Campus anti-spoofing system based on large model

Abstract

The invention relates to the technical field of security event monitoring, in particular to a campus anti-spoofing system based on a large model, which comprises a multi-modal signal sensing unit, a multi-modal signal receiving unit, a multi-modal signal sending unit, a multi-modal signal sending unit and a multi-modal signal receiving unit, the large-model intelligent analysis unit extracts spatio-temporal characteristics of video signals and audio signals based on the multi-modal spoofing signals, constructs an audio and video fluid momentum analysis equation to detect limb violent actions and semantic threat, constructs a physiological response perception analysis equation to analyze individual physiological responses, and comprehensively obtains a spoofing event analysis result; the dynamic early warning and response unit uses a risk grading strategy to perform real-time early warning and response to a spoofing event; the event retention recording unit stores the multi-mode spoofing signal and spoofing event analysis result data. The campus anti-spoofing system based on the large model combines an audio and video fluid momentum analysis equation and a physiological reaction perception analysis equation to detect limb violence and semantic threats, and early warns and responds to spoofing events.

Description

Technical Field

[0001] The present invention relates to the technical field of security event monitoring, and in particular to a campus anti-bullying system based on a large model. Background Art

[0002] The campus anti-bullying system based on large models is designed to accurately detect and respond in real time to bullying incidents on campus and analyze the interactive relationship between students' physiological responses and environmental position signals. Through the deep fusion of multimodal signals and the innovative application of fluid dynamics and reaction-diffusion equations, it controls the early warning and dynamic response of bullying behavior and realizes the monitoring, evaluation and response of bullying incidents.

[0003] Existing campus anti-bullying systems usually find it difficult to effectively integrate video, audio, location signals and physiological response signals, and are unable to accurately capture multimodal bullying signals in complex scenarios. In addition, since bullying incidents usually occur in a relatively covert manner, a single video signal cannot be detected in a timely and accurate manner, which will lead to a slow response to low-intensity bullying incidents and miss the best time for timely intervention. For example, hidden threats or subtle changes in emotions cannot be identified in time, which ultimately leads to a large blind spot for school administrators in timely identification and taking effective measures. Therefore, a campus anti-bullying system based on a large model is designed. Summary of the invention

[0004] The purpose of the present invention is to provide a campus anti-bullying system based on a large model to solve the problem raised in the above background technology that bullying incidents usually occur in a hidden manner, and a single video signal cannot be detected in a timely and accurate manner, which will lead to a slow response to low-intensity bullying incidents and miss the best time for timely intervention.

[0005] To achieve the above object, the present invention aims to provide a campus anti-bullying system based on a large model, comprising: A multimodal signal sensing unit, wherein the multimodal signal sensing unit uses a sensor network to collect multimodal bullying signals in real time and pre-process the multimodal bullying signals; It also includes a large model intelligent analysis unit, which extracts the spatiotemporal features of video and audio signals based on multimodal bullying signals, constructs an audio and video fluid momentum analysis equation to detect physical violence and semantic threats, and then constructs a physiological response perception analysis equation to analyze individual physiological responses, thereby comprehensively obtaining bullying event analysis results; It also includes a dynamic early warning and response unit, which uses a risk classification strategy based on the bullying situation analysis results to provide a real-time early warning response to bullying incidents; It also includes an event retention and recording unit, which is used to store multimodal bullying signals and bullying event analysis result data.

[0006] As a further improvement of the technical solution, the multimodal signal sensing unit includes a signal acquisition module and a signal processing module; Wherein, the spatiotemporal synchronous signal acquisition module uses a sensor network to collect multimodal bullying signals in real time; Multimodal bullying signals include video signals, audio signals, location signals, and physiological signals; The signal processing module is used to pre-process the multimodal bullying signals collected by the signal collection module.

