AI Learning-Based Motor Control Method, Device, Smart Door Lock, and Medium

Abstract

The present invention relates to the technical field of intelligent door locks, and discloses a motor control method, device, intelligent door lock and medium based on AI learning, which are applied to an intelligent door lock. The method includes: acquiring motor state data of the intelligent door lock; detecting the opening and closing state of the intelligent door lock; performing AI learning according to the opening and closing state and the motor state data to obtain target control parameters, and controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameters. By designing AI learning based on the motor state data and the opening and closing state of the intelligent door lock to obtain the target control parameters for motor control, the present invention can avoid the influence of excessive current on the motor life when the motor is blocked, not only can extend the service life of the intelligent door lock and reduce the control power consumption of the motor, but also can realize flexible motor control through motor control AI learning, which helps to improve the overall control efficiency and control accuracy of the motor, realizes accurate door lock opening and closing, and meets the high-efficiency use requirements of the door lock.

Description

Technical Field

[0001] The present invention relates to the technical field of smart door locks, and in particular to a motor control method, device, smart door lock and medium based on AI learning. Background Art

[0002] At present, there are two ways for fully automatic intelligent door locks to achieve automatic unlocking. One way is to build the motor into the lock body electronics, and drive the lock tongue through the rotation of the reduction motor to achieve automatic door opening. This method can determine whether the lock is fully opened or closed by triggering the switch through the lock body and lock tongue, and will not cause misjudgment of the switch lock. However, due to the small space inside the lock body, the reduction motor that can be placed is a small motor, so it is difficult to achieve a large torque switch lock; even worse, once the door lock is installed, if there is friction resistance with the door frame, it will cause unlocking failure. In addition, another way is to use a conventional mechanical lock body, put the reduction motor on the handle behind the lock, and then drive the lock tongue through the lock core rotating shaft to achieve automatic door opening. This method has a larger handle space behind the lock, and the reduction motor can be made larger, and the success rate of unlocking is also higher. However, this method uses the motor's stall current to determine whether the lock tongue has completed the unlocking process, which is prone to misjudgment. Therefore, this method has a certain proportion of misjudgment of unlocking in actual applications, and the motor stall is used to judge, the current will exceed the rated current of the motor, causing damage to the reduction gear, and then forming irreversible damage, which also shortens the service life of the door lock.

[0003] Based on the above problems, the prior art improves the motor control method to achieve accurate door lock opening and closing, thereby extending the service life of the door lock. Specifically, most of the current intelligent door lock motor rotation control determines whether it is in place by detecting the stall current, and the stall current is relatively large, so it will generate a large amount of additional power consumption and waste electricity. In order to avoid the serious impact of excessive current on the life of the motor during stall, the control method of the motor on another part of the intelligent door lock is to directly drive the motor to rotate through the motor driver integrated circuit, and then add a limit switch at the position where the motor needs to stop, so that the gear of the motor output shaft can stop the motor after touching the limit switch. However, there is a problem of accuracy through the limit switch method, and there may be an angle deviation for each rotation.

[0004] In summary, the above motor control method has many defects and cannot achieve precise rotation control at any angle, which makes the control effect of the smart door lock performing door opening and closing operations through the motor poor, and it is difficult to achieve efficient control of the motor in the smart door lock. Summary of the invention

[0005] In view of this, the present invention provides a motor control method, device, intelligent door lock and medium based on AI learning to solve the defects of large control power consumption and inflexible control angle of the motor of the existing intelligent door lock, thus resulting in low overall control efficiency of the motor and seriously affecting the precise control of the motor.

[0006] In a first aspect, the present invention provides a motor control method based on AI learning, which is applied to an intelligent door lock. The method includes:

[0007] Obtain the motor state data of the intelligent door lock;

[0008] Detect the opening and closing state of the intelligent door lock;

[0009] Perform AI learning based on the opening and closing state and the motor state data to obtain target control parameters, and control the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameters.

[0010] The present invention focuses on the motor control of the intelligent door lock. By designing AI learning based on the motor state data and the opening and closing state of the intelligent door lock to obtain the target control parameters for motor control, it can avoid the influence of excessive current on the motor life when the motor is blocked, effectively extend the service life of the intelligent door lock, thereby reducing the control power consumption of the motor. At the same time, the motor control AI learning can also achieve flexible control of the motor, further improving the overall control efficiency and control accuracy of the motor, realizing precise door lock opening and closing, and meeting the high-efficiency use requirements of the door lock.

[0011] In an alternative embodiment, obtaining the motor state data of the intelligent door lock includes:

[0012] Collect the pulse signals of the photoelectric sensor, and the photoelectric sensor is installed on the motor of the intelligent door lock;

[0013] Calculate the rotation angle of the motor based on the pulse signals;

[0014] Measure the working current of the motor using a preset measuring device, and determine the working current and the rotation angle as the motor state data.

[0015] The present invention obtains the motor state data through the photoelectric sensor installed on the motor of the intelligent door lock, which can ensure the acquisition accuracy of the data, and thus improve the subsequent precise control of the motor.

[0016] In an alternative embodiment, performing AI learning based on the opening and closing state and the motor state data to obtain target control parameters includes:

[0017] Detect whether the intelligent door lock is connected to the network;

[0018] If the intelligent door lock is not connected to the network, obtain the historical operation data of the motor of the intelligent door lock; fit the historical operation data of the motor to obtain an AI learning model; use the AI learning model for prediction to obtain corresponding output parameters; calibrate the output parameters to obtain the target rotation angle of the motor, record the target rotation angle obtained by each calibration and determine it as the target control parameter.

[0019] The present invention correspondingly designs an AI learning process according to the current network connection state of the intelligent door lock, and designs an adaptive process for the door lock itself when the intelligent door lock is not connected to the network, that is, adaptively outputs the motor rotation angle corresponding to the next control of the door lock to open and close the door by fitting the historical operation data of the motor, which can avoid the phenomenon of equipment damage caused by using the locked-rotor current to control the motor, and improves the service life of the intelligent door lock to a certain extent; at the same time, the designed parameter correction feedback mechanism can ensure the accuracy of the rotation angle, thereby improving the precise control of the motor.

