alternatively, the additional sensor 454 may be an inductive or capacitive sensor, a pressure sensor, a motion or occupancy sensor, a microphone, a pressure pad, a radar array, an RF-based occupancy detection system, or a camera (video, e.g., the camera of a video doorbell).The processor 450 may implement a classifier and / or an anomaly detection algorithm, optionally based on an AI approach.

[0083] The processor 450 may be configured to process sensor data from the sensors 452 and 454 to identify the presence of anomalies (e.g., outliers) that may indicate an anomalous event - in response, the processor may provide an output (e.g., signaling from an associated security or monitoring system) to mark the presence of an anomalous event.

[0084] This provides a smart lock that includes an accelerometer and / or a magnetometer, as well as a separate unit mounted on the door or door frame, which itself includes another sensor, such as an accelerometer and / or a magnetometer. Such an arrangement can facilitate better discrimination of the source / location of a shock or vibration (e.g., whether the lock, the door is near or away from the lock, etc.). Providing different information could be useful in facilitating localization of the source of a disturbance / vibration / shock.

[0085] The smart lock (or door sensor) could contain a processor that handles the calculations based on data from both sources, but equally the data could be sent to, for example, a control unit of a security monitoring system so that the control unit can perform the necessary calculations.

[0086] A shock or vibration sensor may be provided with a processor configured to process sensor data to determine the presence of anomalies in the data, and if an anomaly is detected / detected, the processor may be configured to generate an output. In an optional second embodiment, the processor may be arranged to analyze the sensor data (or processed sensor data) to perform a classification for assigning a detected event to one of several event types, wherein the event types include at least one threat class and at least one non-threat class.

[0087] Fig. Figure 4A schematically illustrates the elements that form an autoencoder 500.

[0088] Essentially, the autoencoder comprises an encoder portion 502, whose job is to compress input data to form an encoded representation 504, and a decoder portion, whose job is to transform the encoded representation 504 so that it reproduces the original input data as accurately as possible. Input data arrives at the encoder input 508, and the reconstructed output is provided at the decoder output 510. Fig. Figure 4B illustrates the layered structure of the autoencoder 500. In this example, the autoencoder comprises 6 fully connected layers. The encoder side applies dimensionality reduction by using fewer nodes for each layer between the input and the encoded portion, for example, from 32 nodes at layer X0 to 16 nodes at X1 to 8 nodes at X2. The layers of the decoder portion 506 also use an increasing number of nodes as we move away from the encoded representation 504 (or Z), with the number of nodes per layer increasing from 8 to 16 to 32. It should be understood that this structure is only exemplary, and that embodiments of the invention may use encoders in which the number of layers and the number of nodes in each layer of the encoder and decoder portions differ from those specified for this example.

[0089] Fig. Figure 5 schematically illustrates how a trained autoencoder can distinguish between "routine" events—labeled here as "in the distribution"—and outlier events (which may represent attacks on the smart lock or the door to which it is mounted), labeled here as "out of the distribution." A suitable threshold t can be selected, for example, based on calibration tests, to distinguish between "in the distribution" and "out of the distribution" events. Violation of the threshold can be used to trigger the reporting of an event (more simply, the provision of an output signal) or to trigger an alarm, or the like.

[0090] Fig. 6 schematically illustrates how an autoencoder according to one aspect of the invention may be integrated into a smart lock 700. The autoencoder 702, which may correspond to the autoencoder 500, may run on a processor 704, which may correspond to the processor 258. The processor may be a microprocessor, but may instead be an MCU, such as a SiliconLabs EFR32xG4 Cortex-M4 incorporating an ARM Cortex-M4 core. A memory 706, which may correspond to the memory 260, stores program instructions for controlling the processor 704 and, in particular, may store code for implementing the autoencoder 702 and the classifier 708. The smart lock 700 further includes an RF transceiver 710, which may correspond to the transceiver 262, a power supply 712, which may correspond to the power supply 250, and a lock actuator 714, which may correspond to the actuator 246, all of which are operatively connected to the processor 704.

[0091] Also coupled to the processor is the first sensor 716, which may be the accelerometer previously referred to as element 275. Optionally, as described above, the smart lock 700 may include at least a second sensor 718, which may be in the form of a pressure sensor 278, an insertion detection device 279, or a microphone 276.

[0092] One or more second sensors 720, 722 may be provided outside the lock 700 and configured to communicate (wirelessly or via a wired connection) with the processor 704. The second sensor may, as previously described, be a door contact sensor (optionally based on the use of magnetism) that detects the state (open, closed, opening) of the door to which the lock 700 is coupled, or it may be another accelerometer coupled to the door or the door frame in which the door is hinged, or another sensor that can provide data relevant to determining the state of the door and / or the occurrence of an attack or other event, or a combination of these events. Typically, the external sensors 720 / 722 may include an RF transceiver for communicating with the lock's RF transceiver 710, although the external sensor may be configured in another manner (e.g.,via a cable connection) to the processor 704.

[0093] In one embodiment, encoder 702 can run as a model using, for example, Tensorflow Lite. The models (autoencoder and classifier, if present) can be quantized from the float32 representation of the weights to int8 during training. Data can be received from each sensor (e.g., 716, 718, 720, 722, or any combination thereof) in packets of 128 samples, which are then provided as input to the encoder program.

