Unlocking control method and device and readable storage medium

Abstract

The invention provides an unlocking control method and device and a readable storage medium, and the method comprises the steps: obtaining the distance information of a first target when it is detected that the first target appears in the detection range of the device; according to the distance information of the first target, determining whether the first target is a person having no door entering demand or a person having a door entering demand; and when it is determined that the first target is a person having no door entering demand, recovering the equipment to a standby state, or when it is determined that the first target is a person having a door entering demand, performing face recognition on the first target. According to the scheme, when the target is detected, whether the target has the door entering requirement or not can be determined, and when the target is determined not to have the door entering requirement, the face recognition process is not triggered, but the equipment is restored to the standby state, so that the situation that the face recognition device of the equipment is mistakenly started due to the fact that people having no door entering requirement pass by can be effectively avoided, and the user experience is improved. Therefore, power consumption of the device can be reduced, and endurance time of the device is prolonged.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of unlocking control, and more specifically, to a method, device, and readable storage medium for unlocking control. Background Art

[0002] As people's demand for convenience in life increases, the facial recognition unlocking function of smart door locks is favored by users. Currently, when a smart door lock senses that a person is approaching the door lock, it will start the facial recognition process: start the facial recognition camera - capture - image comparison - open the door. Even if someone who does not need to enter the door passes by the door, facial recognition will be activated, which will cause a waste of power consumption and seriously affect the battery life of the smart door lock. Summary of the invention

[0003] The present application provides a method, device and readable storage medium for unlocking control. Through the method, device and readable storage medium, when a target is detected, it can be determined whether the target is a person who does not need to enter the door or a person who does need to enter the door. When the target is determined to be a person who does not need to enter the door, the face recognition process will not be triggered, but the device will be restored to standby mode. In this way, it can effectively avoid the false activation of the face recognition device of the device due to the passage of a person who does not need to enter the door, thereby reducing the power consumption of the device and improving the battery life of the device.

[0004] In a first aspect, a method for unlocking control is provided, which is applied to a device, and the method includes: when a first target is detected to appear within a detection range of the device, obtaining distance information of the first target; determining whether the first target is a person who has no need to enter the door or a person who has a need to enter the door based on the distance information of the first target; when it is determined that the first target is a person who has no need to enter the door, restoring the device to a standby state, or when it is determined that the first target is a person who has a need to enter the door, performing facial recognition on the first target.

[0005] The distance information of the first target refers to the distance between the first target and the device.

[0006] Optionally, the device may be a smart door lock, or other devices with facial recognition functions, such as a facial time clock, etc., wherein the smart door lock may be, for example, a house entrance door lock, a unit building access control, a gate access control, a car door lock, etc.

[0007] In an embodiment of the present application, a device (for example, a smart door lock) can, when detecting a target, determine whether the target is a person who has no need to enter the door or a person who has a need to enter the door. When it is determined that the target is a person who has no need to enter the door, the face recognition process will not be triggered, but the state will be restored to standby mode. In this way, it can effectively avoid the false start-up of the face recognition device caused by the passage of a person who has no need to enter the door, thereby reducing the power consumption of the device and improving the battery life of the device.

[0008] In combination with the first aspect, in a possible implementation method, the distance information of the first target includes N distance values, wherein the N distance values ​​are obtained by periodically measuring the distance between the first target and the device when the device detects the first target, and the N distance values ​​are respectively recorded as the i-th distance value according to the order of measurement, i=1,2,3,…,(N-1),N, and N is an integer not less than 1.

[0009] It should be understood that the i-th distance value refers to the i-th distance value among N distance values.

[0010] In combination with the first aspect, in a possible implementation method, determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door based on the distance information of the first target includes: determining whether a preset condition is met based on the distance information of the first target, and the preset condition is that the second distance value among the N distance values ​​is less than or equal to the first distance value among the N distance values; when the preset condition is met, determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door based on the distance information of the first target within a first time period, and the starting time of the first time period is the time when it is determined that the preset condition is met.

[0011] Optionally, the device includes a multimedia chip, and the first duration may be a time period from when the multimedia chip starts to start to when it successfully starts, wherein the moment when the multimedia chip starts to start may be a moment when it is determined that the distance information of the first target meets a preset condition, or a moment when the first target is detected within the detection range of the device.

[0012] In some embodiments, when the preset condition is met, it is periodically determined within a first time period based on the distance information of the first target whether the first target is a person who has no need to enter the door or a person who has a need to enter the door.

[0013] In the embodiment of the present application, a trigger condition is set to determine whether the first target is a person who has no need to enter the door (the first target is staying or approaching). The determination will only start when the trigger condition is met. This can also effectively avoid the occurrence of some events in which face recognition is falsely triggered due to the passing of people who have no need to enter the door, which can further save the power consumption of the device and improve the battery life of the device.

[0014] As a possible implementation method, within the first time period, the first target is periodically identified as a person who does not need to enter the door based on the current distance information of the first target. Considering that the larger the distance information sample of the first target, the more accurate the identification result obtained, the final identification result of the person who does not need to enter the door is based on the last result obtained within the first time period. In this way, the accuracy of identifying the first target as a person who does not need to enter the door can be significantly improved.

[0015] In combination with the first aspect, in a possible implementation manner, the method further includes: at the end moment of the first time period, stopping the periodic measurement of the distance between the first target and the device.

[0016] In the embodiment of the present application, after obtaining the final recognition result, the measurement of the distance information of the first target is ended, which can also save the power consumption of the device to a certain extent and improve the battery life of the device.

[0017] In combination with the first aspect, in a possible implementation method, the device begins to periodically measure the distance between the first target and the device when the first target is detected, including: the device begins to measure the distance between the first target and the device at intervals of a first time period when the first target is detected; within the first time period, determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door based on the distance information of the first target, including: within the first time period, determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door based on the distance information of the first target at intervals of a second time period; the first time period is less than or equal to the second time period.

[0018] In the embodiment of the present application, the distance measurement period is limited to be shorter than the period for determining people who do not need to enter the door, so that the distance information of the first target used in each determination process of people who do not need to enter the door is the latest and different from the previous one (the distance information sample of the first target used in the previous determination process is increased). This can avoid the device from making repeated determinations on the same distance information and avoid some unnecessary resource consumption.

[0019] In combination with the first aspect, in a possible implementation method, when N is less than 10, determining whether the first target is a person who has no need to enter the door or a person who has a need to enter the door within a first time period based on the distance information of the first target, including: determining whether the Nth distance value is an invalid value; if the Nth distance value is an invalid value, determining that the first target is a person who has no need to enter the door; or if the Nth distance value is not an invalid value, and the Nth distance value is greater than a first threshold, determining that the first target is a person who has no need to enter the door.

