Intelligent event monitoring method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses an intelligent event monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: detecting a current working mode when an interrupt instruction is received; if the working mode is a sleep mode, switching the working mode to a signal processing mode; in the signal processing mode, collecting scene data in a current scene, and determining whether an intelligent event occurs in the target scene based on the scene data; if no intelligent event occurs in the target scene, the working mode is triggered to be switched to the sleep mode, and by means of the scheme, the problems that in the related technology, intelligent event monitoring is prone to being interfered by the environment, so that the judgment precision is low, and adaptability to complex behavior scenes is poor can be solved.

Description

Technical Field

[0001] This application relates to the field of security technology, specifically to an intelligent event monitoring method, device, electronic device, and storage medium. Background Technology

[0002] With the continuous development of security technology, smart door locks, smart peepholes, smart doorbells and other smart home products have been widely used in daily life. One of their core functions is to achieve real-time perception and response to target scenarios through intelligent event monitoring, such as detecting events such as users approaching, abnormal lingering, and illegal intrusion, to provide users with security protection and convenient operation experience.

[0003] Current intelligent event monitoring solutions rely on the strength of sensor signals for judgment. For example, when the signal strength of a certain haptic sensor exceeds a set threshold, it is determined to be an emergency event or a preset intrusion event, and the task being performed by the device is interrupted. It can be seen that the current event judgment dimension is single and the judgment logic is simple. That is, the current intelligent event monitoring solutions are susceptible to environmental interference, resulting in low judgment accuracy, and have poor adaptability to complex behavioral scenarios. Summary of the Invention

[0004] This application provides an intelligent event monitoring method, electronic device, apparatus, and storage medium, which can solve the problems in related technologies where intelligent event monitoring is susceptible to environmental interference, resulting in low judgment accuracy and poor adaptability to complex behavioral scenarios.

[0005] In a first aspect, embodiments of this application provide an intelligent event monitoring method, including: When an interrupt command is received, the current operating mode is checked; If the operating mode is sleep mode, then switch the operating mode to signal processing mode; In the signal processing mode, scene data of the current scene is collected, and it is determined whether an intelligent event has occurred in the target scene based on the scene data; If no intelligent event occurs in the target scenario, the working mode will be switched to sleep mode.

[0006] Optionally, in some embodiments of this application, determining whether an intelligent event has occurred in the target scene based on the scene data includes: The event determination value is obtained by weighted fusion calculation of the movement speed and contour features of the triggering object in the scene data and the ambient light intensity of the target scene in the scene data through a preset algorithm. When the event determination value is greater than a preset threshold, it is determined that an intelligent event has occurred in the target scene.

[0007] Optionally, in some embodiments of this application, determining whether an intelligent event has occurred in the target scene based on the scene data includes: Extract the behavioral feature sequence of the triggering object from the scene data; The behavioral feature sequence is compared with a reference feature sequence in a preset intelligent event feature library; If the similarity between the behavioral feature sequence and any reference behavioral feature sequence is greater than a preset similarity threshold, then it is determined that an intelligent event has occurred in the target scene.

[0008] Optionally, in some embodiments of this application, it further includes: If no intelligent event occurs in the target scenario, the working mode will be switched to the early warning mode. In the aforementioned warning mode, the target warning component outputs warning information.

[0009] Optionally, in some embodiments of this application, it further includes: When the interrupt command is received, if the working mode is sleep mode, the working mode will be switched to location analysis mode. In the location analysis mode, the real-time location information of the triggering object and the scene data in the current scene are obtained; Based on the real-time location information and scene data, determine whether the triggering object is in the preset warning area; If the triggering object is in a preset warning area, a preset protection task is executed, and after the preset protection task is executed, the working mode is switched to sleep mode.

[0010] Optionally, in some embodiments of this application, detecting the current operating mode when an interrupt command is received includes: When an interrupt command is received, the command type of the interrupt command is identified; If the instruction type is the first type, then the current working mode is detected; If the instruction type is the second type, the working mode will be switched to the warning mode.