[0094] Then, each batch of 128 samples is divided into 4 subgroups of 32 samples each, and the batch of 4 subgroups is input into the encoder model. Preliminary studies selected a sample size of 128, which proved to be equivalent to the most suitable duration for a sampling frequency of 200 Hz used by the lock's 714 / 275 accelerometer. 128 samples result in a duration of 640 ms, while 32 samples result in a duration of 160 ms. In some embodiments of the invention, these samples and their batches do not overlap, and no sliding window is applied.

[0095] Tanh activation can be used for the autoencoder neural network, but in other implementations Relu or leakyRelu could be used instead of Tanh activation.

[0096] In certain embodiments, it is possible to create a satisfactory neural network with a total number of weights (the sum of the weight numbers for all layers of the network) of 7,624 parameters. This may correspond to a file size of approximately 17 KB, including weight and state. Such a small model can easily run on an MCU despite the memory limitations typical of MCU implementations. If the sensor is a three-axis accelerometer, the input supplied to the autoencoder 702 may be a vector of samples, each with a size of 3 dimensions, representing x, y, and z coordinates. The sample format can be int8, with a length selected from 16, 32, 64 or 128, for example 32. The output of the autoencoder can be a single number, which is the recognition result, with a length of 1 and with an int8 format (with values ​​from 0-127) mapped to values ​​from 0 to 100 (ienormalized to values ​​within this range). The main mechanism of the model may be to calculate expected values ​​(for normal behavior). Expected inputs should elicit low values, for example, close to zero, with a maximum in practice between about 10 and 30 (to provide some error tolerance). The "out-of-distribution" events should yield significantly higher values. An alarm threshold can therefore be set somewhere in the range of 60 to 90 (within an overall range of 0-100). The threshold can be set based on the analysis of the model's output values ​​once the network has been trained with the training data, which includes everyday and out-of-distribution events.

[0097] If a classifier 708 is used to identify events outside the distribution, e.g., to label an anomalous event as lock picking, lock breaking, etc., a suitable model, such as one using a CRNN architecture, may be selected to run on processor 704. If the sensor is a 3-axis accelerometer, the classifier may receive an input vector of samples, each having 3 dimensions representing x, y, and z coordinates. As with the autoencoder, the sample format may be int8, with the length selected from the set 16, 32, 64, and 128, for example, 32. The output of the classifier may be a vector of the classification result for labels / classes, optionally with a uint8 format (values ​​0-100) with a length of 12.

[0098] The classification model can be based on supervised learning using deep learning, provided a well-prepared dataset is available for training the model. For smaller datasets, it may be helpful to use stratified k-fold cross-validation (k=5) to prevent overfitting to specific data and avoid the model making incorrect decisions. This approach can also be useful for larger datasets (e.g., 10,000 or more events). It may also be helpful to pre-train the classification model on all data for a coupling iteration and later iterate on a properly balanced dataset. Alternatively, one could use SVM on some features extracted from the signal. This would be a more traditional approach. It has some limitations, primarily the need to find and select the best features.

[0099] However, using unsupervised learning with the autoencoder is likely to produce better results than supervised learning when real, labeled data is lacking—which will generally be the case for at least some of the attack modes. Unsupervised learning is focused on outlier detection, and this means it should still be able to provide reasonable output when previously unseen data is pushed into the anomaly detection phase—so even new types of attacks can be expected to trigger an alarm notification (or alert).

[0100] If signals from a second sensor (e.g., external sensor 720 or 722) are used in addition to those from the lock's first sensor, the signals from the two (or more) sensors can be combined to provide a long vector (extending the input). For example, if the second sensor is a door state sensor, the longer vector could be in the form |Door Lock Accelerometer|State|Rotation|.

[0101] Alternatively, the state / rotation data could represent the position encoding (the number is modulated as sin / cos and added after the first layers), as described in the document available at the following URL: https: / / medium.com / @hunter-j-phillips / positional-encoding-7a93db4109e6

[0102] These signals could then be used as input to the anomaly detection model and / or the classification model, if used.

[0103] Alternatively, one could implement a decision maker for the detection model in the firmware that only triggers an alarm event when the door on which the smart lock is mounted is closed and no lock rotation occurs.

[0104] It may be possible to improve the overall classification results by using a different type of sensor in addition to using data from the smart lock's accelerometer (or magnetometer), since in general, the more data points, the better the overall classification.

[0105] In practice, there is always a way to normalize data from different sensors and also align them. In general, adding more information can help improve classification accuracy, e.g., from 3 to 30% relative. However, in some special use cases, classification accuracy can be significantly improved. For example, hand-on-handle or hand-on-lock detection (using, for example, capacitive sensing) and a key-in-lock detector (using, for example, impedance sensing) can help classify certain attack modes such as lock picking, lock picking, and lock picking.

[0106] As mentioned earlier, when using multiple sensors, all sensor data can be combined into a single input, concatenating it into a vector as a long series. However, it is also possible to view specific sensor outputs separately.

[0107] If a microphone is used as a second sensor (either in the lock or as an external sensor), it would make sense to perform some kind of feature extraction, optionally pre-filtering, and possibly using FFT, optionally using MFCC (Mel-Frequency Cepstral Coefficient) or CQCC (Constant Q Cepstral Coefficients) to lower the rank of the data and put emphasis only on some frequencies (very low < 50 Hz, most likely in the range 2 - 10 Hz).