[0020] In an optional implementation manner, the output parameters include a predicted rotation angle, a first current threshold, and a second current threshold; wherein, the first current threshold represents the current value corresponding to when the current slope undergoes a sudden change, the second current threshold represents the current value corresponding to after the motor is stably locked-rotor, and the first current threshold is less than the second current threshold; calibrating the output parameters to obtain the target rotation angle of the motor includes:

[0021] Obtain the current working current and the current rotation angle of the motor;

[0022] If the current rotation angle reaches the predicted rotation angle and the current working current is less than the first current threshold, add the predicted rotation angle and a preset angle threshold, and determine the added result as the target rotation angle of the motor;

[0023] If the current rotation angle does not reach the predicted rotation angle and the current working current is greater than the second current threshold, subtract the predicted rotation angle from the preset angle threshold, and determine the subtracted result as the target rotation angle of the motor;

[0024] If the current rotation angle and the current working current do not meet the above conditions, determine the predicted rotation angle as the target rotation angle of the motor.

[0025] The present invention designs two mechanisms, namely, motor detection feedback and current threshold feedback, by using the actual operating data of the motor obtained and the motor predictive control data obtained by AI learning. Among them, the motor detection feedback aims to judge the positional relationship between the current rotation angle and the predicted rotation angle of the motor, and the current threshold feedback aims to judge the positional relationship between the current operating current of the motor and the first current threshold and the second current threshold to correct the data learned by AI, and then obtain the target rotation angle of the motor, which can significantly improve the quality of the target rotation angle, and further realize a more accurate door opening and closing operation for the intelligent door lock.

[0026] In an alternative embodiment, if the intelligent door lock is connected to the network, the motor control method based on AI learning further includes:

[0027] Obtain the historical rotation angle of the motor of the intelligent door lock and upload it to a preset database;

[0028] Perform data fitting on the historical rotation angle of the motor to obtain the first motor rotation curve of the intelligent door lock;

[0029] Obtain the second motor rotation curve of the door lock of the same type as the intelligent door lock from the preset database;

[0030] Calibrate the first motor rotation curve by using the second motor rotation curve to obtain the third motor rotation curve;

[0031] Determine the target rotation angle of the motor according to the third motor rotation curve, and determine the target rotation angle as the target control parameter.

[0032] The present invention correspondingly designs an adaptive process for the door lock and other networked lock bodies when the intelligent door lock is connected to the network, that is, obtains the corresponding motor rotation curve by fitting the historical rotation angle of its own motor, and uses the motor rotation curves of other door locks of the same type obtained through networking for calibration, which can ensure the accuracy and rationality of the motor rotation curve, and then can accurately obtain the target rotation angle, and uses it to realize the precise control of the motor.

[0033] In an alternative embodiment, before determining the target rotation angle of the motor according to the third motor rotation curve, the motor control method based on AI learning further includes:

[0034] Judge whether the third motor rotation curve deviates from the preset threshold;

[0035] If the third motor rotation curve deviates from the preset threshold, return to the step of obtaining the motor state data of the intelligent door lock again, and at the same time control the intelligent door lock to perform a warning process;

[0036] If the third motor rotation curve does not deviate from the preset threshold, execute the step of determining the target rotation angle of the motor according to the third motor rotation curve.

[0037] The present invention verifies the motor rotation curve obtained by networking the intelligent door lock, and correspondingly designs a judgment on whether the curve deviates from the set threshold to ensure the effectiveness of the curve, which helps to ensure the accuracy of the motor rotation curve.

[0038] In an alternative embodiment, before controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameter, the motor control method based on AI learning further includes:

[0039] Collect the actual state data of the motor;

[0040] Judge the deviation degree between the actual state data and the target control parameter;

[0041] If the deviation degree is not within the acceptable range, return to the step of obtaining the motor state data of the intelligent door lock again;

[0042] If the deviation degree is within the acceptable range, execute the step of controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameter.

[0043] The present invention verifies the effectiveness of the parameter by judging whether the deviation degree between the actual state data of the motor and the target control parameter obtained by AI learning is within the acceptable range, which can further ensure the accuracy of the target control parameter, thereby improving the overall control precision of the motor and realizing accurate opening and closing of the door lock.

[0044] In a second aspect, the present invention provides a motor control device based on AI learning, which is applied to an intelligent door lock. The device includes:

[0045] An acquisition module, configured to acquire the motor state data of the intelligent door lock;

[0046] A detection module, configured to detect the opening and closing state of the intelligent door lock;

[0047] A control module, configured to perform AI learning according to the opening and closing state and the motor state data to obtain a target control parameter, and control the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameter.

[0048] The motor control device based on AI learning of the present invention performs AI learning based on the motor state data and the opening and closing state of the intelligent door lock to obtain the target control parameter of the motor, avoiding the phenomenon that the current is too large when the motor is blocked in the prior art, which helps to extend the service life of the intelligent door lock, thereby reducing the control power consumption of the motor. At the same time, it can also achieve flexible control of the motor, improve the overall control efficiency and control precision of the motor, further realize accurate opening and closing of the door lock, and meet the high-efficiency use requirements of the door lock.

[0049] In a third aspect, the present invention provides an intelligent door lock, comprising: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute a motor control method based on AI learning according to the first aspect or any corresponding embodiment thereof.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute a motor control method based on AI learning according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 is a schematic flowchart of a motor control method based on AI learning according to an embodiment of the present invention;

[0053] Figure 2 is a schematic flowchart of another motor control method based on AI learning according to an embodiment of the present invention;

[0054] Figure 3 is a schematic structural diagram of a photoelectric sensor;

[0055] Figure 4 is a schematic diagram of the corresponding current of the motor for opening and closing the door;

[0056] Figure 5 is a schematic diagram of the motor rotation curve;

[0057] Figure 6 is a schematic structural diagram of a motor AI learning control system;

[0058] Figure 7 is a circuit block diagram of an intelligent door lock;

[0059] Figure 8 is a feedback flowchart of a motor AI learning control system;

[0060] Figure 9 is a schematic diagram of the AI learning process of a self-locking body;

[0061] Figure 10 is a schematic structural diagram of an intelligent door lock networking system;

[0062] Figure 11 It is a schematic diagram of the AI learning process for fitting trends of other networked lock bodies;

[0063] Figure 12 It is a block diagram of a motor control device based on AI learning according to an embodiment of the present invention;

[0064] Figure 13 It is a schematic structural diagram of an intelligent door lock according to an embodiment of the present invention. Detailed implementation manners

[0065] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0066] An embodiment of the present invention provides an embodiment of a motor control method based on AI learning. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0067] In this embodiment, a motor control method based on AI learning is provided, which is applied to an intelligent door lock. Figure 1 It is a schematic flowchart of a motor control method based on AI learning according to an embodiment of the present invention, as Figure 1 shown, and this process includes the following steps:

[0068] Step S101, obtain the motor state data of the intelligent door lock.