[0007] As a further improvement of the technical solution, the spatiotemporal synchronous signal acquisition module uses a sensor network to collect multimodal bullying signals in real time. The specific method is as follows: S1.1.1. Acquiring video signals using a multispectral camera network ; S1.1.2. Using microphone array to obtain audio signals ; S1.1.3. Locate the student's position based on the multi-spectral camera and obtain the position signal ; S1.1.4. Obtaining physiological signals based on biosensors worn by students ; in, is the heart rate; It is the electrical response of the skin.

[0008] As a further improvement of the technical solution, the large model intelligent analysis unit includes a spatiotemporal behavior perception module, a physiological position analysis module and a result judgment module; The spatiotemporal behavior perception module is used to extract the spatiotemporal features of video and audio signals, and construct an audio-video fluid momentum analysis equation to analyze physical violence actions and threatening semantic intensity; The physiological position analysis module constructs a physiological response perception analysis equation to analyze individual physiological responses based on the interaction between physiological signals and position signals; The result judgment module calculates the Lyapunov index based on the threatening semantic intensity, and comprehensively obtains the bullying event analysis result by combining the two situations of comparing the physiological response signal concentration with the physiological response signal concentration threshold.

[0009] As a further improvement of the technical solution, the spatiotemporal behavior perception module is used to extract the spatiotemporal features of the video signal and the audio signal, and construct an audio-video fluid momentum analysis equation to analyze the physical violence action and the threatening semantic intensity. The specific method steps are as follows: S2.1.1. Based on video frame sequence , calculate the optical flow field and vorticity field, and combine them into video spatiotemporal features, including the optical flow field and vorticity field ; S2.1.2. Based on sound information , calculate the sound pressure field and sound pressure density, and combine them into audio space-time features, including the sound pressure field and sound pressure density ; S2.1.3. Based on the optical flow field and the sound pressure field, an audio-visual fluid momentum analysis equation is constructed to analyze the physical violence action and the threatening semantic intensity. The audio-visual fluid momentum analysis equation is as follows: ; in, is the behavior density; is the video pressure field; is the social viscosity coefficient; is the momentum transfer term for physical conflict; For audio modulation power; S2.1.4. Based on the vorticity field and acoustic energy density, perform semantic threat analysis and calculation to obtain the threat semantic intensity .

[0010] As a further improvement of the technical solution, the physiological position analysis module constructs a physiological response perception analysis equation to analyze individual physiological responses based on the interaction between physiological signals and position signals. The specific method steps are as follows: S2.2.1. Obtaining position signal and physiological signals ; S2.2.2. Based on the interaction between physiological signals and position signals, the physiological response perception analysis equation is used to analyze the individual physiological response, and the concentration of the physiological response signal is calculated by the physiological response perception analysis equation; S2.2.3. Solve the physiological response perception analysis equation to obtain Upper position The physiological response signal concentration is compared with the physiological response signal concentration threshold: like , the individual's physiological response is at risk, and there is bullying; like , the individual's physiological response is relatively safe, and further judgment is needed on whether there is a bullying incident; in, is the concentration threshold of the physiological response signal.

[0011] As a further improvement of the technical solution, the result judgment module calculates the Lyapunov index based on the threatening semantic intensity, and combines the two situations of comparing the physiological reaction signal concentration with the physiological reaction signal concentration threshold to comprehensively obtain the bullying event analysis results, as follows: S2.3.1. Based on the concentration of physiological response signals and the intensity of threatening semantics, define the state vector, construct the state equation, and calculate the eigenvalues ​​of the Jacobian matrix and the Lyapunov index: State Vector for: ; Equation of state: ; Jacobian matrix : ; Lyapunov exponent: ; in, is the state vector; is a small change in the state vector; S2.3.2 If , and the Lyapunov exponent , there are bullying incidents; like , and the Lyapunov exponent , there is no bullying incident.

[0012] As a further improvement of the present technical solution, the dynamic warning and response unit includes a risk grading module and an event response module.