[0011] Optionally, in some embodiments of this application, it further includes: Determine the environmental area and the user area from the scene data; Add a first Gaussian noise to the regional data corresponding to the environmental region; A second Gaussian noise is added to the regional data corresponding to the user region, and the portrait of the user in the user region is blurred. If no intelligent event occurs, the scene data will be deleted after a preset time. If an intelligent interaction occurs, the processed scene data will be uploaded to the cloud and encrypted.

[0012] Secondly, embodiments of this application provide an intelligent event monitoring device, comprising: The detection module is used to detect the current operating mode when an interrupt command is received; The first switching module is used to switch the working mode to signal processing mode if the working mode is sleep mode. The determination module is used to collect scene data in the current scene under the signal processing mode, and determine whether an intelligent event has occurred in the target scene based on the scene data. The second switching module is used to trigger the switching of the working mode to the sleep mode if no intelligent event occurs in the target scene.

[0013] Accordingly, this application also provides an electronic device, including a memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as described in any of the methods above.

[0014] This application also provides a storage medium storing a processor program that, when executed by a processor, implements any of the methods described above.

[0015] This application provides an intelligent event monitoring method, device, electronic device, and storage medium. When an interrupt command is received, the current working mode is detected. If the working mode is a sleep mode, the working mode is switched to a signal processing mode. In the signal processing mode, scene data of the current scene is collected, and the occurrence of an intelligent event in the target scene is determined based on the scene data. If no intelligent event occurs in the target scene, the working mode is switched back to sleep mode. In the intelligent event monitoring scheme provided by this application, when an interrupt command is received, the current working mode is determined. If the working mode is a sleep mode, the sleep mode is switched to a signal processing mode, and the occurrence of an intelligent event in the target scene is determined by scene data. This method does not rely solely on the intensity of sensor signals for event determination, but rather on scene data. This improves the accuracy of the determination and enhances adaptability to complex scenes. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the intelligent event monitoring method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of the intelligent event monitoring device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0019] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0020] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0021] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0022] The following describes in detail the embodiments involved in this application. It should be noted that the order of description of the embodiments in this application is not intended to limit the priority of the embodiments.

[0023] This application provides an intelligent event monitoring method, apparatus, storage medium, and intelligent terminal. Specifically, the intelligent event monitoring method of this application can be executed by an intelligent terminal or a server, wherein the intelligent terminal can be a terminal. The terminal can be a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other intelligent terminal. The terminal may also include a client, which can be a media playback client or a real-time intelligent event monitoring client, etc.

[0024] This application provides an intelligent event monitoring method, which can be executed by an electronic device or a server. This application example illustrates the intelligent event monitoring method executed by an electronic device. The electronic device includes a touchscreen display and a processor. The touchscreen display is used to present a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. When the user operates the GUI through the touchscreen display, the GUI can control the local content of the electronic device in response to the received operation commands, or it can control the content on the server side in response to the received operation commands.

[0025] The intelligent event monitoring solution provided in this application determines the current working mode when it receives an interrupt command. When the working mode is sleep mode, it switches the sleep mode to signal processing mode and determines whether an intelligent event has occurred in the target scene based on scene data. Instead of judging the event solely based on the intensity of the sensor's sensing signal, it makes a judgment based on scene data, thereby improving the accuracy of the judgment and enhancing its adaptability to complex scenes.

[0026] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0027] A smart event monitoring method includes: when an interrupt command is received, detecting the current working mode; if the working mode is a sleep mode, switching the working mode to a signal processing mode; in the signal processing mode, collecting scene data in the current scene, and determining whether a smart event has occurred in the target scene based on the scene data; if no smart event has occurred in the target scene, triggering the switching of the working mode to a sleep mode.

[0028] Please see Figure 1 , Figure 1 This application provides a flowchart illustrating the intelligent event monitoring method. The specific flow of this intelligent event monitoring method is as follows: 101. When an interrupt command is received, check the current operating mode.

[0029] For example, the outdoor smart security cameras in the community integrate human body sensing sensors (such as infrared sensors) and motion detection modules. When a potential triggering object is detected, an interrupt command is generated and sent to the camera controller. When the camera controller receives the interrupt command, it checks the current working mode.

