WO2023280228A1 - 提示方法及相关设备 - Google Patents

提示方法及相关设备 Download PDF

Info

Publication number
WO2023280228A1
WO2023280228A1 PCT/CN2022/104182 CN2022104182W WO2023280228A1 WO 2023280228 A1 WO2023280228 A1 WO 2023280228A1 CN 2022104182 W CN2022104182 W CN 2022104182W WO 2023280228 A1 WO2023280228 A1 WO 2023280228A1
Authority
WO
WIPO (PCT)
Prior art keywords
knocking
vibration
door lock
doorbell
door
Prior art date
Application number
PCT/CN2022/104182
Other languages
English (en)
French (fr)
Inventor
张新功
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023280228A1 publication Critical patent/WO2023280228A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
    • G07C9/00896—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys specially adapted for particular uses
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B3/00—Audible signalling systems; Audible personal calling systems
    • G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission

Definitions

  • the present application relates to the technical field of terminals, in particular to a prompt method and related equipment.
  • the embodiment of the present application provides a prompting method and related equipment. When there is a knock on the door, the doorbell will ring to improve user experience.
  • the embodiment of the present application provides a reminder method, which is applied to a smart door lock.
  • the smart door lock is installed on the door.
  • the smart door lock includes a doorbell.
  • the method includes: the smart door lock detects the vibration of the door, and the vibration The duration is the first duration; the smart door lock generates the first vibration data based on the vibration; the smart door lock determines one or both of the knocking frequency, the knocking strength, and the identity of the knocking user based on the first vibration data;
  • the door lock notifies the doorbell to ring, and plays the doorbell prompt tone.
  • the doorbell prompt tone is determined based on one or two of the knocking frequency, knocking force, and the identity of the knocking user. Among them, the doorbell prompt tone prompts the knocking user One or more of the volume, rhythm, and intonation of the doorbell prompt tone are determined by one or both of the door knocking frequency and the door knocking strength.
  • the smart door lock can detect the user's door knocking action, and when it is confirmed that there is a door knocking action, notify the doorbell to ring to improve user experience.
  • the method before the smart door lock generates the first vibration data based on the vibration, the method further includes: the smart door lock generates the second vibration data based on the vibration, the second vibration data is in the first part of the first duration The first vibration data is generated during the second part of the first duration, wherein the first part is before the second part; the smart door lock determines that the vibration characteristics indicated by the second vibration data are consistent with the vibration characteristics of the door knocking action. In this way, the smart door lock can preliminarily determine that there is a knocking behavior.
  • the method further includes: the smart door lock detects that a human body approaches the smart door lock. In this way, the smart door lock can enter the normal working mode from the low power consumption mode, and start to detect the user's knocking action.
  • the smart door lock determines one or both of the knocking frequency and the knocking force based on the first vibration data, which specifically includes: the smart door lock determines the knocking frequency based on the first vibration frequency, and the second - The higher the vibration frequency, the higher the door knocking frequency; and/or, the smart door lock determines the knocking force based on the first vibration amplitude, the greater the first vibration amplitude, the greater the knocking force; wherein, the first vibration frequency is the first A frequency of the vibration data, the first vibration amplitude is the amplitude of the first vibration data.
  • the smart door lock can determine the knocking frequency and/or knocking strength based on the first vibration data.
  • the smart door lock determines the identity of the knocking user based on the first vibration data, which specifically includes: the smart door lock preprocesses the first vibration data to obtain the preprocessed first vibration data; The door lock matches the preprocessed first vibration data with the pre-stored door knocking data of the first user, and if the matching is successful, the door knocking user is the first user. In this way, the smart door lock can determine the identity of the user knocking on the door based on the first vibration data.
  • the smart door lock determines the doorbell prompt tone based on one or both of the knocking frequency, the knocking strength, and the identity of the knocking user, specifically including: if the smart door lock determines the knocking frequency Less than the first preset knocking frequency and/or the knocking force is less than the first preset knocking force, then the smart door lock determines that the doorbell sound is the first doorbell sound; or, if the smart door lock determines that the knocking frequency is greater than the first A preset door knocking frequency and/or knocking force is greater than the first preset door knocking force, then the smart door lock determines that the doorbell prompt tone is the second doorbell prompt tone; wherein, the difference between the first doorbell prompt tone and the second doorbell prompt tone One or more of the volume, rhythm, and tone are different, and the content of the first doorbell prompt tone and the content of the second doorbell prompt tone both include the identity of the door-knocking user. In this way, the smart door lock can comprehensively determine the doorbell prompt tone based on one or both
  • the method further includes: the smart door lock uses a camera to collect an image in front of the door; the smart door lock detects that the image in front of the door includes a human figure and/or faces. In this way, for the vibration triggered by no one, the smart door lock can not notify the doorbell to ring.
  • the method further includes: the smart door lock enters a low power consumption mode. In this way, the power consumption of the smart door lock can be reduced.
  • an embodiment of the present application provides an electronic device, which includes one or more processors and one or more memories; wherein, the one or more memories are coupled to the one or more processors, and one or more The multiple memories are used to store computer program codes, and the computer program codes include computer instructions.
  • the electronic device executes the method in any possible implementation manner of the first aspect above.
  • an embodiment of the present application provides a computer storage medium, the computer storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are run on the electronic device, the electronic device is made to perform any of the above-mentioned first aspects.
  • Method in one possible implementation.
  • an embodiment of the present application provides a computer program product, which, when the computer program product is run on a computer, causes the computer to execute the method in any possible implementation manner of the first aspect above.
  • FIG. 1 is a schematic diagram of a system architecture of a smart door lock provided by an embodiment of the present application
  • Fig. 2 is a schematic flowchart of a prompting method provided by the embodiment of the present application.
  • Fig. 3 is a schematic flowchart of another prompting method provided by the embodiment of the present application.
  • Fig. 4 is a schematic structural diagram of an intelligent door lock provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a chip system provided by an embodiment of the present application.
  • the embodiment of the present application provides a prompting method.
  • the smart door lock can detect the knocking vibration (that is, the vibration of the door triggered by the user's knocking action), collect the vibration data generated by the knocking vibration, and then identify the door based on the collected vibration data. Knock on the user's identity and determine whether the doorbell needs to ring. If it is confirmed that the doorbell needs to ring, the smart door lock can also play different doorbell prompts based on the frequency and/or amplitude of the collected vibration data. In this way, the doorbell ringing phenomenon caused by vibrations other than the vibration generated by the door knocking action can be prevented, the diversity of the doorbell prompt tone is increased, and the user experience is improved.
  • Question 2 How to identify the identity of the knocking user based on the data collected based on the vibration triggered by the user knocking on the door.
  • the embodiment of the present application uses the vibration module to obtain the vibration data collected by the gyroscope. If it is detected that the vibration data exceeds the preset threshold, the vibration data will be continuously collected for a period of time (such as 2 seconds, 3 seconds, etc.). Noise reduction, envelope extraction, template matching (and/or envelope fitting)/machine learning offline diagnosis, etc. are performed on the vibration data to further determine whether the user has knocked on the door, that is, whether a knock event has occurred.
  • the embodiment of the present application establishes a gyroscope angular velocity vibration data template feature library and an offline diagnosis library, based on the offline diagnosis library to identify the identity of the knocking user, and the same user knocks the door using the same knocking method, which can be used without networking.
  • the user identification is completed in the state.
  • the embodiment of the present application adds an image decision-making module and a ringing decision-making module.
  • the ringing decision-making module comprehensively judges whether the doorbell needs to ring by collecting data from the image decision-making module and the vibration module, thereby eliminating false triggering/misidentification.
  • the doorbell ringing that is, the vibration triggered by no one, will not produce the doorbell ringing.
  • the embodiment of the present application can also determine the urgency and strength of knocking on the door based on the frequency and amplitude of the angular velocity vibration model, and the frequency and amplitude of the door knocking vibration. Further, it can be played based on different urgency and strength of door knocking. Different doorbell prompt tones, that is, the degree of urgency (vibration frequency) of knocking on the door is different, and the strength (vibration amplitude) of knocking on the door is different, so the played doorbell prompt tones are also different.
  • a schematic diagram of the system architecture of the smart door lock 100 provided by the embodiment of the present application is introduced below.
  • the system architecture may include a low-power system, a decision-making module, an image acquisition and processing module, a vibration module, an operation and maintenance module, a hardware adaptation module, a hardware layer (or called a hardware module), etc.
  • the low-power system interacts with the ringing decision-making module. After the ringing decision-making module detects and recognizes a valid knock event, it can report the decision result to the low-power system. The decision result is used to indicate that the low-power system triggers The doorbell rings.
  • the system architecture includes a plurality of modules, and each module includes a plurality of sub-modules (also called sub-components).
  • each module includes a plurality of sub-modules (also called sub-components).
  • sub-modules also called sub-components.
  • the decision-making module is a background resident process in a low-power system, which can be based on a software operating system (operating system, OS), such as Huawei's Hongmeng operating system etc., providing the operation and maintenance of ringing decision-making and gyroscope data detection threads.
  • the decision-making module is responsible for summarizing and judging the detection results, so as to decide whether to initiate a doorbell ringing event.
  • the decision-making module may include two sub-modules: a ringing decision-making module and an image decision-making module.
  • the ringing decision-making module can receive the door-knock matching result sent by the vibration module, and judge the door-knocking matching result, so as to determine whether there is a door-knocking event.
  • face detection result request after receiving the human figure and/or face detection result sent by the image decision module, the ringing decision module can comprehensively decide whether to initiate the doorbell based on the door knocking matching result and the human figure and/or face detection result Ringing event, if so, further determine the corresponding doorbell prompt tone to be played based on the door knocking matching result.
  • the image decision-making module can receive the request for obtaining human figure and/or face detection results sent by the ringing decision-making module.
  • the image acquisition and processing module can perform a series of processing on the front door image collected by the camera to obtain the human figure and/or face detection result, and send the human figure and/or face detection result to the image decision module. If the image decision-making module determines that there is indeed a human figure and/or face based on the human figure and/or face detection result, the image decision module can send the human figure/face detection result sent by the image acquisition and processing module to the ringing decision module.
  • Image acquisition and processing module 1.
  • the image acquisition and processing module is responsible for the acquisition, preprocessing, detection and reporting of the detection results of the images in front of the door.
  • the image acquisition and processing module may include four sub-modules: an image acquisition module, an image preprocessing module, an image detection module, and a result reporting module.
  • the image acquisition module can obtain the image data in front of the door collected by the camera, and send the image data in front of the door collected by the camera to the image preprocessing module.
  • the image data in front of the door acquired by the image acquisition module may also be image data in front of the door collected by a camera processed by an image signal processor.
  • Image preprocessing module
  • the image preprocessing module can perform image preprocessing on the image data in front of the door sent by the image acquisition module, and send the preprocessed image data in front of the door to the image detection module.
  • Image preprocessing can eliminate irrelevant information in the image, restore useful real information, simplify image data to the greatest extent, and improve the detectability of relevant information.
  • the steps of image preprocessing may include but not limited to the following steps: image down-sampling, image filtering, image smoothing, image enhancement and so on.
  • the image detection module can receive the preprocessed image in front of the door sent by the image preprocessing module, and then perform human shape and/or face detection on the preprocessed image data in front of the door to obtain a human shape and/or face detection result, and Human figure and/or face detection results are sent to the result reporting module.
  • the result reporting module can receive the human figure and/or face detection result sent by the image detection module, and send the human figure and/or face detection result to the image decision module.
  • the vibration module is responsible for obtaining the data collected by the gyroscope, and performing noise reduction, envelope extraction, and door knocking event identification on the data collected by the gyroscope.
  • the vibration module can include six sub-modules: data acquisition module, data noise reduction module, envelope extraction module, door knock matching module, low power consumption operation and maintenance module, and calibration module.
  • the data acquisition module can obtain the angular velocity data collected by the gyroscope, and send the angular velocity data collected by the gyroscope to the data noise reduction module.
  • the data noise reduction module can receive the angular velocity data collected by the gyroscope sent by the data acquisition module, and perform noise reduction processing on the angular velocity data collected by the gyroscope, obtain the gyroscope data after the noise reduction processing, and convert the gyroscope data after the noise reduction processing The data is sent to the extract envelope module.
  • the steps of noise reduction processing may include but not limited to the following steps: removal of constant value drift, angle random walk, rate random walk, quantization noise and rate ramp, etc.
  • Extract the envelope module :
  • the envelope extraction module can receive the gyroscope data after noise reduction processing sent by the data noise reduction module, and perform envelope extraction on the gyroscope data after noise reduction processing to obtain envelope data, and send the envelope data to Knock Matching modules.
  • Envelope extraction is to extract the envelope of the gyroscope data after noise reduction processing, and the methods of envelope extraction include but not limited to the following methods: wave detection method, Hilbert (Hilbert) transform, and the like.
  • envelope extraction methods used in the embodiment of the present application are all existing technologies, and related materials in the prior art may be referred to, and details are not repeated here.
  • the door knock matching module can receive the envelope data sent by the envelope extraction module, and then use the established template feature library and offline diagnosis library to perform template matching/neural network offline diagnosis on the envelope data to obtain the door knock matching result, and The door knock matching result is sent to the ringing decision module.
  • the door knocking matching result may include whether there is a door knocking event, the frequency and/or strength of the door knocking, and the identity of the door knocking user (who is knocking on the door).
  • the low-power operation and maintenance module can maintain the low-power mode of the gyroscope.
  • the passive infrared sensor Passive Infra-Red, PIR
  • the low-power operation and maintenance module can interrupt the gyroscope.
  • the low-power mode of the gyroscope puts the gyroscope into normal detection mode.
  • the calibration module can calibrate the gyroscope after power-on.
  • the gyroscope may have its own calibration function. In this case, no calibration module may be configured in the vibration module.
  • the operation and maintenance module is responsible for the operation and maintenance of each component in the process of knocking and vibrating to turn the doorbell (also called the process of ringing detection), that is, the monitoring and configuration of component running status.
  • the operation and maintenance module can In the process, configuration management, log collection and storage, system operation status statistics and reporting, etc. are performed to provide dynamic operation parameters for the ringing decision module.
  • the operation and maintenance module can include three sub-modules: statistics module, log module, and configuration management module.
  • the statistical module can summarize and count the running status of each component, and report it to the low-power system.
  • the log module can collect the logs of each component, and store the logs locally or send them to the low-power system for storage in the low-power system.
  • the configuration management module can provide configuration capabilities, and can customize the static operating parameters of each component, such as component startup mode, component operation mode, and component health status.
  • the hardware adaptation module is responsible for shielding hardware differences, and provides standard capability interfaces for sub-modules in the vibration module and image acquisition and processing module.
  • the hardware adaptation module may include four sub-modules: image signal processor (Image Signal Processor, ISP) driver, gyroscope (gyroscope, GYRO) driver, passive infrared sensor (Passive Infra-Red, PIR) driver, and other sensor drivers.
  • image signal processor Image Signal Processor, ISP
  • gyroscope gyroscope, GYRO
  • PIR Passive Infra-Red
  • the image signal processor driver can shield the hardware difference of the image signal processor, and provide a standard acquisition interface for the image acquisition and processing module.
  • Gyroscope driver