[0013] As a further improvement of the technical solution, the risk grading module performs risk grading on bullying incidents based on the concentration of physiological response signals and the intensity of threatening semantics to generate a graded warning strategy; The event response module executes the graded warning strategy in real time according to the risk graded results.

[0014] As a further improvement of the technical solution, the event retention recording unit uses a distributed edge cloud data lake to store multimodal bullying signals and bullying event analysis result data; Multimodal bullying signals include video signals, audio signals, location signals, and physiological signals; The bullying incident analysis results include physiological response signal concentration, threatening semantic intensity, audio and video fluid momentum analysis equation data, and physiological response perception analysis equation data.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. In this campus anti-bullying system based on a large model, based on the audio and video fluid momentum analysis equation, physical violence and threatening voices are identified. By coupling the spatiotemporal characteristics of video signals and audio signals, physical conflicts and voice threats are dynamically analyzed, so that hidden bullying behaviors such as pushing, kicking and other violent behaviors and the appearance of threatening language can be discovered in a timely manner in complex campus scenes.

[0016] 2. In the campus anti-bullying system based on the large model, the physiological response perception analysis equation is used to realize the deep coupling analysis of physiological signals and environmental position signals. By monitoring the concentration of individual physiological responses, such as heart rate and skin electrical response, combined with the influence of surrounding environmental position and audio signals, the individual's physiological stress state can be accurately quantified, and by comparing with the physiological response signal threshold, it can be judged in real time whether the individual is at risk of bullying. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is the overall flow chart of the present invention; The meaning of each number in the figure is: 1. Multimodal signal perception unit; 2. Large model intelligent analysis unit; 3. Dynamic warning and response unit; 4. Event retention and recording unit; 11. Signal acquisition module; 12. Signal processing module; 21. Spatiotemporal behavior perception module; 22. Physiological position analysis module; 23. Result judgment module; 31. Risk classification module; 32. Event response module. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, a campus anti-bullying system based on a large model is provided, including: A multimodal signal sensing unit 1, wherein the multimodal signal sensing unit 1 uses a sensor network to collect multimodal bullying signals in real time and pre-process the multimodal bullying signals; The multimodal signal sensing unit 1 includes a signal acquisition module 11 and a signal processing module 12; Wherein, the spatiotemporal synchronous signal acquisition module 11 uses a sensor network to collect multimodal bullying signals in real time; Multimodal bullying signals include video signals, audio signals, location signals, and physiological signals; The signal processing module 12 is used to pre-process the multimodal bullying signal collected by the signal collection module 11 .

[0020] In this embodiment, the spatiotemporal synchronous signal acquisition module 11 uses a sensor network to collect multimodal bullying signals in real time. The specific method is as follows: S1.1.1. Acquiring video signals using a multispectral camera network ; S1.1.2. Using microphone array to obtain audio signals ; S1.1.3. Locate the student's position based on the multi-spectral camera and obtain the position signal ; S1.1.4. Obtaining physiological signals based on biosensors worn by students ; in, is the heart rate; It is the electrical response of the skin.

[0021] It also includes a large model intelligent analysis unit 2, which extracts the spatiotemporal features of the video signal and the audio signal based on the multimodal bullying signal, constructs an audio-video fluid momentum analysis equation to detect physical violence and semantic threats, and then constructs a physiological reaction perception analysis equation to analyze individual physiological reactions, and comprehensively obtains the bullying event analysis results; The large model intelligent analysis unit 2 includes a spatiotemporal behavior perception module 21, a physiological position analysis module 22 and a result judgment module 23; The spatiotemporal behavior perception module 21 is used to extract the spatiotemporal features of the video signal and the audio signal, and construct an audio-video fluid momentum analysis equation to analyze the physical violence action and the threatening semantic intensity; The physiological position analysis module 22 constructs a physiological response perception analysis equation to analyze individual physiological responses based on the interaction between the physiological signal and the position signal; The result judgment module 23 calculates the Lyapunov index based on the threatening semantic intensity, and comprehensively obtains the bullying event analysis result by combining the two situations of comparing the physiological response signal concentration with the physiological response signal concentration threshold.