[0030] Furthermore, if the triggering object is a resident passing by normally, a first type of interrupt command is generated; if the triggering object engages in behaviors such as climbing over walls or wielding weapons, and violent characteristics are detected in the scene data, a second type of interrupt command is generated.

[0031] Optionally, in some embodiments of this application, the step "detecting the current operating mode when an interrupt command is received" may specifically include: When an interrupt command is received, the command type of the interrupt command is identified; If the instruction type is the first type, then the current working mode is detected; If the instruction type is the second type, the working mode will be switched to the warning mode.

[0032] If it is a Type I interrupt instruction, check the current operating mode. If the current mode is sleep mode, proceed to step 102; if the current mode is signal processing or location analysis mode, process them in a queue according to task priority. If it is a second type of interrupt command, it will directly switch to the early warning mode and control the local sound and light early warning unit to start a high-intensity alarm, such as an alarm sound and flashing red light. At the same time, it can also push real-time video streams and early warning information to the property security platform and community police terminal.

[0033] Optionally, in some embodiments of this application, it further includes: When the interrupt command is received, if the working mode is sleep mode, the working mode will be switched to location analysis mode. In the location analysis mode, the real-time location information of the triggering object and the scene data in the current scene are obtained; Based on the real-time location information and scene data, determine whether the triggering object is in the preset warning area; If the triggering object is in a preset warning area, a preset protection task is executed, and after the preset protection task is executed, the working mode is switched to sleep mode.

[0034] The preset protection tasks are determined according to the application scenario. For example, in the smart door lock scenario, the protection tasks are to start identity verification (face recognition, fingerprint recognition) and mechanically reinforce the lock body; in the smart security scenario, the protection tasks are to start video recording, link other smart devices (such as lights and curtains) to enter the alarm state, and make a phone call to emergency contacts; in the smart office scenario, the protection tasks are to restrict access to the area, record the information of the triggered object and upload it to the management backend.

[0035] The positioning analysis mode is a working mode designed by smart cameras for accurate spatial location determination and targeted protection. It is used to simultaneously acquire the real-time location information of the triggering object and multi-dimensional scene data of the target scene to construct a dual judgment input of location and scene; it is also used to determine whether the triggering object is in the preset warning area based on cross-validation of spatial coordinates and scene features, and to start the protection task only when the conditions are met, without executing a generalized response without targeting.

[0036] For example, upon receiving an interrupt command, the smart camera's human body sensor, motion detection module, or associated device detects target activity. If the smart camera's current operating mode is signal processing mode or warning mode, the current task (signal processing mode) is paused (or executed in parallel (warning mode)), prioritizing location determination and protection tasks. Specifically, users can manually draw or select a system-preset template through the camera management app; the warning area is stored in a local database as a set of coordinates. The acquired real-time location coordinates are converted into a coordinate system consistent with the preset warning area to ensure a unified judgment benchmark. Then, a spatial geometric algorithm is used to determine whether the converted real-time coordinate point falls within the coordinate range of the preset warning area: if the coordinate point is within the range, it is initially determined to be within the warning area; if the coordinate point is outside the range, it is initially determined to be outside the warning area.

[0037] If it is initially determined that the area is within a warning zone, and the distance between the triggering object and the camera in the scene data is within the distance range of the warning zone, then it is confirmed that the area is within a warning zone. If the initial determination is that the location is not within the warning zone, but the distance of the triggering object in the scene data is within the warning zone, the location data is collected again for re-determination; if the two determinations are consistent, the final determination result is output; if they are inconsistent, the location is determined to be not within the warning zone to avoid misjudgment.

[0038] Furthermore, if it is determined that the area is in a warning zone, the corresponding preset protection task will be activated, and the location analysis mode will be maintained during the task execution. Once the task is completed (such as recording is completed or the warning is successfully pushed), or if there is no new trigger within a preset time (30 minutes), the working mode will be switched to sleep mode to restore the low power consumption state.