[0108] The smart lock 106 may be used as part of a security monitoring system, for example one rated at Grade 2 or higher according to EN50131, although it may equally be used as a standalone component capable of communicating with one or more user devices and / or a network-based backend (e.g., cloud) (optionally via a local RF connection to a broadband router and from there via a wired and / or wireless connection or via an LPWAN (e.g., via NB-IOT or LTE-M). In one example, such a security monitoring system may be controlled by a video doorbell such as the one in Fig. 1 as 100 shown, as will now be described.

[0109] Fig. Figure 7 schematically illustrates the main components of an example of such a video doorbell 100 suitable for use in embodiments of the invention in conjunction with a smart lock, as described with reference to Figures Fig. 3 to 7. A video doorbell 100 includes a processor 800, which may be a microcontroller (MCU), with an associated memory 802 that stores program instructions ("software") that, when run on the processor 400, control the operation of the video doorbell 100. A pair of transceivers 804, 806 may be provided. A first of the transceivers 804 may establish WLAN communication with a WLAN access point (AP), such as the WLAN router 112 in Fig. 1, for the communication of video signals from video camera 808 and audio signals from microphone 810. The second transceiver 806 may support a lower-bandwidth channel for the transmission of control signals to and event notifications from alarm peripherals such as the Smart Lock 106, external video cameras, door / window contacts (which detect the state of windows or doors—open or closed), etc. Typically, the low-bandwidth channel(s) may be provided using a suitable allocated frequency(s) in the ISM (Industrial, Scientific, Medical) bands—such as (in Europe) 868 MHz. Preferably, the communications on the low-bandwidth channel(s) are encrypted.The primary reason for using a low-bandwidth transmission channel is to enable the use of low-power transceivers (in the alarm peripherals) (and especially lower power consumption than the notoriously power-hungry Wi-Fi transceivers), so that the battery-powered alarm peripherals can achieve the required minimum battery life of 3 to 5 years. Transceivers 804 and 806 are coupled to an antenna array 812, which typically includes (multiple) separate antenna elements for the two transceivers 804 and 806. One or both of the transceivers 804, 806 may support other transmission bands / protocols, such as Bluetooth (RTM) or BLE. The video doorbell 100 may also support communication over an LPWAN (e.g., over NB-IOT or LTE-M), which optionally includes device-to-device (D2D) communication.

[0110] The video doorbell 100 also includes a chime trigger 814, which may comprise a mechanical switch or "ring button," and preferably one that provides tactile feedback upon activation. In a known manner, the chime trigger 814 may be integrated with a lens of the video camera 808, but may equally well be provided separately so that the video camera lens does not need to move when the chime trigger 814 is activated.

[0111] The video doorbell 100 preferably also includes (or can be connected to) a keypad 816 for entering digits (such as passcodes or PINs). Preferably, the keypad 816 is a mechanical device that provides tactile feedback when activated.

[0112] The video doorbell 100 also includes a motion sensing assembly 817, which can be used to trigger the video camera for recording motion-triggered video footage and flagging (notifying) motion—although the video camera can be arranged to be always live to provide continuous monitoring. The motion sensing assembly can include one or more passive infrared sensors (e.g., PIR or T-MOS sensors). Additionally or alternatively, the motion sensing assembly can use radar and / or ultrasound to determine the distance of an object (e.g., a person) from the video doorbell, and this can be combined with passive infrared occupancy detection and / or other types of occupancy detection.The video doorbell may have an associated app or online tool to allow a user to define activity zones, areas, configure sensitivities, etc., so that notifications related to detected motion or presence, for example, are not transmitted related to motion detected in public spaces (e.g., people walking on a sidewalk outside the premises or vehicles passing on a road outside the protected premises).

[0113] The video doorbell 100 may also include illumination 818 (in the form of one or more light sources), particularly infrared illumination, but optionally also illumination to provide visible light illumination.

[0114] The video doorbell 100 may also include a visual display 819 for displaying messages and user feedback. Although it would be possible for the function of the keypad 816 to be incorporated into the display 819, when using a touch-sensitive display, it is preferable to keep these functions separate and use a separate mechanical keypad 816 for both durability and power consumption reasons.

[0115] The video doorbell 100 may also include a sound output device such as a speaker 819 for reproducing speech from a user at the user device 108, for announcements from the processor 800, and optionally for functioning as an alarm sounder or siren during an alarm event—as explained later. The provision of at least one sound output device (two or more may be provided) along with at least one microphone (two or more may be provided) enables two-way audio between a person at the video doorbell and another person, such as a specific user, via a user device (e.g., a smartphone with a video doorbell app or a security monitoring system app).The presence of one or more microphones 810 also enables the use of voiceprint identification as a form of access control—so, for example, a resident of the premises or a trusted visitor (such as a nurse, caregiver, cleaner, etc.) whose voiceprint is stored in the system can gain access to the home by speaking to the video doorbell, which compares the given voice sample to known stored voice samples to identify the speaker. If the identified speaker is on an approved list of individuals, the video doorbell can send an instruction to a smart lock on the relevant access door to allow the identified speaker to open the door, thus gaining access to the protected premises.

[0116] Optionally, the video doorbell 100 also includes a near-field communication (NFC) antenna 820 to enable near-field communication with an NFC device such as a dongle, a smartwatch, an NFC sticker, or a suitably equipped mobile phone - for example, to authenticate a user and possibly to unlock an associated smart lock 106 to gain access to the protected premises.