  • the gyroscope driver can shield the hardware differences of the gyroscope, and provide a standard acquisition interface and operation and maintenance interface for the vibration module.
  • the passive infrared sensor driver can shield the hardware differences of the passive infrared sensor and provide a standard interface to the ringing decision-making module, so that the passive infrared sensor can instruct the ringing decision-making module to start the ringing detection process after detecting a living body approaching the smart door lock.
  • Other sensor drivers may include one or more sensor drivers other than those shown in the figure, which may shield hardware differences of one or more other sensors and provide standard interfaces.
  • the doorbell driver can shield the hardware differences of the doorbell and provide a standard interface, so that the doorbell can be driven to ring when the door knocking behavior occurs.
  • the hardware layer is responsible for using multiple different hardware to complete the hardware implementation of steps such as gyroscope data acquisition, human figure/face image acquisition, and doorbell ringing involved in the process of knocking on the door, vibrating and turning the doorbell.
  • the hardware layer can include gyroscopes, passive infrared sensors, doorbells, image sensors, image signal processors, and other sensors.
  • the gyroscope may collect vibration data generated during door knocking, where the vibration data may include angular velocity data of the gyroscope and the like.
  • Passive infrared sensors can sense motion by detecting energy generated by a living body in motion, such as a human body. For example, when a human body approaches the smart door lock, the passive infrared sensor can detect the moving human body and instruct the ringing decision module to start the ringing detection process.
  • the doorbell can receive instructions or actions that trigger the ringing, and play the specified doorbell prompt tone.
  • the image sensor is an integral part of the camera.
  • a camera may include a lens and an image sensor for capturing images.
  • the object can generate an optical image through the lens and project it onto the image sensor.
  • the image sensor can convert the optical signal into an electrical signal, and then pass the electrical signal to the image signal processor to convert it into a digital image signal, such as standard RGB, YUV and other formats. image signal.
  • the camera can receive an instruction to collect an image in front of the door sent by the image acquisition and processing module, then collect image data in front of the door, and send the collected image data in front of the door to the image signal processor.
  • the image signal processor can receive the image data in front of the door collected and sent by the camera, and process the image data in front of the door.
  • the image signal processor can convert the image data collected by the camera into an image visible to the naked eye, and can also optimize the algorithm of image noise, brightness, skin color, etc., and can also optimize the exposure, color temperature and other parameters of the shooting scene, etc. .
  • the image signal processor can also be arranged in the camera.
  • Other sensors may include one or more sensors other than those shown in the figures, such as fingerprint sensors, pressure sensors, touch sensors, and the like.
  • system architecture of the smart door lock 100 (also referred to as the electronic device 100) shown in FIG. 1 is only an example, and the system architecture may also include more other modules (for example, a lock module, an unlock module, etc.) or other components, or may include fewer modules or components, or may combine two or more modules or components, or may include different module or component configurations. Examples are not limited to this.
  • FIG. 2 exemplarily shows a flow of a prompting method provided by an embodiment of the present application.
  • the prompting method can be applied to the smart door lock 100, and the smart door lock 100 can be installed on the door.
  • the specific steps of the prompting method are described in detail below:
  • Phase 1 Trigger the execution of the ringing detection process
  • the passive infrared sensor PIR detects that a living body approaches, it sends an instruction to start ringing detection to the ringing decision module.
  • the passive infrared sensor PIR can sense motion by detecting energy generated by a moving living body (such as a human body).
  • a moving living body such as a human body
  • the passive infrared sensor PIR can detect that a moving human body is close to the smart door lock 100, and then the passive infrared sensor PIR can send an instruction to start the ringing detection to the ringing decision-making module. It is used to instruct the ringing decision module to trigger the execution of the ringing detection process.
  • the ringing decision module sends an instruction to start the vibration module to the vibration module.
  • the ringing decision-making module After the ringing decision-making module receives the instruction to start ringing detection sent by the passive infrared sensor PIR, it can send an instruction to start the vibration module to the vibration module, which is used to instruct the vibration module to start, that is, the vibration module can start from Low-power mode enters normal operating mode.
  • the vibration module sends an instruction to start the gyroscope to the gyroscope.
  • the vibration module may send an instruction for starting the gyroscope to the gyroscope, where the instruction is used to instruct the gyroscope to start.
  • the gyroscope exits the low power consumption mode and starts to collect vibration data.
  • the gyroscope can start to start after receiving the instruction to start the gyroscope sent by the vibration module, that is, the gyroscope can exit the low power consumption mode, enter the normal detection mode, and start collecting vibration data.
  • the vibration data may include but not limited to the angular velocity data of the gyroscope and the like.
  • the vibration module sends a request for obtaining vibration data 1 to the gyroscope, and then the gyroscope sends the vibration data 1 to the vibration module.
  • the vibration module may send a request for acquiring vibration data 1 to the gyroscope, and the gyroscope may send the vibration data 1 to the vibration module after receiving the request.
  • the vibration data 1 can be used by the vibration module to judge whether there is vibration data generated during the door knocking vibration triggered by the user's door knocking behavior in the vibration data 1 .
  • the vibration module can directly read the vibration data 1 collected by the gyroscope.
  • the vibration module determines that the vibration data 1 contains vibration data generated by knocking on the door.
  • the vibration module can store the vibration data 1 sent by the gyroscope in a certain time window (sliding window), assuming that the above-mentioned certain time window is 1 second , corresponding to the vibration data 1 sent by the gyroscope is 50 angular velocity data (or called angular velocity detection value), then, the vibration module can judge whether there is an angular velocity value exceeding the preset threshold in the above 50 angular velocity data, if there is an angular velocity value exceeding The angular velocity value of the preset threshold value, the vibration module can determine that there is vibration data generated during the door knocking vibration triggered by the user's door knocking behavior (also called a door knocking action) in the vibration data 1.
  • a certain time window sliding window
  • the vibration module can judge whether there is an angular velocity value exceeding the preset threshold in the above 50 angular velocity data, if there is an angular velocity value exceeding The angular velocity value of the preset threshold value, the vibration module can determine that there is vibration data generated
  • the vibration module may determine that the vibration characteristics indicated by the above 50 angular velocity data are consistent with the vibration characteristics of the door knocking behavior, and if they match, the vibration module initially determines that there is a door knocking behavior.
  • the vibration module sends a request for obtaining vibration data 2 to the gyroscope, and then the gyroscope sends the vibration data 2 to the vibration module.
  • the vibration module may send a request for obtaining vibration data 2 to the gyroscope, and the gyroscope may send the vibration data 2 to the vibration module after receiving the request.
  • the vibration data 2 can be used by the vibration module to complete subsequent steps in the ringing detection process based on the vibration data 2 .
  • the vibration module can directly read the vibration data 2 collected by the gyroscope.
  • the vibration module obtains the door-knock matching result based on the vibration data 2, and sends the door-knock matching result to the vibration decision-making module.
  • the vibration module can preprocess the vibration data 2, and then use the established template feature library and offline diagnosis library to perform preprocessing on the preprocessed vibration data 2 Template matching/neural network offline diagnosis, get knock matching results. Afterwards, the vibration module can send the knock matching result to the vibration decision-making module.
  • the door knocking matching result may include information for determining whether there is a door knocking event. If so, the door knocking matching result may also include knocking frequency and/or knocking force, identity of the knocking user (who is knocking) and other information.
  • the above-mentioned vibration data 2 may be the vibration data continuously collected by the gyroscope for a period of time (such as 2 seconds, 3 seconds, etc.). .
  • the process for the vibration module to preprocess the vibration data 2 may include but not limited to the following steps:
  • the data noise reduction processing performed by the vibration module on the vibration data 2 can be realized by adopting the principle of wavelet denoising.
  • the wavelet denoising process mainly includes three basic steps: perform wavelet transform on the noise-containing signal; perform certain processing on the transformed wavelet coefficients to remove the noise contained in them; perform wavelet inverse transform on the processed wavelet coefficients to obtain the denoising signal.
  • noisy signal After performing wavelet denoising on the signal containing noise, many noise signals can be obviously removed, and the signal after wavelet denoising can become smoother.
  • the vibration module may use a wave detection method or a Hilbert transform to perform envelope extraction on the vibration data 2 after data noise reduction processing, so as to obtain envelope data.
  • the embodiment of the present application only uses the detection method or the Hilbert transform as an example to illustrate the envelope extraction process, and is not limited thereto.
  • the envelope extraction process can also use other methods, which are not limited in the embodiment of the present application.
  • the vibration module uses the established template feature library and offline diagnosis library to perform template matching/neural network offline diagnosis on the preprocessed vibration data 2.
  • the specific process is as follows:
  • the vibration module identifies whether there is a knock on the door:
  • the vibration module may perform template matching on the preprocessed vibration data 2 and the pre-stored door knocking vibration data template. If the matching is successful, the vibration module determines that a door knocking event has occurred.
  • the vibration module can input the preprocessed vibration data 2 into the neural network model (or offline diagnosis library) that has been trained in advance to perform neural network offline diagnosis (that is, machine learning offline diagnosis), if the recognition accuracy rate is higher than the preset recognition accuracy rate threshold, the vibration module determines that there is a door knocking event.
  • the neural network model or offline diagnosis library
  • the vibration module determines the knocking frequency and/or knocking force:
  • the vibration module can obtain the frequency and amplitude of the angular velocity data in the preprocessed vibration data 2 based on the preprocessed vibration data 2. Further, the vibration module can determine the knocking frequency based on the frequency of the angular velocity data, and the frequency of the angular velocity data The higher the frequency, the higher the knocking frequency. The vibration module can also determine the knocking force based on the amplitude of the angular velocity data. The greater the amplitude of the angular velocity data, the greater the knocking force.
  • the vibration module determines the identity of the knocking user (who is knocking):
  • the vibration module can identify the identity of the knocking user based on the same knocking habit of the same user, that is, the same user knocks in the same way, and the vibration module can identify the identity of the knocking user.
  • the vibration module can perform template matching on the pre-processed vibration data 2 and the pre-stored door-knocking vibration data of all door knocking users. If the pre-processed vibration data 2 matches one of the pre-stored If the door-knocking vibration data of the door-knocking user 1 is successfully matched, the vibration module can determine that the door-knocking user is the door-knocking user 1 .
  • the vibration module can input the preprocessed vibration data 2 into the neural network model (or called offline diagnosis library) of multiple door-knocking users that has been trained in advance to perform neural network offline diagnosis. Diagnosis (that is, machine learning offline diagnosis), if the recognition accuracy obtained by using the neural network model of the door knocker 1 that has been trained in advance is higher than the preset recognition accuracy threshold, the vibration module can determine that the door knocker is the door knocker User 1.
  • the identity of the door-knocking user identified by the vibration module does not match the pre-stored door-knocking user/the recognition accuracy rate is lower than the preset recognition accuracy threshold, for example, the door-knocking user's knocking
  • the door vibration data is not pre-stored, or the door-knocking user who has pre-stored the door-knocking vibration data intentionally uses a different knocking method to knock on the door, then the vibration module can output the identity of the door-knocking user as an "unknown user".
  • the vibration module may not perform steps S206 and S209, and the gyroscope may not perform steps S207 and S210, but the vibration module may actively read the vibration collected by the gyroscope according to the needs of the ringing detection process. data, and execute step S208 and step S211 based on the read vibration data collected by the gyroscope.
  • the vibration module may not perform steps S206 and S209, but the gyroscope actively performs steps S207 and S210, and sends the collected vibration data to the vibration module in real time.
  • Stage 3 Execute the ringing decision process
  • the ringing decision module determines that there is a door knock event based on the door knock matching result.
  • the ringing decision module can judge whether there is a door knocking event, and if so, the ringing decision module executes step S214. If not, the subsequent steps do not need to be performed again.
  • the vibration module may also send the door knocking matching result to the ringing decision module when it is determined that a door knocking event occurs, and does not need to send the ringing result to the ringing decision module when it is determined that no door knocking event occurs.
  • the decision module sends the knock matching result.
  • the ringing decision-making module sends a request to the image decision-making module to obtain a human figure and/or face detection result.
  • the ringing decision-making module can send a request to the image decision-making module to obtain the human figure and/or face detection result, which is used to request the image decision-making module to send the human figure and/or face detection result.
  • the image decision-making module sends an instruction to perform human figure and/or face detection to the image acquisition and processing module.
  • the image decision-making module After the image decision-making module receives the request for obtaining the human figure and/or face detection result sent by the ringing decision module, it can send an instruction to perform human figure and/or face detection to the image acquisition and processing module for instructing The image acquisition and processing module performs human shape and/or face detection.
  • the image acquisition and processing module detects the human figure and/or face, obtains the human figure and/or face detection result, and sends the human figure and/or face detection result to the image decision module.
  • the image acquisition and processing module after the image acquisition and processing module receives the instruction for human figure and/or face detection sent by the image decision module, it can send an instruction to the camera to collect the image in front of the door, and the instruction is used to instruct the camera to collect the image in front of the door, Further, the image acquisition and processing module can acquire the image data in front of the door collected by the camera, and preprocess the image data in front of the door, and then perform human figure and/or face detection on the preprocessed image data in front of the door, so as to obtain Human shape and/or face detection results. Afterwards, the image acquisition and processing module can send the human figure and/or face detection result to the image decision module.
  • the image data in front of the door collected by the camera may be image data in front of the door for a certain number of frames (for example, 5 frames) or a period of time (for example, 150 ms) continuously collected by the camera.
  • the human figure and/or human face detection result may include whether there is a human figure and/or human face in the image data in front of the door.
  • the camera can always collect the image in front of the door, instead of starting to collect the image in front of the door after receiving an instruction to collect the image in front of the door, the image acquisition and processing module can only obtain a certain number of frames or a segment of the latest image collected by the camera. Time-gated image data.
  • step S215 is optional, and the image acquisition and processing module may periodically perform human shape and/or face detection, and periodically send the human shape and/or face detection results to the image decision module.
  • the image decision module determines that there is a human figure and/or face in front of the door based on the human figure and/or face detection result, and sends the human figure and/or face detection result to the ringing decision module.
  • the image decision-making module After the image decision-making module receives the human figure and/or the human face detection result sent by the image acquisition and processing module, it can judge whether the human figure and/or human face are in front of the door, and if so, send the human figure and the human face to the ringing decision module. /or face detection results.
  • the image decision-making module may not send the human shape and/or face detection result to the ringing decision-making module, and the subsequent steps will not be executed again.
  • the ringing decision module comprehensively determines the doorbell ringing event and the corresponding doorbell prompt tone to be played based on the door knocking matching result and the human figure and/or face detection result, and sends the doorbell ringing initiation to the low-power system request, the corresponding doorbell tone to be played.
  • the ringing decision module can comprehensively determine whether to initiate a doorbell ringing event based on the door knocking matching result and the human figure and/or face detection result.
  • the ringing decision module determines that there is a figure and/or face in front of the door based on the human figure and/or face detection result sent by the image decision module, and before in step S213, the ringing decision module based on the door knocking matching result Having determined that there is a door knocking event, the ringing decision module can comprehensively determine that a doorbell ringing event needs to be initiated.
  • the ringing decision module can also determine the corresponding doorbell prompt tone to be played based on the knocking frequency and/or knocking force in the knocking matching result, and the identity of the knocking user (who is knocking on the door). Wherein, the ringing decision-making module determines that the corresponding doorbell prompt tone to be played includes but is not limited to the following three possible implementations:
