Air quality sensor based on Internet of Things and remote control method thereof

By combining a multi-source heterogeneous sensing fusion system, a spatiotemporal edge gateway system, and a dynamic response collaborative hub system, the problems of coverage, data latency, and operation and maintenance costs of air quality monitoring systems have been solved, realizing closed-loop control of air quality monitoring and purification, and improving the accuracy and response speed of air quality monitoring.

CN120896968AActive Publication Date: 2025-11-04GUANGZHOU HEDONG TECH CO LTD

Patent Information

Application Number
CN202511282110.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-09
Publication Date
2025-11-04
Estimated Expiration
2045-09-09

AI Technical Summary

Technical Problem

Existing air quality monitoring systems suffer from problems such as limited coverage radius of a single station, long data transmission delays, high operation and maintenance costs, and the inability to achieve closed-loop control from monitoring to purification.

Method used

A three-dimensional sensing layer is constructed using a multi-source heterogeneous sensing fusion system. Data topology compression processing is performed through a spatiotemporal edge gateway system to generate a confined space pollution migration cloud strategy. A dynamic response collaborative central system is used to form a linkage control matrix for purification devices, enabling remote control of air quality sensors.

Benefits of technology

It has achieved a three-level technical closed loop for air quality monitoring and purification, breaking through the limitations of traditional single-point measurement by sensors, constructing a quantifiable and analyzable microenvironment quality evolution map, reducing the amount of data, and realizing the coordinated response of purification devices.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120896968A_ABST
    Figure CN120896968A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of air quality monitoring, and provides an air quality sensor based on the Internet of Things and a remote control method thereof, and the air quality sensor comprises a multi-source heterogeneous sensing fusion system, a time-space domain edge gateway system and a dynamic response collaborative central system. The remote control method comprises the steps that a purification device linkage control matrix is processed through a heterogeneous instruction fusion technology to obtain a space optimization control vector set, and the space optimization control vector set forms a man-machine interaction entropy value mechanism; the man-machine interaction entropy value model is processed through an entropy weight dynamic distribution strategy to obtain a space state sensing vector, and the space state sensing vector forms a cross-medium alarm triggering channel; the cross-medium alarm trigger channel is processed by the bidirectional response coupling engine to obtain an equipment state feature topology, and the equipment state feature topology forms a closed-loop control entropy correction instruction. According to the invention, pollution of a physical space is dynamically converted into operable equipment control parameters, and a complete Internet of Things closed-loop system from environment monitoring to purification execution is established.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air quality monitoring, and particularly relates to an air quality sensor based on the Internet of Things and a remote control method thereof. BACKGROUND

[0002] Under the wave of new smart city construction, the global Internet of Things air quality monitoring market is expected to exceed 12 billion US dollars in 2025. At present, about 18,000 monitoring sites have been deployed in key areas in China, but traditional equipment has three major pain points: the single station coverage radius is limited, it is difficult to build a high-resolution pollution map; the data backhaul delay is long, it is difficult to support emergency decision-making; the operation and maintenance cost accounts for a high proportion of the total investment.

[0003] Prior art one, application number: CN 202410521776.1 discloses an air quality intelligent monitoring system and method based on Internet of Things technology, which monitors and collects air parameters in real time through an air quality sensor, such as temperature, humidity, carbon dioxide concentration, sulfur dioxide concentration, ozone concentration, and particle size concentration, and uses Internet of Things technology to transmit data to a backend server, introduces artificial intelligence-based data processing and analysis algorithms in the backend server to perform time series collaborative correlation analysis of these air parameter data, so as to detect the level of air quality. Although it can improve the accuracy of air quality level judgment based on the dynamic collaborative change of each component in the air, so as to provide timely and accurate air quality information and provide a scientific basis for air pollution control and management; but it does not involve edge computing, which cannot quickly extract pollution features locally, resulting in data redundancy and transmission burden; only provides air quality level judgment, does not form a closed-loop control from monitoring to purification, and cannot directly link to purification equipment for dynamic response.

[0004] The prior art two, application number: CN202311092151.X discloses a kind of cloud environment monitoring method and device, comprising: selecting sensor: according to the environmental parameter of need monitoring, selecting sensor, sensor includes temperature sensor, humidity sensor, air quality sensor;Sensor is connected to internet of things equipment: sensor is connected to internet of things equipment, and internet of things equipment includes internet of things gateway or embedded device;Data acquisition and transmission: the data that internet of things equipment is transmitted to cloud platform by wireless communication mode that sensor is collected, and wireless communication mode includes wireless network, cellular network or LoRaWAN;Cloud data storage: cloud platform receives and stores sensor data;Data processing and analysis: cloud platform is handled and analyzed to the environmental data received.The cloud platform sends alarm signal in abnormal condition according to the result of processing and analysis;However, rely on cloud to store and analyze data, not involved in edge computing optimization, resulting in large amount of data, transmission cost is high, and cloud decision exists delay;Only carry out basic data acquisition and alarm, not to the space-time migration law of pollutant is modeled, cannot predict pollutant diffusion trend;Alarm mechanism only stays in the level of notification, not with purification equipment forms automatic control matrix, cannot realize accurate local environment optimization.

[0005] At present, prior art one and prior art two exist air quality monitoring and response high delay, pollution prediction ability needs to be further improved.Problems. Thus, the present application provides an air quality sensor based on internet of things and its remote control method. SUMMARY

[0006] To solve the above technical problems, the present application provides an air quality sensor based on internet of things, comprising:

[0007] Multi-source heterogeneous perception fusion system, for monitoring network composed of multiple groups of heterogeneous sensor nodes, form a stereoscopic perception layer by spatial gridding deployment;Each heterogeneous sensor node collects and acquires the fluctuation of gaseous molecular concentration of physical space in real time, and obtains composite pollution characteristic factor through multi-source heterogeneous fusion processing, and the composite pollution characteristic factor forms a microenvironment quality evolution map;

[0008] Space-time domain edge gateway system, for deploying computing node cluster on the edge side of air quality monitoring area, adopts hierarchical aggregation architecture to process perception data, each edge node carries out edge topology compression processing to the microenvironment map in its coverage range to obtain space-time feature slice, and the space-time feature slice forms a closed space pollution migration cloud strategy;

[0009] Dynamic response coordination hub system, for processing device control vector set from closed space pollution migration cloud strategy through cross-domain strategy decoupling engine, and the device control vector set forms a purification device linkage control matrix.

[0010] Optionally, the space-time domain edge gateway system comprises:

[0011] The space-time dimension decomposition subsystem is used for extracting a pollution propagation potential field and a real-time pollution intensity scalar field in the microenvironment quality evolution atlas through four-dimensional tensor slice extraction of the microenvironment quality evolution atlas, and generating a double-channel space-time data stream.

[0012] The edge topology compression processing subsystem is used for processing the double-channel space-time data stream through an entropy constraint collapse engine; performing adaptive vorticity detection on the pollution propagation potential field to capture a pollution migration direction vector; performing spatial pyramid down-sampling on the real-time pollution intensity scalar field to retain intensity gradient mutation points; and generating a high information density space-time feature slice through tensor cross product fusion of the pollution migration direction vector and the intensity gradient mutation points.

[0013] The pollution migration cloud strategy construction subsystem is used for taking the space-time feature slice as an input unit, calculating a pollution source probability distribution through nonlinear diffusion inversion, generating a pollution concentration equipotential surface and a migration path tangent bundle according to the pollution source probability distribution, and encoding the equipotential surface and the migration path tangent bundle into a dynamic strategy topology net to form a closed space pollution migration cloud strategy capable of describing pollution diffusion rules.

[0014] Optionally, the edge topology compression processing subsystem comprises:

[0015] The pollution propagation potential field processing component is used for scanning a potential energy gradient distribution through a variable-scale differential operator, extracting a vorticity extreme point of potential energy change, generating a pollution migration direction vector set containing a direction angle and a vorticity intensity scalar, processing the pollution migration direction vector set through a vector field sparsification engine to remove noise vectors with a vorticity intensity lower than a dynamic threshold and perform curvature consistency clustering on adjacent vectors, and outputting a simplified pollution migration main direction vector bundle.

[0016] The pollution intensity scalar field processing component is used for constructing a second-order differential curvature graph of the intensity field using the real-time pollution intensity scalar field, identifying a zero-crossing point in the curvature graph as a gradient mutation critical point, establishing a non-uniform sampling grid centered on the critical point, performing adaptive pyramid down-sampling constrained by the critical point, performing intensity mean aggregation in a non-mutation area, retaining original intensity values at the gradient mutation critical point, and generating a pollution intensity gradient mutation point set with a weight marker.

[0017] The double-channel data fusion component is used for converting the pollution migration main direction vector bundle into a direction tensor field, mapping the pollution intensity gradient mutation point set into an intensity weight tensor, performing orthogonal cross multiplication operation of the two tensors, and outputting a space-time feature slice fused with pollution migration direction and intensity mutation features.