[0020] In an embodiment of the present application, a method is provided for determining whether a first target is a person who does not need to enter a door or a person who does need to enter a door. When the number of distance values ​​of the first target currently obtained is less than 10, it can be determined whether the first target is a person who does not need to enter a door based on the last distance value obtained.

[0021] In combination with the first aspect, in a possible implementation method, when N is greater than or equal to 10, determining whether the first target is a person who has no need to enter the door or a person who has a need to enter the door within a first time period based on the distance information of the first target, including: determining whether there are invalid values ​​in the (N-2)th distance value, the (N-1)th distance value and the Nth distance value; if there are invalid values ​​in the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are all invalid values, then determining that the first target is a person who has no need to enter the door; or if there are invalid values ​​in the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the non-invalid values ​​in the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are greater than a first threshold, then determining that the first target is a person who has no need to enter the door.

[0022] In an embodiment of the present application, another method for determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door is provided. When the number of distance values ​​of the first target currently obtained is greater than or equal to 10, it can be determined whether the first target is a person who does not need to enter the door based on the last 3 distance values ​​obtained.

[0023] In combination with the first aspect, in a possible implementation method, when N is greater than or equal to 10, determining whether the first target is a person who has no need to enter the door or a person who has a need to enter the door within a first time period based on the distance information of the first target, including: when there is no invalid value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are all less than a second threshold, determining that the first target is a person who has a need to enter the door; or when there is no invalid value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are all greater than a first threshold, determining that the first target is a person who has no need to enter the door, wherein the second threshold is less than the first threshold.

[0024] In some embodiments, the first threshold is any value between 1.1 meters and 1.2 meters.

[0025] In some embodiments, the second threshold is any value between 0.7 meters and 0.9 meters.

[0026] In an embodiment of the present application, another method for determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door is provided. When the number of distance values ​​of the first target currently obtained is greater than or equal to 10, it can be determined whether the first target is a person who does not need to enter the door based on the last 3 distance values ​​obtained.

[0027] In combination with the first aspect, in a possible implementation method, when N is greater than or equal to 10, determining whether the first target is a person who has no need to enter the door or a person who has a need to enter the door within a first time period based on the distance information of the first target, including: when there is no invalid value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are not all less than the second threshold value, nor are they all greater than the first threshold value, determining whether the (N-2)th distance value, the (N-1)th distance value and the Nth distance value have a distance value less than or equal to a third threshold value, wherein the third threshold value is the sum of the smallest distance value among the N distance values ​​and the first calibration distance; when the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are not all less than the second threshold value, nor are they all greater than the first threshold value, determining whether the (N-2)th distance value, the (N-1)th distance value and the Nth distance value have a distance value less than or equal to a third threshold value When there is a distance value less than or equal to the third threshold value among the distance values, the first target is determined to be a person who needs to enter the door; or when there is no distance value less than or equal to the third threshold value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and they are all greater than the fourth threshold value, the first target is determined to be a person who does not need to enter the door, and the fourth threshold value is the sum of the average value of the distance values ​​corresponding to the three most recent successful face recognition moments and the second calibration distance; or when there is no distance value less than or equal to the third threshold value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the first speed is greater than the fifth threshold value, the first target is determined to be a person who does not need to enter the door, wherein the first speed = ((N-2)th distance value - Nth distance value) / (first time period × 2).

[0028] In some embodiments, the first calibration distance is any value between 0.05 and 0.15.

[0029] In some embodiments, the second calibration distance is any value between 0.1 and 0.3.

[0030] Among them, the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are not all less than the second threshold value, nor are they all greater than the first threshold value, and may include: any one of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value is not less than the second threshold value, nor is it greater than the first threshold value; it may also include: one of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value is not less than the second threshold value, nor is it greater than the first threshold value, and the other two of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are less than the second threshold value or greater than the first threshold value; it may also include: the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are less than the second threshold value or greater than the first threshold value. The method may further include: one of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value is less than the second threshold, and the other two of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are greater than the first threshold; the method may further include: two of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are less than the second threshold, and the other one of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value is greater than the first threshold; the method may further include: one of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value is not less than the second threshold and is not greater than the first threshold, and the other two of the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are respectively less than the second threshold and greater than the first threshold.

[0031] In an embodiment of the present application, another method for determining whether the first target is a person who does not need to enter the door or a person who does need to enter the door is provided. When the number of distance values ​​obtained for the first target is greater than or equal to 10, it can be determined whether the first target is a person who does not need to enter the door based on the last three distance values ​​obtained and the minimum value of the distance values ​​obtained, as well as the average value of the distance values ​​corresponding to the three most recent successful face recognition moments or the moving speed of the first target.

[0032] In the second aspect, a device is provided, which can be used to implement the method in the above-mentioned first aspect and any possible implementation manner of the first aspect. The device includes corresponding modules for executing the method in the above-mentioned first aspect and any possible implementation manner of the first aspect. The modules included in the device can be implemented by software and / or hardware.

[0033] In a third aspect, a device is provided, comprising a memory and a processor, wherein the memory is used to store program code, and the processor is used to execute the program code stored in the memory to implement the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0034] In a fourth aspect, a readable storage medium is provided, in which a program or instruction is stored. When the program or instruction is executed, the method in the above-mentioned first aspect or any possible implementation manner of the first aspect is implemented.

[0035] In a fifth aspect, a chip system is provided, in which instructions are stored. When the instructions are executed on a device, the chip system executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic flow chart of an existing intelligent door lock control method;

[0037] Figure 2 It is a schematic diagram of movement routes in front of a door for a person who has a need to enter a door and a person who does not have a need to enter a door provided in an embodiment of the present application;

[0038] Figure 3 is a schematic flow chart of an unlocking control method provided in an embodiment of the present application;

[0039] Figure 4 is an example diagram of a set of distance information of a first target provided in an embodiment of the present application;

[0040] Figure 5 is a schematic flow chart of a method for determining whether a first target is a person who has no need to enter a door according to distance information of the first target provided by an embodiment of the present application;

[0041] Figure 6 It is a schematic diagram of determining a target algorithm from a plurality of algorithms for identifying people who do not need to enter a door provided in an embodiment of the present application;

[0042] Figure 7 It is a functional module diagram of an unlocking control device provided in an embodiment of the present application;

[0043] Figure 8 It is a schematic flow chart of another unlocking control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The technical solution in the present application will be described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0045] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0046] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.

