Door lock control method, device, equipment, readable storage medium and program product

Abstract

The application relates to a door lock control method, device and equipment, a readable storage medium and a program product, and relates to the technical field of smart home. The method comprises the following steps: when it is detected that the relative distance between an authorized person and a door body is reduced from being greater than a preset first distance threshold to being smaller than a preset second distance threshold, and the movement direction of the authorized person is towards the door body, activating an outdoor image acquisition unit; performing face recognition on a first outdoor image collected by the outdoor image acquisition unit, and performing identity verification on the recognized face to obtain the number of authorized persons and the number of unauthorized persons; and controlling the opening and closing of the door lock according to the combination relationship between the number of authorized persons and the number of unauthorized persons. The method can improve the convenience of the smart door lock while effectively reducing the security risks caused by tailing intrusion.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and in particular to a door lock control method, device, equipment, readable storage medium, and program product. Background Technology

[0002] With the development of smart home technology, smart door locks have been widely used for access control in residential and office settings. Most existing smart door locks employ verification methods such as password input, fingerprint recognition, IC card sensing, or facial recognition via external cameras.

[0003] Existing identification logic cannot effectively distinguish between individuals with a clear intention to unlock the door and unrelated individuals passing by or temporarily stopping at the door, easily leading to unexpected false triggering issues. Furthermore, mainstream smart locks generally lack reliable tailgating detection mechanisms, making it difficult to prevent the security risks of strangers following and breaking in. Summary of the Invention

[0004] Therefore, it is necessary to provide a door lock control method, device, equipment, readable storage medium, and program product that can reduce security risks in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a door lock control method, including:

[0006] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0007] The system performs facial recognition on the first outdoor image acquired by the external image acquisition unit and verifies the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0008] The door lock is controlled to open and close based on the combination of the number of authorized personnel and the number of unauthorized personnel.

[0009] In one embodiment, controlling the opening and closing of the door lock based on the combination of the number of authorized personnel and the number of unauthorized personnel includes:

[0010] If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then the door lock is opened;

[0011] If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock remains closed.

[0012] In one embodiment, the method further includes:

[0013] Human target detection and exit intention recognition are performed on indoor images acquired by the door image acquisition unit to obtain the intention recognition result;

[0014] If the intent recognition result indicates that the person inside intends to leave, then the door-side wireless ranging unit is activated;

[0015] If the relative distance between the person inside the room and the door is determined to be less than a preset third distance threshold by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated.

[0016] Unauthorized personnel detection is performed on the second outdoor image acquired by the door external image acquisition unit to obtain the personnel identity detection result;

[0017] Based on the personnel identity detection results, the door lock is controlled to open or close.

[0018] In one embodiment, controlling the opening and closing of the door lock based on the person identification detection result includes:

[0019] If the personnel identification result indicates that there are unauthorized personnel outside the door, then the door lock remains closed;

[0020] If the personnel identity detection result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

[0021] In one embodiment, the process of performing human target detection and exit intention recognition on the indoor images acquired by the door image acquisition unit to obtain the intention recognition result includes:

[0022] Human target detection is performed on multiple consecutive frames of the indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results;

[0023] If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is determined to be towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then the intention recognition result indicating that the person inside the room has the intention to leave is obtained.

[0024] In one embodiment, the door-side wireless ranging unit is an ultra-wideband positioning anchor deployed around the door, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

[0025] Secondly, this application also provides a door lock control device, comprising:

[0026] The activation module is used to activate the door external image acquisition unit when it detects that the relative distance between the authorized person and the door has decreased from greater than a preset first distance threshold to less than a preset second distance threshold, and the movement direction of the authorized person is towards the door.

[0027] The identity verification module is used to perform face recognition on the first outdoor image acquired by the door image acquisition unit, and to verify the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0028] The control module is used to control the opening and closing of the door lock based on the combination relationship between the number of authorized personnel and the number of unauthorized personnel.

[0029] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0030] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0031] The system performs facial recognition on the first outdoor image acquired by the external image acquisition unit and verifies the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0032] The door lock is controlled to open and close based on the combination of the number of authorized personnel and the number of unauthorized personnel.

