An earthquake information service system and method based on a smart blackboard

Abstract

The application discloses a kind of earthquake information service system and method based on wisdom blackboard, by comparing the frequency consistency of seismic monitoring network data and wisdom blackboard vibration data, earthquake event verification is carried out, building deformation characteristics are detected using touch panel capacitance value abnormal change and building stress state is inferred, key alarm coverage area is determined in combination with threat intensity scanning;Personnel position perception network is established using electrostatic field intensity distribution monitoring technology, capture personnel distribution signal to form alarm adjustment benchmark, obtain active alarm trigger point by time series correlation analysis and execute synchronous alarm;Using visual attention gradient generation technology, the alarm sequence is displayed in stages, the alarm adjustment vector is converted into a pixel brightness gradient coding sequence, the alarm coordination node is determined by multi-level brightness superposition processing, and finally personalized earthquake early warning information is generated, which provides all-round earthquake information service for educational institutions.

Description

Technical Field

[0001] This invention relates to the field of earthquake information service technology, and in particular to an earthquake information service system and method based on a smart blackboard. Background Technology

[0002] Existing earthquake early warning technologies mainly rely on distributed earthquake monitoring networks and standardized early warning broadcasting models. However, these technologies suffer from problems such as poor transmission of early warning information and untimely response by personnel. Traditional early warning methods lack the ability to monitor the damage status of building structures in real time and cannot personalize early warning adjustments based on the actual stress on buildings and the distribution of people, resulting in a mismatch between early warning information and the actual level of danger.

[0003] Smart blackboards, as important information display devices in modern educational settings, possess abundant sensor resources and powerful information processing capabilities. However, they have not yet been effectively applied to earthquake early warning services. Current technologies lack a solution for deeply integrating the touch sensing, display control, and network communication functions of smart blackboards with earthquake monitoring data, thus failing to achieve intelligent earthquake early warning services guided by visual attention. Therefore, there is an urgent need for an earthquake information early warning method that can fully leverage the advantages of smart blackboard technology. Summary of the Invention

[0004] This invention discloses an earthquake information service system and method based on a smart blackboard. It aims to achieve accurate identification of earthquake events and structural safety assessment through earthquake data verification and building deformation characteristic analysis. It utilizes electrostatic field distribution monitoring to establish a personnel location perception network and performs temporal correlation analysis to determine alarm trigger points. Combined with visual attention gradient control and brightness encoding technology, it achieves personalized alarm information display. Ultimately, it forms a comprehensive earthquake information early warning service integrating earthquake monitoring, building safety assessment, personnel positioning, and intelligent early warning, providing educational venues with all-round and personalized earthquake safety protection.

[0005] The first aspect of this invention proposes a method for providing earthquake information services based on a smart blackboard, comprising the following steps:

[0006] Seismic data from the earthquake monitoring network and vibration data from the smart blackboard installation structure are collected. Seismic verification results are obtained by comparing the vibration frequency consistency between the vibration data and the seismic data.

[0007] Threat intensity scanning is performed on the earthquake verification results to extract alarm intensity groups. Abnormal changes in the capacitance value of the touch panel are detected to generate blackboard deformation features. Based on the blackboard deformation features, the stress state of the building is inferred. The alarm intensity groups are structurally correlated with the stress state of the building to determine the key alarm coverage area.

[0008] A personnel position perception network is established by monitoring the electrostatic field intensity distribution of the touch panel within the critical alarm coverage area, a personnel distribution signal is captured by using the personnel position perception network to form an alarm adjustment reference, a time sequence correlation analysis is performed based on the alarm adjustment reference and the alarm intensity group to obtain an active alarm trigger point, and the active alarm trigger point is used to perform synchronous alarm on the critical alarm coverage area to obtain an alarm sequence;

[0009] A visual attention gradient is generated by adjusting the display parameters of different regions of the touch panel, the visual attention gradient is used to perform hierarchical display on the alarm sequence to obtain a visual transmission effect, and an alarm intensity adjustment vector is generated based on the visual transmission effect;

[0010] The alarm adjustment vector is converted into a gradient coding sequence of screen pixel brightness, multi-level brightness superposition processing is performed on the gradient coding sequence to determine an alarm coordination node, alarm information is generated based on the alarm coordination node, and the intelligent blackboard earthquake information service is completed.

[0011] The second aspect of the present application proposes an earthquake information service system based on an intelligent blackboard, comprising:

[0012] A signal acquisition module is configured to acquire seismic data of a seismic monitoring network and vibration data of an intelligent blackboard installation structure, and obtain a seismic verification result by comparing the vibration frequency consistency of the vibration data and the seismic data;

[0013] A building monitoring module is configured to perform threat intensity scanning on the seismic verification result to extract an alarm intensity group, generate a blackboard deformation feature by detecting abnormal changes in the capacitance value of the touch panel, infer a building stress state based on the blackboard deformation feature, determine a critical alarm coverage area by associating the alarm intensity group with the building stress state in terms of structural danger, and

[0014] A personnel perception module is configured to establish a personnel position perception network by monitoring the electrostatic field intensity distribution of the touch panel within the critical alarm coverage area, capture a personnel distribution signal by using the personnel position perception network to form an alarm adjustment reference, perform a time sequence correlation analysis based on the alarm adjustment reference and the alarm intensity group to obtain an active alarm trigger point, and use the active alarm trigger point to perform synchronous alarm on the critical alarm coverage area to obtain an alarm sequence.

[0015] A display adjustment module is configured to generate a visual attention gradient by adjusting the display parameters of different regions of the touch panel, use the visual attention gradient to perform hierarchical display on the alarm sequence to obtain a visual transmission effect, and generate an alarm adjustment vector based on the visual transmission effect.

[0016] The early warning output module is used for converting the alarm adjustment vector into a gradient coding sequence of screen pixel brightness, performing multi-level brightness superposition processing on the gradient coding sequence to determine an alarm coordination node, and generating alarm information based on the alarm coordination node to complete the intelligent blackboard earthquake information service.

[0017] The beneficial effects of the present application are reflected in the following points: first, through seismic data frequency consistency verification and touch panel capacitance change analysis technology, the seismic monitoring network data is deeply fused with the vibration response and deformation detection of the intelligent blackboard, realizing accurate identification of seismic events and real-time detection of building deformation characteristics, effectively filtering false alarm signals and timely discovering building structure stress abnormalities, improving the accuracy of earthquake early warning and the reliability of building safety evaluation. Secondly, through the static electric field intensity distribution monitoring and personnel position perception network construction technology, the capacitance sensing function of the touch panel is fully utilized to establish a personnel positioning system, which can real-time master the personnel distribution and moving track in the educational place, and combined with the seismic threat intensity, the best alarm triggering time is determined through time sequence correlation analysis, realizing personalized early warning adjustment based on perception data, and improving the pertinence and response efficiency of early warning service. Finally, the visual attention gradient generation and pixel brightness gradient coding technology is adopted, the directional visual flow is generated by adjusting the display parameters of different areas of the intelligent blackboard, the alarm adjustment vector is converted into a gradient coding sequence of the screen, and multi-level brightness superposition processing is performed, effectively guiding the visual attention of personnel and enhancing the visual impact of the early warning information, improving the communication effect and user response speed of the earthquake early warning information. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings herein show specific examples of the technical solutions described in the present application, and constitute part of the specification together with the specific embodiments, for explaining the technical solutions, principles and effects of the present application.

[0019] Unless specifically stated or defined otherwise, the same reference signs in different drawings represent the same or similar technical features, and different reference signs may also be used to represent the same or similar technical features.

[0020] Figure 1 is a flow diagram of a seismic information service method based on an intelligent blackboard according to the present application.

[0021] Figure 2 is a structural block diagram of a seismic information service system based on an intelligent blackboard according to the present application. DETAILED DESCRIPTION

[0022] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, and circuits are omitted so as not to obscure the description of the present application with unnecessary detail.

[0023] It is to be understood that the terminology "including", "comprising", "consisting" and "consisting essentially of" used in the specification and the appended claims, are used in their open-ended, non-limiting sense, and are not intended to preclude the presence of other features, steps, elements, components, and / or combinations thereof.

[0024] Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but can refer to different embodiments, although the phrases can be used to describe particular implementations. The terms "including", "comprising", "having", and the like are meant to be inclusive and mean that there can be additional

[0025] The technical solutions of the embodiments of the present application are described below.

[0026] As shown in Figure 1 The embodiment of the present application provides a kind of earthquake information service method based on wisdom blackboard, comprising the following steps S110-S150:

[0027] Step S110, the vibration data of the seismic data of earthquake monitoring network and wisdom blackboard installation structure are collected, and the consistency of vibration frequency of vibration data and seismic data is obtained by comparing vibration data and seismic data to obtain seismic verification result.

[0028] Specifically, seismic data of the earthquake monitoring network and vibration data of the smart blackboard installation structure are collected. The seismic data published by the China Earthquake Early Warning Network is obtained in real time through a standardized interface. The seismic data contains key parameters such as seismic wave frequency components, focal position coordinates, and earthquake time. The seismic data is received in a multi-source parallel acquisition mode, mainly through the official data interface of the China Earthquake Network, supplemented by regional seismic network data for verification. The data acquisition frequency is set to real-time synchronization to ensure timely access to the latest seismic waveform frequency characteristics. The vibration data of the smart blackboard installation structure is obtained through three-axis acceleration sensors installed on the blackboard bracket, wall connection, and display panel. The vibration data collection considers the structural characteristics of the smart blackboard, focusing on monitoring the horizontal and vertical vibration responses. The blackboard structure vibration data includes dynamic parameters such as vibration amplitude, frequency distribution, phase characteristics, and attenuation coefficient. For example, when a 4.2 magnitude earthquake occurs, the earthquake monitoring network records a main frequency of 8.5 Hz, while the smart blackboard 15 kilometers away from the epicenter detects a structural vibration frequency of 8.7 Hz, with a frequency difference of only 0.2 Hz. Data transmission uses wireless communication technology, and seismic data and vibration data are received and stored synchronously through a unified data collection platform. The collection accuracy is guaranteed through sensor calibration and environmental compensation techniques, and temperature drift and zero-point offset are effectively controlled.