[0039] If it is determined that the area is not within the warning zone, the protection task will not be executed, and the working mode will be directly switched to the sleep mode. At the same time, the privacy protection process will be performed on the collected location data and scene data.

[0040] Optionally, in some embodiments of this application, it may further include: Determine the environmental area and the user area from the scene data; Add a first Gaussian noise to the regional data corresponding to the environmental region; A second Gaussian noise is added to the regional data corresponding to the user region, and the portrait of the user in the user region is blurred. If no intelligent event occurs, the scene data will be deleted after a preset time. If an intelligent interaction occurs, the processed scene data will be uploaded to the cloud and encrypted.

[0041] Region segmentation is the foundation of privacy protection. Pixel-level semantic segmentation enables precise identification of sensitive areas, ensuring that de-identification processing only applies to privacy-related areas. For example, specifically, when an outdoor smart camera in a residential community collects scene data of a pedestrian loitering in a warning area in signal processing mode, it determines that an abnormal loitering event has occurred. For the scene data, the Mask R-CNN algorithm can be used to perform pixel-level segmentation of the video frames, marking the pedestrian's face and limb areas as the user area, and the wall and ground as the environment area. Then, a first Gaussian noise (mean 0, variance 0.02) is added to the environment area, and a second Gaussian noise (mean 0, variance 0.08) is added to the user area. A 15×15 kernel Gaussian blur is then applied to the pedestrian's face. Next, the de-identified data is encrypted and stored in a local secure partition (AES-256 encryption), and the de-identified data is uploaded via HTTPS protocol (TLS 1.3).

[0042] 102. If the working mode is sleep mode, switch the working mode to signal processing mode.

[0043] Signal processing mode is the core working mode of the smart camera, designed specifically for scene data acquisition and intelligent event judgment. It is mainly used to synchronously collect multi-dimensional data of the target scene to provide complete input for intelligent event judgment; run preset judgment algorithms (weighted fusion calculation, behavioral feature sequence comparison, etc.) to accurately determine whether an intelligent event has occurred, without directly executing business operations such as early warning and linkage protection.

[0044] Switching the operating mode to signal processing mode allows the controller to control the camera's image sensor, light sensor, and infrared sensor to synchronously acquire scene data. For example, after parsing the interrupt type and confirming that the current mode is sleep mode, a switching command is triggered. Specifically, this can involve disabling low-power configuration, restoring the CPU frequency to 1GHz, and powering the image sensor and light sensor. After powering on, the image sensor starts at 4K / 30 frames / second, and the light sensor starts sampling at 10 times / second.

[0045] 103. In the signal processing mode, scene data of the current scene is collected, and the occurrence of an intelligent event in the target scene is determined based on the scene data.

[0046] Intelligent events refer to specific behaviors or states detected by intelligent cameras in a target scene that require subsequent responses (such as early warning, protection, and data retention). These can include ordinary proximity events, abnormal loitering events, illegal intrusion events, and violent sabotage events. Ordinary proximity events refer to the triggering object slowly moving towards the camera or a preset warning area, with a dwell time of 10-30 seconds; abnormal loitering events refer to the triggering object wandering aimlessly within the warning area for a dwell time exceeding a preset threshold; illegal intrusion events refer to the triggering object breaking through security boundaries (such as climbing over walls or prying open doors and windows) to enter the warning area, with the behavior being sudden; violent sabotage events refer to the triggering object engaging in destructive behavior towards the camera or surrounding protective facilities (such as prying open the camera or wielding weapons), with the scene data containing characteristics such as impact and mechanical force.

[0047] Non-intelligent events refer to events such as pets running, leaves rustling, vehicles passing by, and sudden changes in light that have no security implications, involve non-human subjects, or involve meaningless behavior.

[0048] To avoid misjudgment based on a single dimension, multi-feature cross-validation can be used. Specifically, weighted calculations can be performed on movement speed, contour features, and ambient light intensity to obtain an event determination value. Based on the event determination value, it can be determined whether an intelligent event has occurred in the target scene. That is, optionally, in some embodiments of this application, the step "determining whether an intelligent event has occurred in the target scene based on the scene data" may specifically include: The event determination value is obtained by weighted fusion calculation of the movement speed and contour features of the triggering object in the scene data and the ambient light intensity of the target scene in the scene data through a preset algorithm. When the event determination value is greater than a preset threshold, it is determined that an intelligent event has occurred in the target scene.