[0117] The video doorbell 100 is provided with an external housing or cover 821 to protect the doorbell components. Preferably, the housing 821 is provided with one or more tamper detection assemblies 813, which are operable to generate a tamper alarm when the housing is removed from the video doorbell 100. Such a tamper alarm is preferably handled by the security monitoring system's controller (the controller may optionally be provided either by the video doorbell itself or by a separate unit), regardless of the armed state of the security monitoring system.Users (or the owner(s) of the security surveillance system can be provided with an app that can be used to pre-warn the security surveillance system controller of a scheduled event that would otherwise be treated as an alarm event, so that the security surveillance system controller can be configured to ignore the scheduled event if it occurs. For example, it may be necessary to remove the video doorbell's housing 821 to replace a faulty battery 826. By using the app, a user or service technician can prevent the security surveillance system controller from treating the removal of the housing as a tamper event that must be reported as an alarm event. The same principle applies equally to the lock 106 and its tamper detection.

[0118] The video doorbell 100 is preferably provided with a mains power supply 822 coupled to a power supply 824 including a rechargeable battery 826 (as a backup power supply in the event of a mains failure) and a charging arrangement 828 for managing the charging of the rechargeable battery 826. Preferably, as shown, the video doorbell 100 also includes an interface 830 (such as a micro-USB port, a USB-C port, a "Lightning" jack, or the like) for receiving a low-voltage power supply (e.g., 5 V or 20 V) (e.g.,This allows the video doorbell to accept power from a power bank or external charger, which can be used to recharge the 826 rechargeable battery on-site in the absence of mains power (or in the event of a mains failure), rather than having to remove the battery for charging. This allows the video doorbell to always have power—an important factor if the video doorbell also functions as a controller for a security surveillance system. Alternatively, the video doorbell can be configured to accept wireless (e.g., inductive) charging from an external power source.

[0119] The function of the video doorbell as a control of a security surveillance system is now being discussed in connection with Fig. 8 considered.

[0120] Fig. Figure 8 schematically illustrates an embodiment of a home security monitoring system (home alarm system) 900 that is built around a video doorbell 100 that functions as a controller of the system 900. In the illustrated example, the system 900 includes a smart lock 106, as described with reference to Figure 8. Fig. 2 to 7, so that the system user (e.g., the homeowner) can remotely unlock the door 102 to which the lock 106 is attached to admit a visitor, after optionally verifying the visitor using the video camera of the video doorbell 100.

[0121] The system 900 includes alarm peripherals such as a door contact 902, for example, at the back door 904 of the house (and optionally also at the front door to which the lock 106 is attached), which may be a magnetic sensing switch (such as a reed relay) or a magnetometer or a Hall-effect sensor that detects whether the door 904 is open or closed, or a shock or vibration sensor based on an accelerometer and transmits an alarm that is received by the second transceiver 806 (e.g., 868 MHz transceiver) of the video doorbell 100 and processed by the processor 800 to, when the system is armed, generate an alarm event signal addressed to a (e.g., cloud-based) remote alarm notification service 110 and transmitted by the first (e.g., Wi-Fi) transceiver 804 (the speaker of the video doorbell may also be used immediately as siren activated or to provide another acoustic deterrent).The transmitted alarm event signal may be received by the premises' Wi-Fi access point (AP) 112 and passed through a broadband connection to the internet 115 and thereby to the cloud-based alarm notification service 110 (or it may be transmitted via LTE-M, NBIoT, or the like). If a door sensor 902 is provided for the door to which the lock 106 is attached, the sensor 902, which may be accelerometer-based or magnetically responsive, may operate as the second sensor 454 (or one of them) and / or be the source of the optional additional input 414. An alarm event signal may be sent if the smart lock 106 detects the presence of an anomalous event (as described with reference to any of the . Fig. 4 to 7), whereby the smart lock can optionally determine the presence of an anomalous event even if the door sensor 902 itself does not detect a stimulus that meets its own alarm event threshold: the alarm event can be signaled by the smart lock to the video doorbell for further transmission (although transmission from the smart lock 106 directly to the alarm notification service 110 rather than via the video doorbell is also contemplated).

[0122] In the cloud-based alarm notification service 110, the identity of the security monitoring system (which may be the video doorbell 100 or the smart lock 106) included in the alarm event signal may be verified against a database of registered system identities to retrieve an address (e.g., a SIP address, a mobile phone number, an email address) corresponding to the registered alarm system identity. The alarm notification service 110 may then send a notification to the registered address, for example, presenting the user with a notification (e.g., a native notification) on their smartphone 108 or other personal electronic device and / or receiving an automated phone call providing details of the alarm event—e.g., the identity / type / location of the sensor (e.g., the back door contact sensor or the smart lock 106) that was triggered.A user receiving such a notification may request the streaming of videos or the transmission of images from cameras 906, 906' installed in or on the premises (e.g., house) of the security surveillance system installation: for example, a push notification may include one or more "action buttons" that, when activated by the user, cause the user's device 108 to send an instruction to the alarm reporting service 110 so that the alarm reporting service 110 sends an instruction to the controller of the security surveillance system 900 (i.e., the video doorbell processor) to transmit activation signals to activate the cameras 906, 906', causing them to capture and transmit images and / or videos. The controller of the security surveillance system 900 (i.e.,The video doorbell processor (e.g., the video doorbell processor) can receive these video transmissions using the first (Wi-Fi) transceiver 804, and the same transceiver can be used to retransmit the images / videos to the alarm notification service 110 via the access point 112 and the internet 115. The alarm notification service 110, in turn, can retransmit the images / videos to the user's device 108. The alarm notification service 110 can be configured to store the images / videos captured in this manner (provided the user has paid the required subscription fee).