[0022] In this embodiment, the momentum analysis equation of the audio and video fluid is constructed based on the Navier-Stokes equation; the Navier-Stokes equation is a basic equation that describes the motion of viscous fluids. The movements of characters in the video can be compared to the motion of fluid particles. The optical flow field is similar to the fluid velocity field. The modulation effect of the sound pressure field of the audio signal on the optical flow field of the video signal is similar to the effect of the pressure field on the velocity field in the fluid. The movements of the characters in the video are continuous in time and space, similar to the motion characteristics of fluids; the smoothness of the optical flow field can be described by the viscosity term, reflecting the viscosity of physical conflict; the propagation of the sound pressure field can be described by the pressure term, reflecting the modulation effect of sound on physical movements; Identify high-risk actions such as pushing, kicking, and hitting through optical flow and vorticity fields; Identify threatening speech through sound pressure field and sound energy density; Constructing audio and video fluid momentum analysis equations to achieve deep coupling of video and audio signals and improve the accuracy of bullying incident detection; In this embodiment, the physiological response perception analysis equation is constructed based on the reaction diffusion equation; the reaction diffusion equation is used to describe the diffusion and reaction process of the concentration of a substance in space; the physiological signal can be analogous to the concentration of a reactant, and the environmental position signal can be analogous to the reaction condition; the interaction between the physiological signal and the environmental position signal can be described by the reaction term and the coupling term; The propagation of physiological signals in space can be described by the diffusion term, which reflects the propagation speed of individual physiological responses in space; The influence of environmental position signals on physiological signals can be reflected by coupling terms to reflect the influence of environmental position on individual physiological responses; The triggering effect of audio signals on physiological signals can be described by triggering terms, reflecting the impact of sound on individual physiological responses; The physiological stress state of an individual can be quantified through the concentration of physiological response signals. The presence of a bullying incident can be determined through the concentration and threshold of physiological response signals. The deep coupling of physiological signals and environmental position signals can be achieved through the physiological response perception analysis equation to improve the accuracy of bullying incident detection.

[0023] In this embodiment, the spatiotemporal behavior perception module 21 is used to extract the spatiotemporal features of the video signal and the audio signal, and construct an audio-video fluid momentum analysis equation to analyze the physical violence action and the threatening semantic intensity. The specific method steps are as follows: S2.1.1. Based on video frame sequence , calculate the optical flow field and vorticity field, and combine them into the video spatiotemporal features; Video spatiotemporal features include optical flow field and vorticity field , as follows: ; ; in, is the two-dimensional pixel position coordinate; For time; For in time Upper position The optical flow field; is a sequence of video frames; is the time derivative of the video frame sequence; is the spatial gradient of the video frame; is the optical flow vector to be solved; is the regularization coefficient; is the L2 norm; is the vorticity field; It is the curl operation of the optical flow field; S2.1.2. Based on sound information , calculate the sound pressure field and sound pressure density, and combine them into audio space-time features: Audio temporal and spatial characteristics include sound pressure field and sound pressure density , as follows: ; ; in, is the three-dimensional space position coordinate; For time; For in time Upper position The sound pressure field; is the integration variable; is the Dirac delta function; is the distance between the sound source and the receiving point; is the speed of sound; is the sound pressure attenuation factor; is the sound energy density; is the spatial integration area; is the spatial integration variable; S2.1.3. Based on the optical flow field and the sound pressure field, an audio-visual fluid momentum analysis equation is constructed to analyze the physical violence action and the threatening semantic intensity. The audio-visual fluid momentum analysis equation is as follows: ; ; ; in, is the behavior density; is the video pressure field; is the social viscosity coefficient; is the momentum transfer term for physical conflict; is the violence intensity coefficient; For the Student ID; For the Student ID; For the Students and The distance between students; For audio modulation power; is the audio modulation coefficient; S2.1.4. Based on the vorticity field and acoustic energy density, perform semantic threat analysis and calculation to obtain the threat semantic intensity , as follows: ; in, For in time The intensity of threatening semantics; is the video vorticity weight coefficient; is the audio energy weight coefficient.

