Intelligent security intercom system based on PIR and AI behavior analysis

Abstract

The invention discloses an intelligent security intercom system based on PIR and AI behavior analysis, and belongs to the technical field of intelligent security, and the system comprises a video collection module which is used for obtaining the video data of a monitoring area in real time; the AI behavior analysis module is used for performing three-level model reasoning, cross-camera trajectory tracking and skeleton key point anomaly calculation on the video data, performing dynamic behavior recognition and generating an analysis result; the talkback communication module is used for dynamically configuring a communication strategy through a behavior risk assessment algorithm, establishing a multi-mode response mechanism and establishing a video two-way communication channel based on the multi-mode response mechanism; and the system control module is used for coordinating a transmission link of the video data based on the four-stage pipeline architecture, a dynamic resource scheduling mechanism and an energy efficiency optimization strategy, and triggering talkback when a preset risk behavior is identified. According to the invention, optimal balance between safety protection and energy efficiency ratio can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent security, and particularly to an intelligent security intercom system based on PIR and AI behavior analysis. Background Art

[0002] Traditional security systems are automated protection systems that monitor a target area in real time through a sensor network and trigger an alarm when an anomaly is detected. Its core structure consists of three parts: (1) a data acquisition layer that collects data through sensors such as cameras / PIRs / radars; (2) a data processing layer that performs signal conversion and feature extraction; and (3) a response execution layer that uses alarms / intercom systems to respond to the analysis results. Its basic working principle is a linear process of "perception - analysis - response", where traditional PIR systems rely on changes in infrared thermal radiation to detect biological movement, and pure vision AI systems analyze video content through computer vision algorithms.

[0003] Traditional PIR systems can only detect the movement of heat sources and cannot distinguish the intentions of personnel (such as maintenance workers and burglars), and are easily interfered by environmental temperature; although pure vision AI systems can recognize complex behaviors, they need to continuously run deep models, resulting in high energy consumption, and their performance degrades sharply in scenarios such as low light. The common pain points of both are: the limitations of single sensing modalities, the mismatch between resource allocation and scenario requirements, and the low efficiency of multi-source data collaboration.

[0004] Traditional hierarchical analysis uses fixed cascade models, such as detection - classification - tracking models, which have the problem of a rigid calculation pipeline: over - calculating for simple scenarios (such as still objects still performing full - model analysis), and may miss detections due to insufficient resources for complex events. This architecture lacks dynamic adaptability and is difficult to balance the contradiction between real - time performance and accuracy. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present invention proposes an intelligent security intercom system based on PIR and AI behavior analysis, which can achieve the optimal balance between security protection and energy efficiency ratio.

[0006] An embodiment of the present invention provides an intelligent security intercom system based on PIR and AI behavior analysis, including: a video acquisition module for real-time acquisition of video data in a monitoring area; the video acquisition module includes a low-power standby unit for activating the high-definition video acquisition function through an external trigger signal; the external trigger signal comes from a PIR sensor, which generates a wake-up instruction and transmits it to the video acquisition module after detecting a human heat source; an AI behavior analysis module for performing three-level model inference, cross-camera trajectory tracking, and calculation of the anomaly degree of bone key points on the video data, performing dynamic behavior recognition, and generating an analysis result; the three-level model includes a YOLO-Nano object detection model, a ResNet18 behavior classification model, and a 3D-CNN spatio-temporal modeling model; the AI behavior analysis module includes a dual-mode verification mechanism unit for cross-verifying the PIR signal and the preliminary AI analysis result, and directly triggering a response when the two are consistent by skipping the in-depth analysis steps of the ResNet18 behavior classification model and the 3D-CNN spatio-temporal modeling model; an intercom communication module for dynamically configuring a communication strategy through a behavior risk assessment algorithm, establishing a multi-modal response mechanism, and establishing a video two-way communication channel based on the multi-modal response mechanism; a system control module for coordinating the transmission link of video data based on a four-level pipeline architecture, a dynamic resource scheduling mechanism, and an energy efficiency optimization strategy, and triggering an intercom when a preset risk behavior is recognized; the four-level pipeline architecture includes: an acquisition layer for directly writing data into the FPGA preprocessing unit through a DMA channel when the video acquisition module outputs RAW data; a preprocessing layer for integrating an H.265 hardware encoder to perform dynamic bitrate control on the video stream; a transmission layer for directly mapping the encoded video stream to the network protocol stack memory space by deploying a zero-copy transmission technology; an analysis layer for establishing a priority queue, and the AI behavior analysis module extracts data from the shared memory pool through RDMA.