[0069] It should be noted that the motor state data in this embodiment refers to the relevant data during the operation of the motor, and its specific content and acquisition means are not limited herein. This data can be adaptively determined according to actual needs and obtained with reference to the corresponding conventional methods used by those skilled in the art. For example, the motor state data includes current, and specifically, the working current of the motor can be directly measured by an ammeter, which is only for illustrative purposes.

[0070] Step S102, detect the opening and closing state of the intelligent door lock.

[0071] In this embodiment, the opening and closing states of the intelligent door lock refer to the open state and the closed state of the door lock, and the opening and closing states of the door lock can be further identified by detecting the state of the deadbolt. Specifically, it is determined by detecting whether the deadbolt installed inside the lock body pops out. That is, when the deadbolt does not pop out, the door lock is in the open state, also known as the door-open state; when the deadbolt pops out, the door lock is in the closed state, also known as the door-closed state. Among them, whether the deadbolt pops out or not will generate corresponding trigger signals, and in practice, the opening and closing states of the door lock can be judged according to the type of received trigger signal.

[0072] Step S103: Perform AI learning based on the opening and closing states and the motor state data to obtain target control parameters, and control the motor drive to perform the intelligent door lock opening and closing operations according to the target control parameters.

[0073] It should be noted that the AI learning in this embodiment (for example, using algorithms such as Q-Learning and Deep Q-Network for reinforcement learning, multi-modal learning, and federated learning, and the specific content of AI learning can be adaptively adjusted according to actual needs) essentially means that in the open state and closed state of the door lock, by continuously learning and analyzing the opening state and angle of the door by the user each time, and combining the movement trends of other lock bodies, the target control parameters for the motor to control the door lock to perform the opening and closing operations next time are comprehensively obtained, and they are continuously adjusted and optimized to predict the future movement trends of the door lock.

[0074] The motor control method based on AI learning in the embodiment of the present invention designs AI learning based on the motor state data and the opening and closing states of the intelligent door lock to obtain the target control parameters for motor control, which can avoid the influence of excessive current on the motor life when the motor is blocked, effectively extend the service life of the intelligent door lock, and further reduce the control power consumption of the motor. At the same time, the motor control AI learning can also achieve flexible control of the motor, further improving the overall control efficiency and control accuracy of the motor, realizing precise door lock opening and closing, and meeting the high-efficiency use requirements of the door lock.

[0075] In this embodiment, a motor control method based on AI learning is provided, which is applied to an intelligent door lock. Figure 2 It is a schematic flowchart of another motor control method based on AI learning according to the embodiment of the present invention, as Figure 2 shown, and this process includes the following steps:

[0076] Step S201: Obtain the motor state data of the intelligent door lock.

[0077] Specifically, the above step S201 includes:

[0078] Step S2011: Collect the pulse signals of the photoelectric sensor, and the photoelectric sensor is installed on the motor of the intelligent door lock.

[0079] It should be noted that the photoelectric sensor collects data based on the photoelectric effect. When an object passes through the detection area of the photoelectric sensor, the generated optical signal will be captured by the sensor and an output corresponding pulse signal will be generated. The corresponding motor data can be obtained by analyzing this signal.

[0080] Step S2012, calculate the rotation angle of the motor based on the pulse signal.

[0081] In this embodiment, the rotation speed of the motor is calculated by analyzing the frequency and number of the pulse signal, and then the rotation angle of the motor is calculated based on the rotation speed.

[0082] Step S2013, measure the working current of the motor using a preset measuring device, and determine the working current and rotation angle as the motor state data.

[0083] In this embodiment, the specific type of the preset measuring device is not limited herein and is adaptively determined according to actual needs. For example, a current sensor is only used for illustrative purposes.

[0084] In practical applications, Hall effect sensors are often used for motor state detection. It can measure the strength, direction or change of the magnetic field, and can calculate the rotation speed and angle of the motor by measuring the change of the magnetic field on the motor shaft. However, since it is relatively sensitive to external magnetic field interference, the accuracy of the motor state data collected by this method is low. In this embodiment, by using a photoelectric sensor to collect motor state data, not only is the design convenient, but also it has high resolution and sensitivity, which can ensure the accuracy of data acquisition. Therefore, in this embodiment, a photoelectric sensor is used to collect motor state data. Specifically, by measuring the time difference of an object passing through the detection area, the speed of the object is detected. Each time the gear rotates one grid, it is blocked by light once, generating a switch pulse signal. The rotation speed and rotation angle of the motor are calculated by the frequency and number of the switch pulses, and the rotation angle each time can be accurately calculated and timely feedback. Figure 3 is a schematic structural diagram of the photoelectric sensor, which consists of Figure 3 It can be seen that the sensor includes: a transmitter, a receiver and a detection circuit. For the corresponding functions of the specific components of the sensor, please refer to the content of the rotation angle calculation in the previous text, and will not be repeated here.

[0085] In the embodiment of the present invention, the motor state data is obtained by a photoelectric sensor installed on the motor of the intelligent door lock, which can ensure the accuracy of data acquisition, and thus improve the precise control of the motor in the follow-up.

[0086] Step S202, detect the opening and closing state of the intelligent door lock. For details, please refer to Figure 1 Step S102 of the embodiment shown, which will not be repeated here.

[0087] Step S203: Perform AI learning based on the opening / closing state and motor state data to obtain target control parameters, and control the motor drive to perform intelligent door lock opening / closing operations according to the target control parameters.

[0088] Specifically, in the above step S203, performing AI learning based on the opening / closing state and motor state data to obtain target control parameters includes:

[0089] Step S2031: Detect whether the intelligent door lock is connected to the network.