[0024] In this embodiment, the physiological position analysis module 22 constructs a physiological response perception analysis equation to analyze individual physiological responses based on the interaction between the physiological signal and the position signal. The specific method steps are as follows: S2.2.1. Obtaining position signal and physiological signals ; S2.2.2. Based on the interaction between physiological signals and position signals, the physiological response perception analysis equation is used to analyze individual physiological responses, and the concentration of physiological response signals is calculated by the physiological response perception analysis equation, as follows: Physiological response perception analysis equation: ; in, For in time Upper position The concentration of physiological response signals indicates the individual's physiological stress response; is the diffusion coefficient of physiological signals, which indicates the diffusion degree of physiological signals in space and reflects the propagation speed of individual physiological responses in space; is the Laplace operator of the physiological signal concentration, which represents the change of physiological response in space; is the enhancement coefficient of the physiological signal, indicating the self-enhancement effect of the physiological response; It is the saturation value of the physiological signal, indicating the maximum value of an individual's physiological response, usually the maximum response level under physiological limit or extreme stress state; is the coupling strength between physiological signals and position signals, indicating the influence of position on individual physiological responses; is the signal concentration at the environmental location; is the audio trigger coefficient, which indicates the influence of audio signal on physiological response; is the threshold of the audio signal; is the Heaviside step function; is the coupling coefficient between the physiological signal and the position signal; is the gradient of physiological signal concentration; is the influence coefficient of heart rate on physiological response; is the influence coefficient of skin electrical response on physiological response; is the bias coefficient; is the rate of change of the concentration of the physiological response signal; S2.2.3. Solve the physiological response perception analysis equation to obtain Upper position The physiological response signal concentration is compared with the physiological response signal concentration threshold: like , the individual's physiological response is at risk, and there is bullying; like , the individual's physiological response is relatively safe, and further judgment is needed on whether there is a bullying incident; in, is the concentration threshold of the physiological response signal.

[0025] In this embodiment, the physiological response signal concentration threshold is obtained by experimentally measuring the physiological responses of a large number of individuals in different situations; due to differences in the physiological and psychological characteristics of different individuals, it may be adjusted according to factors such as the individual's age, gender, health status, etc., and set in the biosensor worn by the students.

[0026] In this embodiment, the result judgment module 23 calculates the Lyapunov index based on the threatening semantic intensity, and combines the two situations of comparing the physiological reaction signal concentration with the physiological reaction signal concentration threshold to comprehensively obtain the bullying event analysis results, which are as follows: S2.3.1. Based on the concentration of physiological response signals and the intensity of threatening semantics, define the state vector, construct the state equation, and calculate the eigenvalues ​​of the Jacobian matrix and the Lyapunov index: State Vector for: ; Equation of state: ; Jacobian matrix : ; Lyapunov exponent: ; in, is the state vector; is a small change in the state vector; S2.3.2 If , and the Lyapunov exponent , there are bullying incidents; like , and the Lyapunov exponent , there is no bullying incident.

[0027] It also includes a dynamic warning and response unit 3, which uses a risk classification strategy based on the bullying situation analysis results to provide a real-time warning and response to bullying events; In this embodiment, the dynamic warning and response unit 3 includes a risk classification module 31 and an event response module 32 .

[0028] The risk grading module 31 performs risk grading on bullying incidents based on the concentration of physiological response signals and the intensity of threatening semantics to generate a graded warning strategy; The event response module 32 executes the graded warning strategy in real time according to the risk graded result.