[0007] According to some embodiments of the present invention, the AI behavior analysis module includes: a dynamic sampling regulation unit for real-time acquisition of the target movement speed parameter through a PIR sensor and establishing a frame rate-speed mapping model; the frame rate-speed mapping model includes: when the target movement speed is lower than a first threshold, sampling is performed at a first frame rate interval, and the picture is reconstructed in cooperation with a motion compensation algorithm; when the target movement speed is in the interval greater than the first threshold and less than a second threshold, a second frame rate reference sampling is enabled, and the picture is reconstructed in cooperation with a motion compensation algorithm; when the target movement speed exceeds the second threshold, it switches to a third frame rate full-frame mode.

[0008] According to some embodiments of the present invention, the AI behavior analysis module includes: a regional interest focusing unit, which is used to establish a dynamic area of interest based on the heat source coordinates provided by the PIR, and generate three concentric analysis areas with the heat source as the center: a core area, a buffer area and a peripheral area; perform pixel-level feature analysis on the core area, downsample the buffer area, and only perform motion detection on the peripheral area; use an adaptive ROI segmentation algorithm to automatically merge the analysis areas when the distance between multiple heat sources is less than the first distance.

[0009] According to some embodiments of the present invention, the AI behavior analysis module includes: a multi-level analysis pipeline unit, which is used to construct a three-level cascade analysis architecture to realize three-level model reasoning: a primary pipeline, an intermediate pipeline and an advanced pipeline; the primary pipeline runs a lightweight YOLO-Nano model to complete basic target detection; the intermediate pipeline activates ResNet18 for behavior classification when an anomaly is detected; the advanced pipeline only loads a 3D CNN spatiotemporal model for high-risk events; and confidence valves are set between each level of the pipeline.

[0010] According to some embodiments of the present invention, the AI behavior analysis module includes: a timing association optimization unit, which is used to align PIR pulses and video frame sequences through a hardware timestamp synchronizer to establish an event timeline database; an improved LSTM network is used to analyze continuous events, and when a wandering-climbing-intrusion pattern sequence is detected, the event danger level is automatically increased; and time compression storage is performed on heat sources that have been stationary for more than a first time interval, retaining only the first and last key frames and the middle differential frames.

[0011] According to some embodiments of the present invention, the AI behavior analysis module includes: an energy efficiency perception model unit, a built-in environmental status evaluator, which is used to dynamically adjust the model complexity by comprehensively considering the light intensity and the PIR activation frequency; when the PIR detects no activity for a second consecutive time interval, the behavior recognition model is automatically uninstalled and only the motion detection function is retained; the chip operating condition is monitored through a temperature sensor, and a computing resource reallocation strategy is triggered when overheating occurs.

[0012] According to some embodiments of the present invention, the dual-mode verification mechanism unit is used to design a PIR-AI confidence fusion algorithm; when the PIR is continuously triggered and the AI detects a valid target within the third time interval, it calls the pre-stored response strategy to skip the ResNet18 behavior classification model and the 3D-CNN spatio-temporal modeling model; for verification conflict events, it starts a delay review mechanism: continuously collects data in the fourth time interval and then makes a secondary determination. If there is still a conflict, it is marked as a device failure; among them, the confidence calculation of the PIR-AI confidence fusion algorithm is: PIR confidence = 1 - 0.5^(number of consecutive triggers), AI confidence = detection box IOU × classification probability, PIR-AI fusion confidence = A * PIR confidence + B * AI confidence, where A and B are coefficients; the verification conflict events include: the deviation between the PIR trigger time and the AI detection time window exceeds the set threshold, the PIR is continuously triggered but the AI has no detection, the AI identification is abnormal but the PIR has no feedback, and the difference between the confidence levels of both sides is greater than the set threshold.