[0018] Optionally, the double-channel data fusion component comprises:

[0019] The direction vector beam conversion tensor field subassembly is used for converting each vector direction angle into a unit direction base through tangent space mapping based on the vector beam curvature consistency clustering center of a main direction vector beam of pollution migration, and generating a direction base set;

[0020] The tensor field generation subassembly is used for converting a vortex intensity scalar of each direction base of the direction base set into a direction weight coefficient, constructing a three-dimensional direction tensor with the direction base as an axis and the weight as a module, and outputting a pollution migration direction tensor field with a spatial distribution attribute;

[0021] The mutation point set conversion weight tensor subassembly is used for establishing a radial decay function with a critical point as a center, calculating an intensity amplitude of the decay function according to a point set weight mark, generating a mutation kernel function distribution cloud, and taking a non-uniform sampling grid vertex as a tensor control point, and executing bicubic spline interpolation of the kernel function value between the control points to output a pollution intensity weight tensor field covering the whole space.

[0022] Optionally, the mutation point set conversion weight tensor subassembly comprises:

[0023] The function distribution cloud generation module is used for inputting the pollution intensity gradient mutation point set into a radial decay function constructor, extracting a spatial coordinate and a weight mark value of each critical point, establishing an exponential decay function with the critical point as a center, dynamically adjusting a function decay coefficient by the weight mark value, and generating a decay function unit with an amplitude modulation;

[0024] The kernel function cloud synthesis module is used for superimposing each function unit of all decay function units according to spatial coordinates, eliminating an interference effect in an overlapping area through amplitude normalization, outputting a continuously distributed mutation kernel function distribution cloud, inputting a non-uniform sampling grid vertex into a tensor control point binder, reading a grid vertex spatial coordinate as a control point reference position, injecting a kernel function amplitude of a corresponding position at the control point, and generating a tensor control point set with an amplitude constraint;

[0025] The global tensor interpolation module is used for constructing a three-dimensional parameterized surface with the control point as a node, executing continuity interpolation of the kernel function amplitude along a surface normal, guaranteeing gradient smoothness of the interpolation surface through curvature constraint, and outputting a pollution intensity weight tensor field covering the whole space.

[0026] Optionally, the dynamic response coordination central system comprises:

[0027] The migration cloud strategy decoupling subsystem is used for extracting the pollution concentration equipotential surface features in the pollution migration cloud strategy, generating a pollution intensity gradient tensor, separating the curvature parameters of the migration path tangent bundle, generating a path direction admittance matrix, and outputting a decoupled strategy feature primitive group; the pollution intensity gradient tensor is matched with a purification equipment power response curve, and the path direction admittance matrix is mapped to an equipment spatial orientation topology; a dimensionally orthogonalized equipment control vector set is generated;

[0028] The linkage control matrix construction subsystem is used for constructing an equipment operation unit space with the equipment control vector as a base, distributing equipment control amount weights in the unit space according to the pollution intensity gradient direction; the equipment control amount phase coordination relationship is established according to the equipment spatial orientation topology, the weight distribution and the phase coordination are coded into a multi-dimensional control plane, and a linkage control matrix of a drivable multi-terminal purification device is output.

[0029] The double-channel feedback triggering subsystem is used for synchronously activating a feedback arbitrator.

[0030] Optionally, the double-channel feedback triggering subsystem comprises: a mobile terminal channel, when the pollution intensity weight in the linkage control matrix exceeds a dynamic threshold value: extracting the spatial code of the over-standard area, synthesizing the spatial code and the intensity weight into an over-threshold alarm vector, and pushing the gaseous parameter over-threshold alarm to the gateway; after the gateway receives the gaseous parameter over-threshold alarm, playing, lighting and the clean wind system and the like according to a preset program, and the equipment displays the content of the gaseous parameter over-threshold alarm according to the preset program; at the same time, the gateway pushes the alarm information to the APP through the alarm information pushing platform; and a physical indication channel, according to the phase coordination relationship of the linkage control matrix, analyzing the key pollution nodes in the equipment orientation topology, triggering the spectral early warning pulse sequence of the corresponding position equipment.

[0031] Optionally, the linkage control matrix construction subsystem comprises:

[0032] The phase coordination relationship establishment component is used for calculating the shortest connected path length between any two devices in the equipment spatial orientation topology, converting the path length into an action delay time base, generating a time-space delay field between the devices, generating a diffusion wave front with the pollution source position as a wave source, calculating the phase offset angle of each device control action according to the delay field, and outputting a device control phase difference vector;

[0033] The control amount tensor synthesis component is used for mapping the pollution intensity gradient weight into a control amount amplitude matrix, and converting the phase difference vector into a time sequence coordination operator;

[0034] The multi-dimensional plane construction component is used for constructing a complex control plane with the amplitude matrix as a real part and the time sequence operator as an imaginary part, expanding the complex plane along the equipment spatial dimension to form a three-dimensional control tensor body, performing orthogonal projection compression on the tensor body to generate a multi-dimensional control plane.

[0035] Optionally, the gaseous molecule concentration fluctuation includes air quality parameters of PM2.5, CO2, TVOC, temperature and humidity.

[0036] The application provides a remote control method of an air quality sensor based on Internet of Things, and contains the following steps:

[0037] The purification device linkage control matrix is processed by a heterogeneous instruction fusion technology to obtain a spatial optimization control vector set, and the spatial optimization control vector set forms a man-machine interaction entropy value mechanism.

[0038] The man-machine interaction entropy value model is processed by an entropy weight dynamic distribution strategy to obtain a spatial state perception vector, and the spatial state perception vector forms a cross-medium alarm triggering channel.

[0039] The cross-medium alarm triggering channel is processed by a bidirectional response coupling engine to obtain a device state feature topology, and the device state feature topology forms a closed-loop control entropy correction instruction.

[0040] The application realizes a three-level technical closed loop in the field of Internet of Things air quality monitoring: a multi-source heterogeneous sensing fusion system converts discrete gaseous molecule concentration data into composite pollution characteristic factors with spatial correlation, breaks through the limitation of traditional single-point sensor measurement, and constructs a quantifiable micro-environment quality evolution graph. A time-space domain edge system performs topology compression on high-dimensional graph data to generate a feature slice containing time-space double attributes, so that the original monitoring data quantity is reduced while the migration rule of pollutants in a closed space is still fully characterized. A dynamic response coordination hub system decouples the abstract migration strategy into executable device control vectors, and finally forms a control matrix to realize the coordinated response of the purification device group, so that the traditional independent running purification equipment is changed into a linkage network with spatial strategy.

[0041] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application. The objects and other advantages of the present application will be realized and achieved by means of the instrumentalities particularly pointed out in the written description and the appended drawings.

[0042] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. In the drawings:

[0044] Figure 1 The block diagram of the air quality sensor based on Internet of Things in Example 1 of the present application;

[0045] Figure 2 This is a block diagram of the multi-source heterogeneous sensing fusion system in Embodiment 2 of the present invention;

[0046] Figure 3 This is a block diagram of the spatiotemporal domain edge gateway system in Embodiment 3 of the present invention;

[0047] Figure 4 This is a block diagram of the dynamic response coordination central system in Embodiment 7 of the present invention;

[0048] Figure 5 This is a flowchart of the remote control method for an air quality sensor based on the Internet of Things in Embodiment 11 of the present invention. Detailed Implementation

[0049] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0050] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0051] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0052] Example 1: As Figure 1 As shown, this embodiment of the invention provides an air quality sensor based on the Internet of Things, comprising:

[0053] A multi-source heterogeneous perception fusion system is used for a monitoring network composed of multiple groups of heterogeneous sensor nodes, and a three-dimensional perception layer is formed by spatial grid deployment; each heterogeneous sensor node collects and acquires gaseous molecular concentration fluctuations of a physical space in real time, and a composite pollution characteristic factor is obtained through multi-source heterogeneous fusion processing, and the composite pollution characteristic factor forms a micro-environment quality evolution map; the gaseous molecular concentration fluctuations include air quality parameters such as PM2.5, CO2, TVOC, temperature and humidity;

[0054] A space-time domain edge gateway system is used for deploying a cluster of computing nodes at the edge of an air quality monitoring area, using a hierarchical aggregation architecture to process perception data, each edge node performing edge topology compression processing on the micro-environment map within its coverage range to obtain a space-time feature slice, and the space-time feature slice forms a closed space pollution migration cloud strategy;

[0055] A dynamic response coordination hub system is used for processing the closed space pollution migration cloud strategy through a cross-domain strategy decoupling engine to obtain a device control vector set, and the device control vector set forms a purification device linkage control matrix; an air quality over-standard alarm is pushed through a mobile phone App, and an over-standard feedback is performed through a linkage device indicator light.

[0056] The working principle and beneficial effects of the above technical solutions are as follows: the multi-source heterogeneous perception fusion system of the embodiment acquires gaseous molecular concentration fluctuations of a physical space, and a composite pollution characteristic factor is obtained through multi-source heterogeneous fusion processing, and the composite pollution characteristic factor forms a micro-environment quality evolution map; the space-time domain edge gateway system performs edge topology compression processing on the micro-environment quality evolution map to obtain a space-time feature slice, and the space-time feature slice forms a closed space pollution migration cloud strategy; the dynamic response coordination hub system processes the closed space pollution migration cloud strategy through a cross-domain strategy decoupling engine to obtain a device control vector set, and the device control vector set forms a purification device linkage control matrix. The above scheme realizes a three-level technical closed loop in the field of Internet of Things air quality monitoring: the multi-source heterogeneous perception fusion system converts discrete gaseous molecular concentration data into a composite pollution characteristic factor with spatial correlation, breaking through the limitations of traditional single-point sensor measurement and constructing a quantifiable micro-environment quality evolution map. The space-time domain edge system performs topology compression on high-dimensional graph data to generate a feature slice containing time and space attributes, reducing the amount of original monitoring data while still fully representing the migration rules of pollutants in a closed space. The dynamic response coordination hub system decouples the abstract migration strategy into executable device control vectors, and the final control matrix realizes the coordinated response of the purification device group, so that the traditional independent running purification equipment is transformed into a linkage network with spatial strategy.

[0057] In summary, the embodiment converts the pollution of the physical space into an operable device control parameter through a three-stage data processing chain of perception, calculation and control, and establishes a complete Internet of Things closed-loop system from environmental monitoring to purification execution.

[0058] Embodiment 2: As shown in the embodiment 1, on the basis of the embodiment 1, the multi-source heterogeneous perception fusion system provided by the embodiment of the application comprises Figure 2

[0059] The gaseous molecule concentration fluctuation acquisition subsystem is used for capturing the discrete state gaseous oscillation parameters in the physical space through the distributed resonant sensing array, generating an original oscillation parameter stream; the original oscillation parameter stream is decoupled through the time domain oscillation frequency and is re-calibrated through the space domain gridding, eliminating the time and space reference offset between the multi-source sensing units, and outputting a synchronized oscillation tensor;

[0060] The composite pollution characteristic factor generation subsystem is used for performing multi-order differential manifold expansion on the synchronized oscillation tensor, extracting the gradient mutation characteristics of each gaseous parameter; the gradient mutation characteristics are fused through the rotation invariant convolution kernel to generate a cross-modal pollution entropy value with pollution correlation; the cross-modal pollution entropy value is input into a chaotic topological cluster to output a composite pollution characteristic factor representing the composite pollution intensity;

[0061] The microenvironment quality evolution graph construction subsystem is used for taking the composite pollution characteristic factor as a node, acquiring the pollution propagation potential energy between the nodes through an adaptive field strength program; constructing a three-dimensional space-time connection topological network according to the pollution propagation potential energy, superimposing a real-time pollution intensity scalar field on the three-dimensional space-time connection topological network, and finally forming a microenvironment quality evolution graph with a pollution diffusion path.

[0062] ​The working principle and beneficial effects of the above technical solution are as follows: The gaseous molecule concentration fluctuation acquisition subsystem of this embodiment is used to capture discrete gaseous oscillation parameters in physical space through a distributed resonant sensing array to generate a raw oscillation parameter stream; the raw oscillation parameter stream is decoupled by time-domain oscillation frequency and recalibrated by spatial gridding to eliminate the spatiotemporal reference offset between multi-source sensing units and output a synchronized oscillation tensor; the composite pollution feature factor generation subsystem is used to expand the synchronized oscillation tensor into a multi-order differential manifold and extract the gradient mutation features of each gaseous parameter; the gradient mutation features are fused by rotation-invariant convolution kernels to generate a cross-modal pollution entropy value with pollution correlation; the cross-modal pollution entropy value is input into a chaotic topological clusterer to output a composite pollution feature factor characterizing the intensity of composite pollution; the microenvironmental quality evolution map construction subsystem is used to obtain the pollution propagation potential energy between nodes through an adaptive field strength program, with the composite pollution feature factor as the node; a three-dimensional spatiotemporal connection topology network is constructed based on the pollution propagation potential energy, and a real-time pollution intensity scalar field is superimposed on the three-dimensional spatiotemporal connection topology network to finally form a microenvironmental quality evolution map with pollution diffusion paths. The above scheme uses discrete gaseous oscillation parameters captured by a distributed resonant sensing array to form a highly consistent oscillation tensor through spatiotemporal benchmark synchronization. Based on the cross-modal pollution entropy values ​​extracted using differential manifold unrolling and rotation-invariant convolution kernels, composite pollution feature factors are generated through chaotic topological clustering, achieving multi-parameter pollution correlation modeling. Finally, a three-dimensional spatiotemporal connected topology network constructed by an adaptive field strength program is superimposed with a real-time scalar field to form a micro-environmental quality evolution map with dynamic tracking capabilities for pollution diffusion paths. This achieves a complete process analysis from raw physical signal acquisition to visualization of pollution propagation trends. Its core value lies in establishing a multi-scale environmental quality monitoring framework of "physical signal-feature factor-spatiotemporal evolution." Through heterogeneous data fusion and topology modeling techniques, it overcomes the limitations of single-point discrete measurements in traditional environmental monitoring, providing a spatiotemporally continuous analytical basis for pollution source tracing and diffusion prediction in complex micro-environments.

[0063] Example 3: As Figure 3 As shown, based on Embodiment 1, the spatiotemporal domain edge gateway system provided in this embodiment of the invention includes:

[0064] The spatiotemporal dimension decomposition subsystem is used to extract the pollution propagation potential energy field and real-time pollution intensity scalar field from the microenvironment quality evolution map through four-dimensional tensor slicing, and generate a dual-channel spatiotemporal data stream.

[0065] Edge topology compression processing subsystem, used for double-channel spatio-temporal data stream through entropy constraint collapse engine processing; adaptive vorticity detection is performed on the pollution propagation potential field to capture the pollution migration direction vector; the real-time pollution intensity scalar field is subjected to spatial pyramid downsampling to retain the intensity gradient mutation points; through tensor cross product fusion of the pollution migration direction vector and the intensity gradient mutation points, high information density spatio-temporal feature slices are generated;

[0066] Among them, the edge topology compression processing subsystem is responsible for compressing the huge double-channel data stream into high information density feature slices; the entropy constraint collapse engine is a lossy compression framework, which aims to maximize the information useful for subsequent tasks in the data under the maximum allowed entropy value of the given information entropy or complexity; the maximum allowed entropy value, unit: bits, is a hyperparameter determined by the computing and storage capacity of the edge node, the smaller the maximum allowed entropy value, the higher the compression ratio, and the distortion may also be larger; the Lagrange multiplier λ is used to balance the compression ratio or code rate R and the distortion degree or D in rate-distortion optimization; the quantization scheme that minimizes J=D+λR is automatically found, where J is the cost function; the engine quantizes and encodes the output results of subsequent vorticity detection and downsampling operations to ensure that the data entropy of the finally generated spatio-temporal feature slices does not exceed the maximum allowed entropy value;

[0067] Pollution migration cloud strategy construction subsystem, used for taking spatio-temporal feature slices as input units, calculating pollution source probability distribution through nonlinear diffusion inversion; generating pollution concentration equipotential surface and migration path tangent bundle according to the pollution source probability distribution; encoding the equipotential surface and the migration path tangent bundle into a dynamic strategy topology net to form a closed space pollution migration cloud strategy that can describe the pollution diffusion law;

[0068] The pollution migration cloud strategy construction subsystem uses the compressed feature slices to infer the pollution source and predict its diffusion law; the nonlinear diffusion inversion calculates the pollution source probability distribution:

[0069] The forward model uses the convection-diffusion equation as the physical model for describing pollution evolution:

[0070]

[0071] S(x, y, z) is the pollution source term to be inverted;

[0072] The inversion problem is a typical inverse problem, and the concentration field C obs (information contained in the feature slices) at time t0 is known, and the source term S is to be solved, and since the problem is ill-posed, regularization is needed.

[0073] Objective function:

[0074]

[0075] F(S) represents a forward model operator, which denotes the process of simulating concentration field from source S; R(S) represents a regularization term, such as L1 norm to promote sparse source, Total Variation norm to promote spatial continuity of source, λ ′ is a regularization strength parameter; solving this optimization problem, the obtained S is the pollution source probability distribution, and the higher the probability indicates the greater the possibility that the position is a real source.

[0076] The working principle and beneficial effects of the technical solution are as follows: The space-time dimension decomposition subsystem of the embodiment is used to extract the pollution propagation potential field and the real-time pollution intensity scalar field in the pollution evolution map of the micro environment through four-dimensional tensor slicing of the micro environment quality evolution map, and generate a double-channel space-time data stream; the edge topology compression processing subsystem is used to process the double-channel space-time data stream through an entropy constraint collapse engine; the pollution propagation potential field is subjected to adaptive vorticity detection to capture the pollution migration direction vector; the real-time pollution intensity scalar field is subjected to spatial pyramid down-sampling to retain the intensity gradient mutation points; the pollution migration direction vector and the intensity gradient mutation points are fused through tensor cross multiplication to generate a high-information-density space-time feature slice; the pollution migration cloud strategy construction subsystem is used to take the space-time feature slice as an input unit and calculate the pollution source probability distribution through nonlinear diffusion inversion; the pollution concentration equipotential surface and the migration path tangent bundle are generated according to the pollution source probability distribution; the codes of the equipotential surface and the migration path tangent bundle are encoded into a dynamic strategy topology net to form a closed space pollution migration cloud strategy that can describe the pollution diffusion law. The above-mentioned scheme realizes dynamic quantitative analysis and visual representation of the pollution diffusion law in a closed space through multi-module collaborative processing. Specifically, there are three progressive levels: the space-time dimension decomposition subsystem decouples the original environmental monitoring data into a pollution propagation potential field (vector field) and a real-time pollution intensity field (scalar field) to form a double-channel space-time data stream with physical meaning, providing a structured input for subsequent analysis. The edge topology compression subsystem retains the pollution migration direction characteristics through vorticity detection, extracts the intensity gradient mutation points through the spatial pyramid algorithm, and finally generates a space-time feature slice through tensor operation. This process realizes data dimension reduction and feature enhancement. The pollution migration cloud strategy construction subsystem converts the discrete feature slice into a continuous diffusion model: the pollution source probability distribution is calculated through nonlinear inversion, the generated equipotential surface describes the concentration gradient distribution, and the migration path tangent bundle quantifies the diffusion direction and rate; finally, the output dynamic strategy topology net can completely represent the three-dimensional diffusion kinetic characteristics of pollutants in a closed space.

[0077] In summary, the embodiment realizes end-to-end conversion from original monitoring data to a computable diffusion model, providing a quantitative basis for pollution source tracing, diffusion prediction, and prevention and control decision-making. The error transmission of all modules is controlled within the confidence interval, ensuring the physical consistency of the output strategy.

[0078] In the embodiment 4, on the basis of the embodiment 3, the edge topology compression processing subsystem comprises:

[0079] The pollution propagation potential field processing component is used for scanning the potential gradient distribution by the variable-scale differential operator, extracting the local extreme points of the potential variation, and generating a pollution migration direction vector set containing a direction angle and a vortex intensity scalar. The pollution migration direction vector set is processed by a vector field sparsification engine, noise vectors with a vortex intensity lower than a dynamic threshold are removed, and curvature consistency clustering is performed on adjacent vectors. A simplified pollution migration main direction vector bundle is output.

[0080] The expression of the variable-scale differential operator is a composite operation of the curl operator and the Gaussian smoothing convolution, and the expression is as follows:

[0081]

[0082] Wherein, Ω σ represents the variable-scale differential operator itself, which is an operator family whose specific behavior is determined by the scale parameter σ. A vector field is input into the operator, and another vector field is obtained as the output. represents the curl operator, which is a differential operator in vector calculus, used to measure the rotation trend and intensity of a vector field. A new vector field representing the local rotation of the input vector field is output. represents the Gaussian kernel function, which is a smoothing function with the scale parameter σ as the standard. The convolution operation is denoted by *, which means that the input vector field is smoothed and filtered by the Gaussian kernel function. A scale is selected, the Gaussian kernel at the scale is used for convolution smoothing of the potential field, and a smoothed field is obtained. The curl is calculated for the smoothed field to obtain a vorticity field. The local extreme points of the vorticity modulus in the output vorticity field are the candidate points of the pollution migration direction vector to be captured by the algorithm. A series of different scale parameter values are traversed to analyze the potential field at different scales. Finally, a robust pollution migration direction vector set is generated through a multi-scale fusion strategy.

[0083] The pollution intensity scalar field processing component is used for constructing a second-order differential curvature map of the intensity field using the real-time pollution intensity scalar field, identifying the zero-crossing points in the curvature map as gradient mutation critical points, and establishing a non-uniform sampling grid centered on the critical points. Through adaptive pyramid downsampling constrained by the critical points, the intensity mean value is aggregated in the non-mutation area, the original intensity value is reserved around the gradient mutation critical point, and a pollution intensity gradient mutation point set with weight markers is generated.

[0084] The dual-channel data fusion component is used for converting the pollution migration main direction vector bundle into a direction tensor field, mapping the pollution intensity gradient mutation point set into an intensity weight tensor, performing an orthogonal cross multiplication operation on the two tensors, and outputting a spatiotemporal feature slice that fuses the pollution migration direction and the intensity mutation characteristics.

[0085] The working principle and beneficial effects of the above technical solution are: the pollution propagation potential field processing component of the embodiment is used to scan the potential energy gradient distribution of the pollution propagation potential field through the variable-scale differential operator, extract the vorticity extreme points of the potential energy change, and generate a pollution migration direction vector set containing a direction angle and a vortex intensity scalar; the pollution migration direction vector set is processed by a vector field sparsification engine, noise vectors with a vortex intensity lower than a dynamic threshold are removed, and curvature consistency clustering is performed on adjacent vectors; a topologically simplified pollution migration main direction vector bundle is output; the pollution intensity scalar field processing component is used to construct a second-order differential curvature map of the intensity field using a real-time pollution intensity scalar field, identify zero-crossing points in the curvature map as gradient mutation critical points, and establish a non-uniform sampling grid centered on the critical points; through adaptive pyramid downsampling constrained by the critical points, intensity mean aggregation is performed in non-mutation areas, the original intensity values are retained around the gradient mutation critical points, and a pollution intensity gradient mutation point set with weight markers is generated; the dual-channel data fusion component is used to convert the pollution migration main direction vector bundle into a direction tensor field, map the pollution intensity gradient mutation point set into an intensity weight tensor, perform orthogonal cross multiplication operation on the two tensors, and output a spatiotemporal feature slice that fuses the pollution migration direction and intensity mutation characteristics. The edge topology compression processing subsystem of the above scheme realizes efficient extraction and fusion of pollution diffusion characteristics through modular collaborative work: the pollution propagation potential field processing component converts the continuous potential field into a discrete migration direction vector set through differential operator scanning and vorticity analysis, and then obtains a vector bundle reflecting the main diffusion path through curvature clustering; this process completes the conversion from a continuous field to a discrete topological structure. The pollution intensity scalar field processing component uses second-order differential curvature detection and adaptive sampling to realize data dimension reduction while retaining intensity mutation characteristics, generating a mutation point set with weight markers; this process maintains the topological expression of key intensity mutation information. The dual-channel data fusion component couples the direction and intensity features through tensor operation, and the generated spatiotemporal feature slice contains both the migration direction information and the intensity mutation information of the pollutant.

[0086] In summary, the embodiment realizes topology feature extraction of the original continuous field, selection and clustering of key feature points, and tensor fusion of multi-modal features through cascading processing, and finally outputs a compressed expression with both directionality and intensity mutation characteristics, providing a high information density feature representation for subsequent pollution diffusion analysis.

[0087] Embodiment 5: Based on embodiment 4, the dual-channel data fusion component provided by the embodiment of the application comprises:

[0088] The direction vector bundle to tensor field sub-component is used to convert the direction vector bundle to a tensor field by mapping the direction angle of each vector to a unit direction basis through tangent space mapping, using the curvature consistency clustering center of the vector bundle as the reference point, and generating a direction basis set.

[0089] The tensor field generation sub-component is used to convert the vortex intensity scalar of each directional basis of the directional basis set into directional weight coefficients, construct a three-dimensional directional tensor with the directional basis as the axis and the weight as the modulus, and output a pollution migration directional tensor field with spatial distribution properties.

[0090] The mutation point set to weighted tensor quantum component is used to establish a radial decay function centered on the critical point of the pollution intensity gradient mutation point set, calculate the intensity amplitude of the decay function based on the weight label of the point set, and generate a mutation kernel function distribution cloud; the vertices of the non-uniform sampling grid are used as tensor control points, and bicubic spline interpolation of the kernel function value is performed between the control points to output a pollution intensity weighted tensor field covering the entire space.

[0091] The working principle and beneficial effects of the above technical solution are as follows: The direction vector bundle to tensor field sub-component of this embodiment is used to convert the main direction vector bundle of pollution migration into a unit direction basis by taking the curvature consistency clustering center of the vector bundle as the reference point and converting each vector direction angle into a unit direction basis through tangent space mapping, thereby generating a set of direction basis; The tensor field generation sub-component is used to convert the vortex intensity scalar of each direction basis in the set of direction basis into direction weight coefficients, construct a three-dimensional direction tensor with the direction basis as the axis and the weight as the modulus, and output a pollution migration direction tensor field with spatial distribution attributes; The mutation point set to weight tensor quantum component is used to establish a radial decay function with the critical point as the center of the pollution intensity gradient mutation point set, calculate the intensity amplitude of the decay function according to the weight label of the point set, and generate a mutation kernel function distribution cloud; The vertices of the non-uniform sampling grid are used as tensor control points, and bicubic spline interpolation of the kernel function value is performed between the control points to output a pollution intensity weight tensor field covering the entire space. The dual-channel data fusion component of the above scheme achieves tensor-based representation and spatial fusion of pollution diffusion direction and intensity features through modular processing: the direction vector bundle to tensor field sub-component converts discrete pollution migration direction vector bundles into continuous direction tensor fields. Through curvature-consistent clustering and tangent space mapping, it ensures the geometric continuity of direction features while retaining vortex intensity as a weighting coefficient, enabling the tensor field to reflect the dominant trend of pollution diffusion. The mutation point set to weighted tensor quantum component converts discrete pollution intensity gradient mutation point sets into continuous spatial weighted tensor fields. Through radial decay functions and bicubic spline interpolation, it achieves a smooth transition while maintaining mutation features, ensuring the preservation of the topological structure of intensity changes. Tensor operation fusion performs a positive cross-multiplication operation between the direction tensor field and the intensity weighted tensor field, generating a spatiotemporal feature slice that fuses the pollution diffusion direction and intensity mutation features. This ensures that the final output can characterize both the migration path of pollutants and reflect the intensity change trend in key areas.

[0092] In summary, the implementation of the present embodiment realizes the conversion of discrete features to continuous tensor field, and completes the coupling of multi-modal information through tensor operation, providing spatial feature expression with both directionality and intensity variation for pollution diffusion analysis.

[0093] In the embodiment 5, the mutation point set is converted into the weight tensor subassembly, and the pollution intensity gradient mutation point set is input into the radial attenuation function constructor to extract the spatial coordinates and weight mark value of each critical point.

[0094] The function distribution cloud generating module is configured to input the pollution intensity gradient mutation point set into the radial attenuation function constructor, extract the spatial coordinates and weight mark value of each critical point, establish an exponential attenuation function with the critical point as the center, dynamically adjust the function attenuation coefficient by the weight mark value, and generate an attenuation function unit with amplitude modulation.

[0095] The kernel function cloud synthesis module is configured to superimpose each function unit of all attenuation function units according to the spatial coordinates, eliminate the interference effect in the overlapping area through amplitude normalization, and output a continuously distributed mutation kernel function distribution cloud. The non-uniform sampling grid vertex input tensor control point binder is configured to read the spatial coordinates of the grid vertex as the control point reference position, inject the kernel function amplitude at the corresponding position at the control point, and generate a tensor control point set with amplitude constraint.

[0096] The global tensor interpolation module is configured to construct a three-dimensional parameterized surface with the control point as the node, perform continuous interpolation of the kernel function amplitude along the surface normal, ensure the gradient smoothness of the interpolation surface through curvature constraint, and output a globally covered pollution intensity weight tensor field.

[0097] The working principle and beneficial effects of the above technical solution are as follows: The function distribution cloud generation module of this embodiment inputs the pollution intensity gradient mutation point set into the radial decay function constructor, extracts the spatial coordinates and weight label values ​​of each critical point, establishes an exponential decay function with the critical point as the center, and dynamically adjusts the function decay coefficient by the weight label value to generate a decay function unit with amplitude modulation; the kernel function cloud synthesis module superimposes each function unit of all decay function units according to spatial coordinates, eliminates the interference effect of overlapping areas by amplitude normalization, and outputs a continuously distributed mutation kernel function distribution cloud; the non-uniform sampling grid vertices are input into the tensor control point binder, the spatial coordinates of the grid vertices are read as the reference positions of the control points, and the kernel function amplitude of the corresponding position is injected at the control points to generate a tensor control point set with amplitude constraints; the global tensor interpolation module constructs a three-dimensional parametric surface with the control points as nodes, performs continuous interpolation of the kernel function amplitude along the surface normal, ensures the smoothness of the interpolation surface gradient by curvature constraints, and outputs a pollution intensity weight tensor field with global coverage. The above scheme, through mathematical modeling and spatial interpolation techniques, transforms a discrete set of pollution intensity abrupt change points into a continuous global weighted tensor field. Its main functions are: converting discrete abrupt change points into function units with amplitude modulation using a radial decay function constructor, each unit containing spatial coordinates, weighted labels, and a dynamic decay coefficient; and achieving a mapping from discrete observation data to a continuous function space. When synthesizing kernel function clouds using the superposition principle, L... 2 Norm normalization eliminates amplitude interference in overlapping regions, ensuring that the synthesized kernel function field satisfies physical constraints and avoiding non-physical phenomena such as amplitude overflow. In the parametric surface construction stage, bicubic B-spline basis functions are used for interpolation, and gradient smoothing is achieved by minimizing the curvature energy term. The final output tensor field satisfies the characteristics of elliptic partial differential equations, providing a weight distribution field conforming to differential geometry for subsequent physical simulations.

[0098] In summary, this embodiment constructs a complete mathematical transformation chain from discrete observation data, continuous function representation, to differentiable tensor fields, and its output can be directly used as the parameter field of non-uniform media in finite element analysis or computational fluid dynamics.

[0099] Example 7: As Figure 4 As shown, based on Embodiment 1, the dynamic response collaborative hub system provided in this embodiment of the invention includes:

[0100] The migration cloud strategy decoupling subsystem is used to extract the pollution concentration equipotential surface features in the pollution migration cloud strategy, generate the pollution intensity gradient tensor, separate the curvature parameters of the tangent bundles of the migration path, generate the path direction admittance matrix, and output the decoupled strategy feature primitives; match the pollution intensity gradient tensor with the power response curve of the purification equipment, map the path direction admittance matrix to the equipment spatial orientation topology; and generate a dimensionally orthogonalized set of equipment control vectors.

[0101] A linkage control matrix construction subsystem is configured to construct a device operation unit space based on a device control vector, distribute device control weight in the unit space according to a pollution intensity gradient direction, establish a device control weight phase coordination relationship according to a device space orientation topology, encode the weight distribution and the phase coordination into a multi-dimensional control plane, and output a linkage control matrix of a purifying device that can drive multiple terminals;

[0102] A dual-channel feedback trigger subsystem is configured to synchronously activate a feedback arbitrator in the linkage control matrix;

[0103] A mobile terminal channel is configured to: when the pollution intensity weight in the linkage control matrix exceeds a dynamic threshold, extract a space code of an area exceeding the threshold, synthesize the space code and the intensity weight into an over-threshold alarm vector, and push a gaseous parameter over-threshold alarm to a gateway; after the gateway receives the gaseous parameter over-threshold alarm, the gateway plays, according to a preset program, devices such as a lighting system and a clean air system, and the devices display content of the gaseous parameter over-threshold alarm according to the preset program; at the same time, the gateway pushes the content to an APP through an alarm information push platform; and a physical indication channel is configured to analyze a key pollution node in a device orientation topology according to a phase coordination relationship in the linkage control matrix, and trigger a spectral early warning pulse sequence of a device at a corresponding position.

[0104] The device displays the content of the gaseous parameter over-threshold alarm according to the preset program, and specifically includes:

[0105] A device linkage alarm execution component is configured to drive a device space mapping by the gaseous parameter over-threshold alarm vector, input the over-threshold alarm vector output by the mobile terminal channel to an edge node or a gateway, and the edge node analyzes the space code in the vector, coordinates coupling with a device space orientation topology, and generates a three-dimensional pollution focus positioning matrix.

[0106] A device control weight phase reconstruction component is configured to reconstruct a device control parameter in the positioning matrix according to a phase coordination relationship in the linkage control matrix, extract a wavefront propagation vector of an acoustic unit in the device space orientation topology, analyze a radiation angle distribution function of an optical unit, obtain a vortex generation curvature of a gas flow field modulator, and output a cross-medium field effect parameter set.

[0107] A multi-modal alarm field generation component is configured to convert the field effect parameter set into a device instruction by an edge execution node, generate a standing wave interference field pointing to a pollution focus according to the wavefront propagation vector, form an audible alarm path, emit a pulsed spectral scanning beam according to the radiation angle distribution function, form an optical coordinate identifier at the pollution focus, generate a directional cleaning flow layer based on the vortex generation curvature, and advance along a tangent beam of a migration path to construct a spatial synchronous alarm field.

[0108] The information flow and physical field fusion component is used for converting the intensity weight in the threshold alarm vector into the sound pressure gradient of the acoustic field, which is dynamically modulated by the weight value. The optical pulse frequency is positively correlated with the weight value. The cleaning flow layer flow rate is graded according to the weight value, forming a weight-field intensity coupling response.

[0109] The alarm information digital synchronization component is used for the edge execution node to disassemble the threshold alarm vector into a spatial event fingerprint, which contains a pollution focus coordinate and an intensity weight. A field effect parameter abstract contains a standing wave mode, a spectrum code and a flow layer curvature. The spatial event fingerprint is pushed to a cloud strategy hub. After being received by a user terminal APP, the spatial event fingerprint is restored into a dynamic model of a sound wave navigation path in a three-dimensional space, a time-space evolution trajectory of a pollution focus spectrum identification and a cleaning flow layer motion vector thermodynamic diagram.

[0110] A pollution focus positioning matrix converts abstract space coding into a geometric coordinate system operable by equipment. A field effect parameter set converts a phase relationship of equipment control quantities into a physical field generation rule. An intensity weight value penetrates into a sound pressure gradient / pulse frequency / flow layer flow rate parameter, realizing mathematical isomorphic expression of alarm intensity and pollution degree. A spatial event fingerprint completely retains the time-space characteristics of a physical alarm field. A user terminal accurately reconstructs a three-dimensional alarm scene through a field effect parameter abstract.

[0111] The working principle and beneficial effects of the above technical solution are: the migration cloud strategy decoupling subsystem of the embodiment is used to extract the pollution concentration equipotential surface features in the pollution migration cloud strategy, generate a pollution intensity gradient tensor, separate the curvature parameters of the migration path tangent bundle, generate a path direction admittance matrix, and output a decoupled strategy feature primitive group; match the pollution intensity gradient tensor with the purification equipment power response curve, and map the path direction admittance matrix to the equipment space orientation topology; generate a dimensionally orthogonalized equipment control vector set; the linkage control matrix construction subsystem is used to construct an equipment operation unit space with the equipment control vector as the base, and allocate equipment control weight in the unit space according to the pollution intensity gradient direction; according to the equipment space orientation topology, establish a device control amount phase coordination relationship, encode the weight allocation and phase coordination into a multi-dimensional control plane, and output a multi-terminal driven purification device linkage control matrix; the double-channel feedback trigger subsystem is used to synchronize the activation of the feedback arbitrator in the linkage control matrix; the mobile terminal channel: when the pollution intensity weight in the linkage control matrix exceeds the dynamic threshold: extract the space code of the over-standard area, synthesize the space code and the intensity weight into an over-threshold alarm vector, and push the gaseous parameter over-threshold alarm to the gateway; after the gateway receives the gaseous parameter over-threshold alarm, the devices such as the light and the clean wind system are played according to the preset program, and the devices display the content of the gaseous parameter over-threshold alarm according to the preset program; at the same time, the gateway pushes the alarm information to the APP through the alarm information pushing platform; according to the phase coordination relationship of the linkage control matrix, the key pollution nodes in the device orientation topology are analyzed, and the spectral early warning pulse sequence of the corresponding position device is triggered. The dynamic response coordination center system of the above scheme integrates mathematical modeling and control strategies to build a closed-loop regulation and control system for pollution migration and purification equipment linkage. First, the pollution migration characteristics are mathematically analyzed, the concentration equipotential surface features are extracted to generate a gradient tensor, and the curvature parameters of the migration path are separated to construct a direction admittance matrix; then, the pollution characteristics are matched with the device response characteristics, and an orthogonalized control vector set is established. At the control strategy level, the device control vector is used as the base to construct the device operation space, the control weight is allocated according to the pollution gradient direction, and the phase coordination relationship is established according to the device orientation topology, and finally encoded into a multi-dimensional control plane to form a linkage control matrix of multi-terminal driven devices. The feedback mechanism adopts a double-channel design: the mobile terminal channel monitors the pollution intensity weight, generates an alarm vector and pushes the warning information when the threshold is exceeded; the physical indication channel analyzes the key pollution nodes in the device topology, and triggers the spectral early warning signal of the corresponding device.

[0112] In summary, the embodiment realizes full-process automation regulation and control from pollution feature analysis, control strategy generation to device linkage response, ensuring dynamic optimization and precise intervention of the pollution control process.

[0113] Embodiment 8: Based on embodiment 7, the linkage control matrix construction subsystem provided by the embodiment of the application comprises:

[0114] a phase coordination relationship establishing component for establishing a device spatial orientation topology, calculating the shortest connected path length between any two devices, converting the path length into an action delay time base, and generating a space-time delay field between the devices; the space-time delay field generates a diffusion wave front with the pollution source position as a wave source, calculates a phase offset angle of each device control action according to the delay field, and outputs a device control phase difference vector;

[0115] a control quantity tensor synthesis component for mapping the pollution intensity gradient weight into a control quantity amplitude matrix and converting the phase difference vector into a time sequence coordination operator;

[0116] a multi-dimensional plane construction component for constructing a complex control plane with the amplitude matrix as a real part and the time sequence operator as an imaginary part, expanding the complex plane along the device spatial dimension to form a three-dimensional control tensor body, and performing orthogonal projection compression on the tensor body to generate a multi-dimensional control plane.

[0117] The working principle and beneficial effects of the above technical solution are as follows: the phase coordination relationship establishing component is used to establish a device spatial orientation topology, calculate the shortest connected path length between any two devices, convert the path length into an action delay time base, and generate a space-time delay field between the devices; the space-time delay field generates a diffusion wave front with the pollution source position as a wave source, calculates a phase offset angle of each device control action according to the delay field, and outputs a device control phase difference vector; the control quantity tensor synthesis component is used to map the pollution intensity gradient weight into a control quantity amplitude matrix and convert the phase difference vector into a time sequence coordination operator; and the multi-dimensional plane construction component is used to construct a complex control plane with the amplitude matrix as a real part and the time sequence operator as an imaginary part, expand the complex plane along the device spatial dimension to form a three-dimensional control tensor body, and perform orthogonal projection compression on the tensor body to generate a multi-dimensional control plane. The linkage control matrix construction subsystem of the above solution realizes space-time collaborative optimization of pollution control devices through a modular architecture, and its core significance lies in that: the space-time delay field established by the phase coordination component through device topology path calculation converts the spatial distance quantity into an accurate time delay parameter, so that a dynamic mapping relationship is formed between the pollution diffusion wave front and the device response; and the output phase difference vector quantifies the time sequence difference of each device action, providing a time reference for distributed control. The control quantity tensor component realizes nonlinear conversion of pollution intensity and control quantity through gradient weight mapping, and encodes the phase difference vector into a time sequence operator, thereby constructing a joint expression space of control intensity and time sequence; this tensor representation method retains the multi-dimensional coupling characteristics of the control parameters. The multi-dimensional plane component constructs a mixed parameter space of (amplitude + time sequence) through a complex domain, realizes dimension reduction mapping of high-dimensional control parameters to an operable plane through orthogonal projection compression of a three-dimensional tensor body, and significantly reduces the complexity of the decision space while retaining the core control dimension.

[0118] In summary, the embodiment realizes the closed-loop conversion from the physical space topology to the control parameter space, and through the three-level processing of the space-time delay field modeling, tensor synthesis and dimension reduction projection, the pollution diffusion dynamics characteristics are converted into an executable multi-device collaborative control strategy. Both the physical interpretability of the control parameters and the efficient collaborative decision mechanism are provided.

[0119] In the embodiment 8, the multi-dimensional plane construction component comprises:

[0120] The complex control plane construction sub-component is configured to generate a device control complex unit set by taking each element of the control quantity amplitude matrix as a real part of a complex number and taking a corresponding element of the time sequence operator as an imaginary part of the complex number; and the device control complex unit set establishes a complex plane coordinate system with the device space orientation topology as a reference, maps the complex unit to the complex plane according to the device coordinates, and outputs a complex control plane with the device space correlation.

[0121] The three-dimensional control tensor body generation sub-component is configured to extract a device position coordinate in the device space orientation topology from the complex control plane.

[0122] The tensor body construction sub-component is configured to copy the complex plane along the third dimension to form an initial tensor body, adjust the phase offset of each plane according to the space-time delay field between the devices, and smooth the surface of the tensor body by the curvature continuity constraint to generate a three-dimensional control tensor body carrying the space phase relationship.

[0123] The working principle and beneficial effects of the technical solution are as follows: the complex control plane construction subassembly of the embodiment takes each element of the control amplitude matrix as the real part of a complex number and takes the corresponding element of the time sequence operator as the imaginary part of the complex number to generate a device control complex unit set; the device control complex unit set establishes a complex plane coordinate system with reference to the device spatial orientation topology, maps the complex unit to the complex plane according to the device coordinates, and outputs a complex control plane with device spatial correlation; the three-dimensional control tensor body generation subassembly extracts the device position coordinates in the device spatial orientation topology from the complex control plane, and takes the position coordinates as the third dimension reference axis; the tensor body construction subassembly replicates the complex plane along the third dimension to form an initial tensor body, adjusts the phase offset of each plane according to the space-time delay field between devices, smoothes the surface of the tensor body by curvature continuity constraint, and generates a three-dimensional control tensor body carrying the space phase relationship. The core function of the multi-dimensional plane construction assembly is to expand the two-dimensional control parameter into a three-dimensional decision body with spatial phase characteristics, which can be divided into the following technical meanings: the complex control plane construction subassembly combines the amplitude matrix (real part) and the time sequence operator (imaginary part) into a complex unit set to establish a joint expression of control strength and action time sequence in the complex plane coordinate system; this representation method retains the spatial topology correlation between devices, so that each control instruction carries amplitude and time sequence information at the same time. The three-dimensional control tensor body generation subassembly introduces the device position coordinates as the third dimension to expand the complex plane along the spatial orientation into an initial tensor body; the dimension mapping of the control parameter from the two-dimensional plane to the three-dimensional space is realized, and a structured carrier is provided for subsequent phase adjustment. The tensor body construction subassembly dynamically adjusts the phase offset of each complex plane through the space-time delay field and applies curvature continuity constraint to make the surface of the tensor body smoothly transition; the three-dimensional control tensor body finally generated completely carries the spatial distribution and phase coordination relationship between devices, forming a control strategy space with space-time consistency.

[0124] In summary, the embodiment integrates discrete device control parameters into a continuous and differentiable high-dimensional decision body through three steps of complex plane construction, three-dimensional tensor generation and phase optimization, and provides a mathematical model basis for multi-device collaborative control with spatial correlation and time sequence coordination.

[0125] Embodiment 10: On the basis of Embodiment 9, the tensor body construction subassembly provided by the embodiment of the application comprises:

[0126] An initial tensor body construction module is configured to read a sequence of device position coordinates in the device spatial orientation topology, replicate the complex plane along the third dimension with reference to the coordinate sequence, and generate a discrete layered initial tensor body.

[0127] a phase offset calibration module configured to calibrate the initial tensor body and the time-space delay field between the devices, extract the delay time bases of each device in the delay field, convert the time bases into complex plane rotation angles, perform a unitary transformation of each device layer complex plane with the corresponding rotation angle, and output a phase-synchronized transition tensor body;

[0128] a curvature continuity processing module configured to obtain the curvature tensor of the tensor body surface in the device dimension, align the eigenvalues of the pollution intensity gradient tensor and the surface curvature, optimize the surface continuity by the minimum curvature variation method, and generate a three-dimensional control tensor body that smoothly carries the spatial phase relationship.

[0129] The working principle and beneficial effects of the above technical solution are as follows: the initial tensor body construction module of the embodiment is configured to read the device position coordinate sequence in the device spatial orientation topology, copy the complex plane along the third dimension with the coordinate sequence as the index, and generate a discrete stacked initial tensor body; the phase offset calibration module is configured to calibrate the initial tensor body and the time-space delay field between the devices, extract the delay time bases of each device in the delay field, convert the time bases into complex plane rotation angles, perform a unitary transformation of each device layer complex plane with the corresponding rotation angle, and output a phase-synchronized transition tensor body; the curvature continuity processing module is configured to obtain the curvature tensor of the tensor body surface in the device dimension, align the eigenvalues of the pollution intensity gradient tensor and the surface curvature, optimize the surface continuity by the minimum curvature variation method, and generate a three-dimensional control tensor body that smoothly carries the spatial phase relationship. The tensor body construction subassembly of the above solution realizes the spatial continuity and phase synchronization optimization of the control parameters through stage-by-stage processing, and its technical significance lies in that: the initial tensor body construction module copies the two-dimensional complex plane into a three-dimensional stacked structure through indexing of the device coordinate sequence; this process preserves the integrity of the original control parameters and at the same time establishes an operable framework for the parameters along the spatial dimension, providing a basic topology for subsequent phase calibration. The phase offset calibration module converts the time bases of the time-space delay field into complex plane rotation angles and adjusts the phase synchronization of each device layer through unitary transformation; this operation forms a coherent phase gradient in the complex domain for the discrete distributed device control plane, and the output transition tensor body initially has time-space consistency. The curvature continuity processing module aligns the characteristics of the pollution gradient and the surface curvature to constrain the smoothness of the tensor body by the minimum variation principle; the finally generated three-dimensional control tensor body mathematically satisfies the differential geometric continuity and physically maintains the coupling relationship between the pollution diffusion dynamics and the control phase, forming a differentiable and physically interpretable high-dimensional control strategy space.

[0130] In summary, the embodiment realizes the transformation from a discrete stacked structure to a continuous smooth manifold, and through the triple processing of coordinate indexing and copying, unitary phase calibration, and variation optimization, the control tensor body simultaneously satisfies the three core requirements of topological correctness of spatial distribution, time-domain consistency of phase coordination, and differential continuity of surface evolution.

[0131] Embodiment 11: as shown in the embodiment 1-embodiment 10, the remote control method of the air quality sensor based on the Internet of Things provided by the embodiment of the application comprises the following steps: Figure 5

[0132] S100: the purification device linkage control matrix is processed by a heterogeneous instruction fusion technology to obtain a spatial optimization control vector set, and the spatial optimization control vector set forms a man-machine interaction entropy value mechanism;

[0133] S200: the man-machine interaction entropy value model is processed by an entropy weight dynamic distribution strategy to obtain a spatial state perception vector, and the spatial state perception vector forms a cross-medium alarm triggering channel;

[0134] S300: the cross-medium alarm triggering channel is processed by a bidirectional response coupling engine to obtain a device state feature topology, and the device state feature topology forms a closed-loop control entropy correction instruction.

[0135] The working principle and beneficial effects of the above technical solution are as follows: firstly, the purification device linkage control matrix is processed by a heterogeneous instruction fusion technology to obtain a spatial optimization control vector set, and the spatial optimization control vector set forms a man-machine interaction entropy value mechanism; secondly, the man-machine interaction entropy value model is processed by an entropy weight dynamic distribution strategy to obtain a spatial state perception vector, and the spatial state perception vector forms a cross-medium alarm triggering channel; finally, the cross-medium alarm triggering channel is processed by a bidirectional response coupling engine to obtain a device state feature topology, and the device state feature topology forms a closed-loop control entropy correction instruction. The above scheme realizes intelligent closed-loop management of air quality monitoring and purification control; the heterogeneous instruction fusion technology is used to optimize and integrate the purification device control matrix to generate a spatial optimization control vector set, so that the multi-device collaborative control has spatial adaptability, and a man-machine interaction entropy value mechanism is established to realize the explainability of the control process; the entropy weight dynamic distribution strategy is used to process man-machine interaction data to generate a perception vector accurately reflecting the spatial state change, and multi-dimensional information is synchronously transmitted through the cross-medium alarm triggering channel to ensure reliable transmission of the alarm information; the bidirectional response coupling engine is used to construct a device state feature topology network to form a closed-loop control system with feedback regulation capability, and the control strategy is dynamically optimized through the entropy correction instruction;

[0136] In summary, the embodiment realizes full-link intelligent processing from environmental perception to device control, improves the system response speed while ensuring control accuracy, enables the air quality management system to have self-learning and self-adaptive capabilities, and forms a complete monitoring-analysis-control-optimization closed loop.

[0137] ​It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. An air quality sensor based on the Internet of Things, characterized in that, Include: The multi-source heterogeneous sensing fusion system is used to form a three-dimensional sensing layer through spatial grid deployment of a monitoring network composed of multiple sets of heterogeneous sensor nodes. Each heterogeneous sensor node collects the gaseous molecule concentration fluctuations in the physical space in real time, and obtains composite pollution characteristic factors through multi-source heterogeneous fusion processing. The composite pollution characteristic factors form a microenvironment quality evolution map. The spatiotemporal edge gateway system is used to deploy computing node clusters on the edge side of the air quality monitoring area. It adopts a hierarchical aggregation architecture to process the sensing data. Each edge node performs edge topology compression processing on the micro-environment map within its coverage area to obtain spatiotemporal feature slices. The spatiotemporal feature slices form a confined space pollution migration cloud strategy. The dynamic response coordination hub system is used to process the cloud strategy for migrating pollution in a confined space through a cross-domain strategy decoupling engine to obtain a set of device control vectors, which in turn form a linkage control matrix for the purification device.

2. The air quality sensor based on the Internet of Things as described in claim 1, characterized in that, The spatiotemporal domain edge gateway system includes: The spatiotemporal dimension decomposition subsystem is used to extract the pollution propagation potential energy field and real-time pollution intensity scalar field from the microenvironment quality evolution map through four-dimensional tensor slicing, and generate a dual-channel spatiotemporal data stream. The edge topology compression processing subsystem is used for processing dual-channel spatiotemporal data streams through an entropy-constrained collapse engine; it performs adaptive eddy detection on the pollution propagation potential energy field to capture the pollution migration direction vector; it performs spatial pyramid downsampling on the real-time pollution intensity scalar field to retain intensity gradient abrupt change points; and it generates high-information-density spatiotemporal feature slices by fusing the pollution migration direction vector and the intensity gradient abrupt change points through tensor cross product. The pollution migration cloud strategy construction subsystem is used to calculate the probability distribution of pollution sources through nonlinear diffusion inversion using spatiotemporal feature slices as input units; generate equipotential surfaces of pollution concentration and tangent bundles of migration paths based on the probability distribution of pollution sources; and encode the equipotential surfaces and tangent bundles of migration paths into a dynamic strategy topology network to form a closed-space pollution migration cloud strategy that can describe the law of pollution diffusion.

3. The air quality sensor based on the Internet of Things as described in claim 2, characterized in that, The edge topology compression processing subsystem includes: The pollution propagation potential energy field processing component is used to scan the potential energy gradient distribution of the pollution propagation potential energy field through a variable-scale differential operator, extract the curl extrema of the potential energy change, and generate a pollution migration direction vector set containing scalars of direction angle and vortex intensity. The pollution migration direction vector set is processed by a vector field sparsification engine to remove noise vectors with vortex intensity below the dynamic threshold, and to perform curvature consistency clustering on adjacent vectors. The output is a topology-simplified pollution migration main direction vector bundle. The pollution intensity scalar field processing component is used to construct a second-order differential curvature map of the intensity field using a real-time pollution intensity scalar field, identify zero-crossing points in the curvature map as gradient abrupt change critical points, and establish a non-uniform sampling grid centered on the critical points. Through adaptive pyramid downsampling constrained by the critical points, intensity mean aggregation is performed in non-abrupt regions, and the original intensity values ​​are preserved with the gradient abrupt change critical points as the core, generating a set of pollution intensity gradient abrupt change points with weight labels. The dual-channel data fusion component is used to convert the main direction vector bundle of pollution migration into a direction tensor field, map the set of abrupt change points of pollution intensity gradient into an intensity weight tensor, perform positive cross-multiplication of the two tensors, and output spatiotemporal feature slices that fuse the pollution migration direction and intensity abrupt change features.

4. The air quality sensor based on the Internet of Things as described in claim 3, characterized in that, The dual-channel data fusion component includes: The Directional Vector Beam to Tensor Field Sub-component is used to convert the main directional vector beam of pollution migration into a unit directional basis by using the curvature consistency clustering center of the vector beam as the reference point and through tangent space mapping, thereby generating a set of directional basis beams. The tensor field generation sub-component is used to convert the vortex intensity scalar of each directional basis of the directional basis set into directional weight coefficients, construct a three-dimensional directional tensor with the directional basis as the axis and the weight as the modulus, and output a pollution migration directional tensor field with spatial distribution properties. The mutation point set to weighted tensor quantum component is used to establish a radial decay function centered on the critical point of the pollution intensity gradient mutation point set, calculate the intensity amplitude of the decay function based on the weight label of the point set, and generate a mutation kernel function distribution cloud; the vertices of the non-uniform sampling grid are used as tensor control points, and bicubic spline interpolation of the kernel function value is performed between the control points to output a pollution intensity weighted tensor field covering the entire space.

5. The air quality sensor based on the Internet of Things as described in claim 4, characterized in that, The mutation point set to weighted tensor quantum component includes: The function distribution cloud generation module is used to input the set of pollution intensity gradient abrupt change points into the radial decay function constructor, extract the spatial coordinates and weight label values ​​of each critical point, establish an exponential decay function with the critical point as the center, and dynamically adjust the function decay coefficient by the weight label value to generate a decay function unit with amplitude modulation. The kernel function cloud synthesis module is used to superimpose the function units of all decay function units according to spatial coordinates, eliminate the interference effect in the overlapping area by amplitude normalization, and output a continuously distributed abrupt kernel function distribution cloud; the non-uniform sampling grid vertex input tensor control point binder reads the spatial coordinates of the grid vertex as the reference position of the control point, injects the kernel function amplitude at the corresponding position at the control point, and generates a tensor control point set with amplitude constraints; The global tensor interpolation module is used to construct a three-dimensional parametric surface with control points as nodes, perform continuous interpolation of kernel function amplitude along the surface normal, ensure smooth gradient of the interpolated surface through curvature constraints, and output a pollution intensity weight tensor field covering the entire domain.

6. The air quality sensor based on the Internet of Things as described in claim 1, characterized in that, Dynamic response coordination central system, including: The migration cloud strategy decoupling subsystem is used to extract the pollution concentration equipotential surface features in the pollution migration cloud strategy, generate the pollution intensity gradient tensor, separate the curvature parameters of the tangent bundle of the migration path, generate the path direction admittance matrix, and output the decoupled strategy feature primitive set. The pollution intensity gradient tensor is matched with the power response curve of the purification equipment, and the path direction admittance matrix is ​​mapped to the spatial orientation topology of the equipment; a set of equipment control vectors with orthogonal dimensions is generated. The linkage control matrix construction subsystem is used to construct the equipment operation unitary space based on the equipment control vector, and to allocate the weight of the equipment control quantity in the unitary space according to the direction of the pollution intensity gradient. Based on the spatial orientation topology of the equipment, the phase coordination relationship of the equipment control quantities is established, and the weight allocation and phase coordination are encoded into a multi-dimensional control plane, outputting a purification device linkage control matrix that can drive multiple terminals. A dual-channel feedback triggering subsystem is used to synchronously activate the feedback arbitrator in conjunction with the control matrix.

7. The air quality sensor based on the Internet of Things as described in claim 6, characterized in that, The dual-channel feedback triggering subsystem includes: a mobile terminal channel; when the pollution intensity weight in the linkage control matrix exceeds the dynamic threshold: extracting the spatial code of the exceeding area, synthesizing the spatial code and intensity weight into an over-threshold alarm vector, and pushing a gaseous parameter over-threshold alarm to the gateway; after receiving the gaseous parameter over-threshold alarm, the gateway will link the playback, lighting, and ventilation system devices according to a preset program, and the devices will display the content of the gaseous parameter over-threshold alarm according to a preset program; at the same time, the gateway will push the alarm to the APP through the alarm information push platform. The physical indicator channel analyzes key pollution nodes in the equipment orientation topology based on the phase coordination relationship of the linkage control matrix, and triggers the spectral warning pulse sequence of the corresponding equipment.

8. The air quality sensor based on the Internet of Things as described in claim 6, characterized in that, The linkage control matrix construction subsystem includes: The phase coordination relationship establishment component is used to determine the spatial orientation topology of the equipment, calculate the shortest connection path length between any two equipment, convert the path length into the action delay time base, and generate a spatiotemporal delay field between the equipment. The spatiotemporal delay field generates a diffused wavefront with the pollution source location as the wave source. Based on the delay field, the phase offset angle of the control action of each equipment is calculated, and the equipment control phase difference vector is output. The control tensor synthesis component is used to map the pollution intensity gradient weights to the control magnitude matrix and convert the phase difference vector into a time-series coordination operator. The multidimensional plane construction component is used to construct a complex control plane with the magnitude matrix as the real part and the timing operator as the imaginary part. The complex plane is extended along the device space dimension to form a three-dimensional control tensor. Orthogonal projection compression is performed on the tensor to generate a multidimensional control plane.

9. The air quality sensor based on the Internet of Things as described in claim 1, characterized in that, Fluctuations in gaseous molecule concentration include air quality parameters such as PM2.5, CO2, TVOC, temperature, and humidity.

10. A remote control method for an air quality sensor based on the Internet of Things, characterized in that, Includes the following steps: The purification device linkage control matrix is ​​processed by heterogeneous instruction fusion technology to obtain a spatially optimized control vector set, which forms a human-machine interaction entropy value mechanism. The entropy value model of human-computer interaction is processed by the entropy weight dynamic allocation strategy to obtain the spatial state perception vector, and the spatial state perception vector forms a cross-media alarm triggering channel. The cross-media alarm triggering channel is processed by the bidirectional response coupling engine to obtain the device status feature topology, which forms a closed-loop control entropy correction command.

Citation Information

Patent Citations

  • Cloud environment monitoring method and device

    CN117129036A

  • Air quality intelligent monitoring system and method based on Internet of Things technology

    CN118329119A

  • Air quality monitoring method based on olfaction chip

    CN120294257A

  • Industrial odor online monitoring system based on big data

    CN120416793A

  • Underground heat supply system based on air energy heat pump serving as heat source and remote monitoring method

    CN120593295A

Cited By

  • Cloud computing-based geological disaster risk assessment system

    CN121860437A