[0029] In this embodiment, the hierarchical warning strategy is as follows: Low risk events: and , push lightweight warning messages to class teachers and security personnel; Low risk events: or , sending acoustic deterrent signals to the target area to alert those involved in the bullying incident; Low risk events: and , send an acoustic deterrent signal to the target area and notify the class teacher and security personnel to go to the location where the incident occurred immediately; It also includes an event retention and recording unit 4, which is used to store multimodal bullying signals and bullying event analysis result data; In this embodiment, the event retention and recording unit 4 uses a distributed edge cloud data lake to store multimodal bullying signals and bullying event analysis result data; Multimodal bullying signals include video signals, audio signals, location signals, and physiological signals; The bullying incident analysis results include physiological response signal concentration, threatening semantic intensity, audio and video fluid momentum analysis equation data, and physiological response perception analysis equation data.

[0030] The data lake adopts a distributed edge architecture. Data is not only stored in the cloud, but also on edge devices such as cameras, which can reduce latency. Preliminary processing and analysis can be performed on edge devices before uploading to the cloud for further analysis and storage. Multimodal bullying signal data is stored in the data lake and maintains time series relationships, which facilitates analysis and processing at any time; The bullying incident analysis results are stored in a structured format in the data lake to facilitate subsequent query and update; The data lake manages the relationships between different types of data. Video signals, audio signals, physiological signals, and location signals are stored and marked as related data of the same event, ensuring the consistency and correlation of these multimodal signals in time and space.

[0031] The above shows and describes 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 the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A campus anti-bullying system based on a large model, characterized in that: include: A multimodal signal sensing unit (1), wherein the multimodal signal sensing unit (1) uses a sensor network to collect multimodal bullying signals in real time and pre-processes the multimodal bullying signals; A large model intelligent analysis unit (2), wherein the large model intelligent analysis unit (2) extracts the spatiotemporal features of the video signal and the audio signal based on the multimodal bullying signal, constructs an audio-video fluid momentum analysis equation to detect physical violence and semantic threat, and then constructs a physiological response perception analysis equation to analyze individual physiological responses, thereby comprehensively obtaining a bullying event analysis result; A dynamic warning and response unit (3), wherein the dynamic warning and response unit (3) uses a risk classification strategy based on the bullying situation analysis result to provide a real-time warning and response to bullying incidents; An event storage and recording unit (4), wherein the event storage and recording unit (4) is used to store multimodal bullying signals and bullying event analysis result data.

2. The campus anti-bullying system based on a large model according to claim 1 is characterized in that: The multimodal signal sensing unit (1) comprises a signal acquisition module (11) and a signal processing module (12); Wherein, the spatiotemporal synchronous signal acquisition module (11) uses a sensor network to collect multimodal bullying signals in real time; Multimodal bullying signals include video signals, audio signals, location signals, and physiological signals; The signal processing module (12) is used to pre-process the multi-modal bullying signal collected by the signal collection module (11).

3. The campus anti-bullying system based on a large model according to claim 2 is characterized in that: The spatiotemporal synchronous signal acquisition module (11) uses a sensor network to collect multimodal bullying signals in real time, and the specific method is as follows: S1.1.

1. Acquiring video signals using a multispectral camera network ; S1.1.

2. Using microphone array to obtain audio signals ; S1.1.

3. Locate the student's position based on the multi-spectral camera and obtain the position signal ; S1.1.

4. Obtaining physiological signals based on biosensors worn by students ; in, is the heart rate; It is the electrical response of the skin.

4. The campus anti-bullying system based on a large model according to claim 3 is characterized in that: The large model intelligent analysis unit (2) comprises a spatiotemporal behavior perception module (21), a physiological position analysis module (22) and a result judgment module (23); The spatiotemporal behavior perception module (21) is used to extract the spatiotemporal features of the video signal and the audio signal, and construct an audio-video fluid momentum analysis equation to analyze the physical violence action and the threatening semantic intensity; The physiological position analysis module (22) constructs a physiological response perception analysis equation to analyze individual physiological responses based on the interaction between the physiological signal and the position signal; The result judgment module (23) calculates the Lyapunov index based on the threatening semantic intensity, and combines the two situations of comparing the physiological reaction signal concentration with the physiological reaction signal concentration threshold to comprehensively obtain the bullying event analysis results.