[0029] The seismic verification results are obtained by comparing the vibration frequency consistency of the vibration data and the seismic data. Through spectral correlation analysis, the correlation coefficient and matching degree of the vibration data and the seismic data in the frequency domain are calculated. The determination of the seismic verification results is based on the dual standards of frequency deviation threshold and correlation threshold. When the vibration frequency deviation from the seismic frequency is less than the set threshold and the correlation coefficient exceeds the threshold, it is determined as a seismic event. The frequency deviation threshold is dynamically adjusted according to the propagation distance and medium characteristics, with a threshold of ±0.5 Hz for near-distance propagation and a threshold of ±1.0 Hz for long-distance propagation. The correlation threshold is determined through historical data statistical analysis. When the correlation coefficient is greater than 0.8, it is determined as high consistency; when the correlation coefficient is between 0.6 and 0.8, it is determined as medium consistency; and when the correlation coefficient is less than 0.6, it is determined as low consistency or non-seismic vibration. The verification result output includes parameters such as consistency level, reliability index, frequency deviation value, and time delay.

[0030] In step S120, the threat intensity scanning is performed on the seismic verification results to extract the alarm intensity family. The blackboard deformation features are generated by detecting the abnormal changes of the touch panel capacitance value. Based on the blackboard deformation features, the building stress state is inferred, and the key alarm coverage area is determined by structurally dangerous correlation between the alarm intensity family and the building stress state.

[0031] Specifically, the threat intensity scanning is performed on the earthquake verification results to extract the alarm intensity groups. The threat intensity scanning is performed by using a multi-level threshold analysis method, and the threat is divided into four levels of slight, medium, severe and extremely severe. The alarm intensity group contains grouping features such as threat level, influence range, duration and response priority. The slight threat group corresponds to the earthquake event with high frequency consistency but low magnitude, and a prompt alarm mode is adopted. The medium threat group corresponds to the earthquake event with medium magnitude and good frequency matching, and a warning alarm mode is adopted. The severe threat group corresponds to the earthquake event with high magnitude or abnormal frequency, and a mandatory alarm mode is adopted. The extremely severe threat group corresponds to the destructive earthquake event, and an emergency evacuation alarm mode is adopted. The group extraction considers the time characteristics of earthquake development, and multiple earthquake events in a short time are classified into the same threat group for unified processing. The time window of the scanning process is adjusted according to the time scale of the earthquake activity, and a shorter time window is used in the main shock stage and a longer time window is used in the aftershock stage.

[0032] In some embodiments, the blackboard deformation feature is generated by detecting abnormal changes in the touch panel capacitance value, including: performing pattern recognition on the abnormal changes in the touch panel capacitance value to obtain a capacitance field distortion gap; extracting a deformation compensation capacitance sequence in the capacitance field distortion gap; converting the deformation compensation capacitance sequence into a structural stress feature; and establishing a blackboard deformation feature using the structural stress feature.

[0033] The pattern recognition is performed on the abnormal changes in the touch panel capacitance value to obtain a capacitance field distortion gap. The detected abnormal changes in the touch panel capacitance value are analyzed and recognized by pattern to find discontinuous regions and distortion positions in the capacitance field distribution. The capacitance field distortion gap corresponds to the abnormal region of capacitance distribution caused by local deformation of the panel, and the capacitance value of these regions deviates from the normal distribution pattern. The pattern recognition uses image processing technology to convert the capacitance value distribution into a two-dimensional image for analysis, and the abnormal regions appear as gaps or patches with changes in brightness in the image. The identification of the distortion gap is realized by threshold segmentation and connected domain analysis method, and the pixel points with capacitance value deviation exceeding the threshold are classified into the distortion region. The geometric features of the gap include position coordinates, area size, shape features and direction angle parameters. The position coordinates determine the spatial position of the distortion, the area size reflects the influence range of the distortion, and the shape feature describes the geometric pattern of the distortion. The classification of the capacitance field distortion gap includes point-like gap, line-like gap, surface-like gap and composite gap. The point-like gap corresponds to local concentrated deformation, the line-like gap corresponds to linear crack or fold, and the surface-like gap corresponds to large area deformation.

[0034] For example, the extracting the deformation compensation capacitance sequence in the capacitance field distortion gap comprises: identifying a capacitance field discontinuous boundary by using the capacitance field distortion gap; performing a field intensity reconstruction process through the capacitance field discontinuous boundary to form a repaired capacitance field; implementing dynamic balance adjustment on the repaired capacitance field to obtain a balanced capacitance distribution; and forming a deformation compensation capacitance sequence based on the balanced capacitance distribution.

[0035] The capacitance field discontinuous boundary is identified by using the capacitance field distortion gap. In the detected capacitance field distortion gap area, boundary identification and discontinuous point detection are performed to determine the discontinuous position and boundary characteristics of the capacitance field distribution. The capacitance field discontinuous boundary corresponds to the junction of the distortion gap and the normal capacitance field, and there is a significant gradient change and numerical jump in the capacitance value at these positions. By calculating the spatial gradient of the capacitance value, the positions with sharp changes are identified by using gradient detection and edge extraction. The mathematical description of the discontinuous boundary adopts a boundary line equation to describe the geometric shape and spatial position of the boundary. The boundary characteristics include geometric parameters such as boundary length, curvature, direction, and continuity. The boundary length reflects the perimeter size of the distortion gap, the curvature describes the bending degree of the boundary, and the direction indicates the main direction of the boundary. The continuity analysis identifies the breaking and branching positions of the boundary line, which may correspond to more serious deformation areas. The accuracy of the boundary is improved by sub-pixel level edge detection technology to obtain more accurate boundary positioning results. The classification of the discontinuous boundary includes closed boundary, open boundary, and composite boundary, and different types of boundaries correspond to different distortion modes.

[0036] The field intensity reconstruction process is performed through the capacitance field discontinuous boundary to form a repaired capacitance field. Based on the previous capacitance field discontinuous boundary, a sampling band is set on both sides of the boundary line, and the sampling band width is 10% of the boundary length. The capacitance values of the normal region in the sampling band are extracted as the reconstruction boundary conditions. Each boundary line is set with boundary sampling points according to the arc length at equal intervals, and the sampling interval is 5 mm. The field intensity reconstruction process combines interpolation and extrapolation to calculate the capacitance distribution inside the gap using the boundary conditions set on the discontinuous boundary. The reconstruction process uses the Laplace equation to solve the potential distribution, and the boundary conditions are determined by the sampling capacitance values on the discontinuous boundary. For example, after the discontinuous boundary of a 10 cm x 5 cm distortion gap is identified, 32 sampling points are set on the boundary, and the measured boundary capacitance value range is 105 pF-118 pF. The capacitance values of 36 grid points inside the gap are reconstructed by the bilinear interpolation method. The reconstruction process uses the finite element method, and the discontinuous boundary is used as the geometric boundary of the solution domain, and the boundary condition uses the Dirichlet boundary condition.

[0037] The dynamic balance adjustment is based on the principle of energy minimization, and the total energy function of the repair capacitance field is adjusted to reach the balance state. The mathematical model of the balance adjustment uses the variational method to convert the balance problem into the extreme value problem of the energy functional. The adjustment process uses a step-by-step adjustment method, and the balance solution is gradually approached through multiple adjustments. In each adjustment, the capacitance distribution is slightly corrected, and the correction direction is along the negative direction of the energy gradient. The balance criterion is set by the energy change rate and the gradient modulus, and when the change rate is less than the threshold value, it is determined to reach the balance. The dynamic adjustment considers the time evolution characteristics of the capacitance field, and the balance is processed in the time dimension. The physical meaning of the balanced capacitance distribution represents the natural distribution state of the capacitance field under given boundary conditions. The adjustment result is guaranteed by the monotonic decrease of the energy function, ensuring that the processing process can converge to a reasonable solution.

[0038] The deformation compensation capacitance sequence is formed based on the balanced capacitance distribution. In the spatial domain of the balanced capacitance distribution, the capacitance values are sampled at fixed intervals, and the sampling strategy considers the representativeness and computational efficiency of the sequence, increasing the sampling density in areas with large capacitance gradients and reducing the sampling density in areas with slow changes. The data structure of the compensation capacitance sequence uses a numerical pair format with coordinates, and each sequence element contains a spatial coordinate and a corresponding capacitance value. The length of the sequence is balanced according to the required accuracy and computational resources, and an excessively long sequence increases the computational burden, while an excessively short sequence affects the accuracy. The standardization processing of the capacitance sequence maps the capacitance values into a standard interval, facilitating subsequent numerical processing and comparative analysis. The storage format of the deformation compensation capacitance sequence uses compression encoding technology to reduce storage space and transmission time.

