Control method of access control system, access control system and medium

Abstract

The invention discloses a control method of an access control system, the access control system and a medium, relates to the technical field of Internet of Things, and discloses the control method of the access control system, which is applied to the access control system, the access control system comprises an acquisition module, an identification module and a processor which are connected in sequence, the control method of the access control system comprises the steps that if an access control event is triggered when a processor is in a dormancy state, an audio signal and an image signal collected by a collection module are obtained, and in a low-power-consumption state, the data collection precision of the collection module is lower than the data collection precision in a working mode; inputting the audio signal and the image signal into an intention recognition model of a recognition module to obtain an intention recognition result; if the intention recognition result is access control awakening, awakening the processor. Event identification is performed after the access control event is triggered in the low-power-consumption state, and wakeup judgment of the processor is performed based on the intention of the identified event, so that power consumption waste caused by invalid wakeup of the processor is avoided, and the power consumption of the access control system is reduced.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things technology, and in particular to a control method for an access control system, an access control system, and a medium. Background Art

[0002] In the related art, the smart doorbell is set with a low power consumption state. In the low power consumption state, the smart doorbell monitors the surrounding sounds, and when the surrounding volume meets the requirements, the smart doorbell wakes up and enters the normal mode.

[0003] However, this wake-up mechanism ignores invalid events, such as the sound of people passing by, or when the ambient volume is high, the smart doorbell wakes up frequently, resulting in increased power consumption.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a control method for an access control system, an access control system and a medium, aiming to solve the technical problem that a smart doorbell is easily awakened in a low-power state, resulting in increased power consumption.

[0006] To achieve the above objectives, the present application proposes a control method for an access control system, which is applied to the access control system. The access control system includes an acquisition module, an identification module, and a processor connected in sequence. The control method for the access control system includes:

[0007] If an access control event is triggered when the processor is dormant, the audio signal and the image signal collected by the acquisition module are acquired, wherein in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode;

[0008] Inputting the audio signal and the image signal into the intention recognition model of the recognition module to obtain an intention recognition result;

[0009] If the intention recognition result is access control wakeup, wake up the processor.

[0010] In one embodiment, before the step of inputting the audio signal and the image signal into the intention recognition model, the access control system control method further includes:

[0011] Determining the living body type of the moving object in the image signal; and / or

[0012] Determining whether the audio signal matches a preset audio signal;

[0013] If the living body type is not a human body, and / or the audio signal does not match the preset audio, the image signal and the audio signal are ignored.

[0014] In one embodiment, the processor is connected to the acquisition module based on the processing module. If the intention recognition result is access control wakeup, after the step of waking up the processor, the control method of the access control system further includes:

[0015] Acquire the target video and target audio captured by the acquisition module, and perform high-definition encoding processing on the target video and noise reduction and enhancement processing on the audio information based on the processing module;

[0016] Output the processed audio and video information to the display terminal and the client;

[0017] If the access control event is not triggered within a preset period of time, or if the processing signal from the client is not received, the processor is controlled to enter a dormant state.

[0018] In one embodiment, if the processor is in sleep mode and an access control event is triggered, the audio signal and the image signal collected by the acquisition module are acquired, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode, before the step of acquiring the audio signal and the image signal collected by the acquisition module, the access control system control method further includes:

[0019] The access control event is triggered when there is a moving object in the image captured by the capture module, or the intensity of the captured audio is greater than a preset intensity; or

[0020] After detecting the presence of a moving object in the image captured by the capture module, determining whether the intensity of the captured audio is greater than a preset intensity;

[0021] If so, the access control event is triggered.

[0022] In one embodiment, the step of inputting the audio signal and the image signal into the intention recognition model of the recognition module to obtain an intention recognition result includes:

[0023] determining a speech intention of the audio signal and a motion intention of a moving object in the image signal based on the intention recognition model;

[0024] The speech intention and its confidence level, and the action intention and its confidence level are integrated to obtain the intention recognition result.

