Intelligent lock energy consumption control method and system based on AI deep learning and intelligent lock

Abstract

The invention aims to disclose an intelligent lock energy consumption control method and system based on AI deep learning and an intelligent lock, and relates to the technical field of intelligent tool control, and the method comprises the following steps: S1, the intelligent lock adds and starts at least one non-contact unlocking secret key; s2, deeply learning the input frequency and the input time period of the non-contact unlocking secret key in a natural week through AI, and creating a user cycle model taking a natural day as a cycle; s3, creating a common time period, a non-common time period and a silence time period in the user cycle model; s4, in the common time period, the induction heartbeat cycle of the non-contact unlocking secret key is set to be f (T1), in the non-common time period, the induction heartbeat cycle of the non-contact unlocking secret key is set to be f (T2), and f (T1) is smaller than f (T2). A low-frequency heartbeat mode is adopted in a non-common time period; in the silent time period, the heartbeat stops, and the power consumption is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of smart lock control technology, and in particular to a smart lock energy consumption control method and system based on AI deep learning, and a smart lock. Background Art

[0002] Smart locks are powered by dry cells or lithium batteries. Energy consumption is a very important indicator. Saving any unnecessary energy loss as much as possible is the highest energy-saving goal of smart lock energy management. In the working mode of smart locks, the average standby power consumption is mainly determined by the selection of system components, hardware solution design and software energy consumption strategy. After the system components are determined, further energy saving must be achieved through the scheduling algorithm of the smart lock control system. For contactless unlocking methods, the control system usually uses the inspection mode of entering sleep mode and timed wake-up to work alternately to achieve a balance between low power consumption and real-time response of the control system.

[0003] At present, smart locks usually have both contact and contactless unlocking methods. When the contactless unlocking method is enabled, the control system needs to pay attention to external stimuli or input at all times in order to achieve the fastest response speed, resulting in excessive power consumption of the smart lock control system.

[0004] In view of this, it is necessary to develop a smart lock energy consumption control method, system and smart lock based on AI deep learning to overcome the above defects. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to disclose a smart lock energy consumption control method, system and smart lock based on AI deep learning.

[0006] The first object of the present invention is to provide a smart lock energy consumption control method based on AI deep learning.

[0007] The second object of the present invention is to provide an intelligent lock energy consumption control system based on AI deep learning.

[0008] The third object of the present invention is to provide a smart lock.

[0009] To achieve the above first invention objective, the present invention provides a smart lock energy consumption control method based on AI deep learning, comprising the following steps:

[0010] S1: The smart lock adds and enables at least one contactless unlocking key;

[0011] S2: Using AI deep learning to learn the input frequency and input time period of the contactless unlocking key within a natural week, a user cycle model with a natural day as the cycle is created;

[0012] S3: creating a common time period, an uncommon time period and a silent time period in the user cycle model;

[0013] S4: In the commonly used time period, the inductive heartbeat period of the contactless unlocking key is set to f(T1); in the uncommon time period, the inductive heartbeat period of the contactless unlocking key is set to f(T2), and f(T1) is less than f(T2); in the silent time period, the inductive heartbeat of the contactless unlocking key is set to stop.

[0014] To achieve the above first invention objective, the present invention also provides a smart lock energy consumption control method based on AI deep learning, comprising the following steps:

[0015] S1: The smart lock adds and enables at least one contactless unlocking key;

[0016] S2: Using AI deep learning to learn the input frequency and input time period of the contactless unlocking key within a natural week, a user cycle model with a natural day as the cycle is created;

[0017] S3: creating a common time period, an uncommon time period and a silent time period in the user cycle model;

[0018] S4: In the common time period, the inductive heartbeat cycle of the contactless unlocking key is set to f(T1); in the uncommon time period, the inductive heartbeat cycle of the contactless unlocking key is set to f(T2), and f(T1) is less than f(T2); in the silent time period, the inductive heartbeat of the contactless unlocking key is set to stop;

[0019] S5: Determine the battery voltage drop when the contactless unlocking key is input, and if the battery voltage drop is less than a set threshold, the inductive heartbeat of the contactless unlocking key stops.