[0039] The compensation capacitance sequence is converted into structural stress characteristics. Based on the deformation compensation capacitance sequence obtained in the previous step, the capacitance change amplitude of each sampling point in the sequence is extracted as the basis data for conversion. The capacitance-stress conversion is based on the principles of material mechanics and capacitance sensing, and uses the pre-established calibration curve to directly map the capacitance value changes in the compensation capacitance sequence to the corresponding structural stress values. For each capacitance value C_i in the sequence, the corresponding stress value is calculated using the linear calibration relationship σ_i = K × ΔC_i + σ_0, where ΔC_i is the change amount of the point relative to the reference capacitance, K is the calibration coefficient, and σ_0 is the zero-bias stress value. The structural stress characteristics include stress magnitude, stress direction, stress type, and stress distribution. The stress magnitude is directly calculated from the numerical value of the compensation capacitance sequence through the calibration coefficient, and the stress direction is determined by analyzing the capacitance gradient of adjacent sampling points in the sequence. The stress type is classified according to the change pattern of the compensation capacitance sequence, and the increase in the sequence value corresponds to tensile stress, while the decrease in the sequence value corresponds to compressive stress. The stress distribution is obtained by combining the spatial coordinates of the compensation capacitance sequence with the converted stress values to form a stress contour map.

[0040] The blackboard deformation feature is formed by structural stress characteristics. Based on the converted structural stress characteristics, the stress size, distribution, direction, and time characteristics are integrated by multi-parameter fusion. The deformation feature includes comprehensive description parameters such as deformation mode, deformation degree, deformation position, and deformation trend. The deformation mode is classified by the stress distribution mode, including uniform deformation, concentrated deformation, bending deformation, and torsional deformation. The deformation degree is quantified by the maximum stress value and the average stress value, reflecting the severity of deformation. The deformation position is determined by the coordinates of the stress concentration area, indicating the main position of deformation. The deformation trend is determined by the change direction of the stress time sequence, including intensification, stability, mitigation, and recovery. The data format of the blackboard deformation feature adopts structured description, including numerical parameters, classification labels, and time stamps.

[0041] The building stress state is inferred based on the blackboard deformation feature. According to the blackboard deformation feature, the stress change of the building main structure is analyzed. When the blackboard deformation feature shows uniform deformation mode and the deformation degree exceeds the threshold value, it indicates that the building is subjected to overall load; when the deformation feature shows concentrated deformation mode, it indicates that the building is subjected to concentrated load at a specific position. The deformation position parameter directly corresponds to the spatial distribution of building stress, and the left deformation of the blackboard corresponds to the stress of the west wall of the building, and the right deformation corresponds to the stress of the east wall. The upper deformation corresponds to the stress of the floor or roof. The intensification state of the deformation trend indicates that the building stress is increasing, the stable state indicates that the stress is basically constant, and the mitigation state indicates that the stress is weakening. The quantitative calculation of the building stress state is based on the deformation degree value, which is converted into the building deformation by the structure amplification coefficient, and then the building stress level is calculated. When the deformation degree exceeds 5mm and the deformation trend is intensification, the building stress state is inferred as dangerous level; when the deformation degree is 2-5mm and the trend is stable, it is inferred as warning level; when the deformation degree is less than 2mm, it is inferred as normal level. The building stress state output includes stress level, stress position, and development trend parameters.

[0042] The key alarm coverage area is determined by structurally dangerous correlation between the alarm intensity group and the building stress state. A two-dimensional risk correlation matrix is established based on the alarm intensity group classification and the building stress state. When the alarm intensity group is at a serious level and the building stress state is at a dangerous level, the risk correlation level is determined to be a first-level key; when the alarm intensity group is at a medium level and the building stress state is at a warning level, the risk correlation level is a second-level key; and when the alarm intensity group is at a slight level and the building stress state is at a normal level, the risk correlation level is a third-level general. The spatial range of the key alarm coverage area is determined based on the stress position parameter in the building stress state, and the building area corresponding to the stress position and its influence range are included in the coverage area. The alarm priority is allocated according to the response priority of the group and the development trend of the stress state, and the area with high group priority and intensified stress trend obtains the highest alarm priority. The first-level key area adopts an emergency evacuation alarm mode with a playing frequency of once every 10 seconds; the second-level key area adopts a forced alarm mode with a playing frequency of once every 30 seconds; and the third-level general area adopts a prompt alarm mode with a playing frequency of once every 60 seconds. The final output of the key alarm coverage area includes information such as area coordinates, risk level, alarm mode and playing parameters.

[0043] In step S130, a personnel position perception network is established by monitoring the electrostatic field intensity distribution of the touch panel in the key alarm coverage area, a personnel distribution signal is captured by using the personnel position perception network to form an alarm adjustment reference, a live alarm trigger point is obtained by time correlation analysis based on the alarm adjustment reference and the alarm intensity group, and a synchronous alarm is performed on the key alarm coverage area by using the live alarm trigger point to obtain an alarm sequence.

[0044] In some embodiments, the personnel position perception network is established by monitoring the electrostatic field intensity distribution of the touch panel, including: identifying a human body induced disturbance area by using the electrostatic field intensity distribution of the touch panel; forming an induced trajectory sequence by tracking the change of the electrostatic field through the human body induced disturbance area; obtaining a personnel position coordinate set by spatial coordinate mapping of the induced trajectory sequence; and forming a personnel position perception network based on the personnel position coordinate set.

[0045] The human-induced disturbance region is identified by the electrostatic field intensity distribution of the touch panel. In the electrostatic field monitoring of the smart blackboard touch panel, the change pattern of the field intensity distribution is analyzed to identify the electrostatic field disturbance region caused by the approach of the human body. The human-induced disturbance region corresponds to the spatial range of the influence of the human body capacitance effect on the electrostatic field distribution, and the field intensity value in these regions deviates from the background field intensity level. The identification of the disturbance region uses a differential detection method to compare the real-time measured field intensity distribution with the reference field intensity distribution to identify the regions where the difference exceeds the threshold. The electrostatic field intensity distribution uses a gridding measurement method, and the panel surface is divided into several measurement units, each unit corresponding to a field intensity measurement value. The field intensity change characteristics induced by the human body exhibit a concentric circle distribution centered on the human body position, and the closer to the human body, the more obvious the field intensity change. The boundary of the disturbance region is determined by the contour method, and the positions where the field intensity change reaches the detection threshold are connected to form a closed boundary line. The region identification considers the size characteristics and posture changes of the human body, and the induced region of an adult is about 1-1.5 meters in diameter, and the induced region of a child is about 0.8-1 meter in diameter. When multiple people exist at the same time, the disturbance regions may overlap and need to be independently identified by region separation technology. The disturbance intensity is quantified by the amplitude of the field intensity change, and the larger the change amplitude, the closer the human body is to the panel. The stability of the disturbance region is analyzed by continuous monitoring, and a stable disturbance region corresponds to a stationary person, and a moving disturbance region corresponds to a moving person.

[0046] The electrostatic field change tracking is performed on the human-induced disturbance region to form an induced trajectory sequence. According to the stability characteristics of the disturbance region analyzed above, the identified human-induced disturbance region is classified and tracked: for stable disturbance regions, a static monitoring mode is adopted, and the tracking frequency is set to 2 times per second; for moving disturbance regions, a dynamic tracking mode is adopted, and the tracking frequency is increased to 10 times per second. The electrostatic field change tracking uses the centroid tracking method, and the geometric center of the disturbance region is taken as the representative point of the human body position for tracking. The induced trajectory sequence includes trajectory elements such as time stamp, position coordinates, disturbance intensity and region stability label. The continuity of the trajectory is ensured by the position association method, and the position points at adjacent times are associated by the shortest distance principle. When the personnel move quickly, the disturbance region may appear tailing phenomenon, and the tracking process needs to consider this dynamic effect. The data format of the trajectory sequence uses time series array, and each array element contains the position information at a time. For example, when a student walks from the front row to the back row in the classroom, the induced trajectory sequence will record about 20 consecutive position points to form a complete moving trajectory. The trajectory smoothing uses the moving average filter to remove the noise and jitter in the position measurement. The detection of abnormal trajectories is determined by the speed and acceleration thresholds, and the trajectory points that exceed the reasonable range will be marked or corrected.

[0047] The space coordinate mapping is performed on the induction trajectory sequence to obtain a personnel position coordinate set. The recorded induction trajectory sequence is converted from the panel local coordinate system to the building global coordinate system. Before the coordinate conversion, data preprocessing is performed using the previously detected abnormal trajectory markers: the trajectory points marked as abnormal are corrected using an interpolation method based on adjacent normal trajectory points to calculate a reasonable position; the trajectory points exceeding the acceleration threshold are directly excluded from the coordinate mapping. The space coordinate mapping considers the installation position, orientation angle, and height of the smart blackboard, and establishes a conversion relationship between the panel coordinates and the global coordinates. The mathematical transformation of the coordinate mapping includes geometric transformations such as translation, rotation, and scaling, and the transformation parameters are determined through the calibration process during the installation of the blackboard. The personnel position coordinate set contains all the monitored personnel position information, represented in three-dimensional coordinates, including x, y, and z position components. The coordinate accuracy is guaranteed through multiple calibration and error compensation techniques, with a position accuracy of centimeter level. The coordinates of multiple smart blackboards are unified through the global coordinate system, and the personnel positions monitored by different blackboards can be compared and analyzed in the unified coordinate system. The time marker of the coordinate set is consistent with the trajectory sequence, supporting time series analysis of personnel positions. The storage format of the coordinate set uses a structured array, supporting efficient query and statistical analysis.