[0025] In one embodiment, if the processor is in sleep mode and an access control event is triggered, after the step of acquiring the audio signal and the image signal acquired by the acquisition module, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode, the access control system control method further includes:

[0026] Obtaining the target stay area corresponding to the access control system;

[0027] determining a stay time of the moving object in the target stay area in the image signal;

[0028] If the dwell time is less than the preset time, the system will run based on the current operating parameters.

[0029] In one embodiment, the access control system is connected to a neighboring device, and the control method of the access control system further includes:

[0030] If an access control event is triggered while the processor is in sleep mode, obtaining a target recognition result of the access control event fed back by the neighboring device;

[0031] If the target recognition result is a valid event, wake up the processor; otherwise

[0032] The access control system operates based on current operating parameters.

[0033] In one embodiment, if the processor is in sleep mode and an access control event is triggered, after the step of acquiring the audio signal and the image signal acquired by the acquisition module, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode, the access control system control method further includes:

[0034] Record the current moment and continuously obtain access control event recognition results and recognition frequency within the preset time period;

[0035] If the access control event is still triggered within the preset time period, and the recognition frequency is greater than the preset frequency corresponding to the current moment, the processor is awakened.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an access control system, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the control method of the access control system as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the control method of the access control system as described above are implemented.

[0038] One or more technical solutions proposed in this application have at least the following technical effects:

[0039] When the access control system triggers an access control event in a low-power state, to prevent the access control event from being an invalid event and erroneously waking up the system processor, the recognition module identifies and analyzes the audio and video captured by the acquisition module to obtain moving objects in the image signal and audio recognition information from the audio signal. If the moving object does not match the preset identity and the audio recognition result does not match the preset audio, the access control system determines that the access control event is an invalid event. The access control system then operates based on the current operating parameters, meaning the processor continues to sleep and the access control system remains in low-power mode. Therefore, invalid events can be identified in the access control system's low-power state. At the same time, the data acquisition accuracy in the low-power state is lower than that in the working mode. Compared to waking up the access control system and performing identification and analysis based on higher-definition data, identifying low-precision data can effectively reduce the power consumption of the access control system and improve its battery life. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 This is a schematic diagram of the functional modules of the access control system for this application;

[0043] Figure 2 This is a schematic diagram of the circuit structure of the access control system of this application;

[0044] Figure 3 A flowchart of the first embodiment of the control method for the access control system of the present application is provided;

[0045] Figure 4 A flowchart of the second embodiment of the control method for the access control system of the present application is provided;

[0046] Figure 5 A schematic diagram of a simplified flow chart of a control method for an access control system according to an embodiment of the present application;

[0047] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the control method of the access control system in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0050] In order to better understand the technical solution of this application, this application will be described in detail in conjunction with the accompanying drawings and specific implementation methods.

[0051] In the related art, the smart doorbell is set with a low power consumption state. In the low power consumption state, the smart doorbell monitors the surrounding sounds, and when the surrounding volume meets the requirements, the smart doorbell wakes up and enters the normal mode.

[0052] However, this wake-up mechanism ignores invalid events, such as the sound of people passing by, or when the ambient volume is high, the smart doorbell wakes up frequently, resulting in increased power consumption.

[0053] The main solution of the embodiment of the present application is: if an access control event is triggered when the processor is in sleep mode, the audio signal and image signal collected by the acquisition module are obtained, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode; the audio signal and the image signal are input into the intention recognition model of the recognition module to obtain the intention recognition result; if the intention recognition result is access control wake-up, the processor is woken up.

[0054] Specifically, after an access control event is triggered in a low-power state, relevant information of the triggering event is identified instead of directly waking up the processor to put the access control system into normal working mode, thereby avoiding false triggering of invalid events and increasing the power consumption of the access control system.

[0055] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, an access control system, etc., and the access control system can be a smart doorbell. The following uses the access control system as an example to illustrate this embodiment and the following embodiments.