[0047] The terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations on the present application. As used in the specification and the appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear contrary indication in the context. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" refer to one, two or more. The term "and / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist; for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0048] References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "one embodiment", "some embodiments", "another embodiment", "some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0049] The method provided in the embodiments of the present application can be applied to devices with face recognition functions, such as smart door locks, smart terminals, etc., and can also be applied to any device with face recognition functions, such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiments of the present application do not impose any restrictions on the specific types of devices.

[0050] As people's demand for convenience in life increases, the face recognition unlocking function of smart door locks is favored by users. At present, smart door locks can sense the approach of a person to the door lock through a person infrared radiation (PIR) or ultrasound. When a person is sensed to be close to the door lock, the face recognition process will begin: start the face recognition camera - capture - image comparison - open the door. Even if someone who does not need to enter the door passes by the door, face recognition will be activated, which will cause a waste of power consumption and seriously affect the battery life of the smart door lock. Taking Huawei Smart Door Lock Pro as an example, through big data analysis, it can be seen that if the average number of people who do not need to enter the door passes by the door more than 15 times a day, the battery life of the smart door lock will be reduced by at least 1 month, and the greater the flow of people, the greater the impact on the battery life of the smart door lock.

[0051] For example, Figure 1 A schematic flow chart of an existing smart door lock control method 100 is shown. The smart door lock includes a controller, an exit signal triggering device and a face recognition device, such as Figure 1 As shown, the method 100 includes:

[0052] S101: The controller detects whether there is an exit signal triggered by an exit signal triggering device.

[0053] S102: When there is an exit signal triggered by the exit signal triggering device, the controller controls the face recognition device to stop the face recognition operation within a first preset time period according to the exit signal.

[0054] In the method, an exit signal triggered by an exit signal triggering device is used as a criterion for distinguishing between people entering and leaving the door, thereby avoiding false activation of the face recognition device due to the presence of people leaving the door, so that the face recognition device stops the face recognition operation within a first preset time period and enters a sleep state, thereby reducing the power consumption of the face recognition smart door lock.

[0055] However, although this method has reduced the power consumption of smart door locks to a certain extent, this method reduces the power consumption of smart door locks by avoiding false activation of the face recognition device caused by people going out, and does not solve the power consumption problem caused by false activation of the face recognition device due to people passing by without any need to enter the door. Moreover, due to the difference in occurrence frequency, the power consumption caused by false activation of the face recognition device due to people passing by without any need to enter the door is generally much higher than the power consumption caused by false activation of the face recognition device due to people going out.

[0056] In view of this, the present application provides a method, device and readable storage medium for unlocking control. Through the method, device and readable storage medium, it is possible to effectively avoid the false activation of the face recognition device caused by the passing of people who have no need to enter the door, thereby reducing the power consumption of the smart door lock and improving the battery life of the smart door lock.

[0057] In order to more clearly understand the movement routes of people who have the need to enter the door and those who do not have the need to enter the door in front of the door, for example, Figure 2 A schematic diagram of movement routes in front of a door for a person who has a need to enter a door and a person who does not have a need to enter a door provided in an embodiment of the present application is shown.

[0058] like Figure 2 As shown in the figure, the dotted line route represents the route of people who do not need to enter the door, and the solid line route represents the route of people who need to enter the door. Figure 2 The example of movement routes of person 1 who has a need to enter the door, person 2 who has a need to enter the door, person 1 who does not have a need to enter the door, person 2 who does not have a need to enter the door, and person 3 who does not have a need to enter the door in front of the door are shown. Figure 2 It can be seen that in the actual scenario where the user unlocks the door through face recognition, when the user (for example: person 1 who needs to enter the door, person 2 who needs to enter the door) needs to enter the door, they usually walk straight to the door, the distance between the user and the door is getting closer and closer, and the movement speed is gradually slowing down, and finally approaching 0 (the distance between the user and the door is very close at this time). When the user (for example: person 1 who does not need to enter the door, person 2 who does not need to enter the door, person 3 who does not need to enter the door) passes by the door, generally: within the ranging range of the smart door lock, the distance between the user and the door is always changing, the distance between the user and the door generally does not get closer and closer, and it is very likely that the distance between the user and the door is first approached and then moved away, and the user's movement speed will not slow down as the distance between the user and the door becomes smaller, and when the distance between the user and the door is closest, the user's movement speed will not approach 0. In view of this, we can further determine whether to wake up the face recognition function of the smart door lock by identifying whether the user is a person who needs to enter the door or a person who does not need to enter the door.

[0059] For example, Figure 3 FIG. 3 is a schematic flow chart of a method 300 for unlocking control provided in an embodiment of the present application. Figure 3 As shown, the method 300 includes:

[0060] S301: When the device is in a standby state, when it is detected that a first target appears within a detection range of the device, distance information of the first target is obtained.

[0061] Optionally, the device is a smart door lock, and the device can also be other devices with face recognition function, such as: face clock-in machine, etc., wherein the smart door lock can be, for example, a house entrance door lock, a unit building access control, a gate access control, a car door lock, etc.

[0062] In an ideal state, the detection range of the device is a sector-shaped area, the image acquisition device of the device is the center of the sector-shaped area, and the detection range has a clear field of vision (FOV). For specific diagrams, see Figure 2 The dotted sector area shown in .

[0063] The first target refers to a target detected by a sensing device of the device, which may be a dynamic target or a static target. The sensing device of the device may be, for example, a human infrared sensor (PIR).

[0064] Among them, the distance information of the first target refers to the distance between the first target and the device, for example, it can be the horizontal distance between the first target and the device, or it can be the straight-line distance between the first target and the device, etc., wherein the value of the distance can be the average value of the distance between the device and multiple feature points on the first target, or it can be the maximum value of the distance between the device and multiple feature points on the first target, or it can be the minimum value of the distance between the device and multiple feature points on the first target.

[0065] Specifically, the distance information of the first target may refer to multiple distance values ​​between the first target and the device, and the multiple distance values ​​may be measured at a certain ranging frequency starting when the first target is detected to appear within the detection range of the device, wherein the measurement process may be stopped when the multimedia chip is started, and the multimedia chip starts when the first target is detected to appear within the detection range of the device.

[0066] In one achievable manner, when the device detects the first target within the detection range, it further determines whether the first target is a human body. If so, it obtains the distance information of the first target, wherein human body detection technology can be used to determine whether the first target is a human body.

[0067] Optionally, the device can detect whether the first target appears within the detection range through a sensor; it can also detect whether the first target appears within the detection range through a ranging module. Specifically, when the distances of the same object measured by the ranging module twice or more times are different, it can be determined that the first target appears within the detection range.

[0068] In some embodiments, the distance information of the first target is obtained by using a time of flight (TOF) method, wherein the time of flight method is a 3D measurement technology that is often used to measure distance or used for a 3D imaging camera.