[0048] A personnel position perception network is formed based on the personnel position coordinate set. Using the obtained personnel position coordinate set, a perception network structure is constructed to support personnel position monitoring and information sharing. The personnel position perception network adopts a hierarchical architecture design, with the bottom layer being a position detection node, the middle layer being a data aggregation node, and the top layer being a network control node. The position detection node corresponds to each smart blackboard and is responsible for local personnel position detection and preliminary processing. The data aggregation node is responsible for collecting position information from multiple detection nodes, performing data fusion and conflict resolution. The network control node is responsible for the coordination and management of the entire perception network and decision control. The network communication adopts a combination of wired and wireless methods, with wired connection providing high reliability and wireless connection providing deployment flexibility. The coverage range of the perception network is consistent with the key alarm coverage area, ensuring complete coverage of the monitoring area. The fault tolerance of the network is achieved through redundancy design, and partial node failure will not affect the overall perception function. Real-time sharing of personnel position information is achieved through network broadcast mechanism, and each node can obtain the global personnel distribution. The perception network supports multiple query functions, including personnel number query, position distribution query, and moving trajectory query. The network is designed for scalability to facilitate the easy access of new detection nodes, adapting to the expansion needs of the monitoring area.

[0049] A personnel location sensing network is used to capture personnel distribution signals and establish an alarm adjustment benchmark. Through this network, functions such as personnel count query, location distribution query, and movement trajectory query are invoked to capture the real-time distribution of personnel within key alarm coverage areas. The personnel count query function statistically analyzes the signals of individual human bodies within the sensing range, with each body corresponding to an independent electrostatic disturbance source. The location distribution query function calculates the precise location of personnel using triangulation and determines coordinates based on the signal strength differences among multiple sensing nodes. The movement trajectory query function continuously monitors changes in personnel location, obtaining dynamic parameters such as movement speed and direction. Based on the distribution signals obtained from the queries, personnel density and distribution patterns are analyzed to form a benchmark reference for alarm intensity adjustment. Aggregation density is quantified by calculating the number of people per unit area; areas with higher density require stronger alarm signals. The alarm adjustment benchmark considers both the spatial and temporal characteristics of personnel distribution. Spatially, alarm intensity allocation is determined based on personnel density distribution; temporally, alarm timing is adjusted based on personnel flow. For example, when a classroom is detected with 40 students, the alarm adjustment benchmark for that area is set to a high-intensity alarm; while a classroom with only 5 students is set to a medium-intensity alarm. The baseline parameters include control parameters such as alarm volume, repetition frequency, duration, and priority, which are dynamically adjusted according to real-time changes in personnel distribution.

[0050] In some embodiments, the step of obtaining active alarm trigger points by performing time-series correlation analysis based on the alarm adjustment benchmark and the alarm intensity group includes: decomposing the alarm adjustment benchmark into a dynamic adjustment sequence by time window; calculating the seismic propagation delay of the alarm intensity group to generate an arrival time matrix; performing phase matching between the dynamic adjustment sequence and the arrival time matrix to form a time-series coupling diagram; and extracting resonance enhancement nodes from the time-series coupling diagram to determine active alarm trigger points.

[0051] The alarm adjustment reference is decomposed into a dynamic adjustment sequence according to a time window. The obtained alarm adjustment reference is segmented and decomposed according to the time dimension, and the dynamic adjustment characteristics in the reference parameters are mainly utilized: the real-time change characteristics of the reference are taken as the main basis for decomposition, a shorter time window is used for a period of rapid change to improve the resolution, and a longer time window is used for a period of slow change to reduce the calculation amount. The time window decomposition adopts an adaptive window technology, and the window length is determined according to the dynamic adjustment amplitude: the window length is set to 15 seconds for a period with an adjustment amplitude greater than 30%, the window length is set to 30 seconds for a period with an adjustment amplitude between 10% and 30%, and the window length is set to 60 seconds for a period with an adjustment amplitude less than 10%. The dynamic adjustment sequence includes parameters such as alarm intensity demand, personnel distribution density, and emergency level grade in each time window. The sequence decomposition considers the time delay of alarm response, and the reference parameters are advanced by a certain time to compensate for the response delay. The data format of the dynamic adjustment sequence adopts a parameter array marked by time, and each array element corresponds to the adjustment parameters of a time window. The smoothing of the sequence is realized by time domain filtering, which eliminates the mutation and oscillation of the adjustment parameters. The quantification of the dynamic characteristics is measured by the change rate and fluctuation amplitude of the sequence, and a sequence with rapid change needs more frequent alarm adjustment.

[0052] The arrival time matrix is generated by calculating the seismic wave propagation delay of the alarm intensity group. For the alarm intensity group, the propagation delay of the seismic wave from the epicenter to each monitoring point is calculated to form a matrix structure describing the distribution of the arrival time of the seismic wave. The calculation of the seismic wave propagation delay considers the propagation speed, propagation path and medium characteristics of the seismic wave, and the basic calculation formula is t=d / v+Δt, where t is the arrival time of the seismic wave, d is the propagation distance from the epicenter to the monitoring point, v is the propagation speed of the seismic wave, and Δt is the medium correction time. The propagation speed of the seismic wave is determined according to the wave type and medium type, and the speed of P wave is about 6-8 km / s, and the speed of S wave is about 3-4 km / s. The propagation path is determined by the geometric relationship between the epicenter position and the monitoring point position, and the straight-line distance is used as the main calculation parameter. The rows of the arrival time matrix correspond to different alarm intensity groups, the columns correspond to different monitoring positions, and the matrix elements represent the arrival time of the corresponding seismic wave. For example, when the epicenter is 15 kilometers away from a teaching building, the arrival time of P wave is about 2.5 seconds, and the arrival time of S wave is about 4.5 seconds, and these time data constitute the corresponding elements of the arrival time matrix. The accuracy of the time delay calculation is ensured by high-precision timing and distance measurement, and the time accuracy reaches millisecond level and the distance accuracy reaches meter level. The time delay calculation in the case of multiple sources is handled by the superposition principle, and each source contributes an independent arrival time component.

[0053] The dynamic adjustment sequence is phase-matched with the arrival time matrix to form a time-coupling graph. The obtained dynamic adjustment sequence is time-aligned with the arrival time matrix for analysis, and a coupling distribution graph reflecting the relationship between alarm demand and seismic arrival time is constructed. The dynamic adjustment sequence records the change of alarm intensity demand in each 30-second time window, for example, the dynamic adjustment sequence of a certain teaching building shows that the demand intensity is medium (35 students) during the 10:20-10:25 period, high (60 students) during the 10:25-10:30 period, and extremely high (80 students) during the 10:30-10:35 period. Time-coupling analysis matches these dynamic adjustment sequences with the seismic wave arrival time matrix to find the degree of coincidence between the peak of personnel gathering and the arrival time of seismic waves. When the dynamic adjustment sequence shows that a certain period is of extremely high demand intensity, and the arrival time matrix shows that the P wave of the earthquake arrives at that period, a strong coupling relationship is formed between the two. The time-coupling graph uses a grid representation, with the horizontal axis representing the time process of the dynamic adjustment sequence and the vertical axis representing different building locations. The value at the intersection of the grid represents the alarm urgency at that time and location. The coupling strength is determined by the matching degree of the demand level of the dynamic adjustment sequence and the intensity of the seismic wave. Locations with high demand and approaching seismic waves are shown as high-coupling areas. The color coding of the coupling graph uses a red-yellow-green color system, with red representing high coupling (immediate alarm), yellow representing medium coupling (preparation for alarm), and green representing low coupling (normal monitoring).

[0054] Resonance-enhanced nodes are extracted from the time-coupling graph to determine active alarm trigger points. In the constructed time-coupling graph, key nodes with the best alarm effect are identified, which correspond to the space-time intersection points where personnel gather and seismic impact is about to arrive. Resonance-enhanced nodes represent locations where both personnel gathering density and seismic threat level reach their peaks. Triggering alarms at these nodes can achieve the best early warning effect. Node identification is achieved through peak search methods, finding grid points with the highest values and exceeding the trigger threshold in the coupling graph. For example, when 3rd floor of No. 5 teaching building shows 80 teachers and students gathering at a certain time, and the seismic threat level at this location reaches the serious level, this space-time point is marked as a resonance-enhanced node. The selection of active alarm trigger points prioritizes nodes with the greatest impact on personnel safety, including locations with personnel density exceeding 50 people / 100 square meters and seismic threat level above medium. The time window of the trigger point is set to 30 seconds before the arrival of the seismic wave to 10 seconds after the arrival, ensuring that the alarm can function effectively within the effective time. Coordination between multiple trigger points is achieved through priority ordering, with teaching buildings taking priority over office buildings, lower floors taking priority over higher floors, and densely populated areas taking priority over sparsely populated areas. Once the active alarm trigger points are determined, alarm instructions are sent to the corresponding area of the smart blackboard, including specific information such as alarm intensity level, duration, and evacuation direction. The execution status of the trigger point is monitored through real-time feedback to ensure the correct transmission and execution of the alarm instructions.