[0033] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0034] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0035] The system performs facial recognition on the first outdoor image acquired by the external image acquisition unit and verifies the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0036] The door lock is controlled to open and close based on the combination of the number of authorized personnel and the number of unauthorized personnel.

[0037] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0038] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0039] The system performs facial recognition on the first outdoor image acquired by the external image acquisition unit and verifies the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0040] The door lock is controlled to open and close based on the combination of the number of authorized personnel and the number of unauthorized personnel.

[0041] The aforementioned door lock control method, device, equipment, readable storage medium, and program product activate the external image acquisition unit only when the relative distance between the authorized person and the door decreases from a preset first distance threshold to a preset second distance threshold, and the direction of movement is clearly towards the door. This effectively filters interference from distant, irrelevant personnel and accurately distinguishes between authorized personnel with the intention to open the door and irrelevant personnel merely passing by. This significantly reduces false triggering of image acquisition and recognition, avoiding unnecessary frequent system startups and resource consumption. Furthermore, after triggering, the system automatically acquires the first... Outdoor images are used for facial recognition and identity verification. The number of authorized and unauthorized personnel in the scene is counted, and the door lock is dynamically controlled based on the combination of these two numbers. This constructs a reliable door scene perception and tailgating detection mechanism. It not only solves the problems of difficulty in accurately identifying the real intention to open the door and high false trigger rate in traditional solutions, but also can promptly identify unauthorized personnel following behind when authorized personnel unlock the door. This avoids the security vulnerability of criminals tailgating in from the door lock control level. While improving the convenience of using smart door locks, it effectively reduces the security risks caused by tailgating. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the door entry process of the door lock control method in one embodiment;

[0044] Figure 2 This is a schematic diagram of the door entry process in one embodiment of the door lock control method;

[0045] Figure 3This is a schematic diagram of the exit process of the door lock control method in one embodiment;

[0046] Figure 4 This is a schematic diagram of the exit process of the door lock control method in one embodiment;

[0047] Figure 5 This is a hardware architecture diagram of a door lock control method in one embodiment;

[0048] Figure 6 This is a structural block diagram of a door lock control device in one embodiment;

[0049] Figure 7 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various objects, but these objects are not limited by these terms. These terms are only used to distinguish the first object from the second object. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0052] The door lock control method provided in this application embodiment can be applied to an application environment consisting of four core components: an external image acquisition unit, an internal image acquisition unit, a UWB (Ultra Wide Band) positioning module, and a smart door lock body.

[0053] Specifically, the external image acquisition unit can be an infrared wide dynamic range camera, configured to acquire image data of a preset monitoring area outside the door. This image data is used for facial recognition and personnel detection at the door. As an optional implementation, the camera can be installed on the outer panel of the door or on the upper part of the door frame. Those skilled in the art should understand that any installation location that can completely cover the target monitoring area outside the door and meet the image acquisition requirements falls within the protection scope of this application.

[0054] The image acquisition unit inside the door can specifically employ a wide-angle camera, configured to acquire image data of a preset monitoring area inside the door. This image data is used for indoor personnel movement recognition. As an optional implementation, the camera can be installed on the inner panel of the door or on the interior walls surrounding the door. Those skilled in the art should understand that any installation location that can completely cover the target monitoring area inside the door and meet the requirements for movement recognition acquisition falls within the protection scope of this invention.

[0055] The UWB positioning module includes at least one UWB base station and at least one UWB tag. The UWB base station has a built-in UWB positioning chip and is deployed at predetermined locations around the door. The UWB tag is carried by authorized personnel and can take the form of, but is not limited to, dedicated standalone UWB tags, smartphones with integrated UWB functionality, smart bracelets, smart keychains, or other portable devices. This positioning module uses a two-way ranging algorithm or a time-of-arrival (TOA) algorithm to obtain the precise relative distance between the authorized personnel and the door, with ranging accuracy down to the centimeter level. Simultaneously, it can calculate the direction and speed of the authorized personnel's movement relative to the door based on continuous ranging data.