  • the ringing decision module can determine the corresponding doorbell tone to be played based only on the knocking frequency and/or knocking strength in the door knocking matching result:
  • the knocking frequency is less than a certain preset frequency threshold (ie, the frequency of the angular velocity vibration model), and/or, the knocking force is less than a certain preset force threshold (ie, the amplitude of the angular velocity vibration model), it may indicate
  • a certain preset frequency threshold ie, the frequency of the angular velocity vibration model
  • the knocking force is less than a certain preset force threshold (ie, the amplitude of the angular velocity vibration model)
  • the doorbell notification sound can be a piece of preset music with a relatively gentle rhythm or a simple "ding dong ⁇ ding dong ⁇ ding dong ⁇ " sound or the like.
  • the volume of the doorbell prompt tone can be lower, and the tone of the doorbell prompt tone can be softer.
  • the knocking frequency when the knocking frequency is greater than a certain preset frequency threshold, and/or, when the knocking force is greater than a certain preset force threshold, it may indicate that the knocking user is performing an abnormal knocking action, that is, the knocking user may If there is something urgent, or the user who knocks on the door may be committing vandalism, then the rhythm of the doorbell prompt tone can be more urgent, and the doorbell prompt tone can be an alarm tone, such as a quick "beep beep beep", or "found Abnormal behavior, please pay attention to safety! and so on.
  • the volume of the doorbell prompt tone can be higher, and the tone of the doorbell prompt tone can be rougher.
  • the ringing decision module can also preset a plurality of door-knocking frequency ranges, and each door-knocking frequency range corresponds to one or more different doorbell prompts in rhythm, volume, and intonation. For example, in different knocking frequency ranges, the lower the knocking frequency, the gentler the rhythm of the doorbell notification, the lower the volume, and the gentler the tone; the higher the knocking frequency, the more urgent the rhythm of the doorbell notification. The louder the volume can be, the rougher the tone can be.
  • the ringing decision-making module may first determine which door-knocking frequency range interval the door-knocking frequency is in, and then determine the doorbell prompt tone corresponding to the door-knocking frequency range interval.
  • the ringing decision module can also pre-set a plurality of door knocking strength range intervals, and each door knocking strength range interval corresponds to one or more different doorbell prompts in a rhythm, volume, and intonation .
  • each door knocking strength range interval corresponds to one or more different doorbell prompts in a rhythm, volume, and intonation .
  • the ringing decision module can first determine which knocking force range interval the door knocking force is in, and then determine the doorbell prompt tone corresponding to the door knocking force range range.
  • one or more of the rhythm, volume, and intonation of the doorbell tone is determined by the door knocking frequency and/or the door knocking force. Therefore, the doorbell tone can reflect the door knocking frequency and/or or knocking strength.
  • the ringing decision module can determine the corresponding doorbell tone to be played only based on the identity of the knocking user (who is knocking) in the knock matching result:
  • the doorbell prompt tone may be "Xiaohong is here", or , "Xiaohong is knocking on the door” and so on.
  • the doorbell prompt tone may be "welcome the guest", or "the guest is coming” and so on.
  • the content of the doorbell prompt tone includes the identity of the door knocking user, therefore, the doorbell prompt tone may reflect the identity of the door knocking user.
  • the ringing decision module can comprehensively determine the corresponding doorbell prompt tone to be played based on the knocking frequency and/or knocking force in the knocking matching result and the identity of the knocking user (who is knocking on the door) :
  • the knocking frequency is less than a certain preset frequency threshold, and/or, the knocking force is less than a certain preset force threshold, and it is confirmed that the knocking user is a pre-stored user, for example, the knocking user is user 1 , assuming that the name of user 1 is "Xiaohong", the doorbell prompt tone can be "Ding Dong ⁇ Xiaohong is here", or "Ding Dong ⁇ Xiaohong is knocking on the door", etc., that is, the rhythm of the doorbell prompt tone It can be relatively gentle, and the content of the doorbell prompt tone includes the identity of the door knocking user (for example, the name of the door knocking user).
  • the volume of the doorbell prompt tone can be lower, and the tone of the doorbell prompt tone can be softer.
  • the knocking frequency is greater than a certain preset frequency threshold, and/or, the knocking force is greater than a certain preset force threshold, and it is confirmed that the knocking user is a user pre-stored by the owner, for example, the knocking user is a user 1, assuming that the name of user 1 is "Xiaohong", the doorbell prompt tone can be "Xiaohong is here, the owner quickly opens the door", or "Xiaohong is initiating abnormal behavior, please pay attention to safety! etc., That is, the rhythm of the doorbell prompt tone can be relatively urgent, and the content of the doorbell prompt tone includes the identity of the door knocking user (such as the name of the door knocking user).
  • the volume of the doorbell prompt tone can be higher, and the tone of the doorbell prompt tone can be rougher.
  • the doorbell prompt tone can be "welcome guest Come", or, "guests are coming" and so on, that is, the rhythm of the doorbell prompt tone can be relatively gentle, and the content of the doorbell prompt tone includes the identity of the door-knocking user, for example, the identity of the door-knocking user can be "guest”.
  • the volume of the doorbell prompt tone can be lower, and the tone of the doorbell prompt tone can be softer.
  • the doorbell prompt tone can be "stranger". Come, open the door quickly", or, "The stranger is initiating abnormal behavior, please pay attention to safety! and so on, that is, the rhythm of the doorbell notification tone can be more urgent, and the content of the doorbell notification tone includes the identity of the knocking user, For example, the identity of the door knocking user may be "stranger".
  • the volume of the doorbell prompt tone can be higher, and the tone of the doorbell prompt tone can be rougher.
  • one or more of the rhythm, volume, and intonation of the doorbell notification tone is determined by the knocking frequency and/or knocking force, and the content of the doorbell notification tone includes the knocking user's Therefore, the doorbell prompt tone can not only reflect the knocking frequency and/or knocking strength, but also reflect the identity of the knocking user.
  • the doorbell prompt tone may not prompt the identity of the door knocking user, that is, the content of the doorbell prompt tone may not include the identity of the door knocking user.
  • the ringing decision module determines the doorbell ringing event and the corresponding doorbell prompt tone to be played, it can send a request to initiate the doorbell ringing and the corresponding doorbell prompt tone to be played to the low power consumption system.
  • corresponding doorbell prompt tones to be played are only some examples, and the corresponding doorbell prompt tones to be played may also be other, which is not limited in this embodiment of the present application.
  • the low power consumption system sends to the doorbell an instruction to initiate the doorbell ringing and the corresponding doorbell prompt tone to be played.
  • the low-power system can send an instruction to initiate doorbell ringing, the corresponding doorbell tone to be played to the doorbell. Chime to trigger the doorbell to ring.
  • the low-power system may not send the doorbell an instruction to initiate the doorbell ringing, and the corresponding doorbell prompt tone to be played, that is, the doorbell ringing will not be triggered.
  • the doorbell after the doorbell receives the instruction to start the doorbell ringing sent by the low-power system and the corresponding doorbell prompt tone to be played, it can execute the ringing action and play the corresponding doorbell prompt tone, thereby realizing door knocking vibration switching. Ring the doorbell.
  • the low-power system sends an instruction to enter the low-power mode to the ringing decision-making module, the ringing decision-making module enters the low-power mode, the ringing decision-making module sends an instruction to enter the low-power mode to the vibration module, and the vibration module Entering the low power consumption mode, the vibration module sends an instruction to enter the low power consumption mode to the gyroscope, and the gyroscope enters the low power consumption mode.
  • the low-power system can send an instruction to enter the low-power mode to the ringing decision-making module, so that the ringing decision-making module enters the low-power consumption mode. Further, the ringing decision-making module can send The vibration module sends an instruction to enter the low-power mode, so that the vibration module enters the low-power mode. Further, the vibration module can send an instruction to the gyroscope to enter the low-power mode, so that the gyroscope enters the low-power mode, reducing Sampling frequency of the gyroscope.
  • the smart door lock can detect the door knocking vibration (that is, the vibration of the door triggered by the user's knocking action), collect the vibration data generated by the door knocking vibration, and then identify the door based on the collected vibration data. Knock on the user's identity and determine whether the doorbell needs to ring. If it is confirmed that the doorbell needs to ring, the smart door lock can also play different doorbell prompts based on the frequency and/or amplitude of the collected vibration data. In this way, the doorbell ringing phenomenon caused by vibrations other than the vibration generated by the door knocking action can be prevented, the diversity of the doorbell prompt tone is increased, and the user experience is improved.
  • the door knocking vibration that is, the vibration of the door triggered by the user's knocking action
  • FIG. 3 exemplarily shows the flow of another prompting method provided by the embodiment of the present application.
  • the prompting method can be applied to the smart door lock 100, and the smart door lock 100 can be installed on the door.
  • the specific steps of the prompting method are described in detail below:
  • PIR detects that there is a living body approaching the smart door lock 100, the gyroscope exits the low power consumption mode and enters the detection mode, and collects vibration data
  • the smart door lock 100 can detect a moving human body approaching the smart door lock 100 through the passive infrared sensor PIR, and then the smart door lock 100 can instruct the gyroscope to exit the low power consumption mode. mode, enter the detection mode, and start collecting vibration data.
  • step S301 to step S302 reference may be made to the relevant content of step S201 to step S205 in FIG. 2 , which will not be repeated here.
  • the smart door lock 100 judges whether the vibration data is abnormal.
  • the smart door lock 100 can judge whether the vibration data collected by the gyroscope is abnormal, that is to say, the smart door lock 100 can judge whether the vibration data collected by the gyroscope is abnormal. Whether the collected vibration data is the vibration data generated during the door knocking vibration triggered by the user knocking on the door. If yes, the smart door lock 100 determines that the vibration data collected by the gyroscope is normal data; if not, the smart door lock 100 determines that the vibration data collected by the gyroscope is abnormal data.
  • the smart door lock 100 can determine whether the magnitude of the angular velocity data exceeds a preset threshold in the angular velocity data collected by the gyroscope within a certain time window, and if , the smart door lock 100 may continue to acquire the angular velocity data collected by the gyroscope for a period of time, and perform subsequent steps to perform subsequent related processing on the angular velocity data within this period of time.
  • the smart door lock 100 determines that the vibration data is interference data.
  • the smart door lock 100 may further determine that the abnormal data is interference data.
  • the smart door lock 100 Based on the vibration data, the smart door lock 100 performs data noise reduction, envelope extraction, and door knocking behavior recognition.
  • the smart door lock 100 can perform data noise reduction, envelope extraction, door knocking behavior recognition, etc. based on the vibration data. , that is, the smart door lock 100 determines that there is a door knocking event, and the smart door lock 100 can continue to perform subsequent steps.
  • step S305-step S307 for the specific execution process of step S305-step S307, reference may be made to the relevant content of step S211 to step S212 in FIG. 2 , which will not be repeated here.
  • the smart door lock 100 makes a ringing decision and an image decision, and if the decision is passed, the doorbell rings.
  • the smart door lock 100 can make a ringing decision and an image decision, comprehensively determine whether to initiate a doorbell ringing event, and if the decision is passed, notify the doorbell to ring.
  • step S308-step S310 for the specific execution process of step S308-step S310, reference may be made to the relevant content of step S213 to step S223 in FIG. 2 , which will not be repeated here.
  • the first duration may be the duration of the vibration of the door generated by knocking on the door
  • the first vibration data may be vibration data 2
  • the second vibration data may be vibration data 1
  • the first part of the first duration may be is the certain time window described above corresponding to the vibration data 1
  • the second part of the second duration can be the duration of continuous collection of the vibration data 2
  • the first vibration frequency can be the frequency of the first vibration data
  • the first vibration amplitude It can be the amplitude of the first vibration data
  • the first user can be user 1
  • the first preset knocking frequency can be a certain preset frequency threshold
  • the first preset knocking force can be a certain preset force threshold
  • the first preset knocking frequency can be a certain preset force threshold.
  • a doorbell prompt tone can be the doorbell prompt tone played when the knocking frequency is less than the first preset knocking frequency and/or the knocking force is less than the first preset knocking force
  • the second doorbell prompt tone can be the knocking frequency
  • Fig. 4 exemplarily shows the structure of a smart door lock 100 provided by the embodiment of the present application.
  • the smart door lock 100 may include: a processor 401 , a memory 402 , a sensor 403 , a doorbell 404 , a bus 405 , a camera 406 , and a power supply 407 . These components may be connected by a bus 405 . in:
  • the processor 401 can be used to read and execute computer-readable instructions, and includes one or more processing cores.
  • the processor 401 executes various functional applications and information processing by running software programs and modules.
  • the processor 401 may mainly include a controller, an arithmetic unit, and a register.
  • the controller is mainly responsible for instruction decoding, and sends out control signals for the operations corresponding to the instructions.
  • the arithmetic unit is mainly responsible for performing fixed-point or floating-point arithmetic operations, shift operations, and logic operations, and can also perform address operations and conversions.
  • the register is mainly responsible for saving the register operands and intermediate operation results temporarily stored during the execution of the instruction.
  • the hardware architecture of the processor 401 may be an application specific integrated circuit (Application Specific Integrated Circuits, ASIC) architecture, MIPS architecture, ARM architecture, or NP architecture, etc.
  • the memory 402 is connected to the processor 401 through a bus 405 .
  • Memory 402 may be used to store various software programs and/or sets of program instructions.
  • the processor 401 is configured to execute at least one program instruction, so as to implement the technical solutions of the foregoing embodiments. Its implementation principle and technical effect are similar to those of the related embodiments of the method above, and will not be repeated here.
  • the sensor 403 is connected to the processor 401 through the bus 405 and can be used to collect various sensory data.
  • the sensor 403 may include one or more sensors, for example, a gyro sensor, a pressure sensor, a fingerprint sensor, a touch sensor, and the like.
  • the sensor 403 may include a gyroscope sensor and a passive infrared sensor, the gyroscope sensor may be used to collect vibration data (such as angular velocity data) generated during knocking on the door, and the passive infrared sensor may be used to detect whether there is a human body Close to smart door lock 100.
  • the doorbell 404 is connected to the processor 401 through the bus 405 and can be used to ring the doorbell and play the corresponding doorbell prompt tone when the door knocking event occurs.
  • the camera 406 is connected to the processor 401 through the bus 405 and can be used to capture still images or videos. In the embodiment of the present application, the camera 406 can be used to capture human body images or face images of the user knocking on the door.
  • the power supply 407 can be used to supply power to the processor 401 , memory 402 , sensor 403 , doorbell 404 , camera 406 and other internal components.
  • the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or Execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application.
  • a general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the methods disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
  • the memory may be a non-volatile memory, such as a hard disk (hard disk drive, HDD) or a solid-state drive (solid-state drive, SS), etc., or a volatile memory (volatile memory), such as Random-access memory (RAM).
  • a memory is, without limitation, any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
  • the memory in the embodiment of the present application may also be a circuit or any other device capable of implementing a storage function, and is used for storing program instructions and/or data.
  • the methods provided in the embodiments of the present application may be fully or partially implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, network equipment, user equipment or other programmable devices.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (solid state disk, SSD)), etc.
  • the processes can be completed by computer programs to instruct related hardware.
  • the programs can be stored in computer-readable storage media.
  • When the programs are executed may include the processes of the foregoing method embodiments.
  • the aforementioned storage medium includes: ROM or random access memory RAM, magnetic disk or optical disk, and other various media that can store program codes.
  • the structure shown in FIG. 4 does not constitute a specific limitation on the smart door lock 100 .
  • the smart door lock 100 may include more or fewer components than shown in the figure, or combine certain components, or separate certain components, or arrange different components.
  • the illustrated components can be realized in hardware, software or a combination of software and hardware.
  • FIG. 5 exemplarily shows a chip system provided by an embodiment of the present application.
  • the chip system includes at least one processor 501 and at least one interface circuit 502 .
  • the processor 501 and the interface circuit 502 may be interconnected by wires.
  • interface circuit 502 may be used to receive signals from other devices.
  • the interface circuit 502 may be used to send signals to other devices (such as the processor 501).
  • the interface circuit 502 can read instructions stored in the memory, and send the instructions to the processor 501 .
  • the smart door lock 100 can be made to execute various steps performed by the smart door lock 100 in the above-mentioned embodiments.
  • the chip system may also include other discrete devices, which is not specifically limited in this embodiment of the present application.