[0056] The functional modules of the access control system of this application are as follows Figure 1 As shown, the access control system includes an acquisition module, an identification module, and a processor connected in sequence. These three modules perform data acquisition, identification, and processing, respectively. When an access control event is triggered, data acquisition, valid event identification, and processor wakeup are completed. In low-power mode, the acquisition module operates in this low-power state, resulting in lower data acquisition accuracy than in normal mode.

[0057] The processor is connected to the acquisition module via the processing module and is used to process the data collected by the acquisition module. Optionally, the access control system further includes a display module, a storage module, and a communication module, with the processor connected to the display module, the storage module, and the communication module, respectively. When the processor is dormant, the access control system is in a low-power state.

[0058] For details, please refer to Figure 1 and Figure 2 The acquisition module consists of multiple cameras (also known as image sensors) and microphones. The cameras capture video images in front of the door, providing real-time visual information such as human activity and object movement. The microphones collect sound information, including voices and knocks. In low-power mode, the processor is dormant. When no events occur, the acquisition module operates in a low-power mode, maintaining only basic signal detection capabilities. Upon detecting an approaching person or a sound intensity reaching a certain threshold, the acquisition module transmits the captured video and sound information to the recognition and processing modules.

[0059] Optionally, the acquisition module can also be configured to include a low-cost piezoelectric vibration sensor or a dedicated low-power infrasonic microphone. The sensor can effectively distinguish between human activities such as approaching, stomping, and knocking on the door, and environmental noise such as wind, distant car sounds, running sounds, and talking sounds, thereby reducing the shortcomings of audio detection when the ambient audio is relatively noisy.

[0060] Please continue to refer to Figure 2 The recognition module also includes an analog front-end unit, a signal processing unit, and an output interface. After the microphone and image sensor of the acquisition module send data to the recognition module, the recognition module uses the analog front-end unit based on the audio interface protocol (I 2 C bus) and clock signal interface (CLK) for data feedback. Furthermore, the analog front-end unit is used to perform preliminary processing on the video signal collected by the camera and the audio signal collected by the microphone, such as amplifying the audio signal, converting the format of the video signal, etc., and transmit the processed signal to the signal processing unit; the signal processing unit recognizes the amplified and converted audio and video signals, such as recognizing faces and human body movements in the video, recognizing specific sounds in the audio (such as preset door opening sounds, specific voice commands), etc., and transmits the recognition results to the processor through the output interface, so that the processor switches states (such as waking up the processor) or performs corresponding operations according to the recognition results. Optionally, the signal processing unit of the recognition module also sets an intention recognition model, and recognizes and processes the signal through the intention recognition model to identify the user's intention to open the door in the audio and video data. The intention recognition model can be a pre-trained neural network model or a lightweight artificial intelligence model.

[0061] The processing module includes a video processing unit, an audio processing unit and a communication interface. The video processing unit processes the image information collected by the acquisition module, the audio processing unit processes the audio data collected by the acquisition module, and transmits the processed data to the processor based on the communication interface.

[0062] Furthermore, the processor, serving as the core control unit of the access control system, controls the switching of the operating state of the entire intelligent access control system, for example, switching from a low-power state to an active state, based on the recognition results transmitted by the recognition module. It is understood that when the processor is dormant, the intelligent access control system is in a low-power state, and after the processor wakes up, the intelligent access control system is in an active state. Simultaneously, the processor analyzes and processes the audio and video information processed by the processing module and performs corresponding operations, such as triggering an alarm based on the communication module, storing video images and audio in the storage module, and sending information to the user's mobile phone via the communication module.

[0063] The display module is used to display relevant information of the access control system, such as real-time video images, historical record playback, operation prompt information, etc., so that users can intuitively understand the situation in front of the door and the status of the equipment.

[0064] The storage module is used to store information such as video image data collected by the camera, audio data collected by the microphone, and recognition results, so that users can view and analyze them later.