[0069] S302: Determine whether the first target is a person who has no need to enter the door according to the distance information of the first target. If yes, execute step S303; if no, execute step S304.

[0070] This step can also be described as "determining whether the first target is passing by the door according to the distance information of the first target. If so, execute step S303; if not, execute step S304".

[0071] Specifically, the movement route and / or movement speed of the first target is first obtained according to the distance information of the first target, and then according to the movement route and / or movement speed of the first target, it is determined whether the first target is a person who has no need to enter the door.

[0072] In some embodiments, when the direction corresponding to the movement route of the first target is a door, the first target is determined to be a person who needs to enter the door; when the direction corresponding to the movement route of the first target is not a door, the first target is determined to be a person who does not need to enter the door.

[0073] In some other embodiments, when the movement speed of the first target changes from fast to slow and finally approaches 0 within a range where the distance from the device is less than a first threshold, the first target is determined to be a person who needs to enter the door; otherwise, the first target is determined to be a person who does not need to enter the door.

[0074] In some other embodiments, when the direction corresponding to the movement route of the first target is the door, and the movement speed of the first target changes from fast to slow and finally approaches 0 within a range where the distance from the device is less than a first threshold, the first target is determined to be a person who needs to enter the door; otherwise, the first target is a person who does not need to enter the door.

[0075] S303: Restore the device to standby mode.

[0076] It should be understood that the device resuming the standby state includes operations such as powering off the multimedia chip of the device.

[0077] That is to say, when the first target is determined to be a person who has no need to enter the door, the face recognition process will not be triggered.

[0078] S304: Perform face recognition on the first target.

[0079] In other words, the facial recognition process will be triggered only when the first target is determined to be a person who needs to enter the door.

[0080] In the embodiment of the present application, taking the smart door lock as an example, when a target is detected, it can be determined whether the target is a person who has no need to enter the door or a person who has a need to enter the door. When the target is determined to be a person who has no need to enter the door, the face recognition process will not be triggered, but the smart door lock will be restored to standby mode. In this way, it can effectively avoid the false start-up of the face recognition device caused by the passage of people who have no need to enter the door, thereby reducing the power consumption of the smart door lock and improving the battery life of the smart door lock.

[0081] To understand more clearly Figure 3 The distance information of the first target obtained in step S301 in the illustrated embodiment is, for example, Figure 4 An example diagram of distance information of a group of first targets provided by an embodiment of the present application is shown.

[0082] like Figure 4 As shown, the distance information of the first target can be a set of distance values ​​consisting of multiple distances between the first target and a device (for example, a smart door lock) obtained by ranging. The multiple distances can be obtained by the device through periodic ranging starting from detecting the first target.

[0083] In one implementation, the distance information of the first target includes a set of first distance values, wherein the set of first distance values ​​includes N distance values, where N is an integer not less than 1. Figure 3 In the embodiment shown in FIG. 1 , the last three distance values ​​among the N distance values ​​are respectively recorded as D1, D2, and D3, and the minimum distance value among the N distance values ​​is recorded as D m , the distance values ​​corresponding to the successful face recognition moments in the last three face recognition processes are recorded as D f1 , D f2 , D f3 , D f1 , D f2 , D f3 The average value is recorded as D f , that is, D f =(D f1 +D f2 +D f3 ) / 3.

[0084] If the distance value corresponding to the moment of successful face recognition in the last three face recognition processes is greater than 1.5 meters, or equal to 0 or -1, it will not be recorded. In other words, D f1 , D f2 , D f3The value of refers to the distance value corresponding to the moment of successful face recognition in the last three valid face recognition processes. If the number of the last three valid face recognition processes is less than 3 times, then D f The value is the default value: 0.9m.

[0085] Among them, D1, D2, and D3 can be used to represent the moving position of the first target corresponding to the last time period within the measurement time of the distance information of the first target; the acquisition time of the set of distance values ​​corresponding to the three most recent successful face recognitions is earlier than the acquisition time of the set of first distance values, and the time difference with the acquisition time of the set of first distance values ​​is the shortest.

[0086] Among them, the N distance values ​​can be expressed as: d1, d2, d3, d4, d5, d6, d7, d8, d9, d 10 ,…,d (N-3) d (N-2) d (N-1) d N Among them, D1, D2, and D3 are d (N-2) d (N-1) d N , the unit of the N distance values ​​is mm.

[0087] It can be understood that the distance values ​​in the set of first distance values ​​can be periodically measured from the time the first target is detected, or can be periodically measured from the time the first target is detected and the first target meets the measurement conditions. For example, when the distance value between the first target and the device corresponding to the mth measurement cycle is recorded in the mth measurement cycle, at this time, the set of first distance values ​​includes n distance values ​​(i.e., N=n); when the measurement cycle enters the m+1th measurement cycle from the mth measurement cycle, the device records the distance value between the first target and the device corresponding to the m+1th measurement cycle. At this time, the set of first distance values ​​includes n+1 distance values ​​(i.e., N=n+1). In other words, the number N of distance values ​​included in the set of first distance values ​​gradually increases with the progress of the ranging process; each time the ranging is performed, the value of N increases by 1, and the corresponding values ​​of D1, D2, and D3 will also change, and the corresponding D m The value of D may also change. f The value of is obtained based on the set of three distance values ​​that are closest to the acquisition time of the set of first distance values, and its value does not change during the recording process of the set of first distance values.

[0088] The first target meets the measurement condition when: the distance between the first target and the device is measured twice, and the distance values ​​measured twice are equal, or the distance value measured in the second time is less than the distance value measured in the first time. In some embodiments, the distance values ​​measured twice are the first two distance values ​​among the N distance values ​​recorded in the set of first distance values.

[0089] For example, Figure 5 FIG. 5 is a schematic flow chart of a method 500 for determining whether a first target is a person who has no need to enter a door according to distance information of the first target provided by an embodiment of the present application. Figure 5 As shown, the method 500 includes:

[0090] When the first target is detected and meets the measurement conditions, the first distance value set is periodically recorded, the multimedia chip is started, and the person recognition algorithm without the need to enter the door is started (ie, the method 500 is executed).

[0091] The first target meets the measurement condition when: the distance between the first target and the device is measured twice, and the distance values ​​measured twice are equal, or the distance value measured in the second time is less than the distance value measured in the first time. In some embodiments, the distance values ​​measured twice are the first two distance values ​​among the N distance values ​​recorded in the set of first distance values.

[0092] S501, determine whether N is less than 10, if so, execute step S502; if not, execute step S504.

[0093] Wherein, N is the number of distance values ​​in the set of first distance values ​​corresponding to the first target.