Abstract

本申请公开了一种提示方法及相关设备，智能门锁可以检测到敲门振动，采集敲门振动产生的振动数据，然后基于采集的振动数据识别敲门用户的身份并判断是否需要门铃振铃，如果确认需要门铃振铃，智能门锁还可以基于采集的振动数据的频率和/或幅度来播放不同的门铃提示音。这样，可以防止出现敲门动作产生的振动之外的其他振动引起的门铃振铃现象，增加了门铃提示音的多样化，提高了用户体验。

Description

提示方法及相关设备
本申请要求于2021年07月09日提交中国国家知识产权局、申请号为202110781962.5、申请名称为“提示方法及相关设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及终端技术领域，尤其涉及一种提示方法及相关设备。
背景技术
随着智能家居的发展，智能门锁广泛应用于人们的生活中，当人们到访私人住所或办公区域时，通常会通过按门铃或敲门的方式来提示屋内人员开门。然而，在儿童身高不足无法触碰到门铃按钮，门铃按钮安装位置不固定需要用户主动寻找，用户双手携带重物不方便按门铃等多个应用场景中，按门铃的方式会造成诸多不便，因而在实际访客到访过程中，用户还是普遍习惯用敲门的方式进行提示，但在敲门声音较小等情况下，屋内人员不易察觉到有人敲门，用户体验差。
发明内容
本申请实施例提供了一种提示方法及相关设备，在有敲门行为发生的情况下，门铃进行振铃，提高用户体验。
第一方面，本申请实施例提供了一种提示方法，应用于智能门锁，智能门锁安装在门上，智能门锁包括门铃，该方法包括：智能门锁检测到门的振动，振动的持续时长为第一时长；智能门锁基于振动产生第一振动数据；智能门锁基于第一振动数据确定敲门频率、敲门力度中的一项或两项，以及敲门用户的身份；智能门锁通知门铃振铃，播放门铃提示音，门铃提示音是基于敲门频率、敲门力度中的一项或两项、以及敲门用户的身份确定的，其中，门铃提示音提示敲门用户的身份，门铃提示音的音量、节奏、语调中的一项或多项是由敲门频率、敲门力度中的一项或两项确定的。
本申请实施例通过实施第一方面的方法，智能门锁可以检测用户的敲门动作，确认有敲门行为发生的情况下，通知门铃振铃，提高用户体验。
在一种可能的实现方式中，在智能门锁基于振动产生第一振动数据之前，该方法还包括：智能门锁基于振动产生第二振动数据，第二振动数据是在第一时长的第一部分产生的，第一振动数据是在第一时长的第二部分产生的，其中，第一部分在第二部分之前；智能门锁确定第二振动数据指示的振动特征与敲门动作的振动特征相符。这样，智能门锁可以初步确定存在敲门行为。
在一种可能的实现方式中，在智能门锁基于振动产生第二振动数据之前，该方法还包括：智能门锁检测到有人体靠近智能门锁。这样，智能门锁可以从低功耗模式进入正常工作模式，开始检测用户的敲门动作。
在一种可能的实现方式中，智能门锁基于第一振动数据确定敲门频率、敲门力度中的一项或两项，具体包括：智能门锁基于第一振动频率确定敲门频率，第一振动频率越高，敲门 频率越高；和/或，智能门锁基于第一振动幅度确定敲门力度，第一振动幅度越大，敲门力度越大；其中，第一振动频率是第一振动数据的频率，第一振动幅度是第一振动数据的幅度。这样，智能门锁可以基于第一振动数据来确定敲门频率和/或敲门力度。
在一种可能的实现方式中，智能门锁基于第一振动数据确定敲门用户的身份，具体包括：智能门锁对第一振动数据进行预处理，得到预处理后的第一振动数据；智能门锁将预处理后的第一振动数据与预存的第一用户的敲门数据进行匹配，若匹配成功，则敲门用户为第一用户。这样，智能门锁可以基于第一振动数据来确定敲门用户的身份。
在一种可能的实现方式中，智能门锁基于敲门频率、敲门力度中的一项或两项、以及敲门用户的身份确定门铃提示音，具体包括：若智能门锁确定敲门频率小于第一预设敲门频率和/或敲门力度小于第一预设敲门力度，则智能门锁确定门铃提示音为第一门铃提示音；或，若智能门锁确定敲门频率大于第一预设敲门频率和/或敲门力度大于第一预设敲门力度，则智能门锁确定门铃提示音为第二门铃提示音；其中，第一门铃提示音与第二门铃提示音的音量、节奏、语调中的一项或多项不同，第一门铃提示音的内容和第二门铃提示音的内容中均包括敲门用户的身份。这样，智能门锁可以基于敲门频率、敲门力度中的一项或两项、以及敲门用户的身份来综合确定门铃提示音。
在一种可能的实现方式中，在智能门锁通知门铃振铃，播放门铃提示音之前，该方法还包括：智能门锁利用摄像头采集门前图像；智能门锁检测到门前图像中包括人形和/或人脸。这样，对于无人触发的振动，智能门锁可以不通知门铃振铃。
在一种可能的实现方式中，在智能门锁通知门铃振铃，播放门铃提示音之后，该方法还包括：智能门锁进入低功耗模式。这样，可以减少智能门锁的功耗。
第二方面，本申请实施例提供了一种电子设备，该电子设备包括一个或多个处理器和一个或多个存储器；其中，一个或多个存储器与一个或多个处理器耦合，一个或多个存储器用于存储计算机程序代码，计算机程序代码包括计算机指令，当一个或多个处理器执行计算机指令时，使得电子设备执行上述第一方面任一项可能的实现方式中的方法。
第三方面，本申请实施例提供了一种计算机存储介质，该计算机存储介质存储有计算机程序，计算机程序包括程序指令，当程序指令在电子设备上运行时，使得电子设备执行上述第一方面任一项可能的实现方式中的方法。
第四方面，本申请实施例提供了一种计算机程序产品，当计算机程序产品在计算机上运行时，使得计算机执行上述第一方面任一项可能的实现方式中的方法。
附图说明
图1是本申请实施例提供的一种智能门锁的系统架构示意图；
图2是本申请实施例提供的一种提示方法的流程示意图；
图3是本申请实施例提供的另一种提示方法的流程示意图；
图4是本申请实施例提供的一种智能门锁的结构示意图；
图5是本申请实施例提供的一种芯片系统的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。其中，在本申请实施例的描述中，除非另有说明，“/”表示或的意思，例如，A/B可以表示A或B；文本中的“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况，另外，在本申请实施例的描述中，“多个”是指两个或多于两个。
应当理解，本申请的说明书和权利要求书及附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本申请中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本申请所描述的实施例可以与其它实施例相结合。
目前，在人们到访私人住所或办公区域时，通常会通过按门铃或敲门的方式来提示屋内人员开门。当前现有的门铃触发是根据用户按下门外的门铃按钮来触发。然而，在儿童身高不足无法触碰到门铃按钮，门铃按钮安装位置不固定需要用户主动寻找，用户双手携带重物不方便按门铃等多个应用场景中，按门铃的方式会造成诸多不便，因而在实际访客到访过程中，用户还是普遍习惯用敲门的方式进行提示，但在敲门声音较小、屋门的隔音效果较好等情况下，屋内人员不易察觉到有人敲门，用户体验差。
本申请实施例提供了一种提示方法，智能门锁可以检测到敲门振动(即用户的敲门动作触发的门的振动)，采集敲门振动产生的振动数据，然后基于采集的振动数据识别敲门用户的身份并判断是否需要门铃振铃，如果确认需要门铃振铃，智能门锁还可以基于采集的振动数据的频率和/或幅度来播放不同的门铃提示音。这样，可以防止出现敲门动作产生的振动之外的其他振动引起的门铃振铃现象，增加了门铃提示音的多样化，提高了用户体验。
本申请实施例提供的方法主要解决以下三个问题：
问题一：在用户通过敲门触发的振动过程中，智能门锁如何采集并检测振动数据。
问题二：基于用户敲门触发的振动来采集到的数据如何识别敲门用户的身份。
问题三：在用户敲门触发的振动过程中，门铃振铃容易被其他振动误触发。
针对以上三个问题，本申请实施例提供了以下解决方案：
针对问题一，本申请实施例通过利用振动模块来获取陀螺仪采集的振动数据，若检测到有振动数据超过预设阈值，则持续采集一段时间(例如2秒、3秒等)的振动数据，并对该振动数据进行降噪、包络提取、模板匹配(和/或包络拟合)/机器学习离线诊断等来进一步判断用户是否产生了敲门行为，即是否发生了敲门事件。
针对问题二，本申请实施例建立了陀螺仪角速度振动数据模板特征库和离线诊断库，基于离线诊断库来识别敲门用户的身份，同一个用户使用相同敲门方式敲门，可以在不联网的 状态下完成用户身份识别。
针对问题三，本申请实施例增加了图像决策模块和振铃决策模块，振铃决策模块通过收集图像决策模块和振动模块的数据来综合判断是否需要门铃振铃，从而消除误触发/误识别引起的门铃振铃，即无人触发的振动，不会产生门铃振铃。
此外，本申请实施例还可以基于角速度振动模型的频率和幅度、敲门振动的频率和幅度来确定敲门的紧急程度与力度，进一步地，可以基于不同的敲门的紧急程度与力度来播放不同的门铃提示音，即敲门的紧急程度(振动频率)不同、敲门的力度(振动幅度)不同，播放的门铃提示音也不同。
下面介绍本申请实施例提供的智能门锁100的系统架构示意图。
如图1所示，该系统架构可以包括低功耗系统、决策模块、图像采集与处理模块、振动模块、运行与维护模块、硬件适配模块、硬件层(或者称为硬件模块)等。
低功耗系统与振铃决策模块进行交互，振铃决策模块在检测并识别到有效的敲门事件之后，可以将决策结果上报给低功耗系统，该决策结果用于指示低功耗系统触发门铃振铃。
该系统架构中包括多个模块，每一个模块包括多个子模块(也可以称为子组件)，下面对该系统架构中的每一个模块及其子模块的功能进行详细介绍：
1、决策模块：
决策模块是低功耗系统中的后台常驻进程，可以基于软件操作系统(operatingsystem，OS)，例如华为的鸿蒙操作系统
Figure PCTCN2022104182-appb-000001
等，提供振铃决策和陀螺仪数据检测线程的运行与维护。决策模块负责对检测结果进行汇总、判断，从而决策是否发起门铃振铃事件。
决策模块可以包括两个子模块：振铃决策模块、图像决策模块。
振铃决策模块：
振铃决策模块可以接收振动模块发送的敲门匹配结果，并对敲门匹配结果进行判断，从而确定是否有敲门事件发生，同时，振铃决策模块还可以向图像决策模块发送获取人形和/或人脸检测结果的请求，在接收到图像决策模块发送的人形和/或人脸检测结果之后，振铃决策模块可以基于敲门匹配结果和人形和/或人脸检测结果综合决策是否发起门铃振铃事件，若是，再进一步基于敲门匹配结果确定所要播放的相应的门铃提示音。
图像决策模块：
图像决策模块可以接收到振铃决策模块发送的获取人形和/或人脸检测结果的请求，在接收到该请求之后，图像决策模块可以向图像采集与处理模块发送进行人形和/或人脸检测的指令，图像采集与处理模块可以对摄像头采集的门前图像进行一系列处理得到人形和/或人脸检测结果，并将人形和/或人脸检测结果发送给图像决策模块。若图像决策模块基于人形和/或人脸检测结果判断出确实有人形和/或人脸，则图像决策模块可以将图像采集与处理模块发送的人形/人脸检测结果发送给振铃决策模块。
2、图像采集与处理模块：
图像采集与处理模块负责对门前图像进行采集、预处理、检测以及检测结果上报等。
图像采集与处理模块可以包括四个子模块：图像采集模块、图像预处理模块、图像检测模块、结果上报模块。
图像采集模块：
图像采集模块可以获取摄像头采集的门前图像数据，并将摄像头采集的门前图像数据发 送给图像预处理模块。
在一些实施例中，图像采集模块获取的门前图像数据也可以是经过图像信号处理器处理过的摄像头采集的门前图像数据。
图像预处理模块：
图像预处理模块可以对图像采集模块发送的门前图像数据进行图像预处理，并将预处理后的门前图像数据给图像检测模块。
图像预处理可以消除图像中的无关信息、恢复有用的真实信息，最大限度地简化图像数据，提高有关信息的可检测性。
图像预处理的步骤可以包括但不限于以下步骤：图像降采样、图像滤波、图像平滑、图像增强等。
其中，图像预处理过程中每个步骤的具体执行细节均为现有技术，可以参照现有技术中的相关资料，在此不再赘述。
图像检测模块：
图像检测模块可以接收图像预处理模块发送的预处理后的门前图像，然后对预处理后的门前图像数据进行人形和/或人脸检测，得到人形和/或人脸检测结果，并将人形和/或人脸检测结果发送给结果上报模块。
其中，人形和/或人脸检测过程的具体执行细节均为现有技术，可以参照现有技术中的相关资料，在此不再赘述。
结果上报模块：
结果上报模块可以接收图像检测模块发送的人形和/或人脸检测结果，并将人形和/或人脸检测结果发送给图像决策模块。
3、振动模块：
振动模块负责获取陀螺仪采集的数据，并对陀螺仪采集的数据进行降噪、提取包络、识别敲门事件等。
振动模块可以包括六个子模块：数据采集模块、数据降噪模块、提取包络模块、敲门匹配模块、低功耗运行与维护模块、校准模块。
数据采集模块：
数据采集模块可以获取陀螺仪采集的角速度数据，并将陀螺仪采集的角速度数据发送给数据降噪模块。
数据降噪模块：
数据降噪模块可以接收数据采集模块发送的陀螺仪采集的角速度数据，并对陀螺仪采集的角速度数据进行降噪处理，得到降噪处理后的陀螺仪数据，并将降噪处理后的陀螺仪数据发送给提取包络模块。
降噪处理的步骤可以包括但不限于以下步骤：去除常值漂移、角度随机游走、速率随机游走、量化噪声和速率斜坡等。
其中，降噪处理过程中每个步骤的具体执行细节均为现有技术，可以参照现有技术中的相关资料，在此不再赘述。
提取包络模块：
提取包络模块可以接收数据降噪模块发送的降噪处理后的陀螺仪数据，并对降噪处理后的陀螺仪数据进行包络提取，得到包络数据，并将包络数据发送给敲门匹配模块。
包络提取是对降噪处理后的陀螺仪数据的包络进行提取，包络提取的方法包括但不限于以下方法：检波法、希尔伯特(Hilbert)变换等。
其中，本申请实施例使用的包络提取的方法均为现有技术，可以参照现有技术中的相关资料，在此不再赘述。
敲门匹配模块：
敲门匹配模块可以接收提取包络模块发送的包络数据，然后可以利用已经建立的模板特征库和离线诊断库对包络数据进行模板匹配/神经网络离线诊断，得到敲门匹配结果，并将敲门匹配结果发送给振铃决策模块。
敲门匹配结果中可以包括是否有敲门事件发生、敲门频率和/或敲门力度、敲门用户的身份(哪个人在敲门)。
对于敲门匹配模块对包络数据进行模板匹配/神经网络离线诊断，得到敲门匹配结果的具体执行过程在后续实施例中会详细介绍，在此先不展开。
低功耗运行与维护模块：
低功耗运行与维护模块可以维持陀螺仪的低功耗模式，在被动式红外传感器(Passive Infra-Red,PIR)检测到有活体靠近智能门锁之后，低功耗运行与维护模块可以中断陀螺仪的低功耗模式，使陀螺仪进入正常探测模式。
校准模块：
校准模块可以对上电后的陀螺仪进行校准。
在一些实施例中，陀螺仪可以自带校准功能，在这种情况下，振动模块中可以不配置校准模块。
4、运行与维护模块：
运行与维护模块负责敲门振动转门铃过程(也可以称为振铃检测过程)中的各个组件的运行维护即组件运行状态监测和配置，具体地，运行与维护模块可以在敲门振动转门铃过程中进行配置管理、日志收集与存储、系统运行状态统计与上报等，给振铃决策模块提供动态运行参数。
运行与维护模块可以包括三个子模块：统计模块、日志模块、配置管理模块。
统计模块：