[0020] Preferably, in step S1, if the smart lock has not added a contactless unlocking key, the card inspection module, radar module and Bluetooth module are not enabled.

[0021] Preferably, the contactless unlocking key is at least one of an IC card key, a face recognition key or a Bluetooth key.

[0022] Preferably, the f(T2)=1min-10min, and the f(T1)=300ms-1000ms.

[0023] Preferably, the fastest induced heartbeat f(T min );

[0024] In the f(T min)±Xmin, f(T1)=300ms-500ms;

[0025] In the f(T min )±Xmin, the f(T1) is equal to f(T min )±Xmin as the center and gradually expand to 1000ms.

[0026] Based on the same inventive principle, in order to achieve the above second inventive object, the present invention provides an intelligent lock energy consumption control system based on AI deep learning, including an IC card recognition unit, a face recognition unit, a Bluetooth recognition unit and an AI deep learning unit;

[0027] The IC card recognition unit includes a card inspection module, the face recognition unit includes a radar module, and the Bluetooth recognition unit includes a Bluetooth module;

[0028] Add and enable at least one contactless unlocking key in the IC card recognition unit, face recognition unit or Bluetooth recognition unit;

[0029] The AI ​​deep learning unit counts the input frequency and input time period of the user's contactless unlocking key with a natural week as a cycle, creates a user cycle model with a natural day as a cycle, and creates a common time period, an uncommon time period and a silent time period in the user cycle model;

[0030] The inductive heartbeat of the contactless unlocking key enables a high-frequency heartbeat mode in the common time period, the inductive heartbeat of the contactless unlocking key enables a low-frequency heartbeat mode in the uncommon time period, and the inductive heartbeat of the contactless unlocking key enables a stop heartbeat mode in the silent time period.

[0031] Preferably, if the battery voltage drop when the contactless unlocking key is input is less than a set threshold, the inductive heartbeat of the contactless unlocking key stops.

[0032] Preferably, the sensing heartbeat period f(T1) of the high-frequency heartbeat mode is 300ms-1000ms, and the sensing heartbeat period f(T2) of the low-frequency heartbeat mode is 1min-10min;

[0033] In the high frequency heartbeat mode, the fastest sensed heartbeat f(T min );

[0034] In the f(T min )±Xmin, f(T1)=300ms-500ms;

[0035] In the f(T min )±Xmin, the f(T1) is equal to f(Tmin )±Xmin as the center and gradually expand to 1000ms.

[0036] Based on the same inventive principle, in order to achieve the above-mentioned third invention purpose, the present invention provides a smart lock, including the smart lock energy consumption control system based on AI deep learning described in the second invention.

[0037] Compared with the prior art, the technical effects of the present invention are as follows:

[0038] Based on the user's living habits and unlocking habits, according to the input frequency and input time period of the contactless unlocking key within a natural week, a user cycle model with a natural day as the cycle is created, and common time periods, uncommon time periods and silent time periods are created in the user cycle model; in common time periods, a high-frequency heartbeat mode is adopted, and the inductive heartbeat cycle of the contactless unlocking key is f(T1); in uncommon time periods, a low-frequency heartbeat mode is adopted, and the inductive heartbeat cycle of the contactless unlocking key is f(T2), and f(T1) is less than f(T2); in silent time periods, a stop heartbeat mode is adopted; so that the user's inductive heartbeat cycle of the contactless unlocking key is short in common time periods, and the user can use a contactless method to open the smart lock very sensitively; while in uncommon time periods, the inductive heartbeat cycle of the contactless unlocking key is longer, that is, the f(T2) interval is longer, the inductive heartbeat frequency is reduced, and the inductive heartbeat stops in the silent time period, thereby greatly reducing the power consumption of the smart lock. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 This is a flow chart of the smart lock energy consumption control method based on AI deep learning in Example 1 of the present invention.