[0090] In this embodiment, the detection method of whether the intelligent door lock is connected to the network is not limited herein and can be adaptively set according to actual requirements. For example, the network connection status can be obtained through the status indicator light of the door lock itself. That is, in actual applications, the intelligent door lock is equipped with a status indicator light, and lights of different colors or flashing frequencies can represent the network connection status. For example, a green light that is always on may indicate successful network connection, and a red flashing light may indicate a problem with the network connection; or, by checking the router or gateway of the home where the door lock is located, that is, by checking the list of connected devices. If the device name or physical address of the intelligent door lock can be found in this list, it means that the door lock has established a connection with the network. Otherwise, it means that the door lock is not connected to the network. This is only for illustrative purposes.

[0091] Step S2032: If the intelligent door lock is not connected to the network, obtain the historical operation data of the motor of the intelligent door lock; perform fitting on the historical operation data of the motor to obtain an AI learning model; use the AI learning model for prediction to obtain corresponding output parameters; calibrate the output parameters to obtain the target rotation angle of the motor, record the target rotation angle obtained by each calibration, and determine it as the target control parameter.

[0092] In this embodiment, the output parameters include the predicted rotation angle, the first current threshold, and the second current threshold; among them, the first current threshold represents the current value corresponding to the sudden change of the current slope, and the second current threshold represents the current value corresponding to the motor after stalling and stabilizing. The first current threshold is less than the second current threshold.

[0093] It should be noted that in this embodiment, the first current threshold is the value corresponding to the current slope mutation point; the second current threshold is the value corresponding to the locked-rotor current balance point; setting two current thresholds is aimed at better judging the angle generated by the feedback motor. For example, the motor rotation angle generated by AI learning fitting is 89 degrees. However, when the motor controls the door body to rotate to 89 degrees at this time, the corresponding current is still very small, that is, less than the first current threshold, indicating that the motor has not exerted much force and may still rotate a little more. Then let the motor rotate a little more until it reaches the first current threshold. At this time, the actual rotation angle of the motor is equal to 89 + 0.5 = 89.5 degrees; in addition, if the rotation angle generated by AI learning fitting is 91 degrees, when the motor controls the door body to rotate to 90 degrees at this time, it has been detected that the current is greater than the second current threshold, indicating that the current is already very large at this time and has reached the locked-rotor current, indicating that the motor has rotated in place and can stop rotating. At this time, the actual rotation angle of the motor is 90 degrees, that is, 90 - 1 = 90 degrees. Refer to Figure 4 the current schematic diagram corresponding to the motor opening and closing the door. It should be noted that Figure 4 in (a) and (b) of Figure 4 respectively correspond to the current conditions of the motor in the door opening / closing scenarios. Among them, the first threshold is the first current threshold (which is the current mutation point before reaching the locked-rotor current, and at this moment, the current and time slope mutate), and the second threshold is the second current threshold (which is the locked-rotor current point, that is, the maximum current point when reaching the locked-rotor). It should be explained that when the motor is almost in place during door opening, the current will definitely suddenly increase from a stable state; the first threshold is the starting point of the sudden increase, equivalent to the current mutation point, and at this time, the mutation point is the point with the largest slope change in the current curve; in addition, the second threshold is the current point after the locked-rotor current is balanced. Since there is a peak and then a stable state in the actual locked-rotor current, the second threshold in this embodiment is the stable point of the locked-rotor current. For example, for a series of current data collected from the motor, specifically: 0.1, 0.5, 1, 2, 1, 0.5, 0.5, 0.5, 0.6, 0.8, 0.8, 0.9, 2, 4.3, 4.1, 4.0, 4.0, 4.0; among them, 0.9 is the first current threshold (because the current value suddenly changes from 0.9 to 2); 4.0 is the second current threshold (the stable point of the locked-rotor current).

[0094] In the embodiment of the present invention, an AI learning process is designed corresponding to the current network connection state of the intelligent door lock, and an adaptive process for the door lock itself is designed when the intelligent door lock is not connected to the network, that is, by fitting the historical operation data of the motor, the motor rotation angle corresponding to the next control of the door lock to open and close the door is adaptively output, which can avoid the phenomenon of equipment damage caused by using the locked-rotor current to control the motor, and to a certain extent, improve the service life of the intelligent door lock; at the same time, the designed parameter correction feedback mechanism can ensure the accuracy of the rotation angle, thereby improving the precise control of the motor.

[0095] Specifically, after calibrating the output parameters in step S2032, obtaining the target rotation angle of the motor includes:

[0096] Step A1, obtaining the current working current and the current rotation angle of the motor.

[0097] In this embodiment, for the specific obtaining methods of the current working current and the current rotation angle of the motor, refer to the foregoing content and will not be repeated here.

[0098] Step A2, if the current rotation angle reaches the predicted rotation angle and the current working current is less than the first current threshold, then add the predicted rotation angle and the preset angle threshold, and determine the added result as the target rotation angle of the motor.

[0099] In this embodiment, the preset angle threshold is used to adjust the data deviation obtained by AI learning, that is, in the case where the motor does not rotate in place according to the self-learned data (i.e., the predicted rotation angle) (based on the rotation angle and the actually measured motor rotation angle, and the determination results of the actually measured motor current and the two current thresholds), the predicted rotation angle is corrected by the set angle threshold (i.e., the preset angle threshold). It should be noted that the specific value of the preset angle threshold is not limited here and can be adaptively adjusted according to actual requirements.

[0100] Step A3, if the current rotation angle does not reach the predicted rotation angle and the current working current is greater than the second current threshold, then subtract the preset angle threshold from the predicted rotation angle, and determine the subtracted result as the target rotation angle of the motor.

[0101] Step A4, if the current rotation angle and the current working current do not meet the above conditions, then determine the predicted rotation angle as the target rotation angle of the motor.

[0102] It should be noted that in this embodiment, step A4 indicates that the motor rotates in place according to the self-learned data, that is, it conforms to the actually measured motor rotation angle rotating in place, and the actual motor operation meets the two current thresholds and does not require additional adjustment. Specifically, by using the two current thresholds to judge and control the data deviation of AI learning, it is possible to avoid using the traditional method, that is, continuously using the locked-rotor current for judgment, which not only improves the rotation accuracy of the motor, but also saves the duration of the locked-rotor current and further saves the control power consumption, meeting the high-efficiency control requirements of the door lock.