[0049] For example, the pixel coordinates of the trigger object can be obtained from 10 consecutive video frames. The actual movement distance can be calculated by the calibration relationship between pixels and actual distance. For example, 10 pixels equals 0.5 actual distance. Dividing by the frame interval time gives the movement speed, which is then normalized to [0,1]. At the same time, the Canny edge detection algorithm is used to extract the contour key points of the trigger object. These are compared with locally stored contour templates of adults, children, and pets to calculate the contour similarity. The similarity pair is then normalized to the [0,1] interval. In addition, the light intensity captured by the camera can be normalized to the [0,1] interval to correct contour extraction errors.

[0050] Furthermore, the weights corresponding to contour features, movement speed, and ambient light intensity are assigned as a, b, and c, respectively, and the event determination value is determined by the preset formula: event determination value = a * contour similarity + b * movement speed + c * ambient light intensity, where a + b + c = 1; if the determination value is greater than the preset threshold, an intelligent event is determined to have occurred.

[0051] Furthermore, the behavioral feature sequence of the triggering object can be extracted and compared with a preset intelligent event feature library. Optionally, in some embodiments of this application, the step "determining whether an intelligent event has occurred in the target scene based on the scene data" may specifically include: Extract the behavioral feature sequence of the triggering object from the scene data; The behavioral feature sequence is compared with a reference feature sequence in a preset intelligent event feature library; If the similarity between the behavioral feature sequence and any reference behavioral feature sequence is greater than a preset similarity threshold, then it is determined that an intelligent event has occurred in the target scene.

[0052] Using 30 frames of video data corresponding to 1 second as a time window, features are continuously extracted from 4 time windows to form a 3×30 behavioral feature matrix (i.e., behavioral feature sequence). Specifically, 3 key features are extracted from each frame, including limb movement state, change in movement direction, and dwell time percentage (i.e., the percentage of frames in the monitoring area where the triggering object is located within the time window, normalized to the [0,1] interval). The preset intelligent event feature library contains standard feature sequences of events such as ordinary approach, abnormal lingering, illegal intrusion, and violent destruction. Then, the Dynamic Time Warping (DTW) algorithm is used to calculate the distance between the sequence to be judged and the standard sequence (the smaller the distance, the higher the similarity), and the distance value is converted into a similarity score. If the similarity score is greater than the preset similarity score, the corresponding type of intelligent event is judged to have occurred. If the similarity score is less than or equal to the preset similarity score, but greater than or equal to the baseline similarity score, a second acquisition is triggered and a re-judgment is performed. If the similarity score is less than the baseline similarity score, the intelligent event is judged not to have occurred.

[0053] Optionally, in some embodiments of this application, it may further include: If no intelligent event occurs in the target scenario, the working mode will be switched to the early warning mode. In the aforementioned warning mode, the target warning component outputs warning information.

[0054] The target early warning component is a multi-functional early warning module integrated into smart devices, including an audible and visual early warning unit, a remote communication unit, and a local alert unit. Different early warning strategies correspond to different types of smart events: for ordinary proximity events, only the local alert unit outputs a soft light alert (such as flashing blue LEDs); for abnormal loitering events, the audible and visual early warning unit outputs a low-intensity audible and visual alert, while simultaneously pushing reminder information to associated terminals via the remote communication unit; for illegal intrusion events, the audible and visual early warning unit outputs a high-intensity audible and visual alarm, and the remote communication unit simultaneously pushes real-time early warning information, including event type, occurrence time, and scene screenshots, to associated terminals and the property security platform.

[0055] 104. If no intelligent event occurs in the target scenario, the working mode will be switched to sleep mode.