[0065] The communication module supports communication with terminal devices such as user mobile phones, and transmits information collected by the smart doorbell, alarm information, etc. to the user's mobile phone APP in real time through wireless networks (such as Wi-Fi, 4G / 5G). Users can also remotely control related functions of the smart access control through the mobile phone APP.

[0066] Based on the functional modules of the access control system described above, the present application provides a control method for the access control system. Figure 3 , Figure 3 This is a flow chart of the first embodiment of the control method of the access control system of the present application.

[0067] In this embodiment, the control method of the access control system includes steps S10 to S30:

[0068] Step S10: If an access control event is triggered when the processor is in sleep mode, the audio signal and image signal collected by the collection module are obtained.

[0069] In this embodiment, the access control system is in a low-power state when the processor is dormant, and the access control event refers to the wake-up condition of the access control system in the conventional low-power state, such as the bell ringing event, the human passing event, the pet approaching the access control, and the excessive ambient sound. In a conventional smart doorbell or smart access control, when the movement of people, the loud ambient sound, and the user ringing the bell are detected in the low-power state, the processor of the access control system is awakened, causing the access control system to enter normal mode. Among these events, there are usually invalid events, such as the passing of neighbors in the human passing event, or the arrival and dropping of items by takeaway personnel or couriers, and the excessive ambient sound events include the sound of heavy rain, the noisy sound of people talking, etc. When the processor is awakened based on an invalid event, the access control system enters an invalid working state, which increases the power consumption of the access control system.

[0070] After the acquisition module collects image and audio data, it can use a simple image change detection algorithm to determine whether there are moving objects in the graphics, and use an audio detection algorithm to detect whether the sound intensity is greater than the preset intensity, so as to trigger access control events based on information such as moving objects and sound intensity.

[0071] Therefore, as an optional implementation, if there is a moving object in the image captured by the acquisition module, or the intensity of the captured audio exceeds a preset intensity, then an access control event is triggered. Thus, if there is movement of people or objects around the access control system, or if the sound is loud, it is determined that an event is currently occurring.

[0072] In another optional embodiment, after the acquisition module detects the presence of a moving object in the image, it is further necessary to determine whether the captured audio intensity exceeds a preset intensity. If so, an access control event is triggered. This ensures that the access control event is triggered only when both conditions are met, increasing the confidence level of the access control event. Furthermore, if the audio intensity exceeds the preset intensity, the system can further determine whether a moving object is present in the image.

[0073] After the access control event is triggered, the image signal collected by the image sensor of the acquisition module and the audio signal collected by the microphone are obtained, so that the image signal and the audio signal can be analyzed and judged by the recognition module to determine whether the access control event is a valid event.

[0074] It should be noted that after responding to these invalid events, the conventional access control system enters the working mode, and operates based on normal power in the working mode. After the access control system is awakened, the acquisition module continues to collect high-quality data, and the processor continues to analyze the high-quality data. Compared with identifying the data collected in the low-power state, the power consumption of a single erroneous access control system working mode switch is much higher than identifying the low-quality data collected in the low-power state.

[0075] Therefore, after the access control system enters operating mode due to an incorrect processor wakeup, the processor must continue to analyze and process data, including continuously collecting and analyzing high-precision video and audio data within a preset period of time. Due to the larger amount of data and higher data accuracy, the power consumption is relatively higher. Therefore, the power consumption loss caused by the access control system processing actions executed after the processor is woken up by an invalid event is much higher than the power consumption used during the normal recognition process.

[0076] Step S20: Input the audio signal and the image signal into the intention recognition model of the recognition module to obtain an intention recognition result.

[0077] In this embodiment, the recognition module can be configured with an intent recognition model, which can be a pre-trained neural network model or a lightweight artificial intelligence model. When recognizing audio and image signals, the intents corresponding to the audio and image signals can be identified separately and the identified intents can be integrated to obtain an intent recognition result.