5. The campus anti-bullying system based on a large model according to claim 4 is characterized in that: The spatiotemporal behavior perception module (21) is used to extract the spatiotemporal features of the video signal and the audio signal, and construct an audio-video fluid momentum analysis equation to analyze the physical violence action and the threatening semantic intensity. The specific method steps are as follows: S2.1.

1. Based on video frame sequence , calculate the optical flow field and vorticity field, and combine them into video spatiotemporal features. Video spatiotemporal features include optical flow field and vorticity field ; S2.1.

2. Based on sound information , calculate the sound pressure field and sound pressure density, and combine them into audio time-space features. Audio time-space features include sound pressure field and sound pressure density ; S2.1.

3. Based on the optical flow field and the sound pressure field, an audio-visual fluid momentum analysis equation is constructed to analyze the physical violence action and the threatening semantic intensity. The audio-visual fluid momentum analysis equation is as follows: ； in, is the behavior density; is the video pressure field; is the social viscosity coefficient; is the momentum transfer term for physical conflict; For audio modulation power; S2.1.

4. Based on the vorticity field and acoustic energy density, perform semantic threat analysis and calculation to obtain the threat semantic intensity .

6. The campus anti-bullying system based on a large model according to claim 5 is characterized in that: The physiological position analysis module (22) constructs a physiological response perception analysis equation to analyze individual physiological responses based on the interaction between the physiological signal and the position signal. The specific method steps are as follows: S2.2.

1. Obtaining position signal and physiological signals ; S2.2.

2. Based on the interaction between physiological signals and position signals, the physiological response perception analysis equation is used to analyze the individual physiological response, and the concentration of the physiological response signal is calculated by the physiological response perception analysis equation; S2.2.

3. Solve the physiological response perception analysis equation to obtain Upper position The physiological response signal concentration is compared with the physiological response signal concentration threshold: like , the individual's physiological response is at risk, and there is bullying; like , the individual's physiological response is relatively safe, and further judgment is needed on whether there is a bullying incident; in, is the concentration threshold of the physiological response signal.

7. The campus anti-bullying system based on a large model according to claim 6 is characterized in that: The result judgment module (23) calculates the Lyapunov index based on the threatening semantic intensity, and combines the two situations of comparing the physiological reaction signal concentration with the physiological reaction signal concentration threshold to comprehensively obtain the bullying event analysis results, which are as follows: S2.3.

1. Based on the concentration of physiological response signals and the intensity of threatening semantics, define the state vector, construct the state equation, and calculate the eigenvalues ​​of the Jacobian matrix and the Lyapunov index: The state vector is: ; Equation of state: ； Jacobian matrix : ； Lyapunov exponent : ； in, is the state vector; is a small change in the state vector; S2.3.2 If , and the Lyapunov exponent , there are incidents of bullying; like , and the Lyapunov exponent , there is no bullying incident.

8. The campus anti-bullying system based on a large model according to claim 7 is characterized in that: The dynamic early warning and response unit (3) comprises a risk grading module (31) and an event response module (32).

9. The campus anti-bullying system based on a large model according to claim 8 is characterized in that: The risk grading module (31) performs risk grading on bullying incidents based on the concentration of physiological response signals and the intensity of threatening semantics to generate a graded warning strategy; The event response module (32) executes a graded warning strategy in real time according to the risk grading result.

10. The campus anti-bullying system based on a large model according to claim 9 is characterized in that: The event retention recording unit (4) uses a distributed edge cloud data lake to store multimodal bullying signals and bullying event analysis result data; Multimodal bullying signals include video signals, audio signals, location signals, and physiological signals; The bullying incident analysis results include physiological response signal concentration, threatening semantic intensity, audio and video fluid momentum analysis equation data, and physiological response perception analysis equation data.

Images