[0055] The active alarm trigger point is used to perform synchronous alarm on the key alarm coverage area to obtain an alarm sequence. Based on the determined active alarm trigger point, a coordinated synchronous alarm is performed in the key alarm coverage area to form an ordered alarm information sequence. The synchronous alarm is executed in a distributed control manner, and each alarm device starts the alarm function according to the trigger point information. The alarm sequence includes sequence parameters such as alarm content, playing order, time interval, and stop condition. The alarm content is individually designed according to the earthquake threat level and personnel distribution, and includes information such as earthquake reminder, evacuation instruction, and safety precautions. The playing order is determined according to the priority and emergency degree of the trigger point, and high-risk areas are played first and low-risk areas are played later. The time interval is controlled within 3-5 seconds to ensure complete transmission of alarm information and understanding and digestion of personnel. The stop condition includes trigger conditions such as earthquake end, personnel evacuation completion, and manual termination. The coverage range of the synchronous alarm is consistent with the key alarm coverage area, ensuring that all personnel in the area can receive the alarm information. The generation of the alarm sequence considers technical factors such as device performance and network delay, and ensures the consistency of each device through a time synchronization protocol. The execution status of the sequence is monitored through a feedback mechanism to discover and handle faults or abnormalities of the alarm device in a timely manner. The effectiveness of the alarm sequence is tracked through personnel response, and the sequence mode with good response can be used for subsequent alarm strategies.

[0056] In step S140, a visual attention gradient is generated by adjusting the display parameters of different regions of the touch panel, the alarm sequence is displayed in stages using the visual attention gradient to obtain a visual transmission effect, and an alarm adjustment vector is generated based on the visual transmission effect.

[0057] In some embodiments, the visual attention gradient is generated by adjusting the display parameters of different regions of the touch panel, including: identifying a pixel-level brightness distribution using the touch panel; performing visual focus control using the pixel-level brightness distribution to form a focused display area; adjusting the spatial contrast of the focused display area to obtain a directional visual flow; and forming a visual attention gradient based on the directional visual flow.

[0058] The pixel-level brightness distribution is recognized by the touch panel. In the display control of the smart blackboard touch panel, the brightness value of each pixel point on the screen surface is accurately detected and analyzed to obtain the brightness distribution characteristics of the entire display area. The pixel-level brightness distribution detection uses light sensor array technology, with micro light-sensitive elements arranged on the back of the panel to monitor the luminous intensity of each pixel point in real time. The spatial resolution of brightness detection is consistent with the pixel density of the panel, ensuring that each pixel has a corresponding brightness measurement value. The brightness distribution data is stored in a two-dimensional matrix format, with the number of rows and columns corresponding to the number of pixel rows and columns of the panel, and the matrix element value representing the brightness level of the corresponding pixel. The quantization of brightness value uses 8-bit digital representation, with a value range of 0-255, where 0 represents complete darkness and 255 represents maximum brightness. The real-time update frequency of pixel-level brightness distribution is set to 30 times per second, synchronized with the display refresh frequency. The analysis of distribution characteristics is based on the calculation of the brightness mean value, providing a reference for subsequent focus area setting. The brightness mean value reflects the overall display brightness level and serves as the basis for relative brightness adjustment.

[0059] The visual focus control is performed by pixel-level brightness distribution to form a focused display area. Based on the obtained pixel-level brightness distribution information and the calculated brightness mean value reference, a visual focus area is created by adjusting the brightness parameters of a specific region. The brightness setting of the focused display area is based on the relative adjustment of the brightness mean value: when the full-screen brightness mean value is below 128, the focus area brightness is set to 1.5 times the mean value; when the mean value is above 128, the focus area is set to a fixed increment of mean + 80, ensuring that an effective brightness contrast can be formed under different ambient light conditions. The principle of visual focus control is based on the sensitivity of the human eye to brightness contrast, with high brightness areas naturally attracting visual attention and low brightness areas being ignored by the eye. The setting of the focused display area uses a region selection method to determine the screen area that needs to be highlighted based on the importance and urgency of the alarm content. The geometric shape of the focus area includes types such as circles, rectangles, ellipses, and irregular shapes, with the shape selection determined based on the characteristics of the display content. The region boundary processing uses a gradual transition method to avoid sudden brightness jumps that can cause visual discomfort. The dynamic characteristics of the focus area are achieved through the time variation of brightness, including slow pulsing, rapid flashing, and gradual changes. For example, when displaying an emergency evacuation route, the route area is set as the focused display area, with relative enhancement based on the current brightness mean value and a slow pulsing mode of 1 time per second. The coordination of multiple focus areas is achieved through priority management, with high-priority focus areas receiving stronger brightness enhancement.

[0060] The spatial contrast adjustment is applied to the focused display area to obtain the directional visual flow. Within the set focused display area, the directional visual guidance effect is created by adjusting the contrast distribution between adjacent pixels, forming the directional visual flow. The spatial contrast adjustment adopts the gradient control technology to establish the directional brightness gradient distribution in the focused area, guiding the visual attention to move along a specific direction. The direction of the directional visual flow is determined according to the alarm content and evacuation requirements, usually pointing to the location of the safety exit, evacuation path or important prompt information. The establishment of the contrast gradient is realized by controlling the brightness difference between adjacent pixels, gradually increasing or decreasing the pixel brightness along the desired visual flow direction. The gradient slope control is 2-5 brightness levels per pixel, ensuring the continuity and smoothness of the visual flow. The width of the directional visual flow is set to 20-50 pixels, and the width is too narrow to form an effective guide, and the width is too wide to disperse attention. The shape of the flow line is designed as a straight line, a curve or a polyline, determined according to the actual geometric characteristics of the guide path. The intensity of the visual flow is controlled by the contrast amplitude, and the emergency guidance adopts a high-contrast strong flow line, and the general prompt adopts a weak flow line with medium contrast. The design of multiple visual flows considers the mutual influence and interference, and avoids visual confusion through spatial separation and time alternation. The dynamic effect of the directional visual flow is realized by the time variation of the gradient, including flow, wave and flicker motion modes. The flow mode produces a visual motion feeling by the spatial displacement of the gradient, and the wave mode produces a wave effect by the periodic variation of the contrast.

[0061] A visual attention gradient is formed based on the directional visual flow. By comprehensively designing the spatial distribution and intensity variation of the established directional visual flow, a complete visual attention gradient distribution is formed. The visual attention gradient divides the entire touch panel into different attention level areas, with high level areas strongly attracting visual attention and low level areas maintaining a visual background state. The spatial distribution of the gradient adopts a center-periphery structure, with the most important information area located at the center of the gradient and secondary information distributed at the periphery of the gradient. The quantification of attention intensity adopts a 0-10 level standard, with level 10 representing the strongest attention attraction and level 0 representing complete neglect. The formation of the gradient comprehensively considers the brightness enhancement of the focused display area and the directional guidance of the directional visual flow, with both working together to produce a stereoscopic attention distribution. The continuity of the gradient is ensured by smooth transitions in brightness and contrast, avoiding visual discomfort caused by abrupt changes. The gradient variation in the time dimension is realized by dynamic adjustment of the parameters, adjusting the gradient intensity according to the emergency level of the alarm and the response of the personnel. For example, during an emergency evacuation, the gradient intensity of the evacuation exit direction is set to level 9, the evacuation path is set to level 7, and other areas are set to level 3, forming a clear visual guidance hierarchy. The effective range of the visual attention gradient covers more than 80% of the visible area of the panel, ensuring that observers can feel the gradient guidance from any angle.

[0062] Visual attention gradients are used to hierarchically display alarm sequences to achieve better visual communication. Alarm sequences are presented visually differently based on their specific parameters: different visual codes are assigned according to the type of alarm content (earthquake alert, evacuation instructions, safety precautions). Earthquake alerts are highlighted in red, evacuation instructions are flashed in orange, and safety precautions are displayed steadily in yellow. The visual hierarchy is arranged according to the playback order of the alarm sequence, with priority content occupying the highest level area of ​​the visual attention gradient, and subsequent content allocated to the middle level area. The duration of the visual display is adjusted according to the time interval parameter of the alarm sequence; alarm content with a 3-second interval is displayed for 2.5 seconds, and content with a 5-second interval is displayed for 4.5 seconds, ensuring the timing coordination between visual display and audible alarm. The differentiated visual presentation based on the generated visual attention gradient improves the efficiency of visual communication of alarm information. Level 1 alarms use the strongest visual gradient, with a bright red flashing indicator in the center of the screen, reaching a brightness of over 90%, and a flashing frequency of 3 times per second. Level 2 alarms use a strong visual gradient, displaying a medium-bright flashing orange indicator, with a brightness set to 70%-80%, and a flashing frequency of 2 times per second. Level 3 alarms use a medium visual gradient, displaying a stable yellow light with a brightness setting of 50%-60%. Level 4 alarms use a weak visual gradient, displaying a low-brightness green light with a brightness setting of 30%-40%. The effectiveness of visual transmission is evaluated by attention capture time and information recognition accuracy.