[0041] Figure 2 It is a schematic diagram of the commonly used time periods and the uncommon time periods of the present invention.

[0042] Figure 3 This is a flow chart of the smart lock energy consumption control method based on AI deep learning in Example 2 of the present invention.

[0043] Figure 4 This is a block diagram of the smart lock energy consumption control system based on AI deep learning in the present invention. DETAILED DESCRIPTION

[0044] The present invention is described in detail below in conjunction with the various embodiments shown in the accompanying drawings, but it should be noted that these embodiments are not limitations of the present invention, and any equivalent transformations or substitutions in functions, methods, or structures made by ordinary technicians in the field based on these embodiments are all within the scope of protection of the present invention.

[0045] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0046] Example 1

[0047] Ginseng Figure 1 As shown, this embodiment discloses a specific implementation method of a smart lock energy consumption control method based on AI deep learning.

[0048] Smart lock energy consumption control method based on AI deep learning, Figure 1 As shown, the following steps are included:

[0049] S1: The smart lock adds and enables at least one contactless unlocking key; specifically, the contactless unlocking key is at least one of an IC card key, a face recognition key or a Bluetooth key; the IC card key unlocks the lock through an IC card identification unit, and the IC card identification unit has a card checking module, which detects whether an IC card is approaching with a certain sensing heartbeat cycle; the face recognition key unlocks the lock through a face recognition unit, and the face recognition unit has a radar module, which detects whether a face is approaching with a certain sensing heartbeat cycle; the Bluetooth key unlocks the lock through a Bluetooth identification unit, and the Bluetooth identification unit has a Bluetooth module, which detects whether a Bluetooth is approaching with a certain sensing heartbeat cycle.

[0050] S2: Create a user cycle model with a natural day as the cycle by using AI deep learning to determine the input frequency and input time period of the contactless unlocking key within a natural week; obtain the user's input frequency and input time period of the contactless unlocking key based on the user's living habits and unlocking habits, create a user cycle model with a natural day as the cycle by using AI deep learning and Poisson distribution algorithm, and formulate a sensing heartbeat cycle based on the user cycle model.

[0051] S3: Create common time periods, uncommon time periods and silent time periods in the user cycle model; specifically, AI deep learning uses a natural week as a learning cycle, and determines the input probability of the contactless unlocking key and the length of the time period according to the Poisson distribution algorithm, so as to determine the common time periods, uncommon time periods and silent time periods of each day. The common time period refers to the time period when the input probability of the contactless unlocking key exceeds 50%, the uncommon time period refers to the time period when the input probability of the contactless unlocking key is less than 50%, and the silent time is the time period when the contactless unlocking key is not input within a week or the input probability is close to 0.

[0052] S4: In the commonly used time period, the inductive heartbeat period of the contactless unlocking key is set to f(T1); in the uncommon time period, the inductive heartbeat period of the contactless unlocking key is set to f(T2), and f(T1) is less than f(T2); in the silent time period, the inductive heartbeat of the contactless unlocking key is set to stop. Specifically, f(T2)=1min-10min, f(T1)=300ms-1000ms, f(T2) is 60 times-2000 times of f(T1). Under normal circumstances, the duration of the user's uncommon time period will be greater than or much greater than the duration of the common time period. In the uncommon time period, the sensing heartbeat cycle adopts f(T2), which will greatly reduce the sensing heartbeat frequency, thereby greatly reducing the energy consumption of the smart lock in the uncommon time period; in the common time period, f(T1) is selected as 300ms-1000ms, the heartbeat frequency is high, and it is in the real-time detection of the input state of the contactless unlocking key. The user's unlocking speed is fast and the experience is good. In order to further enhance the user's unlocking experience, the fastest sensing heartbeat f(T min ), in the f(T min )±Xmin, f(T1)=300ms-500ms, that is, in the time period when the user is most likely to unlock the lock, the fastest mental frequency is selected, the user's unlocking speed is fast and the experience is good. During this period of time, the duration lasts for 2Xmin, which has little impact on the overall power consumption of the smart lock; in the f(T min )±Xmin, the f(T1) is equal to f(T min )±X min as the center and gradually expand to 1000ms, that is, the distance f(T min )±X min, the closer the range is, the higher the probability of the user unlocking the door, so a higher heartbeat frequency is enabled, and the distance is the distance f(T min )±X min, the probability of the user unlocking the lock gradually decreases, and a gradually decreasing heartbeat frequency is enabled to reduce the power consumption of the smart lock even during the common time period; during the silent time period, unless the control panel of the smart lock is touched, the inductive heartbeat of the contactless unlocking key stops, thereby greatly reducing the power consumption of the smart lock.

