CN-122027768-A - Intelligent event monitoring method, device, electronic equipment and medium

Abstract

The embodiment of the application discloses an intelligent event monitoring method, an intelligent event monitoring device, electronic equipment and a storage medium, which comprise the steps of detecting a current working mode when an interrupt instruction is received, switching the working mode to a signal processing mode if the working mode is a dormant mode, acquiring scene data in a current scene under the signal processing mode, determining whether an intelligent event occurs in a target scene or not based on the scene data, and triggering the switching of the working mode to the dormant mode if the intelligent event does not occur in the target scene.

Inventors

• CHEN LUBIN
• WANG SEN

Assignees

• 深圳市小鹰视界智能有限公司

Dates

Publication Date

20260512

Application Date

20251216

Claims (10)

1. 1. An intelligent event monitoring method, comprising: When an interrupt instruction is received, detecting a current working mode; If the working mode is the sleep mode, switching the working mode to a signal processing mode; in the signal processing mode, scene data in a current scene are collected, and whether an intelligent event occurs in the target scene is determined based on the scene data; and if the intelligent event does not occur in the target scene, triggering to switch the working mode to the sleep mode.
2. 2. The smart event monitoring method of claim 1, wherein the determining whether a smart event has occurred in the target scene based on the scene data comprises: carrying out weighted fusion calculation on the moving speed and contour characteristics of the triggering object in the scene data and the ambient illumination intensity of the target scene in the scene data through a preset algorithm to obtain an event judgment value; and when the event judgment value is larger than a preset threshold value, determining that an intelligent event occurs in the target scene.
3. 3. The smart event monitoring method of claim 1, wherein the determining whether a smart event has occurred in the target scene based on the scene data comprises: Extracting a behavior feature sequence of a trigger object from the scene data; comparing the behavior feature sequence with a reference feature sequence in a preset intelligent event feature library; and if the similarity between the behavior feature sequence and any one of the reference behavior feature sequences is greater than a preset similarity threshold, determining that an intelligent event occurs in the target scene.
4. 4. The intelligent event monitoring method of claim 1, further comprising: triggering to switch the working mode to an early warning mode if the intelligent event occurs in the target scene; And in the early warning mode, the control target early warning component outputs early warning prompt information.
5. 5. The intelligent event monitoring method of claim 1, further comprising: when the interrupt instruction is received, if the working mode is a dormant mode, switching the working mode into a positioning analysis mode; acquiring scene data of the triggering object in the current scene of the real-time position information under the positioning analysis mode; Determining whether the triggering object is in a preset warning area or not based on the real-time position information and the scene data; And if the triggering object is in the preset guard area, executing a preset protection task, and switching the working mode to the sleep mode after executing the preset protection task.
6. 6. The intelligent event monitoring method according to claim 1, wherein detecting the current operation mode when receiving the interrupt command comprises: When an interrupt instruction is received, identifying the instruction type of the interrupt instruction; if the instruction type is the first type, detecting a current working mode; and if the instruction type is the second type, switching the working mode to the early warning mode.
7. 7. The intelligent event monitoring method of claim 1, further comprising: Determining an environment area and a user area in the scene data; adding first Gaussian noise to the region data corresponding to the environment region, and; adding second Gaussian noise to the region data corresponding to the user region, and carrying out fuzzy processing on the portrait of the user in the user region; If no intelligent event occurs, deleting the scene data after the preset time; if intelligent scene data are generated, uploading the processed scene data to a cloud, and encrypting the scene data.
8. 8. An intelligent event monitoring device, comprising: the detection module is used for detecting the current working mode when receiving an interrupt instruction; The first switching module is used for switching the working mode to the signal processing mode if the working mode is the dormant mode; The determining module is used for acquiring scene data in the current scene in the signal processing mode and determining whether an intelligent event occurs in the target scene based on the scene data; And the second switching module is used for triggering the switching of the working mode to the sleep mode if the intelligent event does not occur in the target scene.
9. 9. An electronic device comprising a memory, a processor and a processor program stored on the memory and executable on the processor, wherein the processor executes the program steps of the intelligent event monitoring method according to any of claims 1 to 7.
10. 10. A storage medium storing a computer processing program capable of being loaded by a processor and executing the intelligent event monitoring method according to any of claims 1 to 7.

Description

Intelligent event monitoring method, device, electronic equipment and medium Technical Field The application relates to the technical field of security protection, in particular to an intelligent event monitoring method, an intelligent event monitoring device, electronic equipment and a storage medium. Background With the continuous development of security technology, intelligent home products such as intelligent door locks, intelligent cat eyes and intelligent doorbell have been widely applied to daily life, and one of the core functions is to realize real-time sensing and response to a target scene through intelligent event monitoring, for example, detecting events such as approach, abnormal detention, illegal invasion and the like of a user, and provide security protection and convenient operation experience for the user. The current intelligent event monitoring scheme relies on the sensing signal strength of a sensor to determine, for example, when the sensing signal strength of a certain touch sensor exceeds a set threshold, an emergency event or a preset intrusion event is determined, and at this time, a task being executed by the device is interrupted. Therefore, the current event judgment dimension is single, and the judgment logic is single, namely, the current intelligent event monitoring scheme is easy to be interfered by the environment, so that the judgment precision is low, and the adaptability to complex behavior scenes is poor. Disclosure of Invention The embodiment of the application provides an intelligent event monitoring method, electronic equipment, device and storage medium, which can solve the problems of low judgment precision and poor adaptability to complex behavior scenes caused by environmental interference in intelligent event monitoring in related technologies. In a first aspect, an embodiment of the present application provides an intelligent event monitoring method, including: When an interrupt instruction is received, detecting a current working mode; If the working mode is the sleep mode, switching the working mode to a signal processing mode; in the signal processing mode, scene data in a current scene are collected, and whether an intelligent event occurs in the target scene is determined based on the scene data; and if the intelligent event does not occur in the target scene, triggering to switch the working mode to the sleep mode. Optionally, in some embodiments of the present application, the determining whether a smart event occurs in the target scene based on the scene data includes: carrying out weighted fusion calculation on the moving speed and contour characteristics of the triggering object in the scene data and the ambient illumination intensity of the target scene in the scene data through a preset algorithm to obtain an event judgment value; and when the event judgment value is larger than a preset threshold value, determining that an intelligent event occurs in the target scene. Optionally, in some embodiments of the present application, the determining whether a smart event occurs in the target scene based on the scene data includes: Extracting a behavior feature sequence of a trigger object from the scene data; comparing the behavior feature sequence with a reference feature sequence in a preset intelligent event feature library; and if the similarity between the behavior feature sequence and any one of the reference behavior feature sequences is greater than a preset similarity threshold, determining that an intelligent event occurs in the target scene. Optionally, in some embodiments of the present application, further includes: triggering to switch the working mode to an early warning mode if the intelligent event occurs in the target scene; And in the early warning mode, the control target early warning component outputs early warning prompt information. Optionally, in some embodiments of the present application, further includes: when the interrupt instruction is received, if the working mode is a dormant mode, switching the working mode into a positioning analysis mode; acquiring scene data of the triggering object in the current scene of the real-time position information under the positioning analysis mode; Determining whether the triggering object is in a preset warning area or not based on the real-time position information and the scene data; And if the triggering object is in the preset guard area, executing a preset protection task, and switching the working mode to the sleep mode after executing the preset protection task. Optionally, in some embodiments of the present application, when receiving the interrupt instruction, detecting the current working mode includes: When an interrupt instruction is received, identifying the instruction type of the interrupt instruction; if the instruction type is the first type, detecting a current working mode; and if the instruction type is the second type, switching the working mode to the early warning m