[0063] The alarm intensity adjustment is generated based on the visual transmission effect. The feedback adjustment of the alarm intensity is performed according to the two key indicators of the attention capture time and the information recognition accuracy in the measured visual transmission effect. When the attention capture time is more than 2 seconds, it indicates that the current visual intensity is insufficient, and the alarm intensity needs to be enhanced. When the capture time is less than 0.5 seconds, it indicates that the visual stimulation is too strong, and the intensity needs to be appropriately reduced. When the information recognition accuracy is less than 80%, it indicates that the information transmission effect of the visual display is poor, and the visual coding method needs to be adjusted or the auxiliary prompt needs to be increased. The comprehensive calculation formula of the alarm adjustment vector is V = α × f(t) + β × g(A), wherein V is the alarm adjustment vector, t is the attention capture time, A is the information recognition accuracy, f(t) and g(A) are the adjustment functions of the time and the accuracy, and α and β are the weight coefficients. The alarm adjustment vector includes multiple components such as the sound intensity adjustment amount, the visual intensity adjustment amount, the frequency adjustment amount and the duration adjustment amount. The sound intensity adjustment amount is determined according to the attention capture effect. When the capture time is longer, the sound intensity is increased by 5-10 decibels. When the capture time is shorter, the sound intensity is reduced by 2-3 decibels. The visual intensity adjustment amount is adjusted based on the information recognition accuracy. When the accuracy is less than 80%, the visual brightness is increased by 10%-15%. When the accuracy is higher than 95%, the brightness can be appropriately reduced by 5%. The frequency adjustment amount controls the repetition frequency of the alarm signal. When neither of the two effect indicators is ideal, the repetition frequency is increased. When the effect is good, the repetition frequency is reduced to reduce interference. The duration adjustment amount is determined according to the information recognition accuracy. When the accuracy is low, the single alarm display time is prolonged. When the accuracy is high, the time can be appropriately shortened. For example, when the attention capture time of a certain classroom is 3 seconds and the information recognition accuracy is 75%, the adjustment vector indicates that the sound intensity is increased by 8 decibels, the visual brightness is increased by 12%, and the repetition frequency is increased to once every 25 seconds.

[0064] In step S150, the alarm adjustment vector is converted into a gradient coding sequence of screen pixel brightness, a multi-level brightness superposition process is performed on the gradient coding sequence to determine an alarm coordination node, alarm information is generated based on the alarm coordination node, and the intelligent blackboard earthquake information service is completed.

[0065] In some embodiments, the conversion of the alarm adjustment vector into the gradient coding sequence of screen pixel brightness includes: monitoring the brightness oscillation mode of the alarm adjustment vector to generate a brightness oscillation trajectory; injecting an inverted brightness at the wave peak position of the brightness oscillation trajectory to form a brightness standing wave; extracting a deterministic brightness component by using the stable node of the brightness standing wave; and generating a gradient coding sequence by phase superposition of the deterministic brightness component.

[0066] The brightness oscillation mode of the monitoring alarm adjustment vector generates a brightness oscillation trajectory. Comprehensive analysis of the obtained multiple adjustment components in the alarm adjustment vector, the visual intensity adjustment component determines the amplitude characteristics of the oscillation, the frequency adjustment component directly controls the frequency parameter of the brightness oscillation, and the duration adjustment component determines the duration of each oscillation period. The brightness oscillation mode reflects the dynamic change law of the alarm intensity with time, and the oscillation frequency is set according to the frequency adjustment component: when the adjustment component indicates a high-frequency alarm, 2-4 oscillations per second are adopted, and when the adjustment component indicates a low-frequency alarm, 0.5-1 oscillation per second is adopted. The oscillation amplitude is determined according to the visual intensity adjustment component, and is quantified by the difference between the maximum brightness value and the minimum brightness value. The oscillation duration is set according to the duration adjustment component, and a long duration corresponds to a stable oscillation mode, and a short duration corresponds to a rapidly changing oscillation mode. The generation of the brightness oscillation trajectory is obtained by continuously recording the change of the brightness adjustment value with time, and the trajectory data is represented by two-dimensional coordinates of time-brightness. For example, when the alarm adjustment vector shows that a medium-intensity alarm is needed, the frequency is 1.5 times per second, and the duration is 3 seconds, the brightness oscillation trajectory shows that the brightness periodically changes between 150-200, a single period lasts for 0.67 seconds, and a total of about 4.5 complete periods are included. The smoothness of the trajectory is ensured by filtering processing, eliminating noise and mutations in the oscillation.

[0067] Injecting an inverted brightness at the peak position of the brightness oscillation trajectory forms a brightness standing wave. In the identified brightness oscillation trajectory, an inverted brightness signal opposite in phase to the original oscillation is injected at the peak position of the oscillation, and a locally stable brightness standing wave effect is formed by phase cancellation principle. The principle of injecting inverted brightness is based on the interference phenomenon of waves. When two brightness waves with opposite phases and equal amplitudes meet at the same position, they will cancel each other out, forming a relatively stable standing wave node. The identification of the peak position is realized by extreme value detection of the oscillation trajectory. When the brightness value reaches a local maximum, it is determined as the peak position. The amplitude of the inverted brightness is set to be equal to the peak amplitude of the original oscillation, and the phase difference is set to 180 degrees, ensuring effective phase cancellation effect. The formation of the brightness standing wave is spatially manifested as the brightness value at a certain position remaining relatively stable, while the brightness at other positions remains in an oscillation state. The position of the standing wave node corresponds to the spatial position of the inverted injection, and the node spacing is related to the oscillation wavelength. For example, when the wavelength of the brightness oscillation is 20 pixels, the spacing of the standing wave nodes is about 10 pixels, forming alternating stable nodes and oscillation regions. The formation of multiple standing waves is realized by multi-point inverted injection, and inverted signals are injected at different peak positions at the same time.

[0068] For example, the determination of the deterministic luminance component using the stable node of the luminance standing wave includes: performing luminance time scale calibration on the luminance standing wave to form a luminance time sequence; identifying luminance jump points and stable points on the luminance time sequence; segment fitting based on the luminance jump points and the stable points to generate a luminance stability curve; and performing stability degree analysis on the luminance stability curve to form the deterministic luminance component.

[0069] The luminance standing wave is calibrated in a luminance time scale to form a luminance time sequence. The formed luminance standing wave data is calibrated and organized in a unified time scale to generate a luminance time sequence with accurate time coordinates. The time scale is calibrated in an absolute time stamp manner, and each luminance measurement value corresponds to an accurate time point, with a time accuracy of milliseconds. The data format of the luminance time sequence is organized in a time-luminance numerical pair, and is arranged in time sequence to form a one-dimensional time sequence. The sampling frequency of the sequence is set to 100 times per second, ensuring that the details of the luminance change can be captured. The uniformity of the time scale is ensured by clock synchronization technology, and the time sequences of multiple monitoring points have consistent time references. The time sequence characteristics of the luminance standing wave include periodicity, trend and randomness. The periodicity corresponds to the inherent oscillation of the standing wave, the trend corresponds to the long-term luminance change, and the randomness corresponds to the measurement noise and environmental interference. The length of the sequence is determined according to the analysis requirements, and a short sequence is used for real-time analysis and a long sequence is used for trend analysis. The preprocessing of the time sequence includes steps such as detrending, denoising and normalization, which improves the accuracy of subsequent analysis.

[0070] The luminance jump points and stable points are identified on the luminance time sequence. The obtained luminance time sequence is subjected to feature point identification to distinguish jump points where the luminance suddenly changes and stable points where the luminance remains relatively stable. The luminance jump point corresponds to the time position where the luminance value in the time sequence changes significantly, and the identification of the jump is realized by threshold determination of the luminance gradient and the change rate. The determination conditions of the jump point include the gradient threshold and the duration threshold, and when the luminance change rate exceeds the set threshold and the duration is shorter than the threshold, the jump point is determined. The stable point corresponds to the time period where the luminance value in the time sequence remains relatively stable, and the identification of the stability is realized by threshold determination of the luminance variance and the change amplitude. The determination conditions of the stable point include the variance threshold and the duration threshold, and when the luminance variance is less than the set threshold and the duration is longer than the threshold, the stable point is determined. For example, in a 10-second time sequence, 3 jump points (at 2 seconds, 5 seconds and 8 seconds, respectively) and 4 stable points (at 0-2 seconds, 2-5 seconds, 5-8 seconds and 8-10 seconds, respectively) can be identified, and the luminance variance of each stable point is less than 5 luminance units. The labeling of the feature points uses a label array, and each time point corresponds to a label value, which represents the type attribute of the point.

[0071] The luminance stability curve is generated by piecewise fitting with luminance jump points and stable points as boundaries. The identified jump points and stable points are used as segment boundaries for piecewise processing of the time series. Independent curve fitting is performed in each segment to generate the luminance stability curve. Piecewise fitting uses least squares method or polynomial fitting method to select the appropriate fitting function according to the distribution characteristics of the data points in each segment. Constant function or linear function is used to fit the stable segment to reflect the stability of the luminance; exponential function or sigmoid function is used to fit the jump segment to reflect the change characteristics of the luminance. The luminance stability curve describes the change rule and stability of the luminance in each time segment. The slope of the curve reflects the speed of the luminance change, and the smoothness of the curve reflects the stability of the luminance. The fitting process considers the weight distribution of the data points, with higher weight for stable points and lower weight for jump points to highlight the stability characteristics. The fitting quality is tested by correlation coefficient and residual analysis, and the fitting result with correlation coefficient greater than 0.9 is considered acceptable. The connection of multi-segment fitting results uses boundary matching method to ensure the continuity of the fitting curves at the boundary. The parameters of the stability curve include fitting coefficients, fitting errors, stability degree and change trend, which provide quantitative basis for the extraction of deterministic luminance component.