[0053] In order to further reduce power consumption, the commonly used time period can be further divided according to the probability of inputting the contactless unlocking key. That is to say, the commonly used time period can be further divided into multiple non-continuous time periods. For example, when the probability of inputting the contactless unlocking key is between 80% and 100%, refer to Figure 2 , set X = 15min, in the f(T min )±15min, the f(T1)=300ms, in the f(T min )±15min, f(T1) is equal to f(T min )±15min as the center and gradually expand to 1000ms; when the probability of inputting the non-contact unlocking key is between 70% and 80%, set X=10min, and in the f(T min )±10min, the f(T1)=400ms, in the f(T min )±10min, f(T1) is equal to f(T min )±10min as the center and gradually expand to 1000ms; when the probability of inputting the contactless unlocking key is between 50% and 70%, set X=5min, and in the f(T min )±5min, the f(T1)=500ms, in the f(T min )±5min, f(T1) is equal to f(T min )±5min as the center and gradually expand to 1000ms; through the above technical solutions, a balance is achieved in user experience and reducing power consumption of smart locks.

[0054] In step S1, if the smart lock has not added a contactless unlocking key, the card inspection module, radar module and Bluetooth module are not enabled, that is, the sensing heartbeat of the contactless unlocking key is stopped to minimize the power consumption of the smart lock.

[0055] In step S4, see Figure 2 In the non-usual time period, f(T2)=1min-10min, the closer f(T2) is to the common time period, the smaller it is, and the farther f(T2) is from the common time period, the larger it is, so as to reduce the power consumption of the smart lock.

[0056] Through Example 1, based on the user's living habits and unlocking habits, according to the input frequency and input time period of the contactless unlocking key, a user cycle model with a natural day as the cycle is created through AI deep learning, and a common time period, an uncommon time period and a silent time period are created in the user cycle model; in the common time period, a high-frequency heartbeat mode is adopted, and the inductive heartbeat cycle of the contactless unlocking key is f(T1); in the uncommon time period, a low-frequency heartbeat mode is adopted, and the inductive heartbeat cycle of the contactless unlocking key is f(T2), and f(T1) is less than f(T2), so that the user can use the contactless method to open the smart lock very sensitively in the common time period with a short inductive heartbeat cycle of the contactless unlocking key in the common time period; and in the uncommon time period, the inductive heartbeat cycle of the contactless unlocking key is longer, that is, the f(T2) interval is longer, the inductive heartbeat frequency is reduced, and the inductive heartbeat stops in the silent time period, thereby greatly reducing the power consumption of the smart lock.