[0013] According to some embodiments of the present invention, the intercom communication module includes: a behavior risk assessment unit, which is used to construct a spatio-temporal feature vector based on the behavior type, duration, and trajectory coordinates, and output a risk level using an XGBoost classifier.

[0014] According to some embodiments of the present invention, the intercom communication module includes: a multi-modal response mechanism unit, which is used to determine a combined response mode based on the risk level, and the combined response mode includes: a combination of voice inquiry and log recording, a combination of video intercom and AI bypass monitoring, and a combination of alarm linkage and drone tracking.

[0015] According to some embodiments of the present invention, the system control module includes: a dynamic resource scheduling unit, which is used to assign dynamic weights to each video channel based on an improved weighted fair queueing algorithm, and perform computing resource scheduling based on the dynamic weights; the dynamic weight allocation algorithm is as follows: ; where, is the dynamic weight of the i-th video channel, is the PIR trigger intensity, and the PIR trigger intensity = PIR signal amplitude × duration, is the risk level output by the AI behavior analysis, is the computing complexity score of the current analysis model, is a coefficient.

[0016] An intelligent security intercom system based on PIR and AI behavior analysis according to an embodiment of the present invention has at least the following beneficial effects: Through PIR-AI dual-mode verification in the embodiment of the present invention, the advantages of sensors are complemented with each other. Dynamic sampling regulation and a three-level concentric analysis area are used to achieve precise allocation of computing resources. Combining with time-series correlation optimization to solve the problem of multi-source data synchronization. The analysis depth is dynamically adjusted according to the environmental state through an energy efficiency perception model, and the multi-level analysis pipeline realizes intelligent inference degradation through a confidence valve. Through the synergistic effect of the above technical features, the performance bottlenecks of traditional systems in aspects such as false alarm rate, energy consumption, and response speed can be broken through, and the optimal balance between security protection and energy efficiency ratio can be achieved.

[0017] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0019] Figure 1 It is a schematic block diagram of the modules of the system according to an embodiment of the present invention.

[0020] REFERENCE SIGNS

[0021] Video acquisition module 100, AI behavior analysis module 200, intercom communication module 300, system control module 400. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0023] In the description of the present invention, the meaning of "a number of" is one or more, the meaning of "a plurality of" is two or more, and "greater than", "less than", "exceeding", etc. are understood not to include the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" and "second", it is only for the purpose of distinguishing technical features and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the sequence of the indicated technical features.

[0024] Referring to Figure 1 , an embodiment of the present invention provides an intelligent security intercom system based on PIR and AI behavior analysis, including:

[0025] The video acquisition module 100 is used to obtain video data of the monitoring area in real time; the video acquisition module includes a low-power standby unit, which is used to activate the high-definition video acquisition function through an external trigger signal; the external trigger signal comes from a PIR sensor, which generates a wake-up instruction after detecting a human heat source and transmits it to the video acquisition module.

[0026] The AI behavior analysis module 200 is used to perform three-level model inference, cross-camera trajectory tracking, and calculation of the anomaly degree of skeletal key points on the video data, perform dynamic behavior recognition, and generate analysis results; the three-level model includes the YOLO-Nano object detection model, the ResNet18 behavior classification model, and the 3D-CNN spatio-temporal modeling model; the AI behavior analysis module includes a dual-mode verification mechanism unit, which is used to cross-verify the PIR signal and the preliminary AI analysis result. When the two are consistent, the in-depth analysis steps of the ResNet18 behavior classification model and the 3D-CNN spatio-temporal modeling model are skipped, and the response is directly triggered.

[0027] The intercom communication module 300 is used to dynamically configure the communication strategy through the behavior risk assessment algorithm, establish a multi-modal response mechanism, and establish a video two-way communication channel based on the multi-modal response mechanism.

[0028] The system control module 400 is used to coordinate the transmission link of the video data based on a four-level pipeline architecture, a dynamic resource scheduling mechanism, and an energy efficiency optimization strategy, and trigger an intercom when a preset risk behavior is recognized.