统计模块可以对各个组件运行状态进行汇总与统计，并上报给低功耗系统。
日志模块：
日志模块可以收集各个组件的日志，并将日志进行规整后存储到本地或发送给低功耗系统，存储到低功耗系统中。
配置管理模块：
配置管理模块可以提供配置能力，可以定制各个组件的静态运行参数，例如组件启动方式、组件运行方式、组件的健康状态等。
5、硬件适配模块：
硬件适配模块负责屏蔽硬件差异，对振动模块和图像采集与处理模块中的子模块提供标准的能力接口。
硬件适配模块可以包括四个子模块：图像信号处理器(Image Signal Processor,ISP)驱动、陀螺仪(gyroscope,GYRO)驱动、被动式红外传感器(Passive Infra-Red,PIR)驱动、其他传 感器驱动。
图像信号处理器驱动：
图像信号处理器驱动可以屏蔽图像信号处理器的硬件差异，对图像采集与处理模块提供标准的采集接口。
陀螺仪驱动：
陀螺仪驱动可以屏蔽陀螺仪的硬件差异，对振动模块提供标准的采集接口和运行与维护接口。
被动式红外传感器驱动：
被动式红外传感器驱动可以屏蔽被动式红外传感器的硬件差异，对振铃决策模块提供标准接口，从而实现被动式红外传感器在检测到有活体靠近智能门锁之后可以指示振铃决策模块启动振铃检测流程。
其他传感器驱动：
其他传感器驱动可以包括除了图中所示传感器驱动之外的一个或多个传感器驱动，可以屏蔽一个或多个其他传感器的硬件差异，提供标准接口。
门铃驱动：
门铃驱动可以屏蔽门铃的硬件差异，提供标准接口，从而实现在敲门行为发生时可以驱动门铃进行振铃。
6、硬件层：
硬件层负责利用多个不同硬件来完成敲门振动转门铃过程中涉及的陀螺仪数据采集、人形/人脸图像采集、门铃振铃等步骤的硬件实现。
硬件层可以包括陀螺仪、被动式红外传感器、门铃、图像传感器、图像信号处理器、其他传感器。
陀螺仪：
陀螺仪可以采集敲门过程中产生的振动数据，其中，振动数据可以包括陀螺仪的角速度数据等。
被动式红外传感器：
被动式红外传感器可以通过检测运动中的活体(例如人体)产生的能量来感知运动。例如，在有人体靠近智能门锁时，被动式红外传感器可以检测到有运动的人体，并指示振铃决策模块启动振铃检测流程。
门铃：
门铃可以接收触发振铃的指令或动作，并播放指定的门铃提示音。
图像传感器：
图像传感器是摄像头的一个组成部分。摄像头可以包括镜头和图像传感器，用于采集图像。物体可以通过镜头生成光学图像投射到图像传感器上，图像传感器可以把光信号转换成电信号，之后可以将电信号传递给图像信号处理器转换成数字图像信号，例如标准的RGB、YUV等格式的图像信号。
在本申请实施例中，摄像头可以接收图像采集与处理模块发送的采集门前图像的指令，之后采集门前图像数据，并将采集的门前图像数据发送给图像信号处理器。
图像信号处理器：
图像信号处理器可以接收摄像头采集并发送的门前图像数据，并对该门前图像数据进行 处理。例如，图像信号处理器可以将摄像头采集的图像数据转化为肉眼可见的图像，还可以对图像的噪点、亮度、肤色等进行算法优化，还可以对拍摄场景的曝光、色温等参数进行优化等等。在一些实施例中，图像信号处理器也可以设置在摄像头中。
其他传感器：
其他传感器可以包括除了图中所示传感器之外的一个或多个传感器，例如指纹传感器、压力传感器、触摸传感器等等。
需要说明的是，图1所示的智能门锁100(也可以称为电子设备100)的系统架构仅仅是一个示例，该系统架构中还可以包括比图1所示的更多的其它模块(例如关锁模块、开锁模块等等)或其他部件，或者可以包括更少的模块或部件，或者可以组合两个或多个的模块或部件，或者可以包括不同的模块或部件配置，本申请实施例对此不作限定。
下面介绍本申请实施例提供的一种提示方法。
图2示例性示出了本申请实施例提供的一种提示方法流程。
如图2所示，该提示方法可以应用于智能门锁100，智能门锁100可以安装在门上，下面详细介绍该提示方法的具体步骤：
阶段一、触发执行振铃检测流程
S201-S202、被动式红外传感器PIR在检测到有活体靠近时，向振铃决策模块发送启动振铃检测的指令。
具体地，被动式红外传感器PIR可以通过检测运动中的活体(例如人体)产生的能量来感知运动。在门外有人靠近智能门锁100时，被动式红外传感器PIR可以检测到有运动的人体靠近智能门锁100，之后，被动式红外传感器PIR可以向振铃决策模块发送启动振铃检测的指令，该指令用于指示振铃决策模块触发执行振铃检测流程。
S203、振铃决策模块向振动模块发送启动振动模块的指令。
具体地，振铃决策模块在接收到被动式红外传感器PIR发送的启动振铃检测的指令之后，可以向振动模块发送启动振动模块的指令，该指令用于指示振动模块开始启动，即振动模块可以从低功耗模式进入正常工作模式。
S204、振动模块向陀螺仪发送启动陀螺仪的指令。
具体地，振动模块在接收到振铃决策模块发送的启动振动模块的指令之后，可以向陀螺仪发送启动陀螺仪的指令，该指令用于指示陀螺仪开始启动。
S205、陀螺仪退出低功耗模式，开始采集振动数据。
具体地，陀螺仪在接收到振动模块发送的启动陀螺仪的指令之后，可以开始启动，即陀螺仪可以退出低功耗模式，进入正常探测模式，开始采集振动数据。
其中，振动数据可以包括但不限于陀螺仪的角速度数据等。
阶段二、执行振铃检测流程
S206-S207、振动模块向陀螺仪发送获取振动数据1的请求，之后，陀螺仪向振动模块发送振动数据1。
具体地，振动模块可以向陀螺仪发送获取振动数据1的请求，陀螺仪在接收到该请求之后，可以向振动模块发送振动数据1。
其中，该振动数据1可以用于振动模块判断振动数据1中是否存在用户敲门行为触发的敲门振动过程中产生的振动数据。
在一些实施例中，振动模块可以直接读取陀螺仪采集的振动数据1。
S208、振动模块基于振动数据1确定该振动数据1存在敲门行为产生的振动数据。
示例性地，振动模块在接收到陀螺仪发送的振动数据1之后，振动模块可以以一定的时间窗(滑窗)对陀螺仪发送的振动数据1进行存储，假设上述一定的时间窗为1秒，对应陀螺仪发送的振动数据1是50个角速度数据(或者称为角速度探测值)，那么，振动模块可以判断上述50个角速度数据中是否存在有超过预设阈值的角速度值，若存在有超过预设阈值的角速度值，则振动模块可以确定振动数据1中存在用户敲门行为(也可以称为敲门动作)触发的敲门振动过程中产生的振动数据。
在一种可能的实现方式中，振动模块可以判断上述50个角速度数据所指示的振动特征与敲门行为的振动特征相符，若相符，则振动模块初步确定存在敲门行为。
S209-S210、振动模块向陀螺仪发送获取振动数据2的请求，之后，陀螺仪向振动模块发送振动数据2。
具体地，振动模块可以向陀螺仪发送获取振动数据2的请求，陀螺仪在接收到该请求之后，可以向振动模块发送振动数据2。
其中，该振动数据2可以用于振动模块基于振动数据2来完成振铃检测流程中的后续步骤。
在一些实施例中，振动模块可以直接读取陀螺仪采集的振动数据2。
S211-S212、振动模块基于振动数据2得到敲门匹配结果，并向振动决策模块发送该敲门匹配结果。
具体地，振动模块在接收到陀螺仪发送的振动数据2之后，振动模块可以对振动数据2进行预处理，然后可以利用已经建立的模板特征库和离线诊断库对预处理后的振动数据2进行模板匹配/神经网络离线诊断，得到敲门匹配结果。之后，振动模块可以向振动决策模块发送该敲门匹配结果。
其中，该敲门匹配结果中可以包括确定是否有敲门事件发生的信息。若是，则该敲门匹配结果中还可以包括敲门频率和/或敲门力度、敲门用户的身份(哪个人在敲门)等信息。
上述振动数据2可以是陀螺仪持续采集一段时间(例如2秒、3秒等等)的振动数据，在本申请实施例中，上述振动数据2是以陀螺仪持续采集2秒的角速度数据为例。
振动模块对振动数据2进行预处理的过程可以包括但不限于以下步骤：
1、数据降噪处理：
示例性地，振动模块对振动数据2进行数据降噪处理可以采用小波去噪原理来实现。
小波去噪过程主要包括三个基本的步骤：对含有噪声的信号进行小波变换；对变换得到的小波系数进行某种处理以去除其中包含的噪声；对处理后的小波系数进行小波逆变换得到去噪后的信号。对含有噪声的信号进行小波去噪后可以明显去除很多噪声信号，小波去噪后 的信号可以变得更平滑。
其中，利用小波去噪进行数据降噪处理的具体执行过程均为现有技术，可以参照现有技术的相关资料，在此不再赘述。
需要说明的是，本申请实施例仅仅以小波去噪为例对数据降噪处理过程进行说明，不限于此，数据降噪处理还可以用其他去噪方法，本申请实施例对此不作限定。
2、提取包络：
示例性地，振动模块可以使用检波法或Hilbert变换对数据降噪处理后的振动数据2进行包络提取，从而得到包络数据。
其中，利用检波法或Hilbert变换进行包络提取的具体执行过程均为现有技术，可以参照现有技术的相关资料，在此不再赘述。
需要说明的是，本申请实施例仅仅以检波法或Hilbert变换为例对包络提取过程进行说明，不限于此，包络提取过程还可以用其他方法，本申请实施例对此不作限定。
振动模块利用已经建立的模板特征库和离线诊断库对预处理后的振动数据2进行模板匹配/神经网络离线诊断具体过程如下：
1、振动模块识别是否有敲门事件发生：
在一种可能的实现方式中，振动模块可以将预处理后的振动数据2与预存的敲门振动数据模板进行模板匹配，若匹配成功，则振动模块确定有敲门事件发生。
在另一种可能的实现方式中，振动模块可以将预处理后的振动数据2输入到提前已经训练好的神经网络模型(或者称为离线诊断库)中进行神经网络离线诊断(即机器学习离线诊断)，若识别正确率高于预设识别正确率阈值，则振动模块确定有敲门事件发生。
2、振动模块确定敲门频率和/或敲门力度：
振动模块可以基于预处理后的振动数据2获取到预处理后的振动数据2中的角速度数据的频率和幅度，进一步地，振动模块可以基于角速度数据的频率来确定敲门频率，角速度数据的频率越高，敲门频率越高，振动模块还可以基于角速度数据的幅度来确定敲门力度，角速度数据的幅度越大，敲门力度越大。
3、振动模块确定敲门用户的身份(哪个人在敲门)：
振动模块可以基于同一个用户的相同敲门习惯来识别出敲门用户的身份，即同一用户使用相同敲门方式敲门，振动模块可以识别出敲门用户的身份。
在一种可能的实现方式中，振动模块可以将预处理后的振动数据2与预存的全部敲门用户的敲门振动数据进行模板匹配，若该预处理后的振动数据2与其中一个预存的敲门用户1的敲门振动数据匹配成功，则振动模块可以确定该敲门用户为敲门用户1。
在另一种可能的实现方式中，振动模块可以将预处理后的振动数据2输入到提前已经训练好的多个敲门用户的神经网络模型(或者称为离线诊断库)中进行神经网络离线诊断(即机器学习离线诊断)，若利用提前已经训练好的敲门用户1的神经网络模型得到的识别正确率高于预设识别正确率阈值，则振动模块可以确定该敲门用户为敲门用户1。
在另一种可能的实现方式中，振动模块识别出的敲门用户的身份与预存的敲门用户均不匹配/识别正确率均低于预设识别正确率阈值，例如，敲门用户的敲门振动数据不是预存的，或者，预存了敲门振动数据的敲门用户故意使用不同于之前的敲门方式进行敲门，则振动模块可以输出敲门用户的身份为“陌生用户”。
在一些实施例中，振动模块也可以不执行步骤S206和步骤S209，而且陀螺仪也可以不执行步骤S207和S210，而是振动模块可以根据振铃检测流程的需要主动读取陀螺仪采集的振动数据，并基于读取的陀螺仪采集的振动数据来执行步骤S208和步骤S211。
在另一些实施例中，振动模块也可以不执行步骤S206和步骤S209，而是陀螺仪主动执行步骤S207和S210，实时向振动模块发送采集的振动数据。
阶段三、执行振铃决策流程
S213、振铃决策模块基于敲门匹配结果确定有敲门事件发生。
具体地，振铃决策模块在接收到振动模块发送的敲门匹配结果之后，可以判断是否有敲门事件发生，若是，则振铃决策模块执行步骤S214。若否，则后续步骤不需要再执行。
在一种可能的实现方式中，振动模块也可以在确定有敲门事件发生的情况下向振铃决策模块发送敲门匹配结果，在确定无敲门事件发生的情况下则不需要向振铃决策模块发送敲门匹配结果。
S214、振铃决策模块向图像决策模块发送获取人形和/或人脸检测结果的请求。
具体地，振铃决策模块在确定有敲门事件发生之后，可以向图像决策模块发送获取人形和/或人脸检测结果的请求，用于请求图像决策模块发送人形和/或人脸检测结果。
S215、图像决策模块向图像采集与处理模块发送进行人形和/或人脸检测的指令。
具体地，图像决策模块在接收到振铃决策模块发送的获取人形和/或人脸检测结果的请求之后，可以向图像采集与处理模块发送进行人形和/或人脸检测的指令，用于指示图像采集与处理模块进行人形和/或人脸检测。
S216-S217、图像采集与处理模块进行人形和/或人脸检测，得到人形和/或人脸检测结果，并向图像决策模块发送该人形和/或人脸检测结果。
具体地，图像采集与处理模块在接收到图像决策模块发送的进行人形和/或人脸检测的指令之后，可以向摄像头发送采集门前图像的指令，该指令用于指示摄像头采集门前图像，进一步地，图像采集与处理模块可以获取摄像头采集的门前图像数据，并对该门前图像数据进行预处理，之后对预处理后的门前图像数据进行人形和/或人脸检测，从而得到人形和/或人脸检测结果。之后，图像采集与处理模块可以将该人形和/或人脸检测结果发送给图像决策模块。
其中，摄像头采集的门前图像数据可以是摄像头持续采集的一定帧数(例如5帧)或一段时间(例如150ms)的门前图像数据。上述人形和/或人脸检测结果中可以包括门前图像数据中是否有人形和/或人脸。
可选地，摄像头也可以一直采集门前图像，而不需要在接收到采集门前图像的指令之后再开始采集门前图像，图像采集与处理模块可以只获取摄像头最新采集的一定帧数或一段时间的门前图像数据。
在一些实施例中，步骤S215是可选的，图像采集与处理模块可以周期性地进行人形和/或人脸检测，并周期性地向图像决策模块发送人形和/或人脸检测结果。
S218-S219、图像决策模块基于人形和/或人脸检测结果确定门前有人形和/或人脸，并向振铃决策模块发送该人形和/或人脸检测结果。
具体地，图像决策模块在接收到图像采集与处理模块发送的人形和/或人脸检测结果之后，可以判断门前是否人形和/或人脸，若是，则向振铃决策模块发送该人形和/或人脸检测结果。
可选地，若否，则图像决策模块可以不向振铃决策模块发送该人形和/或人脸检测结果，后续步骤也不会再执行。
S220-S221、振铃决策模块基于敲门匹配结果和人形和/或人脸检测结果综合确定发起门铃振铃事件、所要播放的相应的门铃提示音，并向低功耗系统发送发起门铃振铃的请求、所要播放的相应的门铃提示音。
具体地，振铃决策模块在接收到图像决策模块发送的人形和/或人脸检测结果之后，可以基于敲门匹配结果和人形和/或人脸检测结果综合确定是否需要发起门铃振铃事件。
示例性地，若振铃决策模块基于图像决策模块发送的人形和/或人脸检测结果确定门前有人形和/或人脸，且之前在步骤S213中，振铃决策模块基于敲门匹配结果已经确定有敲门事件发生，则振铃决策模块可以综合确定需要发起门铃振铃事件。
进一步地，振铃决策模块还可以基于敲门匹配结果中敲门频率和/或敲门力度、敲门用户的身份(哪个人在敲门)来确定所要播放的相应的门铃提示音。其中，振铃决策模块确定所要播放的相应的门铃提示音包括但不限于以下3种可能的实现方式：
可能的实现方式1：振铃决策模块可以只基于敲门匹配结果中敲门频率和/或敲门力度来确定所要播放的相应的门铃提示音：