[0056] The intelligent event monitoring method provided in this application detects the current working mode when an interrupt command is received. If the working mode is a sleep mode, the working mode is switched to a signal processing mode. In the signal processing mode, scene data in the current scene is collected, and the occurrence of an intelligent event in the target scene is determined based on the scene data. If no intelligent event occurs in the target scene, the working mode is switched back to the sleep mode. In the intelligent event monitoring scheme provided in this application, when an interrupt command is received, the current working mode is determined. If the working mode is a sleep mode, the sleep mode is switched to the signal processing mode, and the occurrence of an intelligent event in the target scene is determined based on scene data. This method does not rely solely on the intensity of the sensor's sensing signal to determine the event, but rather on scene data. This improves the accuracy of the determination and enhances the adaptability to complex scenes.

[0057] To facilitate better implementation of the intelligent event monitoring method of this application embodiment, this application embodiment also provides an intelligent event monitoring device. The meanings of the terms used are the same as those in the intelligent event monitoring system described above, and specific implementation details can be found in the description of the system embodiment.

[0058] Please see Figure 2 , Figure 2This is a schematic diagram of the structure of the intelligent event monitoring device provided in an embodiment of this application. The intelligent event monitoring device may specifically include a detection module 201, a first switching module 202, a determination module 203, and a second switching module 204, as follows: The detection module 201 is used to detect the current working mode when an interrupt command is received; The first switching module 202 is used to switch the working mode to signal processing mode if the working mode is sleep mode; The determination module 203 is used to collect scene data in the current scene under the signal processing mode, and determine whether an intelligent event has occurred in the target scene based on the scene data. The second switching module 204 is used to trigger the switching of the working mode to the sleep mode if no intelligent event occurs in the target scene.

[0059] This application provides an intelligent event monitoring device. When the detection module 201 receives an interrupt command, it detects the current working mode. If the working mode is a sleep mode, the first switching module 202 switches the working mode to a signal processing mode. In the signal processing mode, the determination module 203 collects scene data of the current scene and determines whether an intelligent event has occurred in the target scene based on the scene data. If no intelligent event has occurred in the target scene, the second switching module 204 triggers a switch to a sleep mode. In the intelligent event monitoring scheme provided by this application, when an interrupt command is received, the current working mode is determined. When the working mode is a sleep mode, the sleep mode is switched to a signal processing mode, and the scene data is used to determine whether an intelligent event has occurred in the target scene. This is not a simple event judgment based on the sensor's sensing signal strength, but a judgment based on scene data. This improves the accuracy of the judgment and enhances the adaptability to complex scenes.

[0060] Furthermore, embodiments of this application also provide an electronic device, such as... Figure 3 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically: The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more processor-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 302, and by calling data stored in the memory 302, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless intelligent event monitoring. It is understood that the modem processor may also not be integrated into the processor 301.

[0061] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and intelligent event monitoring methods by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0062] The electronic device also includes a power supply 303 that supplies power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 303 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0063] The electronic device may also include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0064] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 302 according to the following instructions, and the processor 301 runs the applications stored in the memory 302 to realize various functions, as follows: When an interrupt command is received, the current working mode is checked; if the working mode is sleep mode, the working mode is switched to signal processing mode; in the signal processing mode, scene data in the current scene is collected, and the scene data is used to determine whether an intelligent event has occurred in the target scene; if no intelligent event has occurred in the target scene, the working mode is switched to sleep mode.

[0065] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0066] In this embodiment, when an interrupt command is received, the current working mode is detected. If the working mode is a sleep mode, the working mode is switched to a signal processing mode. In the signal processing mode, scene data of the current scene is collected, and it is determined whether an intelligent event has occurred in the target scene based on the scene data. If no intelligent event has occurred in the target scene, the working mode is switched to a sleep mode. In the intelligent event monitoring scheme provided in this application, when an interrupt command is received, the current working mode is determined. If the working mode is a sleep mode, the sleep mode is switched to a signal processing mode, and the scene data is used to determine whether an intelligent event has occurred in the target scene. This is not a simple event judgment based on the sensor's sensing signal strength, but a judgment based on scene data. This improves the accuracy of the judgment and enhances the adaptability to complex scenes.

[0067] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a processor-readable storage medium and loaded and executed by a processor.