[0094] In some embodiments, when N is greater than or equal to 5, S501 is executed.

[0095] S502: Determine d N Is it equal to 0, or d N Is it equal to -1? If so, it is determined that the first target is a person who has no need to enter the door; if not, further execute step S503.

[0096] Among them, d N Refers to the distance value most recently recorded in the set of the first distance value. N It can also be expressed as D3.

[0097] Among them, the data of "0" or the data of "-1" represents a distance measurement error, for example, the distance measurement error may be caused by the first target being outside the ranging range, or the distance measurement error may be caused by a sensor (target detection sensor or ranging sensor) failure, or the distance measurement error may be caused by other reasons, and this application does not limit this.

[0098] S503: Determine d N Is it greater than 1.1 meters? If so, it is determined that the first target is a person who has no need to enter the door; if not, it is determined that the first target is a person who has a need to enter the door.

[0099] Optionally, the threshold value 1.1 meters in this step can be replaced by any value between 1 meter and 1.2 meters.

[0100] S504: Determine whether any of the three distance values ​​D1, D2, and D3 is 0 or -1. If yes, execute step S505; if no, execute step S507.

[0101] For explanations of D1, D2, and D3, see Figure 4 For the sake of brevity, the explanations in the illustrated embodiments are not repeated here.

[0102] S505: Determine whether the three distance values ​​D1, D2, and D3 are all 0 or -1. If so, determine that the first target is a person who has no need to enter the door; if not, further execute step S506.

[0103] S506: Determine whether the data of the three distance values ​​D1, D2, and D3 that are not equal to 0 and not equal to -1 are greater than 1.1m. If so, determine that the first target is a person who has no need to enter the door; if not, determine that the first target is a person who has a need to enter the door.

[0104] Optionally, the threshold value 1.1 meters in this step can be replaced by any value between 1 meter and 1.2 meters.

[0105] S507: Preprocess the N distance values ​​in the first distance value set.

[0106] In some embodiments, preprocessing the N distance values ​​in the set of first distance values ​​includes:

[0107] (1) Remove the distance values ​​that are equal to 0 or -1 from the N distance values;

[0108] (2) Determine D m , D f , (D3-D1) / (ranging period × 2).

[0109] Among them, D mIt refers to the minimum distance value among N distance values; the distance values ​​measured at the last three successful face recognitions are recorded as D f1 , D f2 , D f3 , D f D f1 , D f2 , D f3 The average value, D f =(D f1 +D f2 +D f3 ) / 3.

[0110] The value of (D3-D1) / (distance measurement period×2) can be understood as the average speed of the first target in the time period from the measurement time of D1 to the measurement time of D3.

[0111] The ranging period may be 1 ms, 0.5 ms, or other period lengths, which are not limited in this application.

[0112] S508: Determine whether the three distance values ​​D1, D2, and D3 are all less than 0.75 meters. If so, determine that the first target is a person who needs to enter the door; if not, further execute step S509.

[0113] Optionally, the threshold value of 0.75 meters in this step can be replaced by any value between 0.7 meters and 0.9 meters.

[0114] Herein, step S508 may be referred to as a core area determination algorithm.

[0115] S509: Determine whether the three distance values ​​D1, D2, and D3 are all greater than 1.1 meters. If so, determine that the first target is a person who has no need to enter the door; if not, further execute step S510.

[0116] Optionally, the threshold value 1.1 meters in this step can be replaced by any value between 1 meter and 1.2 meters.

[0117] Herein, step S509 may be referred to as an edge area determination algorithm.

[0118] S510: Determine whether the three distance values ​​D1, D2, and D3 are all greater than (D m +100) mm, if so, further execute step S511 and step S512; if not, determine that the first target is a person who needs to enter the door.

[0119] Optionally, the threshold value (D m +100)mm can be replaced by (D m +50)mm to (D mAny value between +150)mm.

[0120] S511: Determine whether the three distance values ​​D1, D2, and D3 are all greater than (D f +200)mm, if so, it is determined that the first target is a person who has no need to enter the door; if not, it is determined that the first target is a person who has a need to enter the door.

[0121] Optionally, the threshold value (D f +200)mm can be replaced by (D f +100)mm to (D f Any value between +300)mm.

[0122] S512: Determine whether the value of (D3-D1) / (distance measurement period×2) is greater than 50 mm. If so, determine that the first target is a person who has no need to enter the door; if not, determine that the first target is a person who has a need to enter the door.

[0123] Optionally, the threshold value of 50 mm in this step can be replaced by any value between 30 mm and 100 mm.

[0124] Herein, steps S510 to S512 may be referred to as a critical region determination algorithm.

[0125] It should be understood that the method 500 is executed within the time period from when the multimedia chip starts to start to when it starts successfully, that is, the person recognition algorithm without the need to enter the door runs within the time period from when the multimedia chip starts to start to when it starts successfully. Specifically, the method 500 is executed periodically within the time period from when the multimedia chip starts to start to when it starts successfully.

[0126] In some embodiments, the method 500 (i.e., algorithm for identifying people without a need to enter a door) is executed once every time a distance value in the set of first distance values ​​corresponding to the first target increases (i.e., the value of N + a). Therefore, the determination result of whether the first target is a person without a need to enter a door may change. Since the more distance values ​​in the set of first distance values ​​(the larger N is), the more accurate the determination result is, the determination result corresponding to the successful startup of the multimedia chip can be used as the final determination result, where a is a positive integer greater than or equal to 1.

[0127] In some other embodiments, the method 500 (i.e., the algorithm for identifying people who do not need to enter the door) is executed periodically. Since the distance measurement of the first target is performed periodically, each time the method 500 is executed, the number of distance values ​​in the corresponding set of first distance values ​​may be more than the previous execution (N increases). Therefore, the determination result of whether the first target is a person who does not need to enter the door may change. Since the more distance values ​​in the set of first distance values ​​(the larger N is), the more accurate the determination result is, the corresponding determination result when the multimedia chip is successfully started can be used as the final determination result.

[0128] In an embodiment of the present application, a method for determining whether a first target is a person who has no need to enter the door or a person who has a need to enter the door is provided. In this method, during the time period from when the multimedia chip starts to start up to when it successfully starts up, the first target is periodically measured in distance, and based on the result of the periodic measurement, it is determined whether the first target is a person who has no need to enter the door or a person who has a need to enter the door. As a result, the device can resume the standby state when the first target is a person who has no need to enter the door, and no longer enter the subsequent face recognition process, which can avoid the power loss of the multimedia chip and the face recognition device during the face recognition process, thereby improving the battery life of the device.