[0056] As an optional implementation of UWB tags, when authorized personnel use smartphones with integrated UWB functionality as positioning tags, the smartphone's operating system continuously runs a positioning service process in the background, exchanging ranging data with UWB base stations at preset time intervals. The smartphone needs to be pre-paired and bound to the smart lock system. Binding methods include, but are not limited to, Bluetooth-assisted pairing, QR code scanning authorization generated by the lock, and manual addition of authorization within the accompanying management app. The smartphone's unique UWB identifier is simultaneously entered into the smart lock system's authorization whitelist to complete the pairing and binding. Once bound, the smartphone is recognized as the authorized personnel's legitimate UWB tag, and its output UWB ranging data has the same positioning accuracy and security level as a dedicated independent UWB tag.

[0057] The smart lock integrates a main control chip, a motor-driven bolt, a wireless communication module, and a buzzer alarm unit. All functions of the lock control module are integrated into the main control chip. The main control chip is configured to receive multi-source data from an external image acquisition unit, an internal image acquisition unit, and a UWB positioning module, perform multi-modal information fusion and judgment, and output control signals to drive the motor bolt to open and close the lock. Simultaneously, when risk scenarios such as tailgating or intrusion are detected, the buzzer alarm unit is triggered to perform an abnormal alarm action.

[0058] In one exemplary embodiment, such as Figure 1 As shown, a door lock control method is provided, including the following steps 101 to 103. Wherein:

[0059] Step 101: When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated.

[0060] In this step, when the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold (e.g., 2m) to less than a preset second distance threshold (e.g., 1m), and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated.

[0061] In one optional implementation, UWB base stations deployed at preset locations around the door scan the UWB tags carried by authorized personnel at a preset scanning frequency (e.g., 10Hz). The system outputs the raw distance data between the tag and the base station based on a two-way ranging algorithm. The control module in the smart lock receives multiple frames of continuous distance data reported by the UWB base stations in real time. It compares the real-time distance data with pre-stored first and second distance thresholds to verify whether the distance change condition of "relative distance gradually decreasing from greater than the first distance threshold to less than the second distance threshold" is met. Simultaneously, it performs motion vector calculations based on the continuous multi-frame distance data to determine whether the authorized personnel's movement direction is towards the door. Only when both the distance change condition and the movement direction condition are simultaneously met does the control module send an activation command to the external image acquisition unit, triggering it to start image acquisition and subsequent identity verification processes.

[0062] Step 102: Perform facial recognition on the first outdoor image acquired by the door image acquisition unit, and verify the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0063] In this step, after the external image acquisition unit receives the activation command from the main control module of the smart lock, it immediately acquires the first outdoor image of the area outside the door. Using a built-in local face detection algorithm, it scans the entire image, extracting feature points of all faces within the frame to obtain multiple sets of facial features. Then, each extracted set of facial features is matched against a pre-stored database of authorized personnel faces. Based on a preset confidence threshold, the identity attribute of each face is determined, identifying whether it belongs to an authorized or unauthorized person, thus obtaining the identity verification result. Finally, based on the identity verification result, the system automatically outputs two statistical data points: the total number of authorized personnel and the total number of unauthorized personnel within the frame. This statistical result is then synchronously transmitted back to the main control module of the smart lock.

[0064] It should be noted that the facial recognition and identity verification steps can also be performed by the control module in the main body of the smart lock.

[0065] Step 103: Control the opening and closing of the door lock based on the combination relationship between the number of authorized personnel and the number of unauthorized personnel.

[0066] In this step, based on the identity verification results obtained in step 102, a differentiated door lock control strategy is implemented by analyzing the numerical combination relationship between authorized and unauthorized personnel.

[0067] In the aforementioned door lock control method, the external image acquisition unit is activated only when the relative distance between the authorized person and the door decreases from a preset first distance threshold to a preset second distance threshold, and the direction of movement is clearly towards the door. This effectively filters interference from distant unrelated personnel and accurately distinguishes between authorized personnel with the intention to open the door and unrelated personnel merely passing by. This significantly reduces false triggers in image acquisition and recognition, avoiding unnecessary frequent system startups and resource consumption. Simultaneously, after triggering, facial recognition and identity verification are performed on the first outdoor image acquired, and the number of authorized and unauthorized personnel in the scene is counted. Finally, the door lock is dynamically controlled based on the combination of these two numbers, constructing a reliable door scene perception and tailgating detection mechanism. This not only solves the problems of difficulty in accurately identifying the true intention to open the door and high false trigger rates in traditional solutions, but also promptly identifies unauthorized personnel following closely behind when authorized personnel unlock the door. This avoids security vulnerabilities caused by unauthorized individuals tailgating at the door lock control level, improving the ease of use of smart door locks while effectively reducing the security risks caused by tailgating.