示例性地，在敲门频率小于某一预设频率阈值(即角速度振动模型的频率)，和/或，敲门力度小于某一预设力度阈值(即角速度振动模型的幅度)时，可能表示敲门用户在进行正常敲门动作，无破坏行为，那么，门铃提示音可以为一段预先设定的节奏较为平缓的音乐或简单的“叮咚～叮咚～叮咚～”声等等。可选地，门铃提示音的音量可以低一些，门铃提示音的语调可以温柔一些。
示例性地，在敲门频率大于某一预设频率阈值，和/或，敲门力度大于某一预设力度阈值时，可能表示敲门用户在进行非正常敲门动作，即敲门用户可能有急事，或者敲门用户可能在实施破坏行为，那么，门铃提示音的节奏可以较为紧急，门铃提示音可以为警报类提示音，例如快速的“滴呜滴呜滴呜”，或者，“发现异常行为，请注意安全！”等等。可选地，门铃提示音的音量可以高一些，门铃提示音的语调可以粗犷一些。
在一些实施例中，振铃决策模块也可以预先设置多个敲门频率范围区间，每一个敲门频率范围区间对应一种节奏、音量、语调中的一项或多项不同的门铃提示音。例如，在不同敲门频率范围区间，敲门频率越低，门铃提示音的节奏可以越平缓，音量可以越低，语调可以越温柔；敲门频率越高，门铃提示音的节奏可以越紧急，音量可以越高，语调可以越粗犷。振铃决策模块可以先确定敲门频率位于哪一个敲门频率范围区间，之后再确定该敲门频率范围区间对应的门铃提示音。
在另一些实施例中，振铃决策模块也可以预先设置多个敲门力度范围区间，每一个敲门力度范围区间对应一种节奏、音量、语调中的一项或多项不同的门铃提示音。例如，在不同敲门力度范围区间，敲门力度越小，门铃提示音的节奏可以越平缓，音量可以越低，语调可 以越温柔；敲门力度越大，门铃提示音的节奏可以越紧急，音量可以越高，语调可以越粗犷。振铃决策模块可以先确定敲门力度位于哪一个敲门力度范围区间，之后再确定该敲门力度范围区间对应的门铃提示音。
上述可能的实现方式1中，门铃提示音的节奏、音量、语调中的一项或多项是由敲门频率和/或敲门力度确定的，因此，门铃提示音可以体现敲门频率和/或敲门力度。
可能的实现方式2：振铃决策模块可以只基于敲门匹配结果中敲门用户的身份(哪个人在敲门)来确定所要播放的相应的门铃提示音：
示例性地，在确认敲门用户为预存的用户时，例如，敲门用户为用户1时，假设用户1的名字为“小红”，则门铃提示音可以为“小红来啦”，或者，“小红在敲门”等等。
示例性地，在确认敲门用户为陌生用户时，则门铃提示音可以为“欢迎客人光临”，或者，“客人来啦”等等。
上述可能的实现方式2中，门铃提示音的内容中包括敲门用户的身份，因此，门铃提示音可以体现敲门用户的身份。
可能的实现方式3：振铃决策模块可以基于敲门匹配结果中敲门频率和/或敲门力度和敲门用户的身份(哪个人在敲门)来综合确定所要播放的相应的门铃提示音：
示例性地，在敲门频率小于某一预设频率阈值，和/或，敲门力度小于某一预设力度阈值，且确认敲门用户为预存的用户时，例如，敲门用户为用户1时，假设用户1的名字为“小红”，则门铃提示音可以为“叮咚～小红来啦”，或者，“叮咚～小红在敲门”等等，即门铃提示音的节奏可以较为平缓，且门铃提示音的内容中包括敲门用户的身份(例如敲门用户的名字)。可选地，门铃提示音的音量可以低一些，门铃提示音的语调可以温柔一些。
示例性地，在敲门频率大于某一预设频率阈值，和/或，敲门力度大于某一预设力度阈值，且确认敲门用户为主人预存的用户时，例如，敲门用户为用户1时，假设用户1的名字为“小红”，则门铃提示音可以为“小红来啦，主人快快开门”，或者，“小红正在发起异常行为，请注意安全！”等等，即门铃提示音的节奏可以较为紧急，且门铃提示音的内容中包括敲门用户的身份(例如敲门用户的名字)。可选地，门铃提示音的音量可以高一些，门铃提示音的语调可以粗犷一些。
示例性地，在敲门频率小于某一预设频率阈值，和/或，敲门力度小于某一预设力度阈值，且确认敲门用户为陌生用户时，则门铃提示音可以为“欢迎客人光临”，或者，“客人来啦”等等，即门铃提示音的节奏可以较为平缓，且门铃提示音的内容中包括敲门用户的身份，例如敲门用户的身份可以为“客人”。可选地，门铃提示音的音量可以低一些，门铃提示音的语调可以温柔一些。
示例性地，在敲门频率大于某一预设频率阈值，和/或，敲门力度大于某一预设力度阈值，且确认敲门用户为陌生用户时，则门铃提示音可以为“陌生人来啦，快快开门”，或者，“陌生人正在发起异常行为，请注意安全！”等等，即门铃提示音的节奏可以较为紧急，且门铃提示音的内容中包括敲门用户的身份，例如敲门用户的身份可以为“陌生人”。可选地，门铃提示音的音量可以高一些，门铃提示音的语调可以粗犷一些。
上述可能的实现方式3中，门铃提示音的节奏、音量、语调中的一项或多项是由敲门频率和/或敲门力度确定的，且门铃提示音的内容中包括敲门用户的身份，因此，门铃提示音可 以既体现敲门频率和/或敲门力度，又体现敲门用户的身份。
可选地，在确认敲门用户为陌生用户时，门铃提示音也可以不提示敲门用户的身份，即门铃提示音的内容也可以不包括敲门用户的身份。
进一步地，振铃决策模块在确定发起门铃振铃事件、所要播放的相应的门铃提示音之后，可以向低功耗系统发送发起门铃振铃的请求、所要播放的相应的门铃提示音。
可以理解，上述对于所要播放的相应的门铃提示音仅仅是一些示例，所要播放的相应的门铃提示音还可以是其他，本申请实施例对此不作限定。
S222、低功耗系统向门铃发送发起门铃振铃的指令、所要播放的相应的门铃提示音。
具体地，低功耗系统在接收到振铃决策模块发送的发起门铃振铃的请求、所要播放的相应的门铃提示音之后，可以向门铃发送发起门铃振铃的指令、所要播放的相应的门铃提示音，以触发门铃振铃。
在一种可能的实现方式中，若低功耗系统检测到智能门锁100处于开锁状态，或者，智能门锁100在一段时间(例如15s)内刚刚关锁，或者，门铃在一段时间(例如15s)内发生过振铃事件，则低功耗系统可以不向门铃发送发起门铃振铃的指令、所要播放的相应的门铃提示音，即不触发门铃振铃。
S223、门铃振铃，播放相应的门铃提示音。
具体地，门铃在接收到低功耗系统发送的发起门铃振铃的指令、所要播放的相应的门铃提示音之后，可以执行振铃动作，并播放相应的门铃提示音，从而实现敲门振动转为门铃振铃。
S224-S229、低功耗系统向振铃决策模块发送进入低功耗模式的指令，振铃决策模块进入低功耗模式，振铃决策模块向振动模块发送进入低功耗模式的指令，振动模块进入低功耗模式，振动模块向陀螺仪发送进入低功耗模式的指令，陀螺仪进入低功耗模式。
具体地，低功耗系统在触发门铃振铃之后，可以向振铃决策模块发送进入低功耗模式的指令，从而使得振铃决策模块进入低功耗模式，进一步地，振铃决策模块可以向振动模块发送进入低功耗模式的指令，从而使得振动模块进入低功耗模式，进一步地，振动模块可以向陀螺仪发送进入低功耗模式的指令，从而使得陀螺仪进入低功耗模式，降低陀螺仪的采样频率。
本申请实施例通过提供上述的提示方法，智能门锁可以检测到敲门振动(即用户的敲门动作触发的门的振动)，采集敲门振动产生的振动数据，然后基于采集的振动数据识别敲门用户的身份并判断是否需要门铃振铃，如果确认需要门铃振铃，智能门锁还可以基于采集的振动数据的频率和/或幅度来播放不同的门铃提示音。这样，可以防止出现敲门动作产生的振动之外的其他振动引起的门铃振铃现象，增加了门铃提示音的多样化，提高了用户体验。
下面介绍本申请实施例提供的另一种提示方法。
图3示例性示出了本申请实施例提供的另一种提示方法流程。
如图3所示，该提示方法可以应用于智能门锁100，智能门锁100可以安装在门上，下面详细介绍该提示方法的具体步骤：
S301-S302、PIR检测到有活体靠近智能门锁100，陀螺仪退出低功耗模式进入探测模式，采集振动数据
具体地，在门外有人靠近智能门锁100时，智能门锁100可以通过被动式红外传感器PIR检测到有运动的人体靠近智能门锁100，之后，智能门锁100可以指示陀螺仪退出低功耗模式，进入探测模式，开始采集振动数据。
其中，步骤S301至步骤S302的具体执行过程可以参照图2中步骤S201至步骤S205的相关内容，在此不再赘述。
S303、智能门锁100判断振动数据是否异常。
具体地，陀螺仪在退出低功耗模式，进入探测模式之后，开始采集振动数据，智能门锁100可以判断陀螺仪采集的振动数据是否异常，也即是说，智能门锁100可以判断陀螺仪采集的振动数据是否为用户敲门行为触发的敲门振动过程中产生的振动数据。若是，则智能门锁100确定陀螺仪采集的振动数据为正常数据，若否，则智能门锁100确定陀螺仪采集的振动数据为异常数据。
示例性地，以陀螺仪采集的振动数据为角速度数据为例，智能门锁100可以判断在一定的时间窗内陀螺仪采集的角速度数据中，角速度数据的幅度是否有超过预设阈值的，若是，智能门锁100可以继续获取陀螺仪采集的一段时间的角速度数据，并执行后续步骤，对该段时间内的角速度数据来进行后续相关处理。
S304、智能门锁100确定振动数据为干扰数据。
具体地，智能门锁100在执行完步骤S303之后，若确定陀螺仪采集的振动数据为异常数据，则智能门锁100可以进一步确定该异常数据为干扰数据。
S305-S307、智能门锁100基于振动数据来进行数据降噪、提取包络、敲门行为识别。
具体地，在智能门锁100确定陀螺仪采集的振动数据为正常数据之后，智能门锁100可以基于该振动数据进行数据降噪、提取包络、敲门行为识别等，若敲门行为识别通过，即智能门锁100确定有敲门事件发生，则智能门锁100可以继续执行后续步骤。
其中，步骤S305-步骤S307的具体执行过程可以参照图2中步骤S211至步骤S212的相关内容，在此不再赘述。
S308-S310、智能门锁100进行振铃决策和图像决策，若决策通过，则门铃振铃。
具体地，智能门锁100在确定有敲门事件发生之后，可以进行振铃决策和图像决策，综合确定是否发起门铃振铃事件，若决策通过，则通知门铃振铃。
其中，步骤S308-步骤S310的具体执行过程可以参照图2中步骤S213至步骤S223的相关内容，在此不再赘述。
在本申请实施例中，第一时长可以是敲门动作产生门的振动的持续时长，第一振动数据 可以是振动数据2，第二振动数据可以是振动数据1，第一时长的第一部分可以是振动数据1对应的前文中所述的一定的时间窗，第二时长的第二部分可以是持续采集振动数据2的时长，第一振动频率可以是第一振动数据的频率，第一振动幅度可以是第一振动数据的幅度，第一用户可以是用户1，第一预设敲门频率可以是某一预设频率阈值，第一预设敲门力度可以是某一预设力度阈值，第一门铃提示音可以是敲门频率小于第一预设敲门频率和/或敲门力度小于第一预设敲门力度的情况下播放的门铃提示音，第二门铃提示音可以是敲门频率大于第一预设敲门频率和/或敲门力度大于第一预设敲门力度的情况下播放的门铃提示音。
图4示例性示出了本申请实施例提供的一种智能门锁100的结构。
如图4所示，智能门锁100可以包括：处理器401、存储器402、传感器403、门铃404、总线405、摄像头406、电源407。这些部件可以通过总线405连接。其中：
处理器401可用于读取和执行计算机可读指令，包括一个或者多个处理核心，处理器401通过运行软件程序以及模块，从而执行各种功能的应用以及信息处理。具体实现中，处理器401可主要包括控制器、运算器和寄存器。其中，控制器主要负责指令译码，并为指令对应的操作发出控制信号。运算器主要负责执行定点或浮点算数运算操作、移位操作以及逻辑操作等，也可以执行地址运算和转换。寄存器主要负责保存指令执行过程中临时存放的寄存器操作数和中间操作结果等。具体实现中，处理器401的硬件架构可以是专用集成电路(Application Specific Integrated Circuits,ASIC)架构、MIPS架构、ARM架构或者NP架构等等。
存储器402通过总线405和处理器401相连。存储器402可用于存储各种软件程序和/或多组程序指令。处理器401用于执行至少一个程序指令，以实现上述实施例的技术方案。其实现原理和技术效果与上述方法相关实施例类似，此处不再赘述。
传感器403通过总线405和处理器401相连，可用于采集多种传感数据。传感器403可以包括一个或多个传感器，例如，陀螺仪传感器、压力传感器、指纹传感器、触摸传感器等等。在本申请实施例中，传感器403可以包括陀螺仪传感器和被动式红外传感器，陀螺仪传感器可以用于采集敲门过程中产生的振动数据(例如角速度数据)，被动式红外传感器可以用于检测是否有人体靠近智能门锁100。
门铃404通过总线405和处理器401相连，可用于在敲门事件发生时振铃，播放相应的门铃提示音。
摄像头406通过总线405和处理器401相连，可用于捕获静态图像或视频，本申请实施例中，摄像头406可用于采集敲门用户的人体图像或人脸图像。
电源407可用于向处理器401、存储器402、传感器403、门铃404、摄像头406等其他内部部件供电。
在本申请实施例中，处理器可以是通用处理器、数字信号处理器、专用集成电路、现场可编程门阵列或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
在本申请实施例中，存储器可以是非易失性存储器，比如硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SS)等，还可以是易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)。存储器是能够用于携带或存储具有指令或数据结构 形式的期望的程序代码并能够由计算机存取的任何其他介质，不限于此。
本申请实施例中的存储器还可以是电路或者其它任意能够实现存储功能的装置，用于存储程序指令和/或数据。本申请各实施例提供的方法中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、网络设备、用户设备或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机可以存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，该流程可以由计算机程序来指令相关的硬件完成，该程序可存储于计算机可读取存储介质中，该程序在执行时，可包括如上述各方法实施例的流程。而前述的存储介质包括：ROM或随机存储记忆体RAM、磁碟或者光盘等各种可存储程序代码的介质。
可以理解的是，图4示意的结构并不构成对智能门锁100的具体限定。在本申请另一些实施例中，智能门锁100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
图5示例性示出了本申请实施例提供的一种芯片系统。
如图5所示，该芯片系统包括至少一个处理器501和至少一个接口电路502。处理器501和接口电路502可通过线路互联。例如，接口电路502可用于从其它装置接收信号。又例如，接口电路502可用于向其它装置(例如处理器501)发送信号。示例性的，接口电路502可读取存储器中存储的指令，并将该指令发送给处理器501。当所述指令被处理器501执行时，可使得智能门锁100执行上述实施例中的智能门锁100执行的各个步骤。当然，该芯片系统还可以包含其他分立器件，本申请实施例对此不作具体限定。
以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (10)