[0029] The four-level pipeline architecture of the embodiment of the present invention includes:

[0030] The acquisition layer is used to directly write the data into the FPGA preprocessing unit through the DMA channel when the video acquisition module outputs RAW data.

[0031] The preprocessing layer is used to integrate an H.265 hardware encoder to perform dynamic bitrate control on the video stream.

[0032] The transmission layer is used to directly map the encoded video stream to the network protocol stack memory space by deploying the zero-copy transmission technology.

[0033] The analysis layer is used to establish a priority queue, and the AI behavior analysis module extracts data from the shared memory pool through RDMA.

[0034] In some embodiments, the AI behavior analysis module 200 includes: a dynamic sampling and control unit, which is used to obtain the target movement speed parameters in real time through a PIR sensor and establish a frame rate-speed mapping model; the frame rate-speed mapping model includes: when the target movement speed is lower than a first threshold, a first frame rate interval sampling is adopted, and the picture is reconstructed in conjunction with a motion compensation algorithm; when the target movement speed is in a range greater than the first threshold and less than the second threshold, a second frame rate baseline sampling is enabled, and the picture is reconstructed in conjunction with a motion compensation algorithm; when the target movement speed exceeds the second threshold, it is switched to a third frame rate full frame rate mode.

[0035] In some embodiments, the AI behavior analysis module 200 includes: a regional interest focusing unit, which is used to establish a dynamic area of interest based on the heat source coordinates provided by the PIR, and generate three concentric analysis areas with the heat source as the center: a core area, a buffer area and a peripheral area; perform pixel-level feature analysis on the core area, downsample the buffer area, and only perform motion detection on the peripheral area; use an adaptive ROI segmentation algorithm to automatically merge the analysis areas when the distance between multiple heat sources is less than the first distance.

[0036] In some embodiments, the AI behavior analysis module 200 includes: a multi-level analysis pipeline unit, which is used to build a three-level cascade analysis architecture to realize three-level model reasoning: primary pipeline, intermediate pipeline and advanced pipeline; the primary pipeline runs a lightweight YOLO-Nano model to complete basic target detection; the intermediate pipeline activates ResNet18 for behavior classification when an anomaly is detected; the advanced pipeline only loads the 3D CNN spatiotemporal model for high-risk events; and confidence valves are set between each level of pipeline.

[0037] In some embodiments, the AI behavior analysis module 200 includes: a timing association optimization unit, which is used to align the PIR pulse and the video frame sequence through a hardware timestamp synchronizer to establish an event timeline database; use an improved LSTM network to analyze continuous events, and automatically increase the event danger level when a wandering-climbing-intrusion pattern sequence is detected; and compress and store the startup time of a heat source that has been stationary for more than a first time interval, retaining only the first and last key frames and the middle differential frames.

[0038] In some embodiments, the AI behavior analysis module 200 includes: an energy efficiency perception model unit, a built-in environmental status evaluator, which is used to dynamically adjust the model complexity by comprehensively considering the light intensity and the PIR activation frequency; when the PIR detects no activity for a second consecutive time interval, the behavior recognition model is automatically uninstalled and only the motion detection function is retained; the chip operating condition is monitored through a temperature sensor, and a computing resource reallocation strategy is triggered when overheating occurs.

[0039] In some embodiments, the dual-mode verification mechanism unit of the embodiments of the present invention is used to design a PIR-AI confidence fusion algorithm; when the PIR is continuously triggered and the AI detects a valid target within the third time interval, the pre-stored response strategy is called to skip the ResNet18 behavior classification model and the 3D-CNN spatio-temporal modeling model; for verification conflict events, a delay review mechanism is started: after continuously collecting data in the fourth time interval, a secondary determination is made, and if there is still a conflict, it is marked as a device failure; among them, the confidence calculation of the PIR-AI confidence fusion algorithm is: PIR confidence = 1 - 0.5^(number of consecutive triggers), AI confidence = detection box IOU × classification probability, PIR-AI fusion confidence = A * PIR confidence + B * AI confidence, where A and B are coefficients; the verification conflict events include: the deviation between the PIR trigger time and the AI detection time window exceeds the set threshold, the PIR is continuously triggered but the AI has no detection, the AI identification is abnormal but the PIR has no feedback, and the difference between the confidence levels of both sides is greater than the set threshold.