[0057] Example 2

[0058] See also Figure 3 Based on Example 1, the smart lock energy consumption control method based on AI deep learning also includes the following steps:

[0059] S5: Determine the battery voltage drop when the contactless unlocking key is input. If the battery voltage drop is less than the set threshold, the inductive heartbeat of the contactless unlocking key stops. Specifically, when the battery is in the dormant state of the smart lock, the voltage of the unlocking motor of the smart lock is basically constant at V1. When the contactless unlocking key is input, the smart lock starts, and the battery has a load. Due to the internal resistance of the battery, the voltage of the unlocking motor of the smart lock will have a certain voltage drop, that is, it drops from V1 to V2. When the difference between V1 and V2 is less than the preset threshold, it means that the working current of the unlocking motor is too small, so it is judged that the battery is in a low-power state, and the inductive heartbeat of the contactless unlocking key stops. If necessary, the user can be reminded to replace the battery.

[0060] For the parts of the smart lock energy consumption control method based on AI deep learning described in Example 2 that are the same as those in Example 1, please refer to Example 1 and will not be repeated here.

[0061] Example 3

[0062] See also Figure 4 This embodiment discloses a specific implementation method of a smart lock energy consumption control system based on AI deep learning.

[0063] Smart lock energy consumption control system based on AI deep learning, Figure 4As shown, it includes an IC card recognition unit, a face recognition unit, a Bluetooth recognition unit and an AI deep learning unit; the IC card recognition unit, the face recognition unit, the Bluetooth recognition unit and the AI ​​deep learning unit are all controlled by an MCU controller; the IC card recognition unit includes a card detection module, the face recognition unit includes a radar module, and the Bluetooth recognition unit includes a Bluetooth module; at least one contactless unlocking key is added and enabled in the IC card recognition unit, the face recognition unit or the Bluetooth recognition unit; the contactless unlocking key is at least one of an IC card key, a face recognition key or a Bluetooth key; the IC card key unlocks the door through the IC card recognition unit, the IC card recognition unit has a card detection module, and the card detection module detects whether an IC card is approaching with a certain sensing heartbeat cycle; the face recognition key unlocks the door through the face recognition unit, the face recognition unit has a radar module, and the radar module detects whether a face is approaching with a certain sensing heartbeat cycle; the Bluetooth key unlocks the door through the Bluetooth recognition unit The lock has a Bluetooth identification unit having a Bluetooth module, and the Bluetooth module detects whether there is a Bluetooth approach with a certain sensing heartbeat cycle; the AI ​​deep learning unit counts the input frequency and input time period of the user's contactless unlocking key with a natural week as a cycle, creates a user cycle model with a natural day as a cycle, and creates a common time period, an uncommon time period and a silent time period in the user cycle model, the common time period refers to a time period when the input probability of the contactless unlocking key exceeds 50%, the uncommon time period refers to a time period when the input probability of the contactless unlocking key is less than 50%, and the silent time is a time period when the contactless unlocking key is not input within a week or the input probability is close to 0; the sensing heartbeat of the contactless unlocking key enables a high-frequency heartbeat mode in the common time period, the sensing heartbeat of the contactless unlocking key enables a low-frequency heartbeat mode in the uncommon time period, and the sensing heartbeat of the contactless unlocking key enables a stop heartbeat mode in the silent time period.

[0064] Specifically, see Figure 2 The sensing heartbeat cycle f(T1) of the high-frequency heartbeat mode is 300ms-1000ms, and the sensing heartbeat cycle executes the high-frequency heartbeat mode in the common time period. The sensing heartbeat cycle f(T2) of the low-frequency heartbeat mode is 1min-10min, and the sensing heartbeat cycle executes the low-frequency heartbeat mode in the uncommon time period. Under normal circumstances, the duration of the uncommon time period of the user will be greater than or much greater than the duration of the common time period. Using heartbeat modes of different frequencies in different time periods can not only meet the user's unlocking experience in the common time period, but also greatly reduce the energy consumption of the smart lock in the uncommon time period; in the high-frequency heartbeat mode, determine the fastest sensing heartbeat f(T min ), in the f(T min)±Xmin, f(T1)=300ms-500ms, that is, in the time period when the user is most likely to unlock the lock, the fastest mental frequency is selected, the user's unlocking speed is fast and the experience is good. During this period of time, the duration lasts for 2Xmin, which has little impact on the overall power consumption of the smart lock; in the f(T min )±Xmin, the f(T1) is equal to f(T min )±X min as the center and gradually expand to 1000ms, that is, the distance f(T min )±Xmin, the closer the range is, the higher the probability of the user unlocking the door, and a higher heartbeat frequency is enabled, and the distance is the distance f(T min )±X min, the probability of the user unlocking the lock gradually decreases, and a gradually decreasing heartbeat frequency is enabled to reduce the power consumption of the smart lock even during the common time period; during the silent time period, the sensing heartbeat stops, thereby greatly reducing the power consumption of the smart lock.