[0123] Each of the video cameras 906, 906' can be practically a "standard" video camera (to keep costs low) that includes only one transceiver, and this transceiver may support Wi-Fi but not a low-bandwidth secondary channel. In such a case, the video doorbell, in the form of a system controller of the security monitoring station, must communicate with and receive communications from the cameras exclusively via Wi-Fi—that is, using the first transceiver 804. Preferably, however, the video cameras 906, 906' support both Wi-Fi and a relevant second channel for communication with the second transceiver 806 of the video doorbell—and preferably, this functionality is provided by including a second transceiver in each of the cameras 906, 906'. Optionally, the video cameras each support an LPWAN technology such as LTE-M and / or NB-IoT.

[0124] The user's device can also be programmed with a supplementary app that allows the user to send instructions to the video doorbell (which, in this embodiment, functions as the security monitoring system controller) to activate selected video cameras so the user can "check in" to the home from outside, and also to arm / disarm the alarm system. Images and videos from the cameras 906, 906' can be transmitted via Wi-Fi between the camera 906, 906' and the video doorbell 100 - and thus these images and videos are received by the first transceiver 804, which is also used for onward transmission to the access point 112. Optionally, in some embodiments, the system can also be configured to transmit lower resolution images and / or lower frame rate videos using the low-bandwidth channel (e.g.,868 MHz) to be received by the second transceiver for use as a backup in case the higher-bandwidth channel (e.g., Wi-Fi) experiences interference, with the video doorbell processor configured to forward the first arriving image / video and then subsequently forward the corresponding higher-resolution / higher-frame-rate image / video if and when it arrives. Likewise, the cameras can be arranged to utilize an LPWAN such as LTE-M and / or NB-IoT for the transmission of video images and, optionally, duplicate images at different resolutions and / or frame rates, as just described.

[0125] Likewise, notifications are preferably provided to the alarm notification service 110 (and further to the user device 108) regarding alerts received from the smart lock 106 (such as upon detection of an anomalous event) or from other alarm peripherals, such as motion-triggered cameras 906, 906' and a window contact sensor 908 (which may also or instead function as a window shock or vibration sensor) connected to a window 810.Likewise, an anomaly report or tamper alarm received from the door lock 106, such as an attempt to pick the lock, to get the lock 106 out of the door 102, or a lock magnetometer sensing the opening of the door when the lock has not been unlocked, or the detection of an anomalous event (such as an attempt to pick the lock or other attack - such as the detection of a drilling attack - on the lock) may be generated by the lock processor based on signals from the smart lock's accelerometer 275 (e.g., as described with reference to any of the . Fig. 4 to 7) and can be handled by the video doorbell processor 800 (in this embodiment), and thereby the user can be notified via the alarm notification service 110. Event notifications from the alarm peripherals can generally be provided over a low-bandwidth channel for reception by the video doorbell's second transceiver 806, since most simpler peripherals (e.g., door contacts, motion sensors, shock or vibration sensors) do not require a high-bandwidth channel (e.g.,they do not require anything like Wi-Fi), but must be cost-effective and have a very long battery life - so they generally only contain a single transceiver each, configured to communicate with the second transceiver 806 (both LTEM and NB-IoT also support low power consumption, especially at low data rates, and support long-range communication, which makes them attractive for this role as well). As mentioned earlier, alarm peripherals in the form of video cameras can benefit from providing a high-bandwidth channel, such asWLAN, since the timely transmission of good quality video images (in color, with high resolution, and an acceptably high frame rate) generally requires quite high bandwidth, and video camera peripherals therefore almost always include a WLAN transceiver and, consequently, are almost always primarily mains-powered (preferably with battery backup). While the WLAN transceiver could be used to transmit event notification signals received from the video doorbell using the first transceiver 804, it is preferable (budget permitting) to provide video cameras that can report events using a low-bandwidth channel (for reception by the second transceiver 806) and that preferably include an additional transceiver to enable this (although, of course, a single multifunction transceiver can be used instead).By providing video camera peripherals with narrowband and broadband communication capability, we make it easier and more convenient to use a system like . Fig. 8 to the improved system of Fig. 9 as described below.

[0126] The video doorbell's ability to detect presence (for example, using one or more PIR sensors, a TMOS sensor, Wi-Fi scanning, radar, or the camera) allows the video doorbell itself to function as an alarm peripheral for the system. This allows the video doorbell to notify of an alarm when the system is armed, just as it would when another alarm peripheral is triggered. While this may only be appropriate in certain circumstances (particularly those determined by the likelihood of false alarms from "safe" actors), it is a potentially valuable option.

[0127] The processor 800 of the video doorbell 100, in the form of the controller of the security monitoring system, can also be configured to check the status of the peripheral devices, including the quality of the communication channel, the status of the peripheral battery, etc.