[0040] In some embodiments, the intercom communication module 300 includes: a behavior risk assessment unit, which is used to construct a spatio-temporal feature vector based on the behavior type, duration, and trajectory coordinates, and output a risk level using an XGBoost classifier.

[0041] In some embodiments, the intercom communication module 300 includes: a multi-modal response mechanism unit, which is used to determine a combined response mode based on the risk level, and the combined response mode includes: a combination of voice inquiry and log recording, a combination of video intercom and AI bypass monitoring, and a combination of alarm linkage and drone tracking.

[0042] In some embodiments, the system control module 400 includes: a dynamic resource scheduling unit, which is used to allocate dynamic weights to each video channel based on an improved weighted fair queue algorithm, and perform computing resource scheduling based on the dynamic weights; the dynamic weight allocation algorithm is as follows:

[0043] ;

[0044] Among them, is the dynamic weight of the i-th video channel, is the PIR trigger intensity, and the PIR trigger intensity = PIR signal amplitude × duration, is the risk level output by the AI behavior analysis, is the computing complexity score of the current analysis model, is the coefficient.

[0045] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any one of the functions and / or processing capabilities described in connection with a particular device or component can be performed by any other device or component. Additionally, although various illustrative implementations and architectures have been described in accordance with embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the illustrative implementations and architectures described herein are also within the scope of the present disclosure.

[0046] Those of ordinary skill in the art will appreciate that all or some of the steps and systems disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery media.

[0047] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present application, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present application.

Claims

1. An intelligent security intercom system based on PIR and AI behavior analysis, characterized in that, Including: A video acquisition module for real-time acquisition of video data in a monitored area; The video acquisition module includes a low-power standby unit for activating the high-definition video acquisition function through an external trigger signal; the external trigger signal comes from a PIR sensor, which generates a wake-up instruction after detecting a human heat source and transmits it to the video acquisition module; An AI behavior analysis module for performing three-level model inference, cross-camera trajectory tracking, and calculation of the abnormality degree of skeletal key points on the video data, performing dynamic behavior recognition, and generating an analysis result; the three-level model includes a YOLO-Nano object detection model, a ResNet18 behavior classification model, and a 3D-CNN spatio-temporal modeling model; the AI behavior analysis module includes a dual-mode verification mechanism unit for cross-verifying the PIR signal and the preliminary AI analysis result. When the two are consistent, the in-depth analysis steps of the ResNet18 behavior classification model and the 3D-CNN spatio-temporal modeling model are skipped, and the response is directly triggered; An intercom communication module for dynamically configuring a communication strategy through a behavior risk assessment algorithm, establishing a multi-modal response mechanism, and establishing a video two-way communication channel based on the multi-modal response mechanism; A system control module for coordinating the transmission link of video data based on a four-level pipeline architecture, a dynamic resource scheduling mechanism, and an energy efficiency optimization strategy, and triggering an intercom when a preset risk behavior is recognized; The four-level pipeline architecture includes: An acquisition layer for directly writing data into the FPGA preprocessing unit through a DMA channel when the video acquisition module outputs RAW data; A preprocessing layer for integrating an H.265 hardware encoder to perform dynamic bitrate control on the video stream; A transmission layer for directly mapping the encoded video stream to the network protocol stack memory space by deploying a zero-copy transmission technology; An analysis layer for establishing a priority queue, and the AI behavior analysis module extracts data from the shared memory pool through RDMA.

2. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, characterized in that The AI behavior analysis module includes: A dynamic sampling regulation unit for real-time acquiring the target movement speed parameter through a PIR sensor and establishing a frame rate-speed mapping model; the frame rate-speed mapping model includes: when the target movement speed is lower than the first threshold, sampling is performed at the first frame rate interval, and the picture is reconstructed in cooperation with a motion compensation algorithm; when the target movement speed is in the interval greater than the first threshold and less than the second threshold, the second frame rate reference sampling is enabled, and the picture is reconstructed in cooperation with a motion compensation algorithm; when the target movement speed exceeds the second threshold, it switches to the third frame rate full-frame mode.

3. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, characterized in that, The AI behavior analysis module includes: A region of interest focusing unit for establishing a dynamic attention region based on the heat source coordinates provided by the PIR, generating a three-level concentric analysis region centered on the heat source: a core region, a buffer region, and a peripheral region; performing pixel-level feature analysis on the core region, performing downsampling processing on the buffer region, and only performing motion detection on the peripheral region; adopting an adaptive ROI segmentation algorithm to automatically merge the analysis regions when the distance between multiple heat sources is less than the first distance.

4. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, wherein The AI behavior analysis module includes: The multi-level analysis pipeline unit is used to build a three-level cascade analysis architecture to implement three-level model reasoning: primary pipeline, intermediate pipeline and advanced pipeline; the primary pipeline runs a lightweight YOLO-Nano model to complete basic target detection; the intermediate pipeline activates ResNet18 for behavior classification when an anomaly is detected; the advanced pipeline only loads the 3D CNN spatiotemporal model for high-risk events; and confidence valves are set between each level of the pipeline.

5. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, characterized in that, The AI behavior analysis module includes: The timing association optimization unit is used to align the PIR pulse and video frame sequence through the hardware timestamp synchronizer to establish an event timeline database; an improved LSTM network is used to analyze continuous events, and when a wandering-climbing-intrusion pattern sequence is detected, the event danger level is automatically increased; the heat source startup time compression storage is performed for heat sources that have been stationary for more than the first time interval, and only the first and last key frames and the middle differential frames are retained.

6. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, characterized in that, The AI behavior analysis module includes: The energy-efficiency perception model unit has a built-in environmental status evaluator, which is used to dynamically adjust the model complexity based on the comprehensive light intensity and PIR activation frequency. When the PIR does not detect activity for the second consecutive time interval, the behavior recognition model is automatically uninstalled and only the motion detection function is retained. The chip operating condition is monitored through the temperature sensor, and the computing resource reallocation strategy is triggered when overheating occurs.

7. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, characterized in that, The dual-mode verification mechanism unit is used to design a PIR-AI confidence fusion algorithm; when the PIR is continuously triggered and the AI detects a valid target within the third time interval, the pre-stored response strategy is called to skip the ResNet18 behavior classification model and the 3D-CNN spatiotemporal modeling model; for verification conflict events, a delayed review mechanism is started: a secondary judgment is made after continuously collecting data at the fourth time interval, and if there is still a conflict, it is marked as a device failure; wherein, the confidence calculation of the PIR-AI confidence fusion algorithm is: PIR confidence = 1-0.5^(number of consecutive triggers), AI confidence = detection box IOU × classification probability, PIR-AI fusion confidence = A*PIR confidence + B*AI confidence, where A and B are coefficients; the verification conflict events include: the deviation between the PIR trigger time and the AI detection time window exceeds the set threshold, the PIR is continuously triggered but the AI has no detection, the AI recognizes abnormalities but the PIR has no feedback, and the difference in confidence between the two parties is greater than the set threshold.

8. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, wherein The intercom communication module comprises: The behavioral risk assessment unit is used to construct a spatiotemporal feature vector based on the behavior type, duration, and trajectory coordinates, and uses the XGBoost classifier to output the risk level.

9. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, characterized in that, The intercom communication module comprises: The multimodal response mechanism unit is used to determine a combined response mode based on the risk level, wherein the combined response mode includes: a combination of voice inquiry and log recording, a combination of video intercom and AI bypass monitoring, and a combination of alarm linkage and drone tracking.

10. The intelligent security intercom system based on PIR and AI behavior analysis according to claim 1, wherein, The system control module comprises: The dynamic resource scheduling unit is used to assign a dynamic weight to each video channel based on an improved weighted fair queue algorithm, and perform computing resource scheduling based on the dynamic weight; the dynamic weight allocation algorithm is as follows: ； Among them, is the dynamic weight of the i-th video channel, is the PIR trigger intensity, and the PIR trigger intensity = PIR signal amplitude × duration, is the risk level output by AI behavior analysis, is the computational complexity score of the current analysis model, is a coefficient.

Images