[0078] Therefore, the speech intention of the audio signal and the action intention of the moving object in the image signal can be determined based on the intention recognition model, and then the speech intention and its confidence, the action intention and its confidence are integrated to obtain the intention recognition result.

[0079] Specifically, as an optional implementation, when the intent recognition model is a neural network model, the image signal can be processed using the model's image recognition algorithm to extract image feature information. This information can then be used to calculate the moving objects in the image, thereby determining the intended motion of the moving objects. Simultaneously, conventional audio processing algorithms, such as voice recognition and audio comparison, can be used to process the signal to determine the intended speech.

[0080] Among them, the action intention includes the action that the mobile object wants to perform, such as moving in a certain direction, knocking on the door, etc., and the corresponding intention recognition result is access control wake-up. The voice intention includes the idea expressed by the mobile object based on voice, such as "Is anyone there?" Its corresponding voice intention is "knock on the door", and the corresponding intention recognition result is access control wake-up. When the user talks, "Why didn't you open the door just now? I've been waiting for you for a long time", the voice intention is normal communication, and its corresponding intention recognition result is invalid intention. Furthermore, the specific weighted fusion process is not described in detail in this application.

[0081] In another optional embodiment, the intention recognition model is a lightweight artificial intelligence model, which performs image and voice recognition analysis based on the artificial intelligence model to obtain more accurate action intentions and voice intentions.

[0082] It should be noted that the audio signal-based recognition and preset audio matching method may identify irrelevant speech with keywords as qualified audio signals. For example, if two people pass by and the conversation is "Why didn't you open the door just now? I've been waiting for you for a long time," although the content related to the keyword "open the door" is recognized, it is essentially a person passing by, resulting in a misjudgment and causing the processor to wake up inadvertently. Similarly, when someone passes by the access control system, it will also cause the processor to wake up inadvertently.

[0083] By identifying the person's action intent and the voice intent of their voice, the system identifies what the user wants to do rather than matching keywords or user identity information, thereby more accurately determining whether the current access control event is a valid event. It is understandable that if there is no person in the image signal, the action intent is null, and the same applies to audio signals.

[0084] Optionally, before step S20, it is also necessary to determine whether the image signal and audio meet the conditions for intention recognition. Therefore, it is also necessary to determine the living body type of the moving object in the image signal based on the recognition model, and / or determine whether the audio signal matches the preset audio. If the living body type is not human, and / or the audio signal does not match the preset audio, the image signal and audio signal need to be ignored. For example, if the moving object is a rolling ball or a pet dog, its living body type is not human and does not meet the requirements. There is no need to process the current signal, that is, there is no need to wake up the processor. Similarly, if there is no content in the audio signal that matches the preset audio, such as no keywords, no knocking sounds, etc., the signal can also be ignored. If at least one of the above conditions is met, both signals can be ignored at the same time to avoid invalid wake-ups.

[0085] Step S30: If the intention recognition result is access control wakeup, wake up the processor.

[0086] In this embodiment, the intention recognition result is access control wake-up and invalid intention, that is, if the user intention is recognized as access control wake-up, the processor needs to be woken up, otherwise the current status quo is maintained.

[0087] It should be noted that if the intent recognition result is access control wakeup, it indicates that the access control event is a valid event, otherwise it is an invalid event. Therefore, when the intent recognition result is an invalid intention, the access control system maintains the current operating parameters to avoid increased power consumption due to invalid event waking up the processor.

[0088] This embodiment provides a control method for an access control system. After an access control event is triggered when the processor is in sleep mode, the audio signal and image signal are recognized and analyzed by a lightweight artificial intelligence model or a neural network model of the recognition module, and whether the access control event is an invalid event is determined based on the identified intent recognition result, thereby effectively reducing the probability of processor false wake-up, improving the battery life of the access control system, and avoiding increased power consumption due to waking up the processor due to invalid events.