[0065] In order to further reduce power consumption, the commonly used time period can be further divided according to the probability of inputting the contactless unlocking key. That is to say, the commonly used time period can be further divided into multiple non-continuous time periods. For example, when the probability of inputting the contactless unlocking key is between 80% and 100%, refer to Figure 2 , set X = 15min, in the f(T min )±15min, the f(T1)=300ms, in the f(T min )±15min, f(T1) is equal to f(T min )±15min as the center and gradually expand to 1000ms; when the probability of inputting the non-contact unlocking key is between 70% and 80%, set X=10min, and in the f(T min )±10min, the f(T1)=400ms, in the f(T min )±10min, f(T1) is equal to f(T min )±10min as the center and gradually expand to 1000ms; when the probability of inputting the contactless unlocking key is between 50% and 70%, set X=15min, and in the f(T min )±5min, the f(T1)=500ms, in the f(T min )±5min, f(T1) is equal to f(T min )±5min as the center and gradually expand to 1000ms; through the above technical solutions, a balance is achieved in user experience and reducing power consumption of smart locks.

[0066] During the uncommon time period, f(T2) = 1min-10min, the closer f(T2) is to the common time period, the smaller it is, and the farther f(T2) is from the common time period, the larger it gradually becomes, so as to reduce the power consumption of the smart lock; during the silent time period, unless the control panel of the smart lock is touched, the inductive heartbeat of the contactless unlocking key will stop.

[0067] The smart lock energy consumption control system based on AI deep learning described in Example 3 executes the smart lock energy consumption control method based on AI deep learning described in Example 1 or Example 2. For the parts that are the same as those in Example 1 and Example 2, please refer to Example 1 and Example 2, and will not be repeated here.

[0068] Example 4

[0069] This embodiment discloses a specific implementation of a smart lock.

[0070] The smart lock includes the smart lock energy consumption control system based on AI deep learning described in Example 3. The smart lock of this embodiment can intelligently learn the input frequency and input time period of the user to open the smart lock through the contactless unlocking key, so that the sleep time period of the smart lock can be divided into a common time period, an uncommon time period and a silent time period. In the common time period, a high-frequency heartbeat mode is adopted, so that the user can use the non-contact method to open the smart lock very sensitively during the common time period because the induction heartbeat cycle of the contactless unlocking key is short; in the uncommon time period, a low-frequency heartbeat mode is adopted, the induction heartbeat cycle of the contactless unlocking key is longer, and the induction heartbeat frequency is reduced; in the silent time period, the induction heartbeat stops, thereby greatly reducing the power consumption of the smart lock.

[0071] For the parts of the smart lock described in Example 4 that are the same as those in Example 3, please refer to Example 3 and will not be repeated here.

Claims

1. The smart lock energy consumption control method based on AI deep learning is characterized by: The following steps are involved: S1: Add and enable at least one contactless unlocking key to the smart lock; S2: Using AI deep learning to learn the input frequency and input time period of the contactless unlocking key within a natural week, a user cycle model with a natural day as the cycle is created; S3: creating a common time period, an uncommon time period and a silent time period in the user cycle model; S4: In the commonly used time period, the inductive heartbeat period of the contactless unlocking key is set to f(T1); in the uncommon time period, the inductive heartbeat period of the contactless unlocking key is set to f(T2), and f(T1) is less than f(T2); in the silent time period, the inductive heartbeat of the contactless unlocking key is set to stop.