[0068] In one exemplary embodiment, controlling the opening and closing of a door lock based on the combination of authorized and unauthorized personnel may include the following steps:

[0069] If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then unlock the door.

[0070] If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock will remain closed.

[0071] In this embodiment, when the number of unauthorized personnel is determined to be 0 and the number of authorized personnel is greater than or equal to 1, the door lock is opened to allow verified authorized personnel to pass normally. When the number of unauthorized personnel is determined to be greater than or equal to 1 and the number of authorized personnel is greater than or equal to 1, the door lock remains locked, the unlocking operation is refused, and an anti-tailgating alarm notification is pushed to the user terminal through the wireless communication module in the smart door lock body, and the captured current outdoor image is stored, thereby avoiding the security risk of unauthorized strangers tailgating and breaking in while authorized personnel are opening the door.

[0072] Reference Figure 2The diagram shows the entry process of the door lock control method provided in this application. After the process is started, the system first detects whether an authorized person is gradually approaching the door using ultra-wideband positioning. It then detects whether the distance change condition of "relative distance gradually decreasing from greater than a first distance threshold to less than a second distance threshold" and the movement orientation condition of "the authorized person's movement direction is towards the door" are met. When both conditions are met, the external image acquisition unit is activated, and then the first outdoor image is acquired and face recognition and identity verification are performed. The identified face is compared with the authorized person's face database to determine the person's identity attributes. Then, it is determined whether there is an authorized person. If not, the door lock remains closed and the process ends. If so, it is further determined whether there is an unauthorized person. If an unauthorized person exists, the door lock remains closed and the process ends. If no unauthorized person exists, the door lock is opened and the process ends. The core logic is that the door lock is opened only when an authorized person is detected and no unauthorized person exists. If either condition is not met, the door remains locked to prevent tailgating and illegal entry.

[0073] In one exemplary embodiment, such as Figure 3 As shown, the door lock control method of this application may further include the following steps:

[0074] Step 301: Perform human target detection and exit intention recognition on the indoor images acquired by the door image acquisition unit to obtain the intention recognition result.

[0075] In this step, an indoor image acquisition unit deployed inside the door acquires indoor images at a preset frequency, performs human target detection on multiple consecutive frames of indoor images, and analyzes the motion trajectory of human key points to determine whether the indoor person intends to leave, thus obtaining the intent recognition result.

[0076] The steps of human target detection and exit intention recognition can be performed by the image acquisition unit inside the door or by the control module in the main body of the smart door lock.

[0077] Step 302: If the intent recognition result indicates that the person inside intends to leave, then activate the door-side wireless ranging unit.

[0078] In this step, when the intent recognition result output in step 301 indicates that the person inside intends to leave, the door image acquisition unit or control module sends an activation command to the wireless ranging unit deployed on the side of the door. The door-side wireless ranging unit can be configured as a UWB base station.

[0079] Step 303: If the relative distance between the person inside the room and the door is less than the preset third distance threshold as determined by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated.

[0080] In this step, when the relative distance between the person inside the room and the door is less than a preset third distance threshold (e.g., 0.8m) detected by the door-side wireless ranging unit, and the person inside the room is moving towards the door, the door-outside image acquisition unit is activated.

[0081] The door-side wireless ranging unit is a UWB base station. Its scanning target is the UWB tag carried by authorized personnel. This tag is pre-registered in the authorized whitelist of the smart door lock system and is uniquely bound to the authorized personnel's identity. Therefore, the indoor personnel carrying this tag detected by the door-side wireless ranging unit are the authorized personnel.

[0082] Step 304: Perform unauthorized personnel detection on the second outdoor image acquired by the door image acquisition unit to obtain the personnel identity detection result.