[0089] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be described in detail later. Figure 4 After step S30, the access control system control method further includes steps S40 to S60:

[0090] Step S40: acquiring the target video and target audio captured by the capture module, and performing high-definition encoding processing on the target video, and performing noise reduction and enhancement processing on the audio information based on the processing module.

[0091] In this embodiment, after waking up the processor, the processor will send a working signal to the processing module. After receiving the working signal, the processing module will switch to normal mode and further process the audio and video information transmitted by the acquisition module, such as high-definition encoding of the video, noise reduction and enhancement of the audio, etc., and transmit the processed information to the processor.

[0092] Step S50: output the processed audio and video information to the display terminal and the client.

[0093] In this embodiment, the processor can perform corresponding operations based on the processed audio and video information and recognition results, such as displaying real-time video on the display module and storing video and audio data in the storage module. The communication module sends alarm information and real-time video to the user's mobile phone, allowing the user to view the situation at the door through the mobile phone app and perform remote operations (such as voice communication with the visitor). Therefore, the processed audio and video information can be output to the display terminal and client.

[0094] Step S60: If the access control event is not triggered within a preset period of time, or if the processing signal from the client is not received, the processor is controlled to enter a dormant state.

[0095] In this embodiment, the processor will also enter a dormant state again if no new event occurs within a period of time, such as a set event-free duration of 5 minutes. The processing module switches back to low-power mode or dormant mode, and the acquisition module returns to a low-power operating state, waiting for the next event trigger. Therefore, if no access control event is triggered within the preset period or no processing signal is received from the client, the processor enters a dormant state.

[0096] This embodiment provides a control method for an access control system, which wakes up a processor to put the access control system into working mode, and uses the processor to intelligently process audio, display and notify data, and automatically sleep when no events occur, thereby avoiding continuous operation of the access control system and reducing the power consumption of the access control system.

[0097] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be repeated hereafter. On this basis, after step S20, the control method of the access control system further includes steps S70 to S90:

[0098] Step S70: Obtain the target stay area corresponding to the access control system.

[0099] Step S80: Determine the residence time of the moving object in the target residence area in the image signal.

[0100] Step S90: If the dwell time is less than the preset time, the system operates based on the current operating parameters.

[0101] In this embodiment, a spatial semantic map is constructed to determine the processor's wake-up recognition. Specifically, the access control system defines high-value areas, such as doormats and package storage areas. A decision is made only after a moving object enters a high-value area and remains there for longer than a preset time. High-value areas are user-defined areas pre-stored in a local database.

[0102] Therefore, when the processor is dormant, it can directly retrieve the target dwell area from the local database, then determine the dwell time of the moving object in the target dwell area in the image signal. If the dwell time is less than the preset time, the system will operate based on the current operating parameters. Based on this, by demarcating specific areas and dwell time, the access control system can effectively avoid frequent processor wake-ups when people pass by, thereby filtering out valid access control events with actual load requirements, such as a user stopping at a doormat waiting for the door to open.

[0103] For example, a courier habitually leaves the item at the door and then leaves. In this case, the courier's time in the target area does not exceed the preset 5 seconds, so there's no need to wake up the processor. This avoids wasted power consumption caused by the absence of a courier after waking up. The above parameters are for illustrative purposes only; the specific preset time value can be set based on actual needs.

[0104] Optionally, in addition to screening pedestrians and identifying them through the recognition module, they can also be identified through neighboring devices connected to the access control system. Neighboring devices are other devices connected to the same local area network that are in continuous operation, such as private elevators, high-definition cameras independent of the access control system, etc. Therefore, when an access control event is triggered while the processor is in sleep mode, the neighboring device can automatically identify the current scene and generate an identification result of the access control event based on the identified scene content, and feed the identification result (simple signaling) back to the access control system. After receiving the signaling, the identification module of the access control system deems the current access control event to be a valid event. At this time, the identification result that the access control event is a valid event is sent to the processor to wake up the processor, thereby performing detection and identification based on other devices in the same local area network. When the processor of the access control system is in sleep mode, it only needs to turn on the low-power signal transmission channel to achieve remote identification of the event. By judging whether to wake up the processor through the neighboring device, the number of false wake-ups of the processor is reduced, thereby reducing power consumption.

[0105] Furthermore, the processor can be determined to wake up by analyzing the frequency of access control event triggering within the current time period. Specifically, after triggering an access control event and acquiring image and audio signals, the current time is recorded and access control event recognition results and recognition frequency are continuously acquired within a preset time period. If an access control event is still triggered within the preset time period, and the recognition frequency is greater than the preset frequency corresponding to the current time, the recognition result of a valid event is sent to the processor to wake it up. For example, if the current time is 6:00 a.m., which is usually the processor's sleep time, and a user is jogging or hiking, and an access control event is triggered at this time, and no access control event is subsequently triggered within the next 1 to 3 minutes, the current access control event is considered an invalid event. Similarly, if the access control event is continuously triggered for more than 3 times within 1 to 3 minutes, it indicates that the current situation is special, and the access control event is determined to be a valid event, and the processor is woken up. Based on this, identification and judgment based on the current time and the number of access control event triggering within the preset time period avoids waking up the processor directly after a single access control event detection, which would cause the access control system to frequently wake up and waste power.

[0106] For example, in order to help understand the implementation process of the control method of the access control system obtained by combining the above embodiments, please refer to Figure 5 , Figure 5A brief flow chart of a control method for an access control system is provided, taking a doorbell as an example. Specifically: when the smart doorbell is started and the processor is in a dormant state, the processing module runs based on low power consumption or enters a dormant state, while the acquisition module performs data detection based on a low power consumption mode. Subsequently, the acquisition module detects whether an event occurs. If an event occurs, the collected information is transmitted to the identification module. Based on the identification module, it is determined whether the event is a valid event. If not, continuous monitoring is performed. If so, the processor is awakened. The processor sends a working signal to the processing module, causing the processing module to switch to a normal mode and perform information processing. The processed information is then transmitted to the processor. Finally, the processor performs corresponding operations such as data display, storage, and communication processing, and then continues to detect whether there are new events. If so, the corresponding operations are continued. If not, the processor is dormant for a preset period of time. The processor module continues to maintain low power consumption or dormancy, and the acquisition module continues to collect information based on low power consumption.

[0107] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the control method of the access control system of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0108] The present application provides an access control system, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the control method of the access control system in the first embodiment described above.

[0109] Reference below Figure 6 , which shows a structural diagram of an access control system suitable for implementing an embodiment of the present application. Figure 6 The access control system shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0110] like Figure 6As shown, the access control system may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the access control system are also stored in the random access memory 1004. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the access control system to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an access control system with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or have instead.

[0111] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0112] The access control system provided by this application utilizes the control method for the access control system in the above-mentioned embodiment, which can solve the technical problem of increased power consumption caused by the easy awakening of smart doorbells in low-power state. Compared with the prior art, the beneficial effects of the access control system provided by this application are the same as those of the control method for the access control system provided by the above-mentioned embodiment. The other technical features of this access control system are the same as those disclosed in the above-mentioned embodiment and are not further described here.

[0113] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0114] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0115] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the control method of the access control system in the above-mentioned embodiment.

[0116] The computer-readable storage medium provided in this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM, Erasable Programmable ReadOnly Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM, CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequency (RF, Radio Frequency), etc., or any suitable combination thereof.

[0117] The computer-readable storage medium may be included in the access control system; or it may exist independently without being installed in the access control system.

[0118] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the access control system, the access control system: if an access control event is triggered when the processor is dormant, obtain the audio signal and image signal collected by the acquisition module, wherein, in the low-power state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode;

[0119] Inputting the audio signal and the image signal into the intention recognition model of the recognition module to obtain an intention recognition result;

[0120] If the intention recognition result is access control wakeup, wake up the processor.