[0103] In the embodiment of the present invention, two mechanisms, namely motor detection feedback and current threshold feedback, are designed by using the actual operation data of the motor obtained and the motor predictive control data obtained by AI learning. Among them, the motor detection feedback aims to judge the positional relationship between the current rotation angle and the predicted rotation angle of the motor, and the current threshold feedback aims to judge the positional relationship between the current working current of the motor and the first current threshold and the second current threshold to correct the data learned by AI, so as to obtain the target rotation angle of the motor, which can significantly improve the quality of the target rotation angle, and then realize a more accurate door opening and closing operation for the intelligent door lock.

[0104] It should be noted that the AI learning of the motor control in this embodiment also takes into account all the data information of the connected lock bodies. By obtaining the opening and closing movement laws similar to this lock body, the common movement trends are found, and then the motor control of its own lock body is improved to achieve a more accurate door opening and closing operation for the door lock. Therefore, if the intelligent door lock is connected to the network, the motor control method based on AI learning in this embodiment further includes:

[0105] Step B1, obtain the historical rotation angle of the motor of the intelligent door lock and upload it to the preset database.

[0106] In this embodiment, the preset database is used to provide data storage space for each connected intelligent door lock, and its specific content can be adjusted adaptively according to actual needs.

[0107] Step B2, perform data fitting on the historical rotation angle of the motor to obtain the first motor rotation curve of the intelligent door lock.

[0108] Step B3, obtain the second motor rotation curve of the door lock of the same type as the intelligent door lock from the preset database.

[0109] It should be noted that both the first motor rotation curve and the second motor rotation curve in this embodiment are curves composed of curve parameters representing the future trend of the motor.

[0110] Step B4, calibrate the first motor rotation curve by using the second motor rotation curve to obtain the third motor rotation curve.

[0111] In a specific embodiment, Figure 5It is a schematic diagram of the motor rotation curve. As can be seen from the figure, this AI learning process is applicable when the lock body of the smart door lock is connected to the network. On the one hand, it can upload the motor rotation angle data of its own lock and unlock operations to the cloud (this data does not involve privacy or security); on the other hand, it can obtain the motor rotation curve data of lock bodies of the same type as this smart door lock from the cloud, that is, obtain the motor rotation curve data of other lock bodies from the cloud: R1~Rn; collect the actual data of its own lock body, and perform AI learning training and fitting based on its own data, that is, fit the future trend curve data according to its own data: R'n+1, and then the AI searches for similar door opening and closing curve data in the database; the two are combined and finally the future trend curve data: Rn+1 is output through AI learning, that is, the future rotation angle trend Rn+1 of this lock body is predicted.

[0112] Step B5, determine the target rotation angle of the motor according to the third motor rotation curve, and determine the target rotation angle as the target control parameter.

[0113] In the embodiment of the present invention, when the smart door lock is connected to the network, an adaptive process for the door lock and other networked lock bodies is correspondingly designed, that is, the corresponding motor rotation curve is obtained by fitting the historical rotation angle of the motor of itself, and the motor rotation curves of other door locks of the same type obtained through networking are used for calibration, which can ensure the accuracy and rationality of the motor rotation curve, and then the target rotation angle can be accurately obtained, and the precise control of the motor is realized by using it.

[0114] It should be noted that in this embodiment, it is aimed to improve the effectiveness of the third motor rotation curve, and a corresponding curve calibration process is designed for this purpose. Therefore, before determining the target rotation angle of the motor according to the third motor rotation curve, the motor control method based on AI learning in this embodiment further includes:

[0115] Step C1, determine whether the third motor rotation curve deviates from the preset threshold.

[0116] In this embodiment, the preset threshold can be adaptively adjusted according to the actual project requirements, and its specific content is not limited here.

[0117] Step C2, if the third motor rotation curve deviates from the preset threshold, then return to the step of obtaining the motor state data of the smart door lock again, and at the same time control the smart door lock to perform a warning process.

[0118] Step C3, if the third motor rotation curve does not deviate from the preset threshold, then execute the step of determining the target rotation angle of the motor according to the third motor rotation curve.

[0119] In the embodiment of the present invention, by verifying the motor rotation curve obtained by connecting the smart door lock to the network, a judgment on whether the curve deviates from the set threshold is correspondingly designed to ensure the effectiveness of the curve, which helps to ensure the accuracy of the motor rotation curve.

[0120] Step S2033, control the motor drive to perform the intelligent door lock switching operation according to the target control parameter.

[0121] In this embodiment, the target control parameter is the motor rotation angle corresponding to the door lock open state or closed state. Control the motor to rotate according to this rotation angle, so as to drive the door body to perform the corresponding opening or closing operation.

[0122] The present invention checks the validity of the parameter by judging whether the actual state data of the motor is the same as the target control parameter obtained by AI learning, which can further ensure the accuracy of the target control parameter, and then improve the overall control accuracy of the motor, realizing accurate door lock opening and closing.

[0123] It should be noted that in order to ensure the accuracy of the motor rotation angle obtained by AI learning in this embodiment, a motor angle calibration process using measured data is correspondingly designed. Therefore, before controlling the motor drive to perform the intelligent door lock switching operation according to the target control parameter, the motor control method based on AI learning in this embodiment further includes:

[0124] Step D1, collect the actual state data of the motor.

[0125] In this embodiment, the actual state data and the target control parameter belong to the same data type, and its specific content is adaptively adjusted according to actual needs. For example, the actual state data is the motor rotation angle, also called the rotation angle.

[0126] Step D2, judge the deviation degree between the actual state data and the target control parameter.

[0127] Step D3, if the deviation degree is not within the acceptable range, return to the step of obtaining the motor state data of the intelligent door lock again.

[0128] Step D4, if the deviation degree is within the acceptable range, execute the step of controlling the motor drive to perform the intelligent door lock switching operation according to the target control parameter.

[0129] In the embodiment of the present invention, by judging whether the deviation degree between the actual state data of the motor and the target control parameter obtained by AI learning is within the acceptable range to check the validity of the parameter, it can further ensure the accuracy of the target control parameter, and then improve the overall control accuracy of the motor, realizing accurate door lock opening and closing.

[0130] In a specific embodiment, a motor AI learning control system is provided. This system is integrated in the intelligent door lock to improve the control efficiency of the motor. Figure 6 It is a schematic structural diagram of the motor AI learning control system. Figure 6It can be known that the system includes: a motor detection module, a signal trigger module, and a motor AI learning module; among them, the motor detection module is integrated on the motor and includes a photoelectric sensor for collecting motor operation data; the signal trigger module is arranged inside the lock body, generates corresponding trigger signals by the ejection or pressing of the deadbolt, and judges the opening or closing state of the door lock according to the trigger signals; the motor AI learning module includes an AI learning chip, which continuously learns and analyzes the opening state and angle of each user; or the movement trend of other lock bodies, obtains the next rotation angle of the lock body, continuously adjusts and optimizes, and predicts the future movement trend. If there is a situation exceeding the threshold, an alarm will be given.

[0131] In this embodiment, the circuit block diagram of the intelligent door lock integrated with the above-mentioned motor AI learning control system is as Figure 7 shown. It can be known from Figure 7 that the circuit of the intelligent door lock includes a motor detection adaptive learning unit and a main control recognition unit; among them, the motor detection adaptive learning unit includes a motor detection module, a signal trigger module, an AI learning module, and a motor; the main control recognition unit includes a main control module, a radar module, a biometric recognition module, and other modules. It should be noted that the other modules include but are not limited to: Bluetooth module, WIFI module, button module, voice module, etc., which can be adaptively added according to the functions actually possessed by the door lock.

[0132] It should be noted that in this embodiment, the continuous adjustment and optimization of the rotation angle of the lock body are realized through motor detection feedback and current threshold feedback. Figure 8 is the feedback flow chart of the motor AI learning control system. It can be known from Figure 8 that the current threshold feedback is to make a comprehensive judgment according to two set current thresholds to calibrate the rotation angle of the motor output adaptively, aiming to improve the accuracy of each lock opening and closing; in addition, the motor detection feedback is to calibrate the rotation angle of the motor output adaptively according to the actual angle detected by the motor, and can accurately detect the real-time actual rotation angle value. Specifically, by designing the above two feedbacks, the accuracy of opening and closing the door can be improved. In addition, without waiting for the stall current residence time to judge, the control power consumption is greatly saved, which helps to improve the overall control efficiency and control accuracy of the motor.

[0133] It should be noted that in this embodiment, the motor AI learning module is designed with two AI learning processes, namely, the AI learning process of the self-locking body and the AI learning process of fitting the trend by networking with other lock bodies. It should be noted that the AI learning process of the self-locking body is for the lock of the intelligent door lock. When opening and closing the door each time, the AI learns and fits the actual rotation angle, and adjusts it with the current threshold. This process is essentially a data process of inputting its own parameters to fit the next unlocking data; the AI learning process of fitting the trend by networking with other lock bodies is for the data integrated from other lock bodies (that is, all the data of the lock in the network and other lock bodies). Observe and analyze the opening trajectories of other lock bodies to see if a curve similar to its own lock body can be found, and use the current data to evaluate and predict the future movement trajectory. If the fitted future trend curve deviates from the normal value, an early warning will be given (that is, assuming that the normal opening value of the current lock body is 1, if the trend of each opening exceeds ±20% of this value, a reminder can be given, that is, if the opening / closing value of the lock body deviates from the corresponding normal range, a reminder will be given, so that the user can observe whether the door lock is installed abnormally or the door body is deformed, etc., and then perform corresponding subsequent processing.

[0134] In this embodiment, Figure 9 is the AI learning process of the self-locking body. From Figure 9 it can be seen that the motor AI learning module records the data and results of the motor's previous n detections (that is, the rotation angle parameters and current data in the figure). According to the rotation angle parameters and the corresponding current data, AI learning fitting is performed (that is, AI learning, analysis, and processing of the input data in the figure), and the next motor angle: D'n+1 is output. At the same time, a first current threshold B1 (that is, the value corresponding to the current slope mutation point) and a second current threshold B2 (that is, the value corresponding to the locked-rotor current balance point) are generated; and the following judgments are made on it:

[0135] ① If the rotation angle reaches D'n+1, but the current < B1, the calibrated rotation angle is: (D'n+1) + ΔD, where ΔD is a preset angle threshold;

[0136] ② If the rotation angle does not reach D'n+1, but the current > B2, the calibrated rotation angle is: (D'n+1) - ΔD;

[0137] ③ Otherwise, the rotation angle is D'n+1.

[0138] Therefore, the actual rotation angle: Dn+1 = D'n+1 or (D'n+1) ± ΔD), and then it is fed back as the input parameter of the AI learning module.

[0139] It should be noted that the input data of the AI learning module are the rotation angles and current parameters of the previous n times, and the training fits and outputs D'n+1, B1, and B2; then, based on the feedback adjustment, Dn+1 is finally output; for example, when inputting the rotation angles and current data of the switch lock for 1 to 10 times, the pre-rotation angle D11', the first threshold B1, and the second threshold B2 of the 11th time are output, and then, based on the feedback adjustment, the actual rotation angle D11 is obtained; then, for the data of the 12th time, the relevant data of 1 to 11 times can continue to be used as the input, D12' and the updated B1 and B2 are output, and finally, the actual output D12 is obtained through feedback adjustment.

[0140] In this embodiment, Figure 10 is a schematic structural diagram of the intelligent door lock networking system. It should be noted that each intelligent door lock can form an intelligent lock networking system by connecting to the same network, and in this system, each intelligent door lock can perform data interaction with the server (i.e., the cloud). Figure 11 is a schematic diagram of the AI learning process for fitting the trends of other connected lock bodies. As can be seen from Figure 11 the detailed implementation process of fitting the trends of other connected lock bodies can be known. It should be explained that in the abnormal judgment of the future trend curve data in the figure, the mean value R* is the standard value corresponding to opening or closing the door, and the specific acquisition method thereof is not limited herein. For example, it can be obtained through offline calibration, or by analyzing the future trend curve data of all lock bodies in the intelligent door lock networking system, which is only for illustrative purposes.

[0141] In summary, the motor control method based on AI learning in the embodiments of the present invention has the following advantages:

[0142] 1. It saves the power consumption caused by the locked-rotor current, thereby saving the energy of the door lock and increasing the battery life.

[0143] 2. The chip in the designed self-learning module can self-learn and continuously update the output, making each door opening or closing operation more accurate.

[0144] 3. The designed motor detection module uses a photoelectric sensor, which is convenient to design and has high resolution, sensitivity, and accuracy.

[0145] 4. The designed motor detection feedback and current threshold feedback can significantly improve the accuracy of opening and closing the door.

[0146] 5. It can adapt to situations such as door body deformation and lock body rust, and can adaptively control the rotation angle of the motor.

[0147] 6. It can use AI to learn all the data information of the connected lock body, obtain the movement law of the lock body, and find out the movement trend. On the one hand, it can provide early warning reference for the next stage of rotation of the lock body. On the other hand, it can optimize the lock body, that is, through AI learning and training based on the data of multiple locks, it can guide the optimization of the development of the next version of the lock body.

[0148] In this embodiment, a motor control device based on AI learning is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As the term "module" used hereinafter, it can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0149] The present invention provides a motor control device based on AI learning, which is applied to an intelligent door lock, such as Figure 12 shown, the device includes:

[0150] An acquisition module 1201, configured to acquire the motor state data of the intelligent door lock.

[0151] A detection module 1202, configured to detect the opening and closing state of the intelligent door lock.

[0152] A control module 1203, configured to perform AI learning based on the opening and closing state and the motor state data to obtain target control parameters, and control the motor drive to perform the opening and closing operation of the intelligent door lock according to the target control parameters.

[0153] In some optional implementation manners, the acquisition module 1201 includes: a first acquisition sub-module, a second acquisition sub-module, and a third acquisition sub-module; wherein, the first acquisition sub-module is configured to collect the pulse signal of the photoelectric sensor, and the photoelectric sensor is installed on the motor of the intelligent door lock; the second acquisition sub-module is configured to calculate the rotation angle of the motor based on the pulse signal; the third acquisition sub-module is configured to measure the working current of the motor by using a preset measuring device, and determine the working current and the rotation angle as the motor state data.

[0154] In some alternative embodiments, the control module 1203 includes: a first control sub-module, a second simulation sub-module, and a third control sub-module; wherein, the first control sub-module is configured to perform AI learning based on the opening / closing state and motor state data to obtain target control parameters, including: detecting whether the intelligent door lock is connected to the network; if the intelligent door lock is not connected to the network, acquiring the historical operation data of the motor of the intelligent door lock; fitting the historical operation data of the motor to obtain an AI learning model; using the AI learning model for prediction to obtain corresponding output parameters; calibrating the output parameters to obtain the target rotation angle of the motor, recording the target rotation angle obtained by each calibration and determining it as the target control parameter; the second control sub-module is configured to, if the intelligent door lock is connected to the network, acquire the historical rotation angle of the motor of the intelligent door lock and upload it to a preset database; perform data fitting on the historical rotation angle of the motor to obtain the first motor rotation curve of the intelligent door lock; acquire the second motor rotation curve of the door lock of the same type as the intelligent door lock from the preset database; use the second motor rotation curve to calibrate the first motor rotation curve to obtain a third motor rotation curve; determine the target rotation angle of the motor according to the third motor rotation curve, and determine the target rotation angle as the target control parameter; the third control sub-module is configured to control the motor drive to perform the intelligent door lock opening / closing operation according to the target control parameter.

[0155] In some alternative embodiments, the first control sub-module includes: a parameter calibration unit, configured to calibrate the output parameters to obtain the target rotation angle of the motor, including: acquiring the current working current and the current rotation angle of the motor; if the current rotation angle reaches the predicted rotation angle and the current working current is less than the first current threshold, adding the predicted rotation angle and the preset angle threshold, and determining the addition result as the target rotation angle of the motor; if the current rotation angle does not reach the predicted rotation angle and the current working current is greater than the second current threshold, subtracting the predicted rotation angle from the preset angle threshold, and determining the subtraction result as the target rotation angle of the motor; if the current rotation angle and the current working current do not meet the above conditions, determining the predicted rotation angle as the target rotation angle of the motor.

[0156] In some alternative embodiments, the second control sub-module includes: a curve verification unit, configured to, before determining the target rotation angle of the motor according to the third motor rotation curve, determine whether the third motor rotation curve deviates from a preset threshold; if the third motor rotation curve deviates from the preset threshold, re-return to the step of acquiring the motor state data of the intelligent door lock, and at the same time control the intelligent door lock to perform a warning process; if the third motor rotation curve does not deviate from the preset threshold, execute the step of determining the target rotation angle of the motor according to the third motor rotation curve.

[0157] In some alternative embodiments, the control module 1203 further includes: a fourth control sub-module, configured to collect the actual state data of the motor before controlling the motor drive to perform the intelligent door lock switching operation according to the target control parameter; determine the deviation degree between the actual state data and the target control parameter; if the deviation degree is not within the acceptable range, return to the step of obtaining the motor state data of the intelligent door lock; if the deviation degree is within the acceptable range, execute the step of controlling the motor drive to perform the intelligent door lock switching operation according to the target control parameter.

[0158] The further function descriptions of the above-mentioned various modules are the same as those in the corresponding embodiments above, and will not be elaborated here.

[0159] The motor control device based on AI learning in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0160] The motor control device based on AI learning according to the embodiment of the present invention avoids the phenomenon that the current is too large when the motor is blocked in the prior art, which affects the service life of the motor, helps to extend the service life of the intelligent door lock, and further reduces the control power consumption of the motor. At the same time, it can also achieve flexible control of the motor, improve the overall control efficiency and control accuracy of the motor, and further achieve accurate door lock opening and closing, meeting the high-efficiency use requirements of the door lock.

[0161] The embodiment of the present invention also provides an intelligent door lock. Please refer to Figure 13 , Figure 13 is a schematic structural diagram of the above-mentioned intelligent door lock provided in an alternative embodiment of the present invention. As shown in Figure 13 , the intelligent door lock includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common main board or installed in other ways as needed. The processor can process instructions executed within the intelligent door lock, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display intelligent door lock coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple intelligent door locks can be connected, and each intelligent door lock provides some necessary operations (for example, determined as a server array, a set of blade servers, or a multi-processor system). Figure 13 Taking one processor 10 as an example in

[0162] The processor 10 may be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device may be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.

[0163] Among them, the memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiments.

[0164] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the intelligent door lock, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the intelligent door lock through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0165] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may also include a combination of the above types of memories.

[0166] The intelligent door lock further includes a communication interface 30 for the main control chip to communicate with other intelligent door locks or a communication network.

[0167] An embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor master control chip, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiment is implemented.

[0168] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A motor control method based on AI learning, applied to an intelligent door lock, characterized in that The method includes: Obtaining the motor status data of the intelligent door lock, including: Collecting the pulse signal of the photoelectric sensor, where the photoelectric sensor is installed on the motor of the intelligent door lock; Calculating the rotation angle of the motor based on the pulse signal; Measuring the working current of the motor using a preset measuring device, and determining the working current and the rotation angle as the motor status data; Detecting the opening and closing status of the intelligent door lock; Performing AI learning based on the opening and closing status and the motor status data to obtain target control parameters, and controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameters; where, performing AI learning based on the opening and closing status and the motor status data to obtain target control parameters includes: Detecting whether the intelligent door lock is connected to the network; If the intelligent door lock is connected to the network, obtaining the corresponding motor rotation curves of the intelligent door lock and the door locks of the same type as the intelligent door lock; calibrating the motor rotation curve of the intelligent door lock using the motor rotation curves of the door locks of the same type as the intelligent door lock to determine the target rotation angle of the motor, and determining the target rotation angle as the target control parameter; where, the motor rotation curve of the intelligent door lock is determined according to the historical rotation angles of the motor of the intelligent door lock; If the intelligent door lock is not connected to the network, obtaining the historical operation data of the motor of the intelligent door lock; fitting the historical operation data of the motor to obtain an AI learning model; performing prediction using the AI learning model to obtain corresponding output parameters; calibrating the output parameters to obtain the target rotation angle of the motor, recording the target rotation angle obtained by each calibration and determining it as the target control parameter.

2. The motor control method based on AI learning according to claim 1, wherein The output parameters include a predicted rotation angle, a first current threshold, and a second current threshold; where, the first current threshold represents the current value corresponding to the sudden change in the current slope, the second current threshold represents the current value corresponding to the stable state after the motor is jammed, and the first current threshold is less than the second current threshold; calibrating the output parameters to obtain the target rotation angle of the motor includes: Obtaining the current working current and the current rotation angle of the motor; If the current rotation angle reaches the predicted rotation angle and the current working current is less than the first current threshold, adding the predicted rotation angle and a preset angle threshold, and determining the added result as the target rotation angle of the motor; If the current rotation angle does not reach the predicted rotation angle and the current working current is greater than the second current threshold, subtracting the predicted rotation angle from the preset angle threshold, and determining the subtracted result as the target rotation angle of the motor; If the current rotation angle and the current working current do not meet the above conditions, determining the predicted rotation angle as the target rotation angle of the motor.

3. The motor control method based on AI learning according to claim 1, wherein If the intelligent door lock is connected to the network, the method further includes: Obtaining the historical rotation angles of the motor of the intelligent door lock and uploading them to a preset database; Performing data fitting on the historical rotation angles of the motor to obtain the first motor rotation curve of the intelligent door lock; Obtaining the second motor rotation curve of the door locks of the same type as the intelligent door lock from the preset database; Calibrate the rotation curve of the first motor using the rotation curve of the second motor to obtain the rotation curve of the third motor; Determine the target rotation angle of the motor according to the rotation curve of the third motor, and determine the target rotation angle as the target control parameter.

4. The motor control method based on AI learning according to claim 3, characterized in that, Before determining the target rotation angle of the motor according to the rotation curve of the third motor, the method further includes: Judge whether the rotation curve of the third motor deviates from the preset threshold; If the rotation curve of the third motor deviates from the preset threshold, return to the step of obtaining the motor state data of the intelligent door lock, and at the same time control the intelligent door lock to perform early warning processing; If the rotation curve of the third motor does not deviate from the preset threshold, execute the step of determining the target rotation angle of the motor according to the rotation curve of the third motor.

5. The motor control method based on AI learning according to claim 1, characterized in that Before controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameter, the method further includes: Collect the actual state data of the motor; Judge the deviation degree between the actual state data and the target control parameter; If the deviation degree is not within the acceptable range, return to the step of obtaining the motor state data of the intelligent door lock; If the deviation degree is within the acceptable range, execute the step of controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameter.

6. A motor control device based on AI learning, applied to an intelligent door lock, characterized in that, The device includes: An acquisition module for acquiring the motor state data of the intelligent door lock, including: Collect the pulse signals of the photoelectric sensor, and the photoelectric sensor is installed on the motor of the intelligent door lock; Calculate the rotation angle of the motor based on the pulse signal; Measure the working current of the motor using a preset measuring device, and determine the working current and the rotation angle as the motor state data; A detection module for detecting the opening and closing state of the intelligent door lock; A control module for performing AI learning according to the opening and closing state and the motor state data to obtain a target control parameter, and controlling the motor drive to perform the intelligent door lock opening and closing operation according to the target control parameter; wherein, performing AI learning according to the opening and closing state and the motor state data to obtain a target control parameter includes: Detect whether the intelligent door lock is connected to the network; If the intelligent door lock is connected to the network, obtain the corresponding motor rotation curves of the intelligent door lock and the door locks of the same type as the intelligent door lock; calibrate the motor rotation curve of the intelligent door lock using the motor rotation curves of the door locks of the same type as the intelligent door lock to determine the target rotation angle of the motor, and determine the target rotation angle as the target control parameter; wherein, the motor rotation curve of the intelligent door lock is determined according to the historical rotation angle of the motor of the intelligent door lock; If the intelligent door lock is not connected to the network, obtain the historical operation data of the motor of the intelligent door lock; fit the historical operation data of the motor to obtain an AI learning model; use the AI learning model for prediction to obtain corresponding output parameters; calibrate the output parameters to obtain the target rotation angle of the motor, record the target rotation angle obtained by each calibration and determine it as the target control parameter.

7. An intelligent door lock, characterized in that, The intelligent door lock includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the AI learning-based motor control method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the AI learning-based motor control method according to any one of claims 1 to 5.

Images