[0068] Therefore, embodiments of this application provide a storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the intelligent event monitoring methods provided in embodiments of this application. For example, the instructions can execute the following steps: When an interrupt command is received, the current working mode is checked; if the working mode is sleep mode, the working mode is switched to signal processing mode; in the signal processing mode, scene data in the current scene is collected, and the scene data is used to determine whether an intelligent event has occurred in the target scene; if no intelligent event has occurred in the target scene, the working mode is switched to sleep mode.

[0069] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0070] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0071] Since the instructions stored in the storage medium can execute the steps of any of the intelligent event monitoring methods provided in the embodiments of this application, the beneficial effects that any of the intelligent event monitoring methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0072] The above provides a detailed description of an intelligent event monitoring method, device, electronic device, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An intelligent event monitoring method, characterized in that, include: When an interrupt command is received, the current operating mode is checked; If the operating mode is sleep mode, then switch the operating mode to signal processing mode; In the signal processing mode, scene data of the current scene is collected, and it is determined whether an intelligent event has occurred in the target scene based on the scene data; If no intelligent event occurs in the target scenario, the working mode will be switched to sleep mode.

2. The intelligent event monitoring method according to claim 1, characterized in that, Determining whether an intelligent event has occurred in the target scene based on the scene data includes: The event determination value is obtained by weighted fusion calculation of the movement speed and contour features of the triggering object in the scene data and the ambient light intensity of the target scene in the scene data through a preset algorithm. When the event determination value is greater than a preset threshold, it is determined that an intelligent event has occurred in the target scene.

3. The intelligent event monitoring method according to claim 1, characterized in that, Determining whether an intelligent event has occurred in the target scene based on the scene data includes: Extract the behavioral feature sequence of the triggering object from the scene data; The behavioral feature sequence is compared with a reference feature sequence in a preset intelligent event feature library; If the similarity between the behavioral feature sequence and any reference behavioral feature sequence is greater than a preset similarity threshold, then it is determined that an intelligent event has occurred in the target scene.

4. The intelligent event monitoring method according to claim 1, characterized in that, Also includes: If no intelligent event occurs in the target scenario, the working mode will be switched to the early warning mode. In the aforementioned warning mode, the target warning component outputs warning information.

5. The intelligent event monitoring method according to claim 1, characterized in that, Also includes: When the interrupt command is received, if the working mode is sleep mode, the working mode will be switched to location analysis mode. In the location analysis mode, the real-time location information of the triggering object and the scene data in the current scene are obtained; Based on the real-time location information and scene data, determine whether the triggering object is in the preset warning area; If the triggering object is in a preset warning area, a preset protection task is executed, and after the preset protection task is executed, the working mode is switched to sleep mode.

6. The intelligent event monitoring method according to claim 1, characterized in that, The step of detecting the current operating mode when an interrupt command is received includes: When an interrupt command is received, the command type of the interrupt command is identified; If the instruction type is the first type, then the current working mode is detected; If the instruction type is the second type, the working mode will be switched to the warning mode.

7. The intelligent event monitoring method according to claim 1, characterized in that, Also includes: Determine the environmental area and the user area from the scene data; Add a first Gaussian noise to the regional data corresponding to the environmental region; A second Gaussian noise is added to the regional data corresponding to the user region, and the portrait of the user in the user region is blurred. If no intelligent event occurs, the scene data will be deleted after a preset time. If an intelligent interaction occurs, the processed scene data will be uploaded to the cloud and encrypted.

8. An intelligent event monitoring device, characterized in that, include: The detection module is used to detect the current operating mode when an interrupt command is received; The first switching module is used to switch the working mode to signal processing mode if the working mode is sleep mode. The determination module is used to collect scene data in the current scene under the signal processing mode, and determine whether an intelligent event has occurred in the target scene based on the scene data. The second switching module is used to trigger the switching of the working mode to the sleep mode if no intelligent event occurs in the target scene.

9. An electronic device, characterized in that, include: A memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as steps of the intelligent event monitoring method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The computer processing program is stored and can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images