[0129] By adjusting Figure 5 The parameters of the person recognition algorithm without the need to enter the door described in the embodiment shown (e.g. Figure 5 D in the embodiment shown m , D f And various determination thresholds), we can derive a recognition algorithm for people who do not need to enter the house that is suitable for different apartment types.

[0130] For example, Figure 6 A schematic diagram of determining a target algorithm from a plurality of recognition algorithms provided in an embodiment of the present application is shown.

[0131] When the device is actually running, before the algorithm takes effect, it will first run multiple algorithms simultaneously. After running, each of the multiple algorithms can output the success rate of identifying people who need to enter the door and the success rate of identifying people who do not need to enter the door. Then, the system continuously screens the multiple algorithms and finally selects the target algorithm that best suits the user's apartment type, and uses the target algorithm as the effective algorithm.

[0132] In one example, an algorithm with a success rate of identifying people who need to enter the door higher than 99% is determined as the target algorithm. If the success rates of identifying people who need to enter the door by multiple algorithms all meet>99%, then the algorithm with the highest success rate of identifying people who do not need to enter the door among the multiple algorithms with success rates of identifying people who need to enter the door meeting>99% is determined as the target algorithm). Figure 6As shown, recognition algorithm 1, recognition algorithm 2 and recognition algorithm 3 are run simultaneously, among which, the recognition success rate of recognition algorithm 1 for people who need to enter the door is 92%, and the recognition success rate of people who do not need to enter the door is >50%; the recognition success rate of recognition algorithm 2 for people who need to enter the door is 100%, and the recognition success rate of people who do not need to enter the door is <5%; the recognition success rate of recognition algorithm 3 for people who need to enter the door is 99%, and the recognition success rate of people who do not need to enter the door is <30%. Among them, the algorithms with recognition success rates of people who need to enter the door higher than 99% are recognition algorithm 2 and recognition algorithm 3. Among recognition algorithm 2 and recognition algorithm 3, the recognition success rate of people who do not need to enter the door by recognition algorithm 3 is higher than the recognition success rate of people who do not need to enter the door by recognition algorithm 2, and recognition algorithm 3 is determined as the target algorithm.

[0133] In an embodiment of the present application, before the device actually runs the algorithm for identifying people without the need to enter the door, it can preliminarily test-run multiple algorithms for identifying people without the need to enter the door with different parameters at the same time, and determine the algorithm for identifying people without the need to enter the door that will ultimately be run based on the success rates of the recognition results corresponding to the multiple algorithms for identifying people without the need to enter the door with different parameters. This can improve the recognition accuracy of the algorithm for identifying people without the need to enter the door, and further improve the user experience while improving the battery life of the device.

[0134] In order to more clearly understand how the unlocking control method provided in the embodiment of the present application specifically improves the battery life of the device, for example, Figure 7 A functional module diagram of an unlocking control device 700 provided in an embodiment of the present application is shown.

[0135] like Figure 7 As shown, the device 700 includes a sensing module 710, a distance measuring module 720, a control module 730, a multimedia chip 740 and a face recognition module 750. The sensing module 710 and the distance measuring module 720 are connected to the control module 730, the control module 730 is connected to the multimedia chip 740, and the multimedia chip 740 is connected to the face recognition module 750. Specifically:

[0136] The sensing module 710 is used to detect whether a first target appears within the detection range of the device.

[0137] The device includes the apparatus 700 .

[0138] In one implementation, the device may directly include the above-mentioned sensing module 710 , ranging module 720 , control module 730 , multimedia chip 740 and face recognition module 750 .

[0139] Optionally, the device is a smart door lock, and the device can also be other devices with face recognition function, such as: face clock-in machine, etc., wherein the smart door lock can be, for example, a house entrance door lock, a unit building access control, a gate access control, a car door lock, etc.

[0140] Among them, under ideal conditions, the detection range of the device is a sector-shaped area, the image acquisition device of the device is the center of the sector-shaped area, and the detection range has a clear field of view FOV. For specific diagrams, please refer to Figure 2 The dotted sector area shown in .

[0141] The first target refers to a target detected by a sensing device of the device, which may be a dynamic target or a static target.

[0142] In some embodiments, the sensing module 710 may be, for example, a human infrared sensor PIR.

[0143] The distance measuring module 720 is used to measure the distance between the first target and the device to obtain the distance information of the first target.

[0144] Among them, the interpretation of the distance information to the first target is Figure 3 In the embodiment shown, the explanation of the distance information of the first target in S301 is the same as that in S302, or the explanation of the distance information of the first target is the same as that in S303. Figure 4 The explanation of the set of first distance values ​​in the illustrated embodiments is the same and will not be repeated here for the sake of brevity.

[0145] In some embodiments, the distance measurement module 720 may be, for example, a time-of-flight (TOF) distance measurement module.

[0146] The control module 730 is used to determine whether the first target is a person who does not need to enter the door based on the distance information of the first target, and when it is determined that the first target is a person who does not need to enter the door, after the multimedia chip is successfully started, the multimedia chip 740 is powered off, that is, the device is restored to standby mode.

[0147] Among them, as the distance measurement module 720 continues to measure the distance, the number of distance values ​​included in the distance information of the first target gradually increases. During the time period when the multimedia chip starts to start and starts successfully, the control module 730 determines whether the first target is a person who does not need to enter the door based on the distance information of the first target. In one example, the control module 730 periodically determines whether the first target is a person who does not need to enter the door based on the distance information of the first target. Each time it is determined, a determination result is obtained. When the multimedia chip 740 is successfully started, the control module 730 determines the final output result based on the multiple results determined. For example, the last result obtained from the multiple results can be used as the final output result, wherein the time difference between the acquisition time of the last result and the time when the multimedia chip is successfully started is the shortest, and then the subsequent operation (that is, restoring the device to standby mode or performing a face recognition operation) is determined according to the final output result.

[0148] In another example, when the multimedia chip 740 is successfully started, the control module 730 can also determine the subsequent operation (ie, restoring the device to the standby state or performing a face recognition operation) according to any of the multiple determination results obtained.

[0149] In some embodiments, the control module 730 may be, for example, a microcontroller unit (MCU).

[0150] In some embodiments, the sensing module 710 and the ranging module 720 may be arranged on the control module 730 .

[0151] The multimedia chip 740 is used to execute the startup operation according to the instruction issued by the control module 730; it is also used to cooperate with the face recognition module 750 to perform the face recognition operation when the first target is a person who needs to enter the door.

[0152] The multimedia chip 740 is usually in a power-off or standby state. When the face recognition process needs to be executed, the control module 730 powers on or wakes it up.

[0153] In some embodiments, the multimedia chip 740 may be, for example, a system on chip (SOC).

[0154] The face recognition module 750 is used to perform face recognition on the first target when it is determined that the first target is a person who needs to enter the door.

[0155] In some embodiments, the face recognition module 750 may be, for example, a face recognition camera.

[0156] In some embodiments, the face recognition module 750 may be arranged on the multimedia chip 740 .

[0157] Since the multimedia chip and the facial recognition module that play a major role in the facial recognition process are high-power consumption modules, in the embodiment of the present application, when a target is detected, it can be determined whether the target is a person who has no need to enter the door or a person who has a need to enter the door. When it is determined that the target is a person who has no need to enter the door, the control module controls the multimedia chip to power off and will not trigger the facial recognition process. In this way, it can effectively avoid the false start-up of the facial recognition device caused by the passage of a person who has no need to enter the door, thereby reducing the power consumption of the smart door lock and improving the battery life of the smart door lock.

[0158] For example, Figure 8 FIG. 8 is a schematic flow chart of another unlocking control method 800 provided in an embodiment of the present application. Figure 8 As shown, the execution body of the method is a control module and a multimedia chip, wherein the control module is provided with a sensing module and a distance measurement module, and the multimedia chip is provided with a face recognition module. The method 800 includes:

[0159] S801: When the sensing module detects a first target, distance information of the first target is acquired through the distance measurement module.

[0160] Among them, the explanation of this step is Figure 3 The explanation of S301 in the illustrated embodiments is the same and will not be repeated here for the sake of brevity.

[0161] Among them, the interpretation of the distance information to the first target is Figure 3 In the embodiment shown, the explanation of the distance information of the first target in S301 is the same as that in S302, or the explanation of the distance information of the first target is the same as that in S303. Figure 4 The explanation of the set of first distance values ​​in the illustrated embodiments is the same and will not be repeated here for the sake of brevity.

[0162] The distance information of the first target may be a set of first distance values, and the set of first distance values ​​includes N distance values.

[0163] In some embodiments, the distance measurement module periodically measures the distance between the first target and the device, and each time a distance is measured, it is recorded in the set of first distance values, and the measurement is continued until the multimedia chip is successfully started and stops.

[0164] In one implementation, the ranging module stops ranging by calling the person_is_go_away function.

[0165] S802: Determine whether the first target meets the measurement condition, if so, execute step S803.

[0166] The first target satisfies the measurement condition when: the distance between the first target and the device is measured twice, and the distance values ​​measured twice are equal, or the distance value measured in the second time is less than the distance value measured in the first time. In some embodiments, the distance values ​​measured twice are the first two distance values ​​among the N distance values ​​recorded in the set of first distance values.

[0167] The measurement condition may also be described as a preset condition.

[0168] S803: The control module starts to pull up the multimedia chip.

[0169] This step can also be described as: the control module starts to power on the multimedia chip.

[0170] S804: The control module periodically determines whether the first target is a person who has no need to enter the door or a person who has a need to enter the door according to the distance information of the first target, and continues to determine until the multimedia chip is successfully started, and further executes step S807.

[0171] Among them, as the ranging module continues to measure the distance, the number of distance values ​​included in the distance information of the first target gradually increases. During the time period when the multimedia chip starts to start and starts successfully, the control module determines whether the first target is a person who does not need to enter the door based on the distance information of the first target. In an example, the control module periodically determines whether the first target is a person who does not need to enter the door based on the distance information of the first target. Each time a determination is made, a determination result is obtained, and a final output result is determined based on the multiple results determined. For example, the last result obtained among the multiple results can be used as the final output, or the latest determination result obtained can cover the last determination result obtained, that is, the final determination result is based on the last determination result obtained.

[0172] In yet another example, the final determination result may be any determination result among the multiple determination results obtained.

[0173] S805: In response to the control module starting to pull up the multimedia chip, the multimedia chip is powered on and started.

[0174] S806: The multimedia chip initializes the 3D imaging camera.

[0175] It should be understood that the execution order of S804 and S805 is not limited, and S804 and S805 can be executed simultaneously.

[0176] In some embodiments, S804 is executed periodically during the period from when the multimedia chip is powered on to when the multimedia chip is successfully started; that is, when the multimedia chip is powered on, S804 starts to be executed; when the multimedia chip is successfully started, S804 stops to be executed.

[0177] S807: When the multimedia chip is successfully started, determine whether the final result is a person who has no need to enter the door or a person who has a need to enter the door. If it is a person who has no need to enter the door, execute step S808; if it is a person who has a need to enter the door, execute step S809.

[0178] The explanation of the final determination result can be found in the relevant description in the above step S804, which will not be repeated here for the sake of brevity.

[0179] S808: The multimedia chip is powered off and the device returns to standby mode.

[0180] S809: The control module starts the face recognition process.

[0181] The following S810 to S813 are steps of the face recognition process.

[0182] S810: Acquire a first image of a first target.

[0183] The first image of the first target may refer to a face image of the first target, or may refer to an entire image of the first target.

[0184] S811: extract facial features from the first image. When the facial feature extraction is successful, execute step S812; when the facial feature extraction fails, execute step S813.

[0185] S812: Perform facial feature comparison. If the comparison is successful, the door is opened; if the comparison fails, the door is not opened.

[0186] Specifically, the facial features extracted from the first image are compared with the facial features of the person who needs to enter the door stored in the device.

[0187] S813: Determine whether the face recognition has timed out. If so, do not open the door; if not, return to step S810.

[0188] Since the multimedia chip and the facial recognition module that play a major role in the facial recognition process are high-power consumption modules, in the embodiment of the present application, when a target is detected, it can be determined whether the target is a person who has no need to enter the door or a person who has a need to enter the door. When it is determined that the target is a person who has no need to enter the door, the control module controls the multimedia chip to power off and will not trigger the facial recognition process. In this way, it can effectively avoid the false start-up of the facial recognition device caused by the passage of a person who has no need to enter the door, thereby reducing the power consumption of the smart door lock and improving the battery life of the smart door lock.

[0189] Through the method provided in this embodiment, for scenes where people who do not need to enter the door pass by, without changing the hardware architecture of the device, compared with the existing face recognition unlocking method, the wake-up time of the face recognition function of the device is reduced from 15s to 2s-4s, and the corresponding device power consumption is saved by more than 70%. For scenes with a large flow of people (for example: the entrance door is facing the staircase, the entrance door is facing the elevator room on the first floor), the battery life of the device can be increased by more than 2 months.

[0190] One or more of the modules or units described herein can be implemented by software, hardware or a combination of the two. When any of the above modules or units are implemented in software, the software exists in the form of program instructions and is stored in a memory, and a processor can be used to execute the program instructions and implement the above method flow. The processor may include but is not limited to at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller (MCU), or an artificial intelligence processor and other types of computing devices that run software, each computing device may include one or more cores for executing software instructions to perform operations or processing. The processor may be built into an SoC (system on chip) or an application specific integrated circuit (ASIC), or it may be an independent semiconductor chip. In addition to the core for executing software instructions for operations or processing in the processor, necessary hardware accelerators may be further included, such as a field programmable gate array (FPGA), a PLD (programmable logic device), or a logic circuit for implementing a dedicated logic operation.

[0191] When the modules or units described in this document are implemented in hardware, the hardware can be any one or any combination of a CPU, a microprocessor, a DSP, an MCU, an artificial intelligence processor, an ASIC, a SoC, an FPGA, a PLD, a dedicated digital circuit, a hardware accelerator, or a non-integrated discrete device, which can run the necessary software or be independent of the software to execute the above method flow.

[0192] When the modules or units described herein are implemented using software, they can be implemented in whole or in part in the form of a program product. The program product includes one or more instructions. When the program instructions are loaded and executed on the device, the process or function described in the embodiment of the present application is generated in whole or in part. The readable storage medium can be any available medium that the device can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a hard disk), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0193] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in hardware, or a combination of software and hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0194] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for unlocking control, applied to a device, characterized in that: The method comprises: When a first target is detected within the detection range of the device, obtaining distance information of the first target; determining, according to the distance information of the first target, whether the first target is a person who has no need to enter a door or a person who has a need to enter a door; When it is determined that the first target is a person who has no need to enter the door, the device is restored to the standby state, or When it is determined that the first target is a person who needs to enter the door, face recognition is performed on the first target.

2. The method according to claim 1, characterized in that The distance information of the first target includes N distance values, wherein the N distance values ​​are obtained by periodically measuring the distance between the first target and the device when the device detects the first target, and the N distance values ​​are recorded as i-th distance values ​​according to the order of measurement, i=1, 2, 3,…, (N-1), N; N is an integer not less than 1.

3. The method according to claim 2, characterized in that The determining, according to the distance information of the first target, whether the first target is a person who has no need to enter a door or a person who has a need to enter a door includes: Determining whether a preset condition is met according to the distance information of the first target, wherein the preset condition is that a second distance value among the N distance values ​​is less than or equal to a first distance value among the N distance values; When the preset condition is met, it is determined within a first time period whether the first target is a person who has no need to enter the door or a person who has a need to enter the door based on the distance information of the first target, and the starting time of the first time period is the time when it is determined that the preset condition is met.

4. The method according to claim 3, characterized in that The method further comprises: At the end of the first time period, the periodic measurement of the distance between the first target and the device is stopped.

5. The method according to claim 3 or 4, characterized in that: When the first target is detected, the device begins to periodically measure the distance between the first target and the device, including: When the first target is detected, the device starts measuring the distance between the first target and the device every first time period; The determining, within the first time period, according to the distance information of the first target, whether the first target is a person who has no need to enter a door or a person who has a need to enter a door includes: Determining whether the first target is a person who has no need to enter the door or a person who has a need to enter the door according to the distance information of the first target at every second time period within the first time period; Wherein, the first time period is less than or equal to the second time period.

6. The method according to any one of claims 3 to 5, characterized in that When N is less than 10, determining whether the first target is a person who has no need to enter a door or a person who has a need to enter a door according to the distance information of the first target within the first time period includes: Determine whether the Nth distance value is an invalid value; If the Nth distance value is an invalid value, it is determined that the first target is a person who has no need to enter the door; or If the Nth distance value is not an invalid value, and the Nth distance value is greater than the first threshold, it is determined that the first target is a person who has no need to enter the door.

7. The method according to any one of claims 3 to 5, characterized in that When N is greater than or equal to 10, determining whether the first target is a person who has no need to enter a door or a person who has a need to enter a door according to the distance information of the first target within the first time period includes: Determine whether there is an invalid value in the (N-2)th distance value, the (N-1)th distance value, and the Nth distance value; If there is an invalid value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are all invalid values, it is determined that the first target is a person who has no need to enter the door; or If there are invalid values ​​among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and non-invalid values ​​among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are greater than the first threshold, then the first target is determined to be a person who has no need to enter the door.

8. The method according to any one of claims 3 to 5, characterized in that When N is greater than or equal to 10, determining whether the first target is a person who has no need to enter a door or a person who has a need to enter a door according to the distance information of the first target within the first time period includes: When there is no invalid value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are all less than a second threshold, it is determined that the first target is a person who needs to enter the door; or When there are no invalid values ​​among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value and the Nth distance value are all greater than a first threshold, it is determined that the first target is a person who has no need to enter the door, wherein the second threshold is less than the first threshold.

9. The method according to any one of claims 3 to 5, characterized in that When N is greater than or equal to 10, determining whether the first target is a person who has no need to enter a door or a person who has a need to enter a door according to the distance information of the first target within the first time period includes: When there is no invalid value among the (N-2)th distance value, the (N-1)th distance value, and the Nth distance value, and the (N-2)th distance value, the (N-1)th distance value, and the Nth distance value are not all less than the second threshold value, nor are they all greater than the first threshold value, determining whether the (N-2)th distance value, the (N-1)th distance value, and the Nth distance value have a distance value less than or equal to a third threshold value, wherein the third threshold value is the sum of the smallest distance value among the N distance values ​​and the first calibration distance; When there is a distance value less than or equal to the third threshold value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, determining that the first target is a person who needs to enter the door; or When none of the (N-2)th distance value, the (N-1)th distance value, and the Nth distance value is less than or equal to the third threshold value, and all are greater than a fourth threshold value, it is determined that the first target is a person who has no need to enter the door, and the fourth threshold value is the sum of an average of the distance values ​​corresponding to the three most recent successful face recognition moments and the second calibration distance; or When there is no distance value less than or equal to the third threshold value among the (N-2)th distance value, the (N-1)th distance value and the Nth distance value, and the first speed is greater than the fifth threshold value, it is determined that the first target is a person who has no need to enter the door, where the first speed = ((N-2)th distance value - Nth distance value) / (first time period × 2).

10. A device, characterized in that: include: one or more processors; one or more memories; and one or more programs, wherein the one or more programs are stored in the one or more memories, and the one or more programs include instructions, which, when executed by the one or more processors, cause the device to perform the method as described in any one of claims 1 to 9.

11. A readable storage medium, characterized in that: The storage medium stores a program or an instruction, and when the program or the instruction is executed, the method according to any one of claims 1 to 9 is implemented.

Images