2. The smart lock energy consumption control method based on AI deep learning is characterized by: The following steps are involved: S1: Add and enable at least one contactless unlocking key to the smart lock; S2: Using AI deep learning to learn the input frequency and input time period of the contactless unlocking key within a natural week, a user cycle model with a natural day as the cycle is created; S3: creating a common time period, an uncommon time period and a silent time period in the user cycle model; S4: In the common time period, the inductive heartbeat cycle of the contactless unlocking key is set to f(T1); in the uncommon time period, the inductive heartbeat cycle of the contactless unlocking key is set to f(T2), and f(T1) is less than f(T2); in the silent time period, the inductive heartbeat of the contactless unlocking key is set to stop; S5: Determine the battery voltage drop when the contactless unlocking key is input, and if the battery voltage drop is less than a set threshold, the inductive heartbeat of the contactless unlocking key stops.

3. The smart lock energy consumption control method based on AI deep learning as described in claim 1 or 2, characterized in that: In step S1, if the smart lock has not added a contactless unlocking key, the card inspection module, radar module and Bluetooth module are not enabled.

4. The smart lock energy consumption control method based on AI deep learning as described in claim 1 or 2, characterized in that: The contactless unlocking key is at least one of an IC card key, a face recognition key or a Bluetooth key.

5. The smart lock energy consumption control method based on AI deep learning as described in claim 1 or 2, characterized in that: The f(T2)=1min-10min, the f(T1)=300ms-1000ms.

6. The smart lock energy consumption control method based on AI deep learning as described in claim 1 or 2, characterized in that: Determine the fastest induced heartbeat f(T min ); In the f(T min )±Xmin, f(T1)=300ms-500ms; In the f(T min )±Xmin, the f(T1) is equal to f(T min )±Xmin as the center and gradually expand to 1000ms.

7. The smart lock energy consumption control system based on AI deep learning is characterized by: Including IC card recognition unit, face recognition unit, Bluetooth recognition unit and AI deep learning unit; The IC card recognition unit includes a card inspection module, the face recognition unit includes a radar module, and the Bluetooth recognition unit includes a Bluetooth module; Add and enable at least one contactless unlocking key in the IC card recognition unit, face recognition unit or Bluetooth recognition unit; The AI ​​deep learning unit counts the input frequency and input time period of the user's contactless unlocking key with a natural week as a cycle, creates a user cycle model with a natural day as a cycle, and creates a common time period, an uncommon time period and a silent time period in the user cycle model; The inductive heartbeat of the contactless unlocking key enables a high-frequency heartbeat mode in the common time period, the inductive heartbeat of the contactless unlocking key enables a low-frequency heartbeat mode in the uncommon time period, and the inductive heartbeat of the contactless unlocking key enables a stop heartbeat mode in the silent time period.

8. The smart lock energy consumption control system based on AI deep learning as claimed in claim 7, characterized in that: If the battery voltage drop when the contactless unlocking key is input is less than a set threshold, the inductive heartbeat of the contactless unlocking key stops.

9. The smart lock energy consumption control system based on AI deep learning as described in claim 7 or 8, characterized in that: The sensing heartbeat period f(T1) of the high-frequency heartbeat mode is 300ms-1000ms, and the sensing heartbeat period f(T2) of the low-frequency heartbeat mode is 1min-10min; In the high frequency heartbeat mode, the fastest sensed heartbeat f(T min ); In the f(T min )±Xmin, f(T1)=300ms-500ms; In the f(T min )±Xmin, the f(T1) is equal to f(T min )±Xmin as the center and gradually expand to 1000ms.

10. Smart lock, characterized in that, Including the smart lock energy consumption control system based on AI deep learning as described in any one of claims 7-9.

Images