[0072] The stability degree analysis of the luminance stability curve forms the deterministic luminance component. Based on the generated luminance stability curve, quantitative analysis of the stability degree is performed to extract the luminance component with high stability as the deterministic luminance component. Stability degree analysis quantifies the curve through statistical indicators such as variance, change rate and fluctuation amplitude. The curve variance reflects the dispersion of the luminance around the mean value, and small variance indicates good stability. The change rate reflects the speed of the luminance change over time, and small change rate indicates good stability. The fluctuation amplitude reflects the maximum change range of the luminance, and small amplitude indicates good stability. The extraction of deterministic luminance component is realized through stability threshold screening, only the curve segment with stability degree exceeding the set threshold is included in the calculation of deterministic component. The extracted deterministic luminance component is calculated by weighted average method, the calculation formula is L=Σ(wi×Li) / Σwi, where L is the deterministic luminance component, Li is the luminance value of the i-th segment, wi is the weight coefficient of the i-th segment, and the weight coefficient wi=αSi+βTi, where Si is the stability degree index, Ti is the duration index, and α and β are weight adjustment parameters. The segment with high stability degree and long duration is assigned a higher weight, and the segment with low stability degree or short duration is assigned a lower weight. The numerical value of the deterministic luminance component represents the most reliable and stable luminance level in the time series, which has good predictability and controllability. The confidence interval of the component is determined by statistical analysis, and the confidence interval reflects the uncertainty range of the deterministic component.

[0073] The deterministic brightness component is superimposed by phase to generate a gradient coding sequence. The extracted deterministic brightness component is used as a basic component, and its confidence interval information is combined for phase superposition design: components with narrow confidence intervals use precise phase control, and components with wide confidence intervals use fuzzy phase control to accommodate uncertainties. Phase superposition is based on the superposition theorem of waves, and gradient distribution is formed by adjusting the phase relationship at different spatial positions. The superposition process introduces different phase delays to the deterministic brightness component at different spatial positions, and the accuracy of the phase delay is determined according to the width of the confidence interval: when the confidence interval is less than 10 brightness units, a 1-degree-precision phase control is used, and when the confidence interval is greater than 10 units, a 5-degree-precision coarse control is used. The generation of the gradient coding sequence uses a phase modulation method, and the phase modulation function uses a linear or exponential form, with linear modulation producing a uniform gradient and exponential modulation producing a non-uniform gradient. For example, to form a brightness gradient from left to right on the screen, the phase of the left pixel is set to 0 degrees, the phase of the middle pixel is set to 90 degrees, and the phase of the right pixel is set to 180 degrees, and the spatial variation of brightness is generated by the phase difference. The superimposed gradient coding sequence exhibits smooth and continuous brightness changes in space and maintains the stability of the deterministic brightness component in time. The data format of the sequence includes three elements: pixel coordinates, brightness values, and phase information, supporting precise brightness control and gradient generation.

[0074] In some embodiments, the multi-level brightness superposition processing of the gradient coding sequence determines an alarm coordination node, including: performing brightness coupling analysis on the gradient coding sequence to obtain brightness coupling response data; constructing a brightness coordination matrix based on the analysis of the coordination effect of each brightness element, including pixel brightness intensity, brightness distribution uniformity, and brightness change gradient; and performing visual focus optimization processing on the brightness coordination matrix to generate an alarm coordination node.

[0075] The brightness coupling analysis is performed on the gradient coding sequence to obtain brightness coupling response data. Three elements of the gradient coding sequence are analyzed: the spatial correlation analysis range and direction are determined based on pixel coordinate information, the brightness value information is used to study the mutual influence of brightness changes, and the time delay characteristics of the coupling effect are analyzed through phase information. The pixel coordinate element is used to establish the spatial adjacency relationship, and the pixels of adjacent coordinates have stronger coupling potential. The brightness value element provides the basis for calculating the coupling strength, and the pixels with large brightness differences produce strong coupling effects. The phase information element is used to analyze the dynamic characteristics of the coupling, and the phase difference determines the delay time and propagation direction of the coupling effect. The brightness coupling analysis is based on the spatial correlation theory, and the brightness changes of adjacent or similar pixels will influence each other, forming a coupling effect. The coupling strength is quantified by the correlation of the brightness changes between pixels, and strong correlation indicates obvious coupling effect. The coupling response data includes coupling strength, coupling range, coupling direction, and coupling delay, etc. The coupling strength is represented by the correlation coefficient, the coupling range is determined by the coordinate distance, and the coupling delay is calculated by the phase difference. For example, when the brightness of the pixel at the center of the screen (coordinates 960, 540) increases from 150 to 200 with a phase of 0 degrees, the brightness of the pixels within a range of 10 pixels around the center will increase by 5-15 units, and the phase delay is 0.1-0.3 seconds, forming a coupling response mode with the center as the diffusion source. The storage format of the response data adopts a spatial matrix structure, and the matrix elements represent the coupling response strength of the corresponding pixel position.

[0076] Based on the brightness coupling response data, a brightness coordination matrix is constructed to analyze the coordination effect of each brightness element, including pixel brightness intensity, brightness distribution uniformity, and brightness change gradient. The spatial matrix structure obtained earlier is used as the basic framework, and the coordination effect data of different brightness elements are filled in the matrix. The row and column coordinates of the spatial matrix correspond to the pixel position, and the matrix elements are expanded from pure coupling response strength to complex data containing the coordination effect of three brightness elements. The coordination of pixel brightness intensity is evaluated by the matching degree of the brightness of adjacent pixels, and the coordination index of brightness intensity is calculated using the adjacency relationship in the spatial matrix. The coordination of brightness distribution uniformity is evaluated by the consistency of the distribution pattern of brightness in the spatial matrix. The coordination of brightness change gradient is evaluated by the numerical change rate of adjacent elements in the matrix. The brightness coordination matrix adopts a hierarchical expansion structure based on the original spatial matrix, and each spatial position corresponds to a 3x3 sub-matrix. The rows and columns of the sub-matrix correspond to the three brightness elements, and the sub-matrix elements represent the coordination degree between the corresponding elements. The coordination degree is represented by a value between 0 and 1, with 1 indicating complete coordination and 0 indicating complete incoordination. For example, when the coordination degree of the pixel brightness intensity and the brightness change gradient at position (960, 540) is 0.8, it indicates that the intensity change and the gradient change at this position are highly consistent.

[0077] The brightness coordination matrix is processed by visual focusing to generate an alarm coordination node. Based on the constructed brightness coordination matrix, the spatial position most suitable for alarm display is identified through the principle of visual focusing to generate an alarm coordination node. The visual focusing process is based on the attention mechanism of the human eye, and the high coordination of the brightness distribution can more effectively attract and maintain visual attention. The processing process is realized by matrix eigenvalue analysis and spatial clustering method, and the area with the highest coordination is identified as the candidate node. The selection criteria of the alarm coordination node include coordination degree, spatial position and visual effect, etc. The coordination degree is quantified by the eigenvalue and trace of the matrix, and the larger the eigenvalue, the better the coordination. The spatial position considers the uniformity and completeness of the node distribution on the screen, avoiding excessive concentration or dispersion of the nodes. The visual effect is evaluated by the attention attraction strength and information transmission efficiency, and the node with good effect is preferentially selected. The geometric characteristics of the node include node center coordinates, influence radius, coordination strength and priority, etc. For example, on a 75-inch smart blackboard, five alarm coordination nodes can be generated: the central node is located at the center of the screen with coordinates (960, 540) and an influence radius of 150 pixels; the four corner nodes are located at the four corners of the screen with an influence radius of 100 pixels, forming a uniformly distributed node distribution. The coordination between multiple nodes is realized by priority scheduling and spatial separation, avoiding mutual interference and competition between nodes.

[0078] The alarm information is generated based on the alarm coordination node to complete the earthquake information service of the smart blackboard. The alarm information containing text, graphics, symbols and animations and other forms is generated by using the determined alarm coordination node as the control reference of information display. The content design of the alarm information considers the urgency, accuracy and easy understanding of the information. The core warning information contains key parameters such as epicenter position, warning time, local estimated intensity, epicenter distance and warning level. The warning level is divided into four levels of red, orange, yellow and blue according to the threat degree, and the danger degree is directly displayed by color coding. The alarm information also contains auxiliary information such as earthquake warning, evacuation instruction, safety prompt and contact information. The text information adopts a display mode with large font and high contrast, and the font size is set to 48-72 pixels. The graphic information contains spatial guidance information such as evacuation route map, safety area identification and danger area warning. The symbol information adopts internationally recognized safety symbols, such as escape exit sign, no entry sign and assembly point sign. The animation information enhances the visual impact of the information through dynamic effects such as arrow movement, text flickering and graphic change. The display position of the alarm information corresponds to the position of the coordination node. High-priority information is displayed on high-brightness nodes, and low-priority information is displayed on low-brightness nodes. The playing time sequence of the information adopts a hierarchical display strategy. The most urgent information is displayed first, and the secondary information is displayed later to avoid information overload. The multi-screen cooperative display is realized through a network synchronization mechanism to ensure the consistency and coherence of the display content of the blackboard in different positions. The completion of the earthquake information service of the smart blackboard is marked by information publishing success, personnel receiving confirmation and evacuation action starting.

[0079] In order to perform the earthquake information service method based on the smart blackboard corresponding to the above-mentioned method embodiment, the corresponding functions and technical effects are realized. Referring to Figure 2 , Figure 2 The structure block diagram of the earthquake information service system 200 based on the smart blackboard provided by the embodiment of the application is shown. For ease of illustration, only the part related to the embodiment is shown. The earthquake information service system 200 based on the smart blackboard provided by the embodiment of the application comprises:

[0080] The signal acquisition module 201 is configured to acquire seismic data of a seismic monitoring network and vibration data of a smart blackboard installation structure, and obtain a seismic verification result by comparing the vibration frequency consistency of the vibration data and the seismic data.

[0081] The building monitoring module 202 is configured to scan the seismic verification result to extract an alarm intensity group, generate a blackboard deformation feature by detecting abnormal changes in the capacitance value of the touch panel, infer a building stress state based on the blackboard deformation feature, determine a key alarm coverage area by associating the alarm intensity group with the building stress state in terms of structural danger.

[0082] The personnel perception module 203 is configured to establish a personnel position perception network by monitoring the static field intensity distribution of the touch panel in the key alarm coverage area, capture a personnel distribution signal by using the personnel position perception network to form an alarm adjustment reference, perform time sequence correlation analysis based on the alarm adjustment reference and the alarm intensity group to obtain an active alarm trigger point, and use the active alarm trigger point to perform synchronous alarm on the key alarm coverage area to obtain an alarm sequence.

[0083] The display adjustment module 204 is configured to generate a visual attention gradient by adjusting the display parameters of different regions of the touch panel, perform hierarchical display on the alarm sequence by using the visual attention gradient to obtain a visual transmission effect, and perform alarm intensity adjustment based on the visual transmission effect to generate an alarm adjustment vector.

[0084] The early warning output module 205 is configured to convert the alarm adjustment vector into a gradient coding sequence of screen pixel brightness, perform multi-level brightness superposition processing on the gradient coding sequence to determine an alarm coordination node, generate alarm information based on the alarm coordination node, and complete the intelligent blackboard earthquake information service.

[0085] The above-described earthquake information service system 200 based on the intelligent blackboard can implement an earthquake information service method based on the intelligent blackboard according to the above-described method embodiment. The optional items in the method embodiment are also applicable to the present embodiment, and will not be described in detail herein. The remaining content of the present embodiment can be referred to the content of the above-described method embodiment, and will not be described in detail herein.

[0086] The above-described embodiments are intended to exemplarily reproduce and deduce the technical solutions of the present application, and to completely describe the technical solutions, objects and effects of the present application. The purpose is to make the public more thoroughly and comprehensively understand the disclosed content of the present application, and does not limit the protection scope of the present application.

[0087] The above-described embodiments are not exhaustive enumeration based on the present application, and there can be multiple other embodiments not listed. Any replacement and improvement made without violating the concept of the present application is within the protection scope of the present application.

Claims

1. A method for providing earthquake information services based on a smart blackboard, characterized in that, include: Seismic data from the earthquake monitoring network and vibration data from the smart blackboard installation structure are collected. Seismic verification results are obtained by comparing the vibration frequency consistency between the vibration data and the seismic data. The process involves: scanning the earthquake verification results to extract alarm intensity clusters; generating blackboard deformation features by detecting abnormal changes in touch panel capacitance values; performing pattern recognition on abnormal changes in touch panel capacitance values ​​to obtain capacitance field distortion gaps; extracting deformation compensation capacitor sequences from the capacitance field distortion gaps; converting the deformation compensation capacitor sequences into structural stress features; establishing blackboard deformation features using the structural stress features; inferring the building's stress state based on the blackboard deformation features; and correlating the alarm intensity clusters with the building's stress state to determine key alarm coverage areas. The extraction of deformation compensation capacitor sequences from the capacitance field distortion gaps includes: identifying capacitance field discontinuities using the capacitance field distortion gaps; performing field strength reconstruction processing through the capacitance field discontinuities to form a repair capacitance field; implementing dynamic balance adjustment of the repair capacitance field to obtain a balanced capacitance distribution; and forming a deformation compensation capacitor sequence based on the balanced capacitance distribution. Within the critical alarm coverage area, a personnel location sensing network is established by monitoring the electrostatic field intensity distribution of the touch panel. The personnel location sensing network is used to capture personnel distribution signals to form an alarm adjustment benchmark. Based on the alarm adjustment benchmark and the alarm intensity cluster, a time-series correlation analysis is performed to obtain active alarm trigger points. The active alarm trigger points are used to execute synchronous alarms in the critical alarm coverage area to obtain alarm sequences. Visual attention gradients are generated by adjusting the display parameters of different areas of the touch panel. The alarm sequence is then displayed in a hierarchical manner using the visual attention gradients to obtain a visual transmission effect. Based on the visual transmission effect, the alarm intensity is adjusted to generate an alarm adjustment vector. The alarm adjustment vector is converted into a gradient encoding sequence of screen pixel brightness. The gradient encoding sequence is subjected to multi-level brightness superposition processing to determine the alarm coordination node. Alarm information is generated based on the alarm coordination node to complete the smart blackboard earthquake information service.

2. The method according to claim 1, characterized in that, The establishment of a personnel location sensing network by monitoring the electrostatic field intensity distribution of the touch panel includes: The electrostatic field intensity distribution of the touch panel is used to identify areas of human body-sensing disturbance. Electrostatic field change tracking is performed through the human body sensing disturbance area to form a sensing trajectory sequence; Spatial coordinate mapping is performed on the sensing trajectory sequence to obtain a set of personnel location coordinates; A personnel location perception network is formed based on the set of personnel location coordinates.

3. The method according to claim 1, characterized in that, The step of obtaining active alarm trigger points through time-series correlation analysis based on the alarm adjustment benchmark and the alarm intensity family includes: The alarm adjustment benchmark is decomposed into a dynamic adjustment sequence according to a time window; The arrival time matrix is ​​generated by calculating the seismic wave propagation delay for the alarm intensity group. The dynamic adjustment sequence is phase-matched with the arrival time matrix to form a timing coupling diagram; The active alarm trigger point is determined by extracting the resonance enhancement node from the time-series coupling diagram.

4. The method according to claim 1, characterized in that, The method of generating visual attention gradients by adjusting display parameters in different areas of the touch panel includes: Utilize the touch panel to identify pixel-level brightness distribution; Visual focus control is performed through the pixel-level brightness distribution to form a focused display area; Spatial contrast adjustment is applied to the focused display area to obtain directional visual flow; A visual attention gradient is formed based on the directional visual flow.

5. The method according to claim 1, characterized in that, The step of converting the alarm adjustment vector into a gradient encoding sequence of screen pixel brightness includes: The brightness oscillation pattern of the alarm adjustment vector is monitored to generate a brightness oscillation trajectory; Injecting inverse brightness at the peak position of the brightness oscillation trajectory forms a brightness standing wave; Deterministic luminance components are extracted using the stable nodes of the luminance standing wave; The deterministic luminance components are superimposed in phase to generate a gradient coding sequence.

6. The method according to claim 1, characterized in that, The step of performing multi-level brightness superposition processing on the gradient coding sequence to determine the alarm coordination node includes: Luminance coupling analysis is performed on the gradient coding sequence to obtain luminance coupling response data; Based on the brightness coupling response data, the coordination effect of each brightness element is analyzed to construct a brightness coordination matrix. Each brightness element includes pixel brightness intensity, brightness distribution uniformity, and brightness variation gradient. The brightness coordination matrix is ​​subjected to visual focusing optimization processing to generate alarm coordination nodes.

7. The method according to claim 5, characterized in that, The extraction of deterministic luminance components using the stable nodes of the luminance standing wave includes: The brightness standing wave is calibrated on a brightness time scale to form a brightness time series; Identify brightness jump points and stable points on the brightness time sequence; A brightness stability curve is generated by segmenting the curve based on the brightness jump point and the stable point. The stability of the brightness stability curve is analyzed to form a deterministic brightness component.

8. An earthquake information service system based on a smart blackboard, characterized in that, include: The signal acquisition module is used to acquire seismic data from the earthquake monitoring network and vibration data from the smart blackboard installation structure. The seismic verification result is obtained by comparing the vibration frequency consistency between the vibration data and the seismic data. The building monitoring module is used to perform threat intensity scanning on the earthquake verification results to extract alarm intensity clusters, and to generate blackboard deformation features by detecting abnormal changes in the capacitance value of the touch panel. This includes: performing pattern recognition on the abnormal changes in the touch panel capacitance value to obtain capacitance field distortion gaps; extracting deformation compensation capacitor sequences from the capacitance field distortion gaps; converting the deformation compensation capacitor sequences into structural stress features; establishing blackboard deformation features using the structural stress features; inferring the building's stress state based on the blackboard deformation features; and correlating the alarm intensity clusters with the building's stress state to determine key alarm coverage areas. The step of extracting the deformation compensation capacitor sequence from the capacitance field distortion gaps includes: identifying capacitance field discontinuities using the capacitance field distortion gaps; performing field strength reconstruction processing through the capacitance field discontinuities to form a repair capacitance field; implementing dynamic balance adjustment on the repair capacitance field to obtain a balanced capacitance distribution; and forming a deformation compensation capacitor sequence based on the balanced capacitance distribution. The personnel sensing module is used to establish a personnel location sensing network by monitoring the electrostatic field intensity distribution of the touch panel within the key alarm coverage area, capture personnel distribution signals using the personnel location sensing network to form an alarm adjustment benchmark, perform time-series correlation analysis based on the alarm adjustment benchmark and the alarm intensity cluster to obtain active alarm trigger points, and use the active alarm trigger points to perform synchronous alarms on the key alarm coverage area to obtain alarm sequences. The display adjustment module is used to generate a visual attention gradient by adjusting the display parameters of different areas of the touch panel, use the visual attention gradient to perform hierarchical display of the alarm sequence to obtain a visual transmission effect, and generate an alarm adjustment vector based on the visual transmission effect to adjust the alarm intensity. The early warning output module is used to convert the alarm adjustment vector into a gradient encoding sequence of screen pixel brightness, perform multi-level brightness superposition processing on the gradient encoding sequence to determine the alarm coordination node, generate alarm information based on the alarm coordination node, and complete the smart blackboard earthquake information service.

Images