[0083] In this step, the second outdoor image acquired by the external image acquisition unit can be used to call a locally pre-trained personnel identification model. Specifically, the real-time extracted facial features and body contour features can be compared with the locally stored authorized personnel feature library. Personnel with feature matching scores lower than a preset matching threshold are identified as unauthorized personnel. The personnel identification results include the following three scenarios: no personnel are outside the door, only authorized personnel are outside the door, and unauthorized personnel are outside the door.

[0084] The step of detecting unauthorized personnel can be performed by the external image acquisition unit or by the control module in the main body of the smart lock.

[0085] Step 305: Based on the personnel identity detection results, control the opening and closing of the door lock.

[0086] In this step, a differentiated door lock control strategy is executed based on the personnel identity detection results generated in step 304.

[0087] In one exemplary embodiment, controlling the opening and closing of a door lock based on the person identification detection result may include the following steps:

[0088] If the personnel identification result indicates that there is an unauthorized person outside the door, then the door lock will remain closed;

[0089] If the personnel identification result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

[0090] In this embodiment, when it is determined that there are unauthorized personnel outside the door, the door lock remains closed, and a preset warning voice, such as "Stranger outside, do not open the door," is output through the voice broadcast module in the smart lock body. A danger alert notification for leaving the house is also pushed to the user terminal via the wireless communication module in the smart lock body. When it is determined that there are no unauthorized personnel outside the door (either no one is outside or only authorized personnel are outside), the door lock is opened to allow normal passage for people inside.

[0091] In an exemplary embodiment, performing human target detection and exit intention recognition on indoor images acquired by the door image acquisition unit to obtain the intention recognition result may include the following steps:

[0092] Human target detection is performed on multiple consecutive frames of indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results;

[0093] If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then an intention recognition result indicating that the person inside the room intends to leave is obtained.

[0094] In this embodiment, for the continuous multiple frames of indoor images acquired in real time by the image acquisition unit inside the door, human target detection is performed sequentially. Based on the human target detection results, the global motion trajectory of the human body in the scene and the local motion trajectory of the corresponding hand key points are calculated synchronously. When the direction of the human body motion trajectory is towards the door, the direction of the hand key point motion trajectory is towards the door handle, and the termination coordinate of the hand key point motion trajectory falls within the predefined threshold range of the door handle neighborhood, the intention recognition result representing that the current indoor person has a clear intention to leave is output.

[0095] In one exemplary embodiment, the door-side wireless ranging unit is an ultra-wideband positioning anchor point deployed around the door, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

[0096] The door-side wireless ranging unit is an ultra-wideband positioning anchor point (such as a UWB base station) deployed around the door. It is configured to establish a communication link with the matching positioning tag (such as a UWB tag) carried by authorized personnel, and to obtain the relative distance and direction of movement between the authorized personnel and the door in real time based on a two-way ranging protocol.

[0097] Reference Figure 4The diagram shows the exit process of the door lock control method provided in this application. After the process is started, the image acquisition unit inside the door first performs human target detection and exit intention recognition. When the intention of an indoor person to exit is detected, the door-side wireless ranging unit is activated. If the relative distance and movement direction between the indoor person and the door are determined to meet the preset conditions based on the ranging data collected by the door-side wireless ranging unit, the image acquisition unit outside the door is activated to detect whether there is an unauthorized person outside the door. If there is an unauthorized person outside the door, the door lock is kept closed. If there is no unauthorized person outside the door, the door lock is opened and the process ends.

[0098] Reference Figure 5 The diagram shows the hardware architecture of the door lock control method provided in this application. It includes an external image acquisition unit deployed on the outside of the door, an internal image acquisition unit deployed on the inside of the door, ultra-wideband positioning anchors deployed around the door, and a matching positioning tag carried by an authorized person. The external image acquisition unit outputs the identity verification result to the control module in the smart door lock body, the internal image acquisition unit outputs the intent recognition result to the control module, and the ultra-wideband positioning anchors output UWB ranging data to the control module. Based on the above multi-source information, the control module outputs control commands to the motor-driven bolt, the buzzer alarm unit, and the wireless communication module to realize door lock opening and closing control, local alarm, and remote notification functions.

[0099] In the entry security verification process, the ranging capability of ultra-wideband positioning anchor points is used to continuously monitor the matching positioning tags carried by authorized personnel, so as to achieve non-sensory triggering and accurate positioning on the outdoor side, ensuring timely response when authorized personnel approach, while avoiding high power consumption and invalid data accumulation caused by long-term operation of the outdoor image acquisition unit.

[0100] In the exit security verification process, the door-inside image acquisition unit is a low-power vision sensor. When the intention of an indoor person to leave is detected, the activated door-inside image acquisition unit is used to confirm the intention. Then, the ultra-wideband positioning anchor point is activated as needed to perform precise ranging verification, so as to achieve a power optimization balance between low-power perception on the indoor side and precise security on the outdoor side. In addition, the indoor environment is relatively closed and controllable, and the behavior patterns of people are predictable. The door-inside image acquisition unit can effectively capture the movement characteristics of the human body moving towards the door and the hand approaching the door handle area, so as to achieve accurate recognition of the intention to leave and avoid ranging errors and false triggering caused by multipath reflections of the ultra-wideband positioning anchor point indoors.

[0101] The door lock control method provided in this application solves the technical problems of insufficient security, low positioning accuracy, lack of tailgating detection mechanism, and lack of security verification in the exit mode of existing smart door locks by integrating indoor and outdoor dual-channel image acquisition and ultra-wideband precise positioning technology.

[0102] In addition, the smart lock system is also equipped with an abnormal event response mechanism: when identity verification fails multiple times in a row, a suspected brute-force attack alarm notification is pushed to the user terminal through the wireless communication module; when illegal damage to the lock is detected, an illegal damage alarm notification is pushed to the user terminal through the wireless communication module, and the buzzer alarm unit is controlled to output a local alarm signal.

[0103] This application achieves centimeter-level positioning accuracy, effective tailgating detection, intrusion prevention protection, and differentiated entry and exit control strategies through multimodal fusion of ultra-wideband positioning and dual-channel image acquisition, significantly improving the security protection capabilities and user experience of smart door locks.

[0104] Door lock control methods can be widely used in home security, hotel apartments, office spaces and long-term rental apartments, etc. They are suitable for tailgating protection in apartments, villas and residences, guest security in hotel security systems, access control in high-security areas such as offices, laboratories and computer rooms, as well as tenant security management and remote alarm record query in long-term rental apartments.

[0105] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0106] Based on the same inventive concept, this application also provides a door lock control device for implementing the door lock control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more door lock control device embodiments provided below can be found in the limitations of the door lock control method described above, and will not be repeated here.

[0107] In one exemplary embodiment, such as Figure 6 As shown, a door lock control device is provided, including: an activation module 601, an identity verification module 602, and a control module 603, wherein:

[0108] The activation module 601 is used to activate the door external image acquisition unit when it detects that the relative distance between the authorized person and the door has decreased from greater than a preset first distance threshold to less than a preset second distance threshold, and the movement direction of the authorized person is towards the door.

[0109] The identity verification module 602 is used to perform face recognition on the first outdoor image captured by the door image acquisition unit, and to verify the identity of the recognized faces to obtain the number of authorized personnel and the number of unauthorized personnel.

[0110] The control module 603 is used to control the opening and closing of the door lock based on the combination relationship between the number of authorized personnel and the number of unauthorized personnel.

[0111] In one exemplary embodiment, the control module 603 is specifically used for:

[0112] If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then unlock the door.

[0113] If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock will remain closed.

[0114] In one exemplary embodiment, the door lock control device is further configured to:

[0115] Human target detection and exit intention recognition are performed on indoor images acquired by the door image acquisition unit to obtain the intention recognition result;

[0116] If the intent recognition result indicates that the person inside intends to leave, then the door-side wireless ranging unit is activated;

[0117] If the relative distance between the person inside the room and the door is determined to be less than the preset third distance threshold by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated.

[0118] Unauthorized personnel detection is performed on the second outdoor image acquired by the external image acquisition unit to obtain the personnel identity detection result;

[0119] The door locks are controlled based on the results of personnel identification.

[0120] In one exemplary embodiment, the door lock control device is further configured to:

[0121] If the personnel identification result indicates that there is an unauthorized person outside the door, then the door lock will remain closed;

[0122] If the personnel identification result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

[0123] In one exemplary embodiment, the door lock control device is further configured to:

[0124] Human target detection is performed on multiple consecutive frames of indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results;

[0125] If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then an intention recognition result indicating that the person inside the room intends to leave is obtained.

[0126] In one exemplary embodiment, the door-side wireless ranging unit is an ultra-wideband positioning anchor point deployed around the door, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

[0127] Each module in the aforementioned door lock control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independently of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0128] In one exemplary embodiment, an electronic device is provided, which can be the main body of a smart door lock, and its internal structure diagram can be as follows. Figure 7 As shown, the electronic device includes a processor, memory, input / output interface, communication interface, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wireless communication with external terminals. When the computer program is executed by the processor, it implements a door lock control method. The input device can be a button or touchpad mounted on the device's casing.

[0129] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0130] In one exemplary embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0131] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0132] The system performs facial recognition on the first outdoor image captured by the external image acquisition unit, and verifies the identity of the identified faces to obtain the number of authorized and unauthorized personnel.

[0133] The door lock is controlled based on the combination of authorized and unauthorized personnel.

[0134] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0135] If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then unlock the door.

[0136] If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock will remain closed.

[0137] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0138] Human target detection and exit intention recognition are performed on indoor images acquired by the door image acquisition unit to obtain the intention recognition result;

[0139] If the intent recognition result indicates that the person inside intends to leave, then the door-side wireless ranging unit is activated;

[0140] If the relative distance between the person inside the room and the door is determined to be less than the preset third distance threshold by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated.

[0141] Unauthorized personnel detection is performed on the second outdoor image acquired by the external image acquisition unit to obtain the personnel identity detection result;

[0142] The door locks are controlled based on the results of personnel identification.

[0143] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0144] If the personnel identification result indicates that there is an unauthorized person outside the door, then the door lock will remain closed;

[0145] If the personnel identification result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

[0146] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0147] Human target detection is performed on multiple consecutive frames of indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results;

[0148] If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then an intention recognition result indicating that the person inside the room intends to leave is obtained.

[0149] In one embodiment, the door-side wireless ranging unit is an ultra-wideband positioning anchor point deployed around the door, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

[0150] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0151] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0152] The system performs facial recognition on the first outdoor image captured by the external image acquisition unit, and verifies the identity of the identified faces to obtain the number of authorized and unauthorized personnel.

[0153] The door lock is controlled based on the combination of authorized and unauthorized personnel.

[0154] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0155] If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then unlock the door.

[0156] If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock will remain closed.

[0157] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0158] Human target detection and exit intention recognition are performed on indoor images acquired by the door image acquisition unit to obtain the intention recognition result;

[0159] If the intent recognition result indicates that the person inside intends to leave, then the door-side wireless ranging unit is activated;

[0160] If the relative distance between the person inside the room and the door is determined to be less than the preset third distance threshold by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated.

[0161] Unauthorized personnel detection is performed on the second outdoor image acquired by the external image acquisition unit to obtain the personnel identity detection result;

[0162] The door locks are controlled based on the results of personnel identification.

[0163] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0164] If the personnel identification result indicates that there is an unauthorized person outside the door, then the door lock will remain closed;

[0165] If the personnel identification result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

[0166] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0167] Human target detection is performed on multiple consecutive frames of indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results;

[0168] If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then an intention recognition result indicating that the person inside the room intends to leave is obtained.

[0169] In one embodiment, the door-side wireless ranging unit is an ultra-wideband positioning anchor point deployed around the door, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

[0170] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0171] When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated;

[0172] The system performs facial recognition on the first outdoor image captured by the external image acquisition unit, and verifies the identity of the identified faces to obtain the number of authorized and unauthorized personnel.

[0173] The door lock is controlled based on the combination of authorized and unauthorized personnel.

[0174] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0175] If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then unlock the door.

[0176] If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock will remain closed.