[0121] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0123] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0124] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned access control system control method. This computer-readable storage medium can address the technical issue of increased power consumption caused by the smart doorbell being easily awakened in a low-power state. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the access control system control method provided in the aforementioned embodiment, and are not further elaborated here.

[0125] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A control method for an access control system, characterized in that: Applied to an access control system, the access control system includes an acquisition module, an identification module, and a processor connected in sequence. When the processor is dormant, the access control system is in a low-power state. The control method of the access control system includes: If an access control event is triggered when the processor is dormant, the audio signal and the image signal collected by the acquisition module are acquired, wherein in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode; Inputting the audio signal and the image signal into the intention recognition model of the recognition module to obtain an intention recognition result; If the intention recognition result is access control wakeup, wake up the processor.

2. The control method of the access control system according to claim 1, characterized in that: Before the step of inputting the audio signal and the image signal into the intention recognition model, the control method of the access control system further includes: Determining the living body type of the moving object in the image signal; and / or Determining whether the audio signal matches a preset audio signal; If the living body type is not a human body, and / or the audio signal does not match the preset audio, the image signal and the audio signal are ignored.

3. The control method of the access control system according to claim 1, characterized in that: The processor is connected to the acquisition module based on the processing module. If the intention recognition result is access control wakeup, after the step of waking up the processor, the control method of the access control system further includes: Acquire the target video and target audio captured by the acquisition module, and perform high-definition encoding processing on the target video and noise reduction and enhancement processing on the audio information based on the processing module; Output the processed audio and video information to the display terminal and the client; If the access control event is not triggered within a preset period of time, or if the processing signal from the client is not received, the processor is controlled to enter a dormant state.

4. The control method of the access control system according to claim 1, characterized in that: Before the step of triggering an access control event when the processor is in sleep mode and acquiring the audio signal and image signal collected by the acquisition module, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode, the control method of the access control system further includes: The access control event is triggered when there is a moving object in the image captured by the capture module, or the intensity of the captured audio is greater than a preset intensity; or After detecting the presence of a moving object in the image captured by the capture module, determining whether the intensity of the captured audio is greater than a preset intensity; If so, the access control event is triggered.

5. The control method of the access control system according to claim 1, characterized in that: The step of inputting the audio signal and the image signal into the intention recognition model of the recognition module to obtain an intention recognition result includes: determining a speech intention of the audio signal and a motion intention of a moving object in the image signal based on the intention recognition model; The speech intention and its confidence level, and the action intention and its confidence level are integrated to obtain the intention recognition result.

6. The control method of the access control system according to claim 1, characterized in that: After the step of triggering an access control event when the processor is in sleep mode, acquiring the audio signal and the image signal collected by the acquisition module, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode, the control method of the access control system further includes: Obtaining the target stay area corresponding to the access control system; determining a stay time of the moving object in the target stay area in the image signal; If the dwell time is less than the preset time, the system will run based on the current operating parameters.

7. The control method of the access control system according to claim 1, characterized in that: The access control system is connected to a neighboring device, and the control method of the access control system further includes: If an access control event is triggered while the processor is in sleep mode, obtaining a target recognition result of the access control event fed back by the neighboring device; If the target recognition result is a valid event, wake up the processor; otherwise The access control system operates based on current operating parameters.

8. The control method of the access control system according to claim 1, characterized in that: After the step of triggering an access control event when the processor is in sleep mode, acquiring the audio signal and the image signal collected by the acquisition module, wherein, in the low power consumption state, the data acquisition accuracy of the acquisition module is lower than the data acquisition accuracy in the working mode, the control method of the access control system further includes: Record the current moment and continuously obtain access control event recognition results and recognition frequency within the preset time period; If the access control event is still triggered within the preset time period, and the recognition frequency is greater than the preset frequency corresponding to the current moment, the processor is awakened.

9. An access control system, characterized in that: The access control system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for controlling the access control system according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the control method of the access control system according to any one of claims 1 to 8 are implemented.

Images