[0128] It is assumed that a video doorbell with the control functionality of the security surveillance system will be installed in new buildings in addition to retrofitting existing houses, optionally together with the Smart Lock 106, as described with reference to one of the Fig. 2 to 7, together with at least one alarm peripheral, optionally in the form of a motion-sensitive video camera, such as 906, 906', and preferably another alarm peripheral in the form of a door contact to sense the state (open or closed) of the front door (equipped with the smart lock 106) and the rear door (or other secondary access door to the premises). Such a system could be installed at relatively low cost, and the smart lock 106 and its door magnet(s) 270 (and optionally frame magnet(s) 266) could, for example, be factory-installed—or at least the door could be factory-prepared for on-site installation of the smart lock 106 and the door (and frame) magnet(s) 266 and 270.The primary occupant of the home would then benefit from the increased security that comes with a professionally installed alarm system, albeit with a subset of all the possible features of such a system—and especially without a professional monitoring service. The design and configuration of the video doorbell and alarm peripherals—which include the Smart Lock 106—are such that, following the installation of a security monitoring system based on their use, as described in... Fig. 8, upgrading the system to include professional monitoring by a Remote Alarm Receiving Center (ARC) can be achieved relatively easily. Of course, such an upgrade may also be attractive to a resident who already has a system such as the one in Fig. 8. Such an upgrade will now be described with reference to Fig. 9 described.

[0129] Fig. 9 generally corresponds to Fig. 8, as it is based on the assumption that a system like the one used in Fig. 8, has been upgraded to include the benefit of professional monitoring by a remote alarm receiving center 1002 - although it is also anticipated that security monitoring systems such as the one used in Fig. 9, can be installed from the beginning. The security monitoring system 1000 differs from the system 900 of Fig. 8 in that it includes a standalone alarm control unit 1004 configured to control the security monitoring system 1000 rather than relying on the video doorbell to act as the controller. The video doorbell 1006 of the system 1000 may be, and preferably will be, the video doorbell 100 that controlled the system 900, but with a reconfigured processor (e.g., through appropriate reprogramming or system updates) to operate (at least in part) as a peripheral reporting to the alarm control unit 1004 rather than continuing to act as the controller of the system 900.

[0130] The present disclosure therefore assumes, as an option, that a first installation comprises a video doorbell as described above, which is operated as a controller of a security monitoring system, which preferably includes a lock as described above with reference to one of the Fig. 2 to 7, and at least one further installed alarm peripheral comprising either a door / window contact for detecting the status of a door or window, a door and / or window shock or vibration sensor for detecting physical attacks against the respective door or window, or a separate motion-activated video camera, wherein the alarm peripheral includes a transceiver for communicating with the first transceiver of the video doorbell.

[0131] The alarm control unit 1004 includes, like the video doorbell described with reference to Fig. 7, a processor 1010, which may be a microcontroller having an associated memory 1012 storing program instructions ("software") that, when run on the processor 1010, control the operation of the alarm control unit 1004 and the security monitoring system 1000. At least one pair of transceivers 1014, 1016 may be provided. A first one of the transceivers 1014 may support Wi-Fi communication, with the alarm control unit being configured to operate as an access point of a Wi-Fi network (having a first SSID associated with the security monitoring system) that may operate in parallel with another Wi-Fi network (having a second SSID) that may support Wi-Fi requirements in the home, such as supporting video streaming services (e.g., Netflix, Amazon Prime, RTMs), working from home, etc.The alarm control unit 1004 is configured to receive video signals from the video cameras 906, 906' using the first of the transceivers 1014. The second transceiver 916 may support a lower-bandwidth channel for transmitting control signals to and event notifications from alarm peripherals such as the video doorbell 1006, the smart lock 106, the video cameras 906, 906' (if they include the appropriate functionality; otherwise, event notifications, etc., are received via Wi-Fi), door / window contacts such as 902 and 908, etc. Typically, the low-bandwidth channel(s) may be provided using a suitable allocated frequency in the ISM (Industrial, Scientific, Medical) bands—such as (in Europe) 868 MHz. Preferably, communications on the low-bandwidth channel(s) are encrypted.The primary reason for using a low-bandwidth transmission channel is to enable the use of low-power transceivers (in the alarm peripherals) (and especially lower power consumption than the notoriously power-hungry Wi-Fi transceivers), so that the battery-powered alarm peripherals can achieve the required minimum battery life of 3 to 5 years. Transceivers 1014 and 1016 are coupled to an antenna array (not shown), typically comprising (multiple) separate antenna elements for the two transceivers 1014 and 1016. One or both of transceivers 1014, 1016 may support other transmission bands / protocols, such as Bluetooth (RTM) or BLE, etc.Preferably, at least one transceiver is provided which is or can be configured to communicate using 4G or 5G (or using another suitable PLMN data protocol) for communication with the ARC 1002, for example in the event of a power failure in the premises or the loss of the wired connection to the Internet 115 - e.g. due to malicious actions of a criminal.

[0132] The alarm control unit 1004 is preferably configured to operate in at least one "armed" mode, in which security around the premises is monitored by door and window sensors such as the door sensor 902, the smart lock 106, and the window sensors 908, and in which at least one occupancy sensor monitors the interior of the premises. For example, the internal occupancy sensor may be a passive infrared sensor (or T-MOS sensor), which may or may not be connected to a video camera. Additionally or alternatively, internal occupancy may be detected using so-called Wi-Fi sensing, wherein the alarm control unit runs a Wi-Fi sensing algorithm and the video doorbell and / or another static Wi-Fi node (or access point) acts as an illuminator for the Wi-Fi sensing.The alarm control unit 1004 is preferably also configured to operate in a disarmed mode, in which internal occupancy is not monitored and in which alarm signals received from door and window sensors are largely ignored by the alarm control unit 604. However, the alarm control unit 1004 is preferably configured to respond to tamper signals, such as from the lock 106 (and also to reports of the detection of an abnormal event) or from other alarm peripherals even in the disarmed mode, since criminals and other malicious actors could exploit the disarmed state to attempt to sabotage or disable peripherals and other components of the system 1000.The alarm control unit 1004 is preferably also configured to operate in at least one "home armed" mode, in which internal occupancy is generally not monitored (or at least alerts relating to detected occupancy are ignored by the alarm control unit 1004), but in which the security of the area or part of the area is monitored so that event signals relating to detected door openings and detected window openings are alerted to and possibly also reported as alarm events (optionally after a time specified by the user on-site, during which the detected event is marked as a false alarm, for example by entering a security code at a user interface or by presenting a dongle, token or mobile phone, for example at an NFC interface).

[0133] The alarm control unit 1004 is operatively coupled to a remote Alarm Receiving Center (ARC) 1002, preferably via both a wired connection (e.g., broadband) and one or more wireless connections (e.g., SigFox (RTM), PLMN using, for example, GPRS, LTE, 4G, or 5G) (e.g., using either NB-IOT (Narrowband IoT, supported by 3GPP) or LTE-M (LTE Machine communication type). Notifications received by the alarm control unit 1004 that fit the profile of possible "alarm events" (based on one or more of the identity of the sensor providing the notification, the nature of the notification, the arming state of the alarm system 1000, the time of day, the day of the week, etc.) can be reported to the ARC 1002, along with the identity of the alarm installation 1000.Such a notification may be generated or initiated by the smart lock 106 detecting or determining the presence of an anomalous event. If the notification is associated with images or videos, for example, because the triggered sensor was a camera or was connected to a camera, then images / videos may also be sent to the ARC. Typically, human operators at the alarm receiving center review the event they were notified about and attempt to verify the event as an alarm event based, for example, on the content of the images / videos, sounds received from microphones in the premises, interactions with a user on-site (for example, via a user interface in the monitored premises). If an event is notified that is verified as an actionable event (e.g., burglary, break-in, fire, etc.), the alarm event may be triggered.or a medical emergency), an alarm is triggered with the local police and / or other emergency services (e.g., fire department, paramedics, etc.). The ARC may additionally contact a registered user or other human contact (relative, support person, caregiver, etc.) by sending a push notification (or other notification) to a user device 108, for example, using a previously described technique.

[0134] In a system such as Fig.9, the video doorbell 1006 may communicate events to and receive control signals from the alarm control unit 1004, preferably using a lower bandwidth channel via the second transceiver 1016. The higher bandwidth of a Wi-Fi channel provided by the first transceiver is preferably used to transmit images / videos from the video doorbell to the control unit 1004, with the control unit further transmitting the images / videos to the alarm receiving location 1002 and optionally to a user device such as 108 via a backend service 110 that sends push notifications to a user's personal communication device 108 when the doorbell is pressed (or optionally when someone approaches the doorbell 100).To support such communications, the control unit 1004 may use its broadband connection 114 to the internet 115, with the backend service 110 sending push notifications to a public mobile network (PLMN) 116, through which notifications are delivered to the user's personal communication device 108. The same communication path may be used to stream live video (and audio) from the video doorbell 100 to the user. A reverse communication path may also be supported to allow the user to speak to a person at the doorbell 100 and also allow the user to activate (i.e., release) the lock 106 to allow the person at the door to open the door 102. The signals to activate (release) the lock are passed to the lock 106 via the control unit 1004, which communicates with the lock 106.

[0135] The video doorbell's video camera, processor, and software are preferably configured together to record and stream (on-demand or on-demand) Full HD video (e.g., 1080p).

[0136] Control of the system, whether provided by the video doorbell 100 or by the alarm control unit 1004, is preferably configured to respond to the entry of a "duress code" on the video doorbell keypad by alerting either the ARC 1002 if the controller is the control unit 904, or by alerting specific individuals through calls (e.g., SIP calls) or notifications, preferably in each case with supporting images or videos captured at the time the duress code is entered (and possibly 30 seconds or more before the duress code is entered). A duress code is a code (e.g., a PIN) that can be used to disarm the security monitoring system or to gain access to the premises, or both, but which is in addition to a "normal" access code.The idea is that under normal circumstances, a normal code is used, and using such a code does not trigger a special notification. However, if a user is threatened (for example, by an abusive partner or ex-partner, a thief, or another type of criminal) and is forced to enter the protected premises, the user enters the duress code instead of the normal code, thus signaling that a duress condition exists. Upon receiving a duress notification, the Alarm Receiving Center staff can contact the police or other security personnel to facilitate intervention. Likewise, a person receiving a duress notification, such as a friend, neighbor, or relative (for example, if the video doorbell acts as a controller for the security surveillance system), can intervene or involve the police for intervention.

[0137] The control of the system, whether provided by the video doorbell 100 or by the alarm control unit 604, may be configured to allow access to the protected premises (e.g., by unlocking the lock 106 and either disarming the system or at least temporarily ignoring a door opening signal with respect to the corresponding access door) based on FaceID - i.e., recognizing a visitor's face that matches the face of a stored identity (the controller stores facial recognition data for one or more known identities for which access is to be provided, or has access to a store containing this data).

[0138] Control of the system, whether provided by the video doorbell 100 or by the alarm control unit 1004, can be configured to allow access to the protected premises (e.g., by unlocking the lock 106 and either disarming the system or at least temporarily ignoring a door opening signal related to the corresponding access door) based on the recognition of a QR code, e.g., a dynamic QR code, presented to the video doorbell camera—for example, by a visitor (or resident) displaying a QR code on the display of their phone or other wearable device (such as a smartwatch). Preferably, any QR code generated by or in connection with the system (e.g., by a corresponding backend system or by a user's video doorbell or system app) has a limited lifetime of 24 hours or less (shorter lifetimes, e.g.,12 hours, 6 hours, 4 hours, can also be used advantageously) to improve system security.

[0139] It is understood that the above description merely illustrates examples of the invention without limiting its scope. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] WO 2023 / 227258

[0003] Cited non-patent literature

[0000] https: / / medium.com / @hunter-j-phillips / positional-encoding-7a93db4109e6

[0101]

Claims

[1] An installation comprising an electronically controlled lock mounted on a door, the electronically controlled lock including a first sensing arrangement in the form of an accelerometer or a magnetometer, the installation comprising a unit separate from the lock mounted on the door or on a door frame receiving the door, the unit including a second sensing arrangement, the second sensing arrangement including an accelerometer or a magnetometer, the installation including digital processor circuitry configured to receive signals from the first and second sensing arrangements and to process the signals to detect a possible intrusion attempt based on sensor data simultaneously sampled from different sensing positions relative to the door and / or the door frame. [2] Installation according to claim 1, wherein the lock includes a keyhole and further comprises one or more additional sensors in the form of: (i) a microphone arranged to preferentially pick up sounds from a keyhole of the lock and / or from the vicinity of a cylinder of the lock; (ii) a pressure sensor; and / or (iii) an insertion detector, optionally based on the mechanical displacement of a sensing element, to detect the insertion of an element such as a key, picking key or lock pick into the keyhole of the lock: and wherein the digital processor circuit is arranged to receive signals or data from each such additional sensor in addition to the signals received from the first sensing arrangement, wherein the digital processor circuit (or a remote processor) is programmed or configured to use signals or data from each such additional sensor to detect and / or classify an anomalous event. [3] An installation according to claim 1 or claim 2, wherein the lock further comprises one or more electronic sensing assemblies for performing hand-on-handle or hand-on-lock detection, for example capacitive sensing, and key-in-lock detection (for example using impedance sensing), and wherein the digital processor circuit is configured to use data from the one or more electronic sensing assemblies in classifying events into particular attack modes such as lock picking, lock picking and lock picking. [4] An installation according to any preceding claim, wherein the digital processor circuit comprises a processor programmed to operate as an autoencoder for processing the sensor data. [5] An installation as claimed in any preceding claim, wherein, in the event that the digital processor circuit detects the presence of an anomaly, the processor circuit is programmed to analyze the sensor data or processed sensor data to assign a detected event to one of a plurality of event types, the event types including at least one threat class and at least one non-threat class. [6] An installation as claimed in claim 5, wherein the threat class includes at least one of lock picking, lock breaking, and lock pulling. [7] An installation as claimed in any preceding claim, wherein the processor circuit comprises a processor which is a component of the electronically controlled lock. [8] An installation as claimed in any preceding claim, further comprising a security monitoring system for premises of which the door forms a part, and optionally at least part of the processor circuit comprising a processor of a controller of the security monitoring system. [9] An installation according to claim 8, wherein control of the security monitoring system is provided by a video doorbell arrangement. [10] An installation according to claim 8 or 9, wherein the security monitoring system has at least one mode of operation in which it is arranged to notify a remote monitoring unit of alarm events. [11] An installation according to claim 10, wherein the security monitoring system has at least one operating mode in which it is arranged to notify the remote monitoring unit of anomalous events detected in the sensor data. [12] Security monitoring installation of premises, which includes a control unit for controlling the operation of the security monitoring installation, the security monitoring installation further comprising: a door vibration sensor integrating a first detector in the form of an accelerometer or a magnetometer, the vibration sensor being coupled to a door of the premises; an electronically controlled lock incorporating a second detector, the second detector being in the form of an accelerometer or a magnetometer, wherein the electronically controlled lock is linked to the door of the premises; wherein the vibration sensor and the electronically controlled lock are configured to transmit signal data derived from their detectors to the control unit; and wherein the control unit is configured / programmed to classify an event based on the signal data derived from the first and second detectors. [13] A premises security monitoring installation according to claim 12, wherein the control unit includes a processor configured to apply a machine learning model, such as an autoencoder, to process received signal data to determine the presence of anomalies in the received signal data. [14] A premises security monitoring installation according to claim 12 or 13, wherein the control unit is configured / programmed to provide a quantized output whose value is selected from at least three levels (ie non-binary output).

Images