[0177] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0178] Human target detection and exit intention recognition are performed on indoor images acquired by the door image acquisition unit to obtain the intention recognition result;

[0179] If the intent recognition result indicates that the person inside intends to leave, then the door-side wireless ranging unit is activated;

[0180] If the relative distance between the person inside the room and the door is determined to be less than the preset third distance threshold by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated.

[0181] Unauthorized personnel detection is performed on the second outdoor image acquired by the external image acquisition unit to obtain the personnel identity detection result;

[0182] The door locks are controlled based on the results of personnel identification.

[0183] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0184] If the personnel identification result indicates that there is an unauthorized person outside the door, then the door lock will remain closed;

[0185] If the personnel identification result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

[0186] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0187] Human target detection is performed on multiple consecutive frames of indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results;

[0188] If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then an intention recognition result indicating that the person inside the room intends to leave is obtained.

[0189] In one embodiment, the door-side wireless ranging unit is an ultra-wideband positioning anchor point deployed around the door, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

[0190] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0191] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0192] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0193] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A door lock control method, characterized in that, The method includes: When the relative distance between the authorized person and the door is detected to decrease from greater than a preset first distance threshold to less than a preset second distance threshold, and the authorized person's movement direction is towards the door, the door external image acquisition unit is activated; The system performs facial recognition on the first outdoor image acquired by the external image acquisition unit and verifies the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel. The door lock is controlled to open and close based on the combination of the number of authorized personnel and the number of unauthorized personnel.

2. The method according to claim 1, characterized in that, The step of controlling the opening and closing of the door lock based on the combination relationship between the number of authorized personnel and the number of unauthorized personnel includes: If the number of unauthorized personnel is zero and the number of authorized personnel is not zero, then the door lock is opened; If the number of unauthorized personnel is not zero and the number of authorized personnel is not zero, then the door lock remains closed.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Human target detection and exit intention recognition are performed on indoor images acquired by the door image acquisition unit to obtain the intention recognition result; If the intent recognition result indicates that the person inside intends to leave, then the door-side wireless ranging unit is activated; If the relative distance between the person inside the room and the door is determined to be less than a preset third distance threshold by the door-side wireless ranging unit, and the person inside the room is moving towards the door, then the door-outside image acquisition unit is activated. Unauthorized personnel detection is performed on the second outdoor image acquired by the door external image acquisition unit to obtain the personnel identity detection result; Based on the personnel identity detection results, the door lock is controlled to open or close.

4. The method according to claim 3, characterized in that, The step of controlling the opening and closing of the door lock based on the personnel identity detection result includes: If the personnel identification result indicates that there are unauthorized personnel outside the door, then the door lock remains closed; If the personnel identity detection result indicates that there are no unauthorized personnel outside the door, then the door lock will be opened.

5. The method according to claim 3, characterized in that, The process of performing human target detection and exit intention recognition on indoor images acquired by the door image acquisition unit to obtain intention recognition results includes: Human target detection is performed on multiple consecutive frames of the indoor images, and the human motion trajectory and hand key point motion trajectory are determined based on the human target detection results; If the direction of the human body's movement trajectory is determined to be towards the door, the direction of the hand's key point movement trajectory is determined to be towards the door handle, and the endpoint of the hand's key point movement trajectory falls within the preset neighborhood of the door handle, then the intention recognition result indicating that the person inside the room has the intention to leave is obtained.

6. The method according to claim 3, characterized in that, The door-side wireless ranging unit is an ultra-wideband positioning anchor point deployed around the door body, used to complete real-time two-way ranging interaction with the matching positioning tag carried by authorized personnel.

7. A door lock control device, characterized in that, The device includes: The activation module is used to activate the door external image acquisition unit when it detects that the relative distance between the authorized person and the door has decreased from greater than a preset first distance threshold to less than a preset second distance threshold, and the movement direction of the authorized person is towards the door. The identity verification module is used to perform face recognition on the first outdoor image acquired by the door image acquisition unit, and to verify the identity of the identified faces to obtain the number of authorized personnel and the number of unauthorized personnel. The control module is used to control the opening and closing of the door lock based on the combination relationship between the number of authorized personnel and the number of unauthorized personnel.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images