CN116089823B - Intelligent community visual real-time supervision method based on big data - Google Patents
Intelligent community visual real-time supervision method based on big data Download PDFInfo
- Publication number
- CN116089823B CN116089823B CN202310317229.7A CN202310317229A CN116089823B CN 116089823 B CN116089823 B CN 116089823B CN 202310317229 A CN202310317229 A CN 202310317229A CN 116089823 B CN116089823 B CN 116089823B
- Authority
- CN
- China
- Prior art keywords
- supervision
- intelligent
- grids
- monitoring
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/163—Property management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a visual real-time supervision method of an intelligent community based on big data, which comprises the following steps: constructing intelligent supervision grids of communities, and constructing each intelligent supervision grid into an intelligent supervision network; performing network analysis on the intelligent supervision network to obtain a plurality of groups of supervision communities, performing association analysis on a plurality of intelligent supervision grids in the plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, and converting each supervision community into a fully-connected association network by using the state association; and determining the visual monitoring grids in each group of monitoring communities, and combining the scene states of the visual monitoring grids in the same monitoring community with the state correlation among the intelligent monitoring grids to obtain the scene states of each intelligent monitoring grid in the monitoring communities. The invention realizes the scene dimension reduction of the global visual supervision, thereby reducing the visual data flow which needs to be processed in real time, ensuring the timeliness of community supervision and improving the community supervision effect.
Description
Technical Field
The invention relates to the technical field of community management, in particular to a visual real-time supervision method for an intelligent community based on big data.
Background
Communities are a large group of life-related people formed by gathering a plurality of social groups or social organizations in a certain field, and most of communities are sites of urban living population. In recent years, along with the acceleration of urban development and the increasing demands of people for high-quality life, the current communities are faced with a plurality of problems, so that the construction maintenance and management means of the previous communities are single and extensive, community management staff cannot grasp information of a plurality of population, and cannot grasp abnormal conditions occurring in the communities for the first time, so that the safety management of the communities is particularly difficult, and in order to meet the realization of a mechanism that the community management staff directly monitors and controls global data of the communities to guide actions, the establishment of a mechanism with effective management in the communities is particularly important.
The existing community supervision adopts global visual supervision, so that the visual data flow is quite huge due to instantaneous processing, the data processing load of the whole supervision system is heavy, the time delay is large, thereby causing hysteresis of community mastering abnormal states, and finally reducing the community supervision effect.
Disclosure of Invention
The invention aims to provide a large data-based intelligent community visual real-time supervision method, which aims to solve the technical problems that in the prior art, global visual supervision is adopted, so that the visual data flow is quite huge due to instantaneous processing, the data processing burden of the whole supervision system is heavy, the time delay is large, the hysteresis of communities on abnormal state mastering is caused, and finally the community supervision effect is reduced.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a visual real-time supervision method of an intelligent community based on big data comprises the following steps:
s1, constructing intelligent supervision grids of communities, and constructing each intelligent supervision grid into an intelligent supervision network;
s2, performing network analysis on the intelligent supervision network to obtain a plurality of groups of supervision communities, performing association analysis on a plurality of intelligent supervision grids in the plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, and converting each supervision community into a fully-connected association network by using the state association;
step S3, determining the visual monitoring grids in each group of supervision communities, and performing state evaluation on visual monitoring data of the visual monitoring grids to obtain scene states of the visual monitoring grids;
and S4, combining the scene states of the visual monitoring grids in the same monitoring community with the state correlation among the intelligent monitoring grids to obtain the scene states of all the intelligent monitoring grids in the monitoring community, so that the correlation among the intelligent monitoring grids is utilized to reduce the large data processing amount of the visual real-time data flow.
As a preferred embodiment of the present invention, the building of the intelligent supervision grid of the community includes:
rectangular meshing is carried out on the plan of the community to obtain a plurality of intelligent supervision meshes;
the grid area of the intelligent supervision grid is smaller than or equal to the monitoring field area of the visual monitoring equipment.
As a preferred embodiment of the present invention, the building each intelligent supervision grid as an intelligent supervision network includes:
taking each intelligent supervision grid as each network node;
obtaining geographic coordinates of central positions of all intelligent supervision grids and historical visual data of all intelligent supervision grids, and calculating the product of Euclidean distance of the geographic coordinates and Euclidean distance of the historical visual data between two intelligent supervision grids in an adjacent relation as the association weight between the two intelligent supervision grids in the adjacent relation;
mapping adjacent relations of the intelligent supervision grids into connecting edges of corresponding network nodes in sequence;
and taking the associated weight as the edge weight of the corresponding connecting edge, and connecting each network node into an intelligent supervision network by utilizing the connecting edge with the edge weight.
The calculation formula of the association weight is as follows:
in which W is i,i+1 Is the firstiPersonal intelligent supervision grid and the firsti+1 intelligent supervisionCorrelation weight between grids, p i Is the firstiGeographical coordinates, p, of the central position of the intelligent supervision grid i+1 Is the firsti+1 geographic coordinates of the intelligent supervision grid center position, d i Is the firstiHistorical visual data of intelligent supervision grid d i+1 Is the firstiHistorical visual data, |p, of +1 intelligent supervision grid i -p i+1 I is p i And p i+1 Euclidean distance, |d i -d i+1 I is d i And d i+1 Is used for the distance of euclidean distance,ito count variable, the firstiPersonal intelligent supervision grid and the firsti+1 intelligent supervision grids are in adjacent relationship.
As a preferred scheme of the invention, the network analysis of the intelligent supervision network is performed to obtain a plurality of groups of supervision communities, which comprises the following steps:
performing community analysis on the intelligent supervision network by utilizing a genetic algorithm to divide the intelligent supervision communities into a plurality of groups of supervision communities;
the intelligent monitoring grids in the same group of monitoring communities have similar scene states, and the intelligent monitoring grids in different groups of monitoring communities have dissimilar scene states.
As a preferred scheme of the invention, the method for carrying out association analysis on a plurality of intelligent supervision grids in a plurality of groups of supervision communities to obtain the state association of the intelligent supervision grids comprises the following steps:
performing association analysis on any two intelligent supervision grids in each group of supervision communities to obtain state association of any two intelligent supervision grids;
the quantitative analysis formula of the state relevance is as follows:
wherein I is j,k Is the first to supervise the communityjPersonal intelligent supervision grid and the firstkIntelligent monitoring of the state correlation between grids, p j Is the first to supervise the communityjPersonal wisdomSupervising the geographical coordinates of the grid centre position, p k Is the first to supervise the communitykGeographical coordinates of the central position of the intelligent supervision grid d j Is the first to supervise the communityjHistorical visual data of intelligent supervision grid d k Is the first to supervise the communitykHistorical visual data, |p, of individual intelligent supervision grids j -p k I is p j And p k Euclidean distance, |d j -d k I is d j And d k And j, k is a count variable.
As a preferred solution of the present invention, the transforming each regulatory community into a fully connected association network by using the state association includes:
taking the state relevance of any two intelligent monitoring grids in each group of monitoring communities as the edge weight of the connecting edge of any two intelligent monitoring grids in each group of monitoring communities;
and connecting any two intelligent supervision grids in each group of supervision communities by using the edge weights with the connecting edges so as to obtain the fully-connected associated network.
As a preferred aspect of the present invention, the determining the visual monitoring grid in each group of supervision communities includes:
performing node centrality measurement on each intelligent supervision grid in the supervision community to obtain node centrality corresponding to each intelligent supervision grid;
and taking the intelligent supervision grid with the highest node centrality as the visual monitoring grid.
As a preferred solution of the present invention, the performing a state evaluation on the visual monitoring data of the visual monitoring grid to obtain a scene state of the visual monitoring grid includes:
inputting the visual monitoring data of the visual monitoring grid to a pre-established state evaluator, and outputting each state score of the scene state of the visual monitoring grid by the state evaluator;
the model expression of the state estimator is:
in the formula, P_label1 is the state score of the state 1 in the scene state, P_labeln is the state score of the state n in the scene state, d_now is the visual monitoring data, and BP is the BP neural network.
As a preferred scheme of the invention, the method for obtaining the scene state of each intelligent monitoring grid in the monitoring community by combining the scene state of the visual monitoring grid in the same monitoring community with the state correlation among the intelligent monitoring grids comprises the following steps:
mapping all state scores of the scene states of the visual monitoring grids in the same monitoring community into the fully-connected associated network, and calculating all state scores of the scene states of all intelligent monitoring grids except the visual monitoring grids in the same monitoring community according to the edge weights of the connecting edges in the fully-connected associated network;
the scoring quantization formulas of all the states of the scene states of all intelligent supervision grids except the visual supervision grid in the same supervision community are as follows:
wherein I is j,k Is the first to supervise the communityjPersonal intelligent supervision grid and the firstkEdge weights of connecting edges among intelligent supervision grids, [ P_lab1, …, P_laben ]] j Is the first to supervise the communityjEach state score of scene states of each intelligent supervision grid, [ P_labl1, …, P_labln] k Is the first to supervise the communitykEach state score of scene states of each intelligent supervision grid, | [ P_labl1, …, P_labln] j -[P_label1,…,P_labeln] k The I is [ P_labl1, …, P_labln] j And [ P_label1, …, P_labeln] k Is a euclidean distance of (c).
As a preferable mode of the present invention, the history visual data is a time sequence composed of visual data at each time sequence in the same history time sequence section.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, network analysis is carried out on the intelligent supervision network to obtain a plurality of groups of supervision communities, association analysis is carried out on a plurality of intelligent supervision grids in the plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, each supervision community is converted into a fully connected association network by using the state association, the visual supervision grids are determined in each group of supervision communities, scene states of the visual supervision grids in the same supervision community are combined with the state association among the intelligent supervision grids to obtain scene states of each intelligent supervision grid in the supervision communities, and the dimension reduction of the scene of global visual supervision is realized, so that visual data flow needing real-time processing is reduced, the community supervision timeliness is ensured, and the community supervision effect is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
Fig. 1 is a flowchart of a visual real-time supervision method for an intelligent community according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention provides a visual real-time supervision method of an intelligent community based on big data, which comprises the following steps:
s1, constructing intelligent supervision grids of communities, and constructing each intelligent supervision grid into an intelligent supervision network;
building an intelligent supervision grid of a community, comprising:
rectangular meshing is carried out on the plan of the community to obtain a plurality of intelligent supervision meshes;
the grid area of the intelligent supervision grid is smaller than or equal to the monitoring field area of the visual monitoring equipment.
Constructing each intelligent supervision grid into an intelligent supervision network, comprising:
taking each intelligent supervision grid as each network node;
obtaining geographic coordinates of central positions of all intelligent supervision grids and historical visual data of all intelligent supervision grids, and calculating the product of Euclidean distance of geographic coordinates between two intelligent supervision grids of adjacent relations and Euclidean distance of the historical visual data to be used as the association weight between the two intelligent supervision grids of the adjacent relations;
mapping adjacent relations of the intelligent supervision grids into connecting edges of corresponding network nodes in sequence;
and taking the associated weight as the edge weight of the corresponding connecting edge, and connecting each network node into an intelligent supervision network by utilizing the connecting edge with the edge weight.
The calculation formula of the association weight is as follows:
in which W is i,i+1 Is the firstiPersonal intelligent supervision grid and the firsti+1 intelligent monitoring network cell correlation weight, p i Is the firstiGeographical coordinates, p, of the central position of the intelligent supervision grid i+1 Is the firsti+1 geographic coordinates of the intelligent supervision grid center position, d i Is the firstiHistorical visual data of intelligent supervision grid d i+1 Is the firstiHistorical visual data, |p, of +1 intelligent supervision grid i -p i+1 I is p i And p i+1 Euclidean distance, |d i -d i+1 I is d i And d i+1 Is used for the distance of euclidean distance,ito count variable, the firstiPersonal intelligent supervision grid and the firsti+1 intelligent supervision grids are in adjacent relationship.
Each intelligent supervision grid of the community is built into an intelligent supervision network, then grid community analysis is carried out by utilizing knowledge in the field of complex networks, community universe is divided into local areas for analysis, intelligent supervision grids of similar scene states are divided into the same supervision community by utilizing grid community analysis for correlation management and analysis, representative grids are selected from a plurality of intelligent supervision grids for visual monitoring, the visual monitoring of the universe is the visual monitoring of the local areas, the dimension reduction of the visual monitoring areas is realized, and the dimension reduction of visual real-time data streams is further realized.
Meanwhile, the Euclidean distance of the geographic coordinates and the Euclidean distance of the historical visual data are utilized to form the association weight in the construction process to serve as the edge weight in the intelligent supervision network, wherein the Euclidean distance of the geographic coordinates characterizes the geographic position association degree between any two connected intelligent supervision grids, the closer the geographic position association degree is, the more similar the geographic position between any two connected intelligent supervision grids is indicated, the greater the possibility of scene state similarity is, or the greater the possibility of scene state interaction degree is, for example, the scene state is accumulated on the ground in a large amount, snow or garbage is accumulated, the similarity degree of the scene state is high due to the fact that the mutual influence possibility exists between the two intelligent supervision grids which are closer to each other in geographic position, the similarity of the scene state is indirectly measured by the Euclidean distance of the geographic positions, the similarity of the scene state between the two intelligent supervision grids is directly measured according to the similarity between the historical data, and therefore, the product of the Euclidean distance of the geographic Euclidean distance and the visual data is well-measured by the product of the Euclidean distance of the geographic coordinates and the intelligent supervision grids, and the intelligent supervision grids can be well analyzed in the aspect that the intelligent supervision grids are located between the two intelligent supervision grids, and the intelligent supervision grids are well-related, and the situation is well under the situation is constructed.
S2, performing network analysis on the intelligent supervision network to obtain a plurality of groups of supervision communities, performing association analysis on a plurality of intelligent supervision grids in the plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, and converting each supervision community into a fully-connected association network by using the state association;
network analysis is carried out on the intelligent supervision network to obtain a plurality of groups of supervision communities, which comprises the following steps:
performing community analysis on the intelligent supervision network by utilizing a genetic algorithm to divide the intelligent supervision communities into a plurality of groups of supervision communities;
the intelligent monitoring grids in the same group of monitoring communities have similar scene states, and the intelligent monitoring grids in different groups of monitoring communities have dissimilar scene states.
Performing association analysis on a plurality of intelligent supervision grids in a plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, including:
performing association analysis on any two intelligent supervision grids in each group of supervision communities to obtain state association of any two intelligent supervision grids;
the quantitative analysis formula of the state association is as follows:
wherein I is j,k Is the first to supervise the communityjPersonal intelligent supervision grid and the firstkIntelligent monitoring of the state correlation between grids, p j Is the first to supervise the communityjGeographical coordinates, p, of the central position of the intelligent supervision grid k Is the first to supervise the communitykGeographical coordinates of the central position of the intelligent supervision grid d j Is the first to supervise the communityjHistorical visual data of intelligent supervision grid d k Is the first to supervise the communitykPersonal intelligent supervisionHistorical visualization data, |p, of grid j -p k I is p j And p k Euclidean distance, |d j -d k I is d j And d k And j, k is a count variable.
Converting each supervision community into a fully connected association network by using the state association, wherein the method comprises the following steps:
taking the state relevance of any two intelligent monitoring grids in each group of monitoring communities as the edge weight of the connecting edge of any two intelligent monitoring grids in each group of monitoring communities;
and connecting any two intelligent supervision grids in each group of supervision communities by using the edge weights with the connecting edges so as to obtain the full-connection association network.
The full-connection association network reflects the state association of scene states between any two intelligent monitoring grids in each group of monitoring communities, so that the scene states of the rest intelligent monitoring grids can be calculated through side weight mapping as long as the scene states of any one intelligent monitoring grid in each group of monitoring communities are known, the monitoring communities are subjected to representative monitoring by only selecting one visual monitoring grid, the dimension reduction of the monitoring grids is realized, the visual monitoring of the community universe is reduced to a plurality of visual monitoring grids, the comprehensive state identification is ensured, and the real-time performance of visual monitoring is improved.
Step S3, determining the visual monitoring grids in each group of supervision communities, and performing state evaluation on visual monitoring data of the visual monitoring grids to obtain scene states of the visual monitoring grids;
determining a visual monitoring grid in each group of supervision communities, comprising:
performing node centrality measurement on each intelligent supervision grid in the supervision community to obtain node centrality corresponding to each intelligent supervision grid;
and taking the intelligent supervision grid with the highest node centrality as a visual monitoring grid.
Performing state evaluation on the visual monitoring data of the visual monitoring grid to obtain the scene state of the visual monitoring grid, wherein the method comprises the following steps:
inputting visual monitoring data of the visual monitoring grid to a pre-established state evaluator, and outputting each state score of the scene state of the visual monitoring grid by the state evaluator;
the model expression of the state estimator is:
in the formula, P_label1 is the state score of the state 1 in the scene state, P_labeln is the state score of the state n in the scene state, d_now is the visual monitoring data, and BP is the BP neural network.
The state estimator is obtained through training big data, so that modeling calculation of scene states is realized, the labor amount of manual calculation is reduced, and the automation efficiency is also improved.
And S4, combining the scene states of the visual monitoring grids in the same monitoring community with the state correlation among the intelligent monitoring grids to obtain the scene states of all the intelligent monitoring grids in the monitoring community, so that the correlation among the intelligent monitoring grids is utilized to reduce the large data processing amount of the visual real-time data flow.
Combining the scene states of the visual monitoring grids in the same monitoring community with the state correlation among the intelligent monitoring grids to obtain the scene states of all intelligent monitoring grids in the monitoring community, wherein the method comprises the following steps:
mapping all state scores of the scene states of the visual monitoring grids in the same monitoring community into a fully-connected associated network, and calculating all state scores of the scene states of all intelligent monitoring grids except the visual monitoring grids in the same monitoring community according to the edge weights of the connecting edges in the fully-connected associated network;
the scoring and quantization formulas of all the states of the scene states of all intelligent supervision grids except the visual supervision grid in the same supervision community are as follows:
wherein I is j,k Is the first to supervise the communityjPersonal intelligent supervision grid and the firstkEdge weights of connecting edges among intelligent supervision grids, [ P_lab1, …, P_laben ]] j Is the first to supervise the communityjEach state score of scene states of each intelligent supervision grid, [ P_labl1, …, P_labln] k Is the first to supervise the communitykEach state score of scene states of each intelligent supervision grid, | [ P_labl1, …, P_labln] j -[P_label1,…,P_labeln] k The I is [ P_labl1, …, P_labln] j And [ P_label1, …, P_labeln] k Is a euclidean distance of (c).
The history visual data is a time sequence composed of visual data at each time sequence in the same history time sequence section.
According to the invention, network analysis is carried out on the intelligent supervision network to obtain a plurality of groups of supervision communities, association analysis is carried out on a plurality of intelligent supervision grids in the plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, each supervision community is converted into a fully connected association network by using the state association, the visual supervision grids are determined in each group of supervision communities, scene states of the visual supervision grids in the same supervision community are combined with the state association among the intelligent supervision grids to obtain scene states of each intelligent supervision grid in the supervision communities, and the dimension reduction of the scene of global visual supervision is realized, so that visual data flow needing real-time processing is reduced, the community supervision timeliness is ensured, and the community supervision effect is improved.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements may be made to the present application by those skilled in the art, which modifications and equivalents are also considered to be within the scope of the present application.
Claims (2)
1. The intelligent community visual real-time supervision method based on big data is characterized by comprising the following steps of:
s1, constructing intelligent supervision grids of communities, and constructing each intelligent supervision grid into an intelligent supervision network;
s2, performing network analysis on the intelligent supervision network to obtain a plurality of groups of supervision communities, performing association analysis on a plurality of intelligent supervision grids in the plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, and converting each supervision community into a fully-connected association network by using the state association;
step S3, determining the visual monitoring grids in each group of supervision communities, and performing state evaluation on visual monitoring data of the visual monitoring grids to obtain scene states of the visual monitoring grids;
step S4, combining the scene states of the visual monitoring grids in the same monitoring community with the state correlation among the intelligent monitoring grids to obtain the scene states of all intelligent monitoring grids in the monitoring community, so that the correlation of the intelligent monitoring grids is utilized to reduce the large data processing amount of the visual real-time data flow;
constructing each intelligent supervision grid into an intelligent supervision network, comprising:
taking each intelligent supervision grid as each network node;
obtaining geographic coordinates of central positions of all intelligent supervision grids and historical visual data of all intelligent supervision grids, and calculating the product of Euclidean distance of geographic coordinates between two intelligent supervision grids of adjacent relations and Euclidean distance of the historical visual data to be used as the association weight between the two intelligent supervision grids of the adjacent relations;
mapping adjacent relations of the intelligent supervision grids into connecting edges of corresponding network nodes in sequence;
the associated weights are used as edge weights of the corresponding connecting edges, and the connecting edges with the edge weights are used for connecting all network nodes into an intelligent supervision network;
the calculation formula of the association weight is as follows:
in which W is i,i+1 Is the firstiPersonal intelligent supervision grid and the firsti+1 intelligent monitoring network cell correlation weight, p i Is the firstiGeographical coordinates, p, of the central position of the intelligent supervision grid i+1 Is the firsti+1 geographic coordinates of the intelligent supervision grid center position, d i Is the firstiHistorical visual data of intelligent supervision grid d i+1 Is the firstiHistorical visual data, |p, of +1 intelligent supervision grid i -p i+1 I is p i And p i+1 Euclidean distance, |d i -d i+1 I is d i And d i+1 Is used for the distance of euclidean distance,ito count variable, the firstiPersonal intelligent supervision grid and the firsti+1 intelligent supervision grids are in adjacent relation;
the network analysis is performed on the intelligent supervision network to obtain a plurality of groups of supervision communities, which comprises the following steps:
performing community analysis on the intelligent supervision network by utilizing a genetic algorithm to divide the intelligent supervision communities into a plurality of groups of supervision communities;
wherein, the intelligent supervision grids in the same group of supervision communities have similar scene states, and the intelligent supervision grids in different groups of supervision communities have dissimilar scene states;
performing association analysis on a plurality of intelligent supervision grids in a plurality of groups of supervision communities to obtain state association among the intelligent supervision grids, wherein the method comprises the following steps:
performing association analysis on any two intelligent supervision grids in each group of supervision communities to obtain state association of any two intelligent supervision grids;
the quantitative analysis formula of the state relevance is as follows:
wherein I is j,k Is the first to supervise the communityjPersonal intelligent supervision grid and the firstkIntelligent monitoring network compartment state switchLinkage, p j Is the first to supervise the communityjGeographical coordinates, p, of the central position of the intelligent supervision grid k Is the first to supervise the communitykGeographical coordinates of the central position of the intelligent supervision grid d j Is the first to supervise the communityjHistorical visual data of intelligent supervision grid d k Is the first to supervise the communitykHistorical visual data, |p, of individual intelligent supervision grids j -p k I is p j And p k Euclidean distance, |d j -d k I is d j And d k J, k is a counting variable;
the method for converting each supervision community into a fully-connected association network by using the state association comprises the following steps:
taking the state relevance of any two intelligent monitoring grids in each group of monitoring communities as the edge weight of the connecting edge of any two intelligent monitoring grids in each group of monitoring communities;
connecting any two intelligent supervision grids in each group of supervision communities by using edge weights with connecting edges so as to obtain the fully-connected associated network;
the method for determining the visual monitoring grid in each group of supervision communities comprises the following steps:
performing node centrality measurement on each intelligent supervision grid in the supervision community to obtain node centrality corresponding to each intelligent supervision grid;
taking the intelligent supervision grid with the highest node centrality as the visual monitoring grid;
the step of performing state evaluation on the visual monitoring data of the visual monitoring grid to obtain the scene state of the visual monitoring grid comprises the following steps:
inputting the visual monitoring data of the visual monitoring grid to a pre-established state evaluator, and outputting each state score of the scene state of the visual monitoring grid by the state evaluator;
the model expression of the state estimator is:
[P_label1,…,P_labeln]=BP(d_now)；
wherein P_label1 is the state score of state 1 in the scene state, P_labeln is the state score of state n in the scene state, d_now is the visual monitoring data, and BP is the BP neural network;
the step of combining the scene states of the visual monitoring grids in the same monitoring community with the state correlation among the intelligent monitoring grids to obtain the scene states of each intelligent monitoring grid in the monitoring community comprises the following steps:
mapping all state scores of the scene states of the visual monitoring grids in the same monitoring community into the fully-connected associated network, and calculating all state scores of the scene states of all intelligent monitoring grids except the visual monitoring grids in the same monitoring community according to the edge weights of the connecting edges in the fully-connected associated network;
the scoring quantization formulas of all the states of the scene states of all intelligent supervision grids except the visual supervision grid in the same supervision community are as follows:
wherein I is j,k Is the first to supervise the communityjPersonal intelligent supervision grid and the firstkEdge weights of connecting edges among intelligent supervision grids, [ P_lab1, …, P_laben ]] j Is the first to supervise the communityjEach state score of scene states of each intelligent supervision grid, [ P_labl1, …, P_labln] k Is the first to supervise the communitykEach state score of the scene states of the intelligent supervision grid,
and [ P_label1, …, P_labeln] k Is the euclidean distance of (2);
the history visual data is a time sequence formed by visual data at each time sequence in the same history time sequence section.
2. The intelligent community visualization real-time supervision method based on big data according to claim 1, wherein the method comprises the following steps: the intelligent supervision grid for constructing communities comprises:
rectangular meshing is carried out on the plan of the community to obtain a plurality of intelligent supervision meshes;
the grid area of the intelligent supervision grid is smaller than or equal to the monitoring field area of the visual monitoring equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310317229.7A CN116089823B (en) | 2023-03-29 | 2023-03-29 | Intelligent community visual real-time supervision method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310317229.7A CN116089823B (en) | 2023-03-29 | 2023-03-29 | Intelligent community visual real-time supervision method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116089823A CN116089823A (en) | 2023-05-09 |
| CN116089823B true CN116089823B (en) | 2023-06-20 |
Family
ID=86212319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310317229.7A Active CN116089823B (en) | 2023-03-29 | 2023-03-29 | Intelligent community visual real-time supervision method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116089823B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729421A (en) * | 2017-09-27 | 2018-02-23 | 华为技术有限公司 | The execution method, apparatus and storage medium of storing process |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10642868B2 (en) * | 2014-08-19 | 2020-05-05 | Tag.Bio, Inc. | Data analysis and visualization |
| CN110109753A (en) * | 2019-04-25 | 2019-08-09 | 成都信息工程大学 | Resource regulating method and system based on various dimensions constraint genetic algorithm |
| CN110223211A (en) * | 2019-07-30 | 2019-09-10 | 浪潮云信息技术有限公司 | A kind of intelligence community building method based on government's big data |
| CN111159601B (en) * | 2019-12-30 | 2021-01-19 | 深圳福恋智能信息科技有限公司 | Social contact method for visually displaying community based on feature data |
| CN112036731A (en) * | 2020-08-27 | 2020-12-04 | 黑龙江昶泰科技有限公司 | Smart cloud community service system |
| CN112925920A (en) * | 2021-03-23 | 2021-06-08 | 西安电子科技大学昆山创新研究院 | Smart community big data knowledge graph network community detection method |
| CN114827221A (en) * | 2022-04-28 | 2022-07-29 | 连云港屋托帮文化传媒有限公司 | Intelligent community comprehensive intelligent analysis and early warning system and method |
| CN115632839B (en) * | 2022-10-10 | 2023-06-09 | 江苏海洋大学 | Intelligent campus environment network supervision method and system |
-
2023
- 2023-03-29 CN CN202310317229.7A patent/CN116089823B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729421A (en) * | 2017-09-27 | 2018-02-23 | 华为技术有限公司 | The execution method, apparatus and storage medium of storing process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116089823A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111429027B (en) | Regional power transmission network operation multidimensional analysis method based on big data | |
| CN103324980B (en) | A kind of method for forecasting | |
| CN110111576A (en) | A kind of urban transportation elastic index and its implementation based on space-time congestion group | |
| CN110689240A (en) | Fuzzy comprehensive evaluation method for economic operation of power distribution network | |
| CN104933505A (en) | Decision and evaluation method for intelligent power distribution network group based on fuzzy assessment | |
| CN108921334A (en) | A kind of project amount control target of extra-high voltage electric transmission and transformation engineering determines method and device | |
| CN104850653A (en) | Short-term tourist traffic and trend prediction system based on streaming data extraction | |
| CN112668821A (en) | Distribution line risk analysis method based on insulator fault probability of sand blown region | |
| CN107481523A (en) | A kind of traffic flow speed Forecasting Methodology and system | |
| CN114865638A (en) | Power grid low-voltage load shedding emergency control method based on deep graph reinforcement learning | |
| CN115915364A (en) | Energy-saving method and device for communication base station, computer readable medium and equipment | |
| Chen et al. | Short-term traffic flow prediction based on data-driven knearest neighbour nonparametric regression | |
| CN114723293A (en) | Drought risk assessment method based on historical typical drought influence indexes of drought in arid years | |
| CN113569411B (en) | Disaster weather-oriented power grid operation risk situation awareness method | |
| CN116089823B (en) | Intelligent community visual real-time supervision method based on big data | |
| CN111738854A (en) | New energy spot transaction decision-making data service system based on cloud computing | |
| CN116663393A (en) | Random forest-based power distribution network continuous high-temperature fault risk level prediction method | |
| CN106384307A (en) | Differentiated evaluation method for county-area power distribution network plan | |
| Bao-ping et al. | Short-term traffic flow prediction based on ANFIS | |
| CN103886393A (en) | Power grid investment optimization method based on simulation investment benefit analysis and learning automatons | |
| CN115017658A (en) | Rail transit network optimization method based on reachability and node importance | |
| CN115034608A (en) | Distribution network risk assessment method based on distribution network element and neural network | |
| Bingxu | Design and analysis of a rural accurate poverty alleviation platform based on big data | |
| CN111612227A (en) | Load prediction method based on K-means clustering and bat optimization neural network | |
| Lyu et al. | Water level prediction model based on GCN and LSTM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |