Doorbell control and application system based on video

Abstract

The invention relates to the technical field of online control, in particular to a video-based doorbell control application system, which specifically comprises a video stream data acquisition module, a behavior characteristic analysis module, a trigger risk assessment module, a control parameter calculation module and a doorbell trigger control module. The doorbell solves the problems that in the prior art, a traditional doorbell is complex in wiring at the initial stage of installation, wiring adjustment at the later stage is difficult, and electricity utilization and electricity taking are difficult.

Description

Technical Field

[0001] The present invention relates to the field of online control technology and is a video-based doorbell control application system. Background Art

[0002] Traditional doorbell systems have shown significant limitations in long-term applications. First, wired doorbells rely on physical wiring, requiring dedicated cables to be buried in advance. The construction complexity is high, and it is difficult to adjust later. Especially in the renovation of old buildings or multi-floor scenarios, the cost of line maintenance increases sharply, and signal attenuation is easily caused by the limitation of the wall structure. Second, there are technical bottlenecks in the power supply method. Traditional wired doorbells need to be connected to the mains power nearby, while wireless doorbells, although getting rid of the wiring constraint, rely on battery power supply. Frequent battery replacement is neither environmentally friendly nor likely to cause equipment failure. In addition, most existing wireless visual doorbells use the 2.4GHz frequency band for transmission, which is vulnerable to interference from devices such as Wi-Fi and Bluetooth, and lacks adaptive frequency hopping technology, resulting in insufficient signal stability.

[0003] At the functional implementation level, traditional doorbells are triggered by physical buttons and cannot actively identify the dynamics in front of the door. Although some solutions introduce video monitoring, most rely on a single camera for collection and lack in-depth analysis of human behavior characteristics. For example, existing technologies only trigger the doorbell through simple motion detection, which is vulnerable to environmental interference, such as changes in light and shadow and pet activities, resulting in false triggers. At the same time, most systems do not integrate environmental parameters for comprehensive decision-making, reducing the reliability of the trigger logic. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] The technical problem to be solved by the present invention is to address the problems in the prior art that traditional doorbells are difficult to adjust the wiring later due to complex wiring during the initial installation and difficult to obtain power. A video-based doorbell control application system is proposed.

[0006] To achieve the above object, the video-based doorbell control application system of the present invention includes the following modules:

[0007] A video stream data acquisition module, a behavior feature analysis module, a trigger risk assessment module, a control parameter calculation module, and a doorbell trigger control module;

[0008] The video stream data acquisition module is used to collect video stream data of the area in front of the door in real time;

[0009] The behavioral feature analysis module is used to build a mapping relationship model between human behavioral features and doorbell trigger responses;

[0010] The trigger risk assessment module evaluates the risk level of the current doorbell trigger according to the mapping relationship model;

[0011] The control parameter calculation module calculates doorbell trigger control parameters according to the trigger risk level;

[0012] The doorbell trigger control module cooperatively controls the doorbell trigger action according to the control parameters.

[0013] Specifically, the doorbell trigger control module includes: a main trigger unit, an auxiliary recognition unit, a false trigger suppression unit, and a signal enhancement unit; among them, the main trigger unit is used to control the core parameters of the doorbell trigger signal, including: trigger response time and signal strength; the auxiliary recognition unit is used to enhance the accuracy of human feature recognition; the false trigger suppression unit is used to filter out environmental interference signals, and the control parameters include: environmental light threshold and moving object size threshold; the signal enhancement unit is used to optimize the transmission stability of the doorbell trigger signal.

[0014] Specifically, the video stream data acquisition module includes: a multi-dimensional sensor group, a historical video storage unit, a human behavioral feature library, an environmental parameter acquisition unit, an interference signal recording unit, and a false trigger log module;

[0015] The multi-dimensional sensor group is used to collect video streams, infrared thermal imaging data, and environmental sound data in front of the door;

[0016] The historical video storage unit is used to store video clips of historical trigger events;

[0017] The human behavioral feature library is used to record feature data such as different human postures and moving speeds;

[0018] The environmental parameter acquisition unit is used to record environmental data such as light intensity and weather conditions;

[0019] The interference signal recording unit is used to store environmental interference data during false triggers;

[0020] The false trigger log module is used to record the timestamps and trigger parameters of false trigger events.

[0021] Specifically, the behavioral feature analysis module is used to run the following strategies:

[0022] S11: Build a multi-modal behavior analysis model, where the input of the model is video stream data and environmental parameters, and the output is the correlation curve between human behavioral features and doorbell trigger probabilities;

[0023] S12: Extract the human body movement speed data and posture feature data from the historical video storage unit, and synchronously extract the light intensity data of the environmental parameter acquisition unit;

[0024] S13: Input the data in S12 into the behavior analysis model to calculate the trigger probability correction coefficient. The specific calculation strategy is as follows:

[0025]

[0026] where pre represents the current timestamp;

[0027] TE pre represents the trigger probability prediction value at the current timestamp;

[0028] TE t represents the reference trigger probability;

[0029] λ is the environmental light influence factor, and α1 and α2 are respectively the movement speed influence factors of the human arm and leg;

[0030] n is a subscript representing the video frame number, and N is the total number of frames; ls n ,zs n are respectively the movement speeds of the human arm and leg in the nth frame; are respectively the average values of the movement speeds of the human arm and leg in N video frames on the circulation pipeline.

[0031] Specifically, the behavior feature analysis module is also used to run the following strategy:

[0032] S14: Extract the interference signal data, environmental parameter data, and historical gain parameters of the signal enhancement unit from the historical mis-trigger log;

[0033] S15: Input the data in S14 into the behavior analysis model to calculate the mis-trigger suppression coefficient. The specific calculation strategy is as follows:

[0034]

[0035] where QP pre represents the mis-trigger suppression coefficient at the current timestamp;

[0036] QP t represents the reference suppression coefficient;

[0037] The calculation strategy for the noise distribution uniformity is the average value of the pixel distances between adjacent noise points in all video frames; M is the scene complexity coefficient;

[0038] f n represents the camera gain adjustment value when the nth data frame is captured; is the average value of the camera gain adjustment values when capturing N data frames in the video stream;

[0039] pc in is the intensity of the human approach event, i is the subscript, representing the i-th approach event, and I is the total number of approach events; is the human residence time of the i-th approach event; is the average residence time of the human body in I approach events;

[0040] pc out is the intensity of the human approach event, j is the subscript, representing the j-th departure event, and J is the total number of departure events; is the human residence time of the j-th departure event; is the average residence time of the human body in J departure events.

[0041] Specifically, the trigger risk assessment module includes: a trigger probability calculation unit, a false trigger suppression coefficient extraction unit, a comprehensive risk assessment unit, and a risk level determination unit; among them, the assessment strategy of the comprehensive risk assessment unit is:

[0042]

[0043] where, Fx pre represents the trigger risk value at the current timestamp.

[0044] Specifically, the assessment strategy executed by the risk level determination unit is as follows:

[0045] Preset threshold ranges Q1, Q2, Q3 for different risk levels to perform risk level assessment;

[0046] When 0 ≤ Fx pre ≤ Q1, it is determined that the perfusion risk level is low risk;

[0047] When Q1 < Fx per ≤ Q2, it is determined that the perfusion risk level is medium risk;

[0048] When Q2 < F pre ≤ Q3, it is determined that the perfusion risk level is high risk.

[0049] Specifically, the control strategy running in the control parameter calculation module is: when the current risk level is medium risk or high risk, extract the maximum trigger probability correction coefficient and the maximum false trigger suppression coefficient, and input them into the behavior analysis model to calculate and obtain the doorbell trigger control parameters; the doorbell trigger control module adjusts the trigger threshold and signal gain according to the control parameters.

[0050] A storage medium stores instructions, which, when read by a computer, cause the computer to run the above-mentioned video-based doorbell control application system.

[0051] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor runs the computer program, it implements the above-mentioned video-based doorbell control application system.

[0052] Compared with the prior art, the technical effects of the present invention are as follows:

[0053] 1. The system of the present invention adopts a pure wireless architecture, realizes device interconnection through LoRaWAN long-distance and low-power communication technology, and the single-node communication distance can reach 3 km (line of sight), without laying dedicated signal lines. With the solar / lithium battery dual power supply system, the device battery life is extended, solving the problems of cumbersome wiring and difficult power supply of traditional doorbells.

[0054] 2. Based on the multi-modal behavior analysis model, the system integrates human movement speed, stay time, posture features (12 basic postures + custom feature library) and environmental parameters for trigger decision-making. The trigger threshold is adjusted in real time through the false trigger suppression coefficient, effectively reducing the false trigger rate.

[0055] 3. Through the continuous iteration of the historical false trigger log and the behavior feature library (updated with more than 1000 feature samples per day on average), the system realizes self-optimization. When the detected trigger risk value is greater than 0.7, it automatically enters the deep learning mode and optimizes the behavior recognition model using the transfer learning algorithm (model update cycle: 4 hours), so that the average false trigger rate of the system is further reduced after 6 months of use, significantly superior to the traditional fixed threshold scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0057] Among them:

[0058] Figure 1 is a schematic structural diagram of the video-based doorbell control application system of the present invention;

[0059] Figure 2 is a schematic flow diagram of the operation strategy of a behavior feature analysis module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification.

[0061] In the following description, numerous specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0062] Secondly, as used herein, "one embodiment" or "an embodiment" refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive of other embodiments.

[0063] Embodiment 1:

[0064] As Figure 1 shown, the video-based doorbell control application system according to an embodiment of the present invention, as Figure 1 shown, includes the following modules:

[0065] A video stream data acquisition module, a behavior feature analysis module, a trigger risk assessment module, a control parameter calculation module, and a doorbell trigger control module;

[0066] The video stream data acquisition module is used to collect video stream data of the area in front of the door in real time;

[0067] The video stream data acquisition module includes: a multi-dimensional sensor group, a historical video storage unit, a human body behavior feature library, an environmental parameter acquisition unit, an interference signal recording unit, and a mis-trigger log module;

[0068] The multi-dimensional sensor group is used to collect video streams, infrared thermal imaging data, and environmental sound data of the area in front of the door;

[0069] The historical video storage unit is used to store video clips of historical trigger events;

[0070] The human body behavior feature library is used to record feature data such as different human postures and moving speeds;

[0071] The environmental parameter acquisition unit is used to record environmental data such as light intensity and weather conditions;

[0072] The interference signal recording unit is used to store environmental interference data during mis-triggering;

[0073] The mis-trigger log module is used to record the time stamps and trigger parameters of mis-trigger events.

[0074] The behavioral feature analysis module is used to construct a mapping relationship model between human body behavior features and doorbell trigger responses;

[0075] The behavioral feature analysis module is used to run the following strategy:

[0076] S11: Construct a multi-modal behavior analysis model, where the input of the model is video stream data and environmental parameters, and the output is the correlation curve between human body behavior features and doorbell trigger probabilities;

[0077] S12: Extract the human body movement speed data and posture feature data in the historical video storage unit, and synchronously extract the light intensity data of the environmental parameter acquisition unit;

[0078] S13: Input the data in S12 into the behavior analysis model to calculate the trigger probability correction coefficient. The specific calculation strategy is:

[0079]

[0080] where pre represents the current timestamp;

[0081] TE pre represents the trigger probability prediction value of the current timestamp;

[0082] TE t represents the benchmark trigger probability;

[0083] λ is the environmental light influence factor, and α1 and α2 are respectively the movement speed influence factors of the human arm and leg;

[0084] n is a subscript representing the video frame number, and N is the total number of frames; ls n ,zs n are respectively the movement speeds of the human arm and leg in the nth frame; are respectively the average values of the movement speeds of the human arm and leg in N video frames on the circulation pipeline.

[0085] S14: Extract the interference signal data, environmental parameter data and historical gain parameters of the signal enhancement unit in the historical mis-triggering log;

[0086] S15: Input the data in S14 into the behavior analysis model to calculate the mis-triggering suppression coefficient. The specific calculation strategy is:

[0087]

[0088] where QP pre represents the mis-triggering suppression coefficient of the current timestamp;

[0089] QP t represents the benchmark suppression coefficient;

[0090] The calculation strategy for the uniformity of noise distribution is the average pixel distance between adjacent noises in all video frames; M is the scene complexity coefficient;

[0091] f n represents the camera gain adjustment value when the nth data frame is captured; is the average value of the camera gain adjustment values when N data frames in the video stream are captured;

[0092] pc in is the intensity of the human approach event, i is a subscript representing the ith approach event, and I is the total number of approach events; is the human stay time of the ith approach event; is the average human stay time among I approach events;

[0093] pc out is the intensity of the human approach event, j is a subscript representing the jth departure event, and J is the total number of departure events; is the human stay time of the jth departure event; is the average human stay time among J departure events.

[0094] The trigger risk assessment module evaluates the risk level of the current doorbell trigger according to the mapping relationship model;

[0095] The trigger risk assessment module includes: a trigger probability calculation unit, a false trigger suppression coefficient extraction unit, a comprehensive risk assessment unit, and a risk level determination unit; among them, the assessment strategy of the comprehensive risk assessment unit is:

[0096]

[0097] Among them, Fx pre represents the trigger risk value at the current timestamp.

[0098] The assessment strategy executed by the risk level determination unit is specifically as follows:

[0099] Preset threshold ranges Q1, Q2, Q3 for different risk levels to perform risk level assessment;

[0100] When 0 ≤ Fx pre ≤ Q1, it is determined that the perfusion risk level is a low risk;

[0101] When Q1 < Fx per ≤ Q2, it is determined that the perfusion risk level is a medium risk;

[0102] When Q2 < F preWhen Q3 ≤, the perfusion risk level is determined to be a high risk.

[0103] The control parameter calculation module calculates the doorbell trigger control parameter according to the trigger risk level;

[0104] The control strategy running in the control parameter calculation module is specifically as follows: when the current risk level is medium risk or high risk, extract the maximum trigger probability correction coefficient and the maximum false trigger suppression coefficient, and input them into the behavior analysis model to calculate and obtain the doorbell trigger control parameter; the doorbell trigger control module adjusts the trigger threshold and signal gain according to the control parameter.

[0105] The doorbell trigger control module collaboratively controls the doorbell trigger action according to the control parameter.

[0106] The doorbell trigger control module includes: a main trigger unit, an auxiliary recognition unit, a false trigger suppression unit, and a signal enhancement unit; wherein, the main trigger unit is used to control the core parameters of the doorbell trigger signal, including: trigger response time and signal strength; the auxiliary recognition unit is used to enhance the accuracy of human feature recognition; the false trigger suppression unit is used to filter environmental interference signals, and the control parameters include: environmental light threshold and moving object size threshold; the signal enhancement unit is used to optimize the transmission stability of the doorbell trigger signal.

[0107] Embodiment 2:

[0108] This embodiment provides an electronic device, including: a processor and a memory, wherein, a computer program that can be called by the processor is stored in the memory;

[0109] The processor runs the above-mentioned video-based doorbell control application system by calling the computer program stored in the memory.

[0110] This electronic device may have relatively large differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) and one or more memories. Among them, at least one computer program is stored in the memory, and this computer program is loaded and executed by the processor to implement the video-based doorbell control application system provided by the above method embodiment. This electronic device can also include other components for realizing the functions of the device. For example, this electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for data input and output. This embodiment will not be elaborated here.

[0111] Embodiment 3:

[0112] This embodiment proposes a computer-readable storage medium, on which a rewritable computer program is stored;

[0113] When the computer program runs on a computer device, it causes the computer device to execute the above-mentioned video-based doorbell control application system.

[0114] For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0115] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution is prior or posterior. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0116] It should be understood that determining B based on A does not mean determining B only based on A, and B can also be determined based on A and / or other information.

[0117] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0118] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0119] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0120] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only one way, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings, direct couplings, or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0123] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0124] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will also have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. A video-based doorbell control application system, characterized in that, The system includes the following modules: A video stream data acquisition module, a behavior feature analysis module, a trigger risk assessment module, a control parameter calculation module, and a doorbell trigger control module; The video stream data acquisition module is used to collect video stream data of the area in front of the door in real time; The behavior feature analysis module is used to build a mapping relationship model between human behavior features and doorbell trigger responses; The trigger risk assessment module evaluates the risk level of the current doorbell trigger according to the mapping relationship model; The control parameter calculation module calculates doorbell trigger control parameters according to the trigger risk level; The doorbell trigger control module cooperatively controls the doorbell trigger action according to the control parameters.

2. The video-based doorbell control application system according to claim 1, wherein The doorbell trigger control module includes: a main trigger unit, an auxiliary recognition unit, a false trigger suppression unit, and a signal enhancement unit; among them, the main trigger unit is used to control the core parameters of the doorbell trigger signal, including: trigger response time and signal strength; the auxiliary recognition unit is used to enhance the accuracy of human feature recognition; the false trigger suppression unit is used to filter environmental interference signals, and the control parameters include: environmental light threshold and moving object size threshold; the signal enhancement unit is used to optimize the transmission stability of the doorbell trigger signal.

3. The video-based doorbell control application system according to claim 2, characterized in that, The video stream data acquisition module includes: a multi-dimensional sensor group, a historical video storage unit, a human behavior feature library, an environmental parameter acquisition unit, an interference signal recording unit, and a false trigger log module; The multi-dimensional sensor group is used to collect video streams, infrared thermal imaging data, and environmental sound data of the area in front of the door; The historical video storage unit is used to store video clips of historical trigger events; The human behavior feature library is used to record feature data such as different human postures and moving speeds; The environmental parameter acquisition unit is used to record environmental data such as light intensity and weather conditions; The interference signal recording unit is used to store environmental interference data during false triggers; The false trigger log module is used to record the timestamps and trigger parameters of false trigger events.

4. The video-based doorbell control application system according to claim 3, wherein, The behavior feature analysis module is used to run the following strategies: S11: Build a multi-modal behavior analysis model, where the input of the model is video stream data and environmental parameters, and the output is an association curve between human behavior features and doorbell trigger probabilities; S12: Extract the human moving speed data and posture feature data in the historical video storage unit, and synchronously extract the light intensity data of the environmental parameter acquisition unit; S13: Input the data in S12 into the behavior analysis model to calculate the trigger probability correction coefficient. The specific calculation strategy is: where pre represents the current timestamp; TE pre Indicates the predicted value of the trigger probability for the current timestamp; TE t represents the reference trigger probability; λ is the environmental light influence factor, and α1 and α2 are the moving speed influence factors of the human arm and leg respectively; n is a subscript representing the video frame number, and N is the total number of frames; ls n , zs n are the moving speeds of the human arm and leg in the n-th frame respectively; are the average values of the moving speeds of the human arm and leg in N video frames on the circulation pipeline respectively.

5. The video-based doorbell control application system according to claim 4, wherein The behavior feature analysis module is also used to run the following strategies: S14: Extract the interference signal data, environmental parameter data, and historical gain parameters of the signal enhancement unit in the historical false trigger log; S15: Input the data in S14 into the behavior analysis model to calculate the false trigger suppression coefficient. The specific calculation strategy is: Among them, QP pre represents the mis-triggering suppression coefficient of the current timestamp; QP t Indicates the reference suppression coefficient; The calculation strategy of the noise distribution uniformity is the average pixel distance between adjacent noises in all video frames; M is the scene complexity coefficient; f n represents the camera gain adjustment value at the capture of the nth data frame; is the average value of the camera gain adjustment values at the capture of N data frames in the video stream; pc in is the intensity of the human approach event, where i is the subscript representing the i-th approach event, and I is the total number of approach events; is the human residence time of the i-th approach event; is the average residence time of humans among I approach events; pc out is the intensity of the human approach event, j is the subscript, representing the j-th departure event, and J is the total number of departure events; is the human residence time of the j-th departure event; is the average residence time of humans in J departure events.

6. The video-based doorbell control application system according to claim 5, characterized in that, The trigger risk assessment module includes: a trigger probability calculation unit, a false trigger suppression coefficient extraction unit, a comprehensive risk assessment unit, and a risk level determination unit; among them, the assessment strategy of the comprehensive risk assessment unit is: Among them, Fx pre represents the trigger risk value of the current timestamp.

7. The video-based doorbell control application system according to claim 6, wherein The assessment strategy executed by the risk level determination unit is specifically as follows: Preset threshold ranges Q1, Q2, Q3 for different risk levels to perform risk level assessment; When 0 ≤ Fx pre ≤ Q1, it is determined that the perfusion risk level is low risk; When Q1 < Fx per ≤ Q2, it is determined that the perfusion risk level is medium risk; When Q2 < F pre ≤ Q3, it is determined that the perfusion risk level is a high risk.

8. The video-based doorbell control application system according to claim 7, wherein The control strategy running in the control parameter calculation module is specifically: when the current risk level is medium risk or high risk, extract the maximum trigger probability correction coefficient and the maximum false trigger suppression coefficient, and input them into the behavior analysis model to calculate and obtain the doorbell trigger control parameter; the doorbell trigger control module adjusts the trigger threshold and signal gain according to the control parameter.

Images