  1. 一种提示方法，其特征在于，应用于智能门锁，所述智能门锁安装在门上，所述智能门锁包括门铃，所述方法包括：
    所述智能门锁检测到所述门的振动，所述振动的持续时长为第一时长；
    所述智能门锁基于所述振动产生第一振动数据；
    所述智能门锁基于所述第一振动数据确定敲门频率、敲门力度中的一项或两项，以及敲门用户的身份；
    所述智能门锁通知门铃振铃，播放门铃提示音，所述门铃提示音是基于所述敲门频率、所述敲门力度中的一项或两项、以及所述敲门用户的身份确定的，其中，所述门铃提示音提示所述敲门用户的身份，所述门铃提示音的音量、节奏、语调中的一项或多项是由所述敲门频率、所述敲门力度中的一项或两项确定的。
  2. 根据权利要求1所述的方法，其特征在于，在所述智能门锁基于所述振动产生第一振动数据之前，所述方法还包括：
    所述智能门锁基于所述振动产生第二振动数据，所述第二振动数据是在所述第一时长的第一部分产生的，所述第一振动数据是在所述第一时长的第二部分产生的，其中，所述第一部分在所述第二部分之前；
    所述智能门锁确定所述第二振动数据指示的振动特征与敲门动作的振动特征相符。
  3. 根据权利要求2所述的方法，其特征在于，在所述智能门锁基于所述振动产生第二振动数据之前，所述方法还包括：
    所述智能门锁检测到有人体靠近所述智能门锁。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述智能门锁基于所述第一振动数据确定敲门频率、敲门力度中的一项或两项，具体包括：
    所述智能门锁基于第一振动频率确定所述敲门频率，所述第一振动频率越高，所述敲门频率越高；
    和/或，
    所述智能门锁基于第一振动幅度确定所述敲门力度，所述第一振动幅度越大，所述敲门力度越大；
    其中，所述第一振动频率是所述第一振动数据的频率，所述第一振动幅度是所述第一振动数据的幅度。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述智能门锁基于所述第一振动数据确定敲门用户的身份，具体包括：
    所述智能门锁对所述第一振动数据进行预处理，得到预处理后的所述第一振动数据；
    所述智能门锁将所述预处理后的所述第一振动数据与预存的第一用户的敲门数据进行匹配，若匹配成功，则所述敲门用户为所述第一用户。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，所述智能门锁基于所述敲门频率、 所述敲门力度中的一项或两项、以及所述敲门用户的身份确定所述门铃提示音，具体包括：
    若所述智能门锁确定所述敲门频率小于第一预设敲门频率和/或所述敲门力度小于第一预设敲门力度，则所述智能门锁确定所述门铃提示音为第一门铃提示音；
    或，
    若所述智能门锁确定所述敲门频率大于所述第一预设敲门频率和/或所述敲门力度大于所述第一预设敲门力度，则所述智能门锁确定所述门铃提示音为第二门铃提示音；
    其中，所述第一门铃提示音与所述第二门铃提示音的音量、节奏、语调中的一项或多项不同，所述第一门铃提示音的内容和所述第二门铃提示音的内容中均包括所述敲门用户的身份。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，在所述智能门锁通知门铃振铃，播放门铃提示音之前，所述方法还包括：
    所述智能门锁利用摄像头采集门前图像；
    所述智能门锁检测到所述门前图像中包括人形和/或人脸。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，在所述智能门锁通知门铃振铃，播放门铃提示音之后，所述方法还包括：
    所述智能门锁进入低功耗模式。
  9. 一种电子设备，其特征在于，所述电子设备包括一个或多个处理器和一个或多个存储器；其中，所述一个或多个存储器与所述一个或多个处理器耦合，所述一个或多个存储器用于存储计算机程序代码，所述计算机程序代码包括计算机指令，当所述一个或多个处理器执行所述计算机指令时，使得所述电子设备执行如权利要求1-8中任一项所述的方法。
  10. 一种计算机存储介质，其特征在于，所述计算机存储介质存储有计算机程序，所述计算机程序包括程序指令，当所述程序指令在电子设备上运行时，使得所述电子设备执行如权利要求1-8中任一项所述的方法。
PCT/CN2022/104182 2021-07-09 2022-07-06 提示方法及相关设备 WO2023280228A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110781962.5 2021-07-09
CN202110781962.5A CN115601858A (zh) 2021-07-09 2021-07-09 提示方法及相关设备

Publications (1)

Publication Number Publication Date
WO2023280228A1 true WO2023280228A1 (zh) 2023-01-12

Family

ID=84801314

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/104182 WO2023280228A1 (zh) 2021-07-09 2022-07-06 提示方法及相关设备

Country Status (2)

Country Link
CN (1) CN115601858A (zh)
WO (1) WO2023280228A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107301695A (zh) * 2016-04-15 2017-10-27 浩思八方科技（北京）有限公司 一种安全门控制系统及方法
CN108242090A (zh) * 2016-12-23 2018-07-03 上海新微技术研发中心有限公司 基于加速度传感器的电子锁及开锁方法
US20180301006A1 (en) * 2015-10-20 2018-10-18 Vivint, Inc. System and methods for correlating sound events to security and/or automation system operations
CN109816899A (zh) * 2019-03-28 2019-05-28 殷艺轩 一种压电门铃
CN111127846A (zh) * 2019-11-18 2020-05-08 北京小米移动软件有限公司 敲门提醒方法、敲门提醒装置及电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180301006A1 (en) * 2015-10-20 2018-10-18 Vivint, Inc. System and methods for correlating sound events to security and/or automation system operations
CN107301695A (zh) * 2016-04-15 2017-10-27 浩思八方科技（北京）有限公司 一种安全门控制系统及方法
CN108242090A (zh) * 2016-12-23 2018-07-03 上海新微技术研发中心有限公司 基于加速度传感器的电子锁及开锁方法
CN109816899A (zh) * 2019-03-28 2019-05-28 殷艺轩 一种压电门铃
CN111127846A (zh) * 2019-11-18 2020-05-08 北京小米移动软件有限公司 敲门提醒方法、敲门提醒装置及电子设备

Also Published As

Publication number Publication date
CN115601858A (zh) 2023-01-13

Similar Documents

Publication Publication Date Title
CN110291489B (zh) 计算上高效的人类标识智能助理计算机
EP3511938B1 (en) Audio events triggering video analytics
US10424175B2 (en) Motion detection system based on user feedback
US10593174B1 (en) Automatic setup mode after disconnect from a network
US10991372B2 (en) Method and apparatus for activating device in response to detecting change in user head feature, and computer readable storage medium
CN109920419B (zh) 语音控制方法和装置、电子设备及计算机可读介质
US20210318743A1 (en) Sensing audio information and footsteps to control power
JP6139765B1 (ja) 検出装置、警報システム、検出方法、及びプログラム
EP3193317A1 (en) Activity classification from audio
CN112634895A (zh) 语音交互免唤醒方法和装置
CN110933345A (zh) 一种降低电视待机功耗的方法、电视机及存储介质
WO2023280228A1 (zh) 提示方法及相关设备
TW201901626A (zh) 安全系統及方法
JP2007114885A (ja) 画像の類似性による分類方法及び装置
WO2020119810A1 (zh) 一种电子设备控制系统和方法
CN115103159A (zh) 一种利用摄像头进行监控的方法、装置、系统及相关设备
CN110173811B (zh) 空调器的控制方法、装置、空调器和存储介质
US10863146B1 (en) Setup and configuration of audio/video recording and communication devices
TWI445353B (zh) 具有影像監控的網路裝置、節能控制系統及影像監控方法
CN110851184A (zh) 智能投影仪的音箱的管理方法及相关产品
CN106228718B (zh) 用于通过网络检测安全威胁的系统和方法
CN110401775A (zh) 一种闹钟设定方法、闹钟设定装置及移动终端
US20210166688A1 (en) Device and method for performing environmental analysis, and voice-assistance device and method implementing same
US11941320B2 (en) Electronic monitoring system having modified audio output
JP2021096270A (ja) 情報処理装置および情報処理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22836973

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE