CN116186594B

CN116186594B - Method for realizing intelligent detection of environment change trend based on decision network combined with big data

Info

Publication number: CN116186594B
Application number: CN202310462050.0A
Authority: CN
Inventors: 邓天英; 赵东南; 司丹丹; 周鹏; 刘灿; 赵宣; 兰林; 李艳莉; 赵丁; 邓婧
Original assignee: Chengdu Environmental Emergency Command And Support Center
Current assignee: Chengdu Environmental Emergency Command And Support Center
Priority date: 2023-04-26
Filing date: 2023-04-26
Publication date: 2023-07-04
Anticipated expiration: 2043-04-26
Also published as: CN116186594A

Abstract

The invention relates to the technical field of environmental analysis, and discloses a method for realizing intelligent detection of environmental change trend based on decision network combined with big data, which comprises the following steps: calculating a similarity coefficient of each data in the current environmental data; carrying out data classification on the current environmental data to obtain classified environmental data, carrying out feature extraction on the classified environmental data to obtain environmental data features, determining environmental factors corresponding to each type of data in the classified environmental data, analyzing the linear relation between the environmental factors and the environmental data features, and analyzing the environmental change trend of the target area to obtain a first analysis result; carrying out decision analysis on the environmental change trend in the historical environmental data to obtain an analysis result, and analyzing the environmental change trend of the target area; and summarizing the first analysis result and the second analysis result to obtain a final analysis result, and generating a detection report of the environmental change trend of the target area. The invention aims to improve the accuracy of intelligent detection of the environmental change trend.

Description

Method for realizing intelligent detection of environment change trend based on decision network combined with big data

Technical Field

The invention relates to the technical field of environmental analysis, in particular to a method for realizing intelligent detection of environmental change trend based on decision network combined with big data.

Background

With the continuous progress of the technology level, the air pollution problem of the global area is increased, most areas are continuously subjected to serious environmental pollution in recent years, and serious pollution can bring a series of adverse effects, including certain effects on physical and mental health of people and living environment of living beings, so that environmental change analysis needs to be carried out on certain areas in advance, environmental change trend is convenient to know, and the environment can be improved in advance and corresponding precautionary measures are taken.

However, the existing detection method of the environmental change trend is to collect environmental data of a detection area through related detection equipment, combine the environmental data with attributes such as geology of the area, analyze the environmental change trend of the detection area, but the method is only to combine the current environmental analysis result through each instrument, not combine the historical data of the area, and not adopt a corresponding data processing network to analyze the data, so that the environmental change trend detection result has errors, the accuracy of the environmental change trend analysis is reduced, and therefore, a method capable of improving the accuracy of the intelligent detection of the environmental change trend is needed.

Disclosure of Invention

The invention provides a method for realizing intelligent detection of an environmental change trend based on a decision network combined with big data, which mainly aims to improve the accuracy of intelligent detection of the environmental change trend.

In order to achieve the above purpose, the method for realizing intelligent detection of environmental change trend based on decision network combined with big data provided by the invention comprises the following steps:

acquiring a target area of an environment to be analyzed, acquiring current environment data of the target area by using a preset environment collector, and calculating a similarity coefficient of each data in the current environment data by using the following formula:

wherein F represents a similarity coefficient of each data in the current environmental data, i represents a serial number of the current environmental data, x represents a total number of the current environmental data, C _i Vector value representing ith data in current environment data, C _i+1 A vector value representing the (i+1) th data in the current environmental data;

according to the similarity coefficient, carrying out data classification on the current environmental data to obtain classified environmental data, and carrying out feature extraction on the classified environmental data to obtain environmental data features;

according to the classified environmental data, determining environmental factors corresponding to each type of data in the classified environmental data, analyzing the linear relation between the environmental factors and the environmental data characteristics, and analyzing the environmental change trend of the target area according to the linear relation to obtain a first analysis result;

The method comprises the steps of calling historical environment data of a target area, carrying out decision analysis on environment change trend in the historical environment data by using a preset decision network to obtain an analysis result, constructing a historical environment graph of the target area according to the analysis result, and analyzing the environment change trend of the target area according to the historical environment graph and the environment factor to obtain a second analysis result;

and summarizing the first analysis result and the second analysis result to obtain a final analysis result, and generating a detection report of the environmental change trend of the target area according to the final analysis result.

Optionally, the classifying the current environmental data according to the similarity coefficient to obtain classified environmental data includes:

preprocessing the current environmental data to obtain target environmental data, and extracting tags from the target environmental data to obtain environmental data tags;

vectorizing the environmental data labels to obtain environmental label vectors, and calculating the similarity between the environmental label vectors to obtain label similarity;

and classifying the target environment data according to the label similarity and the similarity coefficient to obtain classified environment data.

Optionally, the feature extraction of the classified environmental data to obtain environmental data features includes:

performing attribute analysis on the classified environment data to obtain classified data attributes, and extracting classified attribute signals corresponding to the classified data attributes;

calculating the signal weight of each category in the classification attribute signals to obtain classification signal weights, and carrying out signal screening on the classification attribute signals according to the classification signal weights to obtain target classification attribute signals;

extracting the characteristics of the target classification attribute signals to obtain classification signal characteristics, and constructing a signal characteristic matrix corresponding to each category of characteristics in the classification signal characteristics to obtain a classification signal characteristic matrix;

and according to each category, carrying out weighted summation on the classified signal feature matrixes to obtain a target feature matrix, and determining the environmental data features of the classified environmental data according to the target feature matrix.

Optionally, the calculating the signal weight of each category in the classification attribute signal to obtain a classification signal weight includes:

wherein E is _j Representing the signal weight of the jth signal in each category of the classification attribute signals, j representing the signal sequence number corresponding to the classification attribute signals, B _j Represents the signal intensity average value corresponding to the jth signal in the classification attribute signals,

representing the vector covariance corresponding to the jth attribute signal, trace () represents the spatial filter function.

Optionally, the performing weighted summation on the classification signal feature matrix to obtain a target feature matrix includes:

and carrying out weighted summation on the classified signal characteristic matrix by the following formula:

wherein G represents a target feature matrix obtained by weighted summation of the classified signal feature matrices, S represents a sigmoid function,

a+1 and a+u represent matrix serial numbers in the classification signal feature matrix, a+u represents the total number of matrices of the classification signal feature matrix, ω _a Representing matrix weight coefficient, h corresponding to an a-th matrix in the classified signal characteristic matrix _a And (3) representing a matrix mean value corresponding to an a-th matrix in the classification signal feature matrix, wherein a epsilon (a, a+u) represents a selection range of the matrix.

Optionally, the determining, according to the classification environmental data, an environmental factor corresponding to each type of data in the classification environmental data includes:

extracting texts in the classified environment data to obtain data texts, and performing word segmentation on the data texts to obtain data text word segmentation;

Carrying out semantic analysis on each word in the data text word segmentation to obtain word segmentation semantics, and extracting key characters in the data text word segmentation according to the word segmentation semantics;

inquiring environmental factors corresponding to the key characters from a preset environmental character mapping table according to the key characters to obtain first environmental factors;

analyzing the data category corresponding to the data in the classified environmental data, and analyzing the environmental factor corresponding to the classified environmental data according to the data category to obtain a second environmental factor;

and determining the environmental factors corresponding to each type of data in the classified environmental data by combining the first environmental factors and the second environmental factors.

Optionally, the analyzing the linear relationship of the environmental factor and the environmental data feature includes:

calculating a correlation coefficient between the environmental factor and the environmental data feature, and constructing a corresponding scatter diagram between the environmental factor and the environmental data feature according to the correlation coefficient;

fitting the scatter diagram to obtain a fitted scatter diagram, and calculating the curve inclination rate corresponding to a fitted curve in the fitted scatter diagram;

according to the curve inclination rate, analyzing the linear relation between the environmental factor and the environmental data characteristic by using a preset linear function

Optionally, the calculating the association coefficient between the environmental factor and the environmental data feature includes:

calculating a correlation coefficient between the environmental factor and the environmental data feature by the following formula:

wherein L represents a correlation coefficient between the environmental factor and the environmental data feature, D represents a dimension coefficient corresponding to the environmental factor and the environmental data feature, Y represents the number of the environmental data feature, n and n+1 represent serial numbers of the environmental factor and the environmental data feature respectively, and M _n Represent feature vectors corresponding to the nth environmental factor lnM _n Representing the logarithmic value of the eigenvector corresponding to the nth environmental factor, P _n+1 Representing a feature vector corresponding to the n+1st environmental data feature lnP _n+1 The logarithmic value of the feature vector corresponding to the n+1th environmental data feature is represented, max () represents the maximum value of the logarithmic difference value, and min () represents the minimum value of the logarithmic difference value.

Optionally, the performing decision analysis on the environmental change trend in the historical environmental data by using a preset decision network to obtain an analysis result includes:

performing hierarchical division on the historical environment data by using an input layer in a preset decision network to obtain a data hierarchy;

according to the data hierarchy, sequencing the historical environment data to obtain a data sequence, and constructing a data column diagram corresponding to the historical environment data by utilizing a hidden layer in the decision network;

And combining the data sequence and the data bar graph, and utilizing a decision layer in the decision network to perform decision analysis on the historical environment data so as to obtain an analysis result.

In order to solve the above problems, the present invention further provides an environment monitoring system based on unmanned aerial vehicle automatic patrol, the system comprising:

the data acquisition module is used for acquiring a target area of an environment to be analyzed, acquiring current environment data of the target area by using a preset environment collector, and calculating a similarity coefficient of each data in the current environment data by using the following formula:

the feature extraction module is used for carrying out data classification on the current environment data according to the similarity coefficient to obtain classified environment data, and carrying out feature extraction on the classified environment data to obtain environment data features;

the linear analysis module is used for determining environmental factors corresponding to each type of data in the classified environmental data according to the classified environmental data, analyzing the linear relation between the environmental factors and the environmental data characteristics, and analyzing the environmental change trend of the target area according to the linear relation to obtain a first analysis result;

The change analysis module is used for calling historical environment data of the target area, carrying out decision analysis on environment change trend in the historical environment data by utilizing a preset decision network to obtain an analysis result, constructing a historical environment graph of the target area according to the analysis result, and analyzing the environment change trend of the target area according to the historical environment graph and the environment factor to obtain a second analysis result;

and the report generation module is used for summarizing the first analysis result and the second analysis result to obtain a final analysis result, and generating a detection report of the environmental change trend of the target area according to the final analysis result.

According to the invention, the current environmental data of the environment to be analyzed can be obtained by acquiring the current environmental data of the target area through the preset environmental collector, so that the environmental aspect data of the target area can be known, the subsequent analysis of the environmental change trend of the target area is facilitated, the current environmental data can be classified together according to the corresponding rule or rule by carrying out data classification according to the similarity coefficient, the subsequent data processing is facilitated, wherein the specific environmental factors of each type of data in the classified environmental data can be obtained by determining the environmental factors corresponding to each type of data in the classified environmental data according to the classified environmental data, so that the subsequent analysis of the environmental change trend can be accurately carried out, wherein the historical environmental change trend corresponding to the target area can be obtained by analyzing the environmental change trend in the historical environmental data through the preset decision network, and the accuracy of the subsequent environmental change trend analysis of the target area is improved; in addition, the method and the device can improve the accuracy of the analysis of the environmental change trend of the target area by summarizing the first analysis result and the second analysis result, so as to obtain a more accurate environmental change analysis result. Therefore, the intelligent detection method for the environmental change trend based on the decision network combined with the big data can improve the accuracy of the intelligent detection of the environmental change trend.

Drawings

FIG. 1 is a flow chart of a method for realizing intelligent detection of environmental change trend based on decision network combined with big data according to an embodiment of the invention;

FIG. 2 is a functional block diagram of an intelligent detection system for realizing environmental change trend based on decision network combined with big data according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device for implementing the method for implementing the intelligent detection of environmental change trend based on combining decision network with big data according to an embodiment of the present invention.

In the figure, 1-an electronic device; 10-a processor; 11-memory; 12-a communication bus; 13-a communication interface; 100-realizing an intelligent detection system for environmental change trend based on a decision network and big data; 101-a data acquisition module; 102-a feature extraction module; 103-a linear analysis module; 104-a change analysis module; 105-report generation module.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the application provides a method for realizing intelligent detection of environmental change trend based on a decision network and big data. In the embodiment of the present application, the execution body of the intelligent detection method for realizing environmental change trend based on the decision network in combination with big data includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided in the embodiment of the present application. In other words, the intelligent detection method for realizing the environmental change trend based on the decision network and the big data can be executed by software or hardware installed in the terminal equipment or the server equipment, wherein the software can be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

Referring to fig. 1, a flow chart of a method for implementing intelligent detection of environmental change trend based on decision network combined with big data according to an embodiment of the present invention is shown. In this embodiment, the method for implementing intelligent detection of environmental change trend based on decision network combined with big data includes steps S1-S5.

S1, acquiring a target area of an environment to be analyzed, acquiring current environment data of the target area by using a preset environment collector, and calculating a similarity coefficient of each data in the current environment data.

According to the invention, the target area of the environment to be analyzed is obtained, the current environmental data of the target area is acquired by utilizing the preset environmental collector, so that the environmental data of the target area can be known, and the subsequent analysis of the environmental change trend of the target area is facilitated.

The target area is an area needing to be subjected to environmental change trend analysis, the preset environmental collector is equipment for collecting data of the environment, such as a smoke detection sensor, and the current environmental data are data corresponding to the current environment of the target area, such as data of particulate matter content in air, air humidity and the like.

The invention facilitates the subsequent classification processing of the current environmental data by calculating the similarity coefficient of each data in the current environmental data, wherein the similarity coefficient represents the similarity degree of each data in the current environmental data.

As an embodiment of the present invention, the calculating the similarity coefficient of each data in the current environmental data includes:

calculating a similarity coefficient of each data in the current environmental data by the following formula:

wherein F represents a similarity coefficient of each data in the current environmental data, i represents a serial number of the current environmental data, x represents a total number of the current environmental data, C _i Vector value representing ith data in current environment data, C _i+1 A vector value representing the i+1st data in the current environment data.

S2, carrying out data classification on the current environment data according to the similarity coefficient to obtain classified environment data, and carrying out feature extraction on the classified environment data to obtain environment data features.

According to the invention, the current environment data is classified according to the similarity coefficient, so that the current environment data can be divided together according to corresponding rules or laws, and further the subsequent data processing is facilitated, wherein the classified environment data is an attribute obtained after the current environment data is classified.

As an embodiment of the present invention, the classifying the current environmental data according to the similarity coefficient to obtain classified environmental data includes: preprocessing the current environment data to obtain target environment data, extracting tags from the target environment data to obtain environment data tags, vectorizing the environment data tags to obtain environment tag vectors, calculating similarity among the environment tag vectors to obtain tag similarity, classifying the target environment data with the tag similarity and the similarity coefficient to obtain classified environment data.

The target environment data is data obtained by preprocessing the current environment data, the preprocessing comprises operations such as data cleaning, data protocol, data integration and the like, the environment data labels are data identifiers corresponding to the target environment data, the environment label vectors are vector expression forms corresponding to the environment data labels, and the label similarity represents the similarity degree between the environment label vectors.

Furthermore, the tag extraction of the target environment data can be realized through a tag extraction tool, the tag extraction tool is compiled by a scripting language, the vectorization operation of the environment data tags can be realized through a word2vec algorithm, the similarity between environment tag vectors can be obtained by calculating the cosine value of an included angle between the environment tags, and the classification processing of the target environment data can be realized through a classification function, such as an if logic function.

According to the method, the data characterization of the classified environment data can be known by extracting the characteristics of the classified environment data, so that the data analysis of the classified environment data is facilitated, wherein the environmental data characteristics are the characterization of the data in the classified environment data.

As an embodiment of the present invention, the feature extracting the classified environmental data to obtain environmental data features includes: performing attribute analysis on the classified environment data to obtain classified data attributes, extracting classified attribute signals corresponding to the classified data attributes, calculating signal weights of all categories in the classified attribute signals to obtain classified signal weights, performing signal screening on the classified attribute signals according to the classified signal weights to obtain target classified attribute signals, performing feature extraction on the target classified attribute signals to obtain classified signal features, constructing a signal feature matrix corresponding to the features of all the categories in the classified signal features to obtain classified signal feature matrices, performing weighted summation on the classified signal feature matrices according to all the categories to obtain target feature matrices, and determining the environmental data features of the classified environment data according to the target feature matrices.

The classification data attribute is attribute information corresponding to each data in the classification environment data, the classification attribute signal is a fixed physical quantity corresponding to the classification data attribute, the classification signal weight represents importance degree corresponding to signals in each category in the classification attribute signal, the target classification attribute signal is an attribute signal obtained after the classification attribute signal is screened according to the numerical value of the classification signal weight, the classification signal feature is a signal characterization part of the target classification attribute signal, the classification signal feature matrix is a square matrix corresponding to the feature of each category in the classification signal feature, and the target feature matrix is a comprehensive matrix obtained by weighting and summing the classification signal feature matrix.

Further, the attribute analysis of the classification environment data may be implemented by an attribute analysis tool, the attribute analysis tool is Java language compiling, extracting a classification attribute signal corresponding to the classification data attribute may be implemented by a fourier transform method, the signal filtering of the classification attribute signal may be implemented by a vlookup function, the feature extraction of the target classification attribute signal may be implemented by a feature extraction algorithm, for example, a lbp feature extraction algorithm, and the construction of a signal feature matrix corresponding to each category of feature of the classification signal may be implemented by a matrix construction function, for example, a zeros function.

As an optional embodiment of the present invention, the calculating the signal weight of each category in the classification attribute signal to obtain a classification signal weight includes:

calculating the signal weight of each category in the classification attribute signal by the following formula:

As an optional embodiment of the present invention, the performing weighted summation on the classification signal feature matrix to obtain a target feature matrix includes:

S3, determining environmental factors corresponding to each type of data in the classified environmental data according to the classified environmental data, analyzing the linear relation between the environmental factors and the environmental data characteristics, and analyzing the environmental change trend of the target area according to the linear relation to obtain a first analysis result.

According to the method and the device, the environmental factors corresponding to each type of data in the classified environmental data are determined according to the classified environmental data, so that the specific environmental factors of each type of data in the classified environmental data can be obtained, and the environment change trend can be accurately analyzed later, wherein the environmental factors are the environmental factors corresponding to each type of data in the classified environment, such as temperature, humidity and wind power level.

As one embodiment of the present invention, the determining, according to the classification environmental data, an environmental factor corresponding to each type of data in the classification environmental data includes: extracting texts in the classified environment data to obtain data texts, performing word segmentation processing on the data texts to obtain data text word segmentation, performing semantic analysis on each word segmentation in the data text word segmentation to obtain word segmentation semantics, extracting key characters in the data text word segmentation according to the word segmentation semantics, inquiring environment factors corresponding to the key characters from a preset environment character mapping table according to the key characters to obtain first environment factors, analyzing data types corresponding to the data in the classified environment data, analyzing environment factors corresponding to the classified environment data according to the data types to obtain second environment factors, and determining environment factors corresponding to each type of data in the classified environment data by combining the first environment factors and the second environment factors.

The data text is the content of a text form in the classified environment data, the data text word segmentation is a word with logic in the data text, word segmentation semantics are meaning and explanation corresponding to the data text word segmentation, key characters are representative characters in the data text word segmentation, the preset environment character mapping table is a table formed by a large number of environment data training, obtained environment factors and characters with mapping relations, the first environment factors are environment factors in the classified environment data obtained through the key characters, the data category is a type corresponding to the data in the classified environment data, and the second environment factors are environment factors in the classified environment data obtained according to the data category analysis.

Further, as an optional embodiment of the present invention, extracting text in the classification environmental data may be implemented by an OCR text recognition technology, performing word segmentation on the data text may be implemented by an ik word segmentation device, performing semantic analysis on each word in the data text word segmentation may be implemented by a semantic analysis method, extracting key characters in the data text word segmentation may be implemented by a TF-IDF algorithm, querying environmental factors corresponding to the key characters may be implemented by a query function, such as a find function, analyzing data types corresponding to the data in the classification environmental data may be implemented by a decomposition subject analysis method, and environmental factors corresponding to the classification environmental data may be implemented by analyzing data types corresponding to the data types, such as a weather type, a soil type, and a geographic type.

According to the invention, the linear relation between the environmental factors and the environmental data features is analyzed, so that the mapping relation between the environmental factors and the environmental data features can be obtained, and further the analysis of the corresponding change trend of the environment is facilitated, wherein the linear relation represents the mapping relation between the environmental factors and the environmental data features.

As an embodiment of the present invention, the analyzing the linear relation between the environmental factor and the environmental data feature includes: calculating a correlation coefficient between the environmental factor and the environmental data feature, constructing a scatter diagram corresponding to the environmental factor and the environmental data feature according to the correlation coefficient, performing fitting processing on the scatter diagram to obtain a fitted scatter diagram, calculating a curve inclination rate corresponding to a fitted curve in the fitted scatter diagram, and analyzing the linear relation between the environmental factor and the environmental data feature by using a preset linear function according to the curve inclination rate.

The correlation coefficient represents the correlation degree between the environmental factor and the environmental data feature, the scatter diagram is obtained by mutually corresponding the environmental factor and the corresponding environmental data feature according to the correlation coefficient and recording a distribution diagram corresponding to the environmental data feature according to the environmental factor as a coordinate axis, the fitting scatter diagram is a diagram obtained by connecting points in the scatter diagram through a curve according to an order, the curve inclination rate represents the inclination degree corresponding to the fitting scatter diagram, and the preset linear function is a function for analyzing the linear relation between variables, such as a linear function.

Further, as an optional embodiment of the present invention, constructing a scatter plot corresponding to the environmental factor and the environmental data feature may be implemented by a mapping tool, for example, a visio tool, and performing fitting processing on the scatter plot may be implemented by a square curve fitting method, where a curve slope rate calculating method corresponding to a fitted curve in the fitted scatter plot is calculated as follows: k= (y 1-y 2)/(x 1-x 2), k represents a curve inclination rate, x1 and y1 represent coordinate values of one point, and x2 and y2 represent coordinate values of the other point.

Further, as an optional embodiment of the invention, the calculating the association coefficient between the environmental factor and the environmental data feature includes:

According to the method, the environment change trend of the target area is analyzed according to the linear relation, the environment change trend of the target area can be obtained through the linear relation, wherein the first analysis result is the environment change result obtained through the linear relation analysis, and further, the environment change trend of the target area is analyzed through a linear regression analysis method.

S4, historical environment data of the target area are called, a preset decision network is utilized to conduct decision analysis on environment change trend in the historical environment data, analysis results are obtained, an environment change curve graph of the target area is built according to the analysis results, and analysis is conducted on the environment change trend of the target area according to the environment change curve graph, so that a second analysis result is obtained.

According to the invention, by calling the historical environment data of the target area and analyzing the environment change trend in the historical environment data by using a preset decision network, the historical environment change trend situation corresponding to the target area can be obtained, and the accuracy of the environment change trend analysis of the subsequent target area is improved, wherein the historical environment data is the environment parameter information recorded before the target area, and the preset decision network is a neural network for assisting the data in making decisions by a graphical method, such as a Bayesian network.

As an embodiment of the present invention, the performing, by using a preset decision network, a decision analysis on an environmental change trend in the historical environmental data to obtain an analysis result includes: and carrying out hierarchical division on the historical environment data by utilizing an input layer in a preset decision network to obtain a data hierarchy, sorting the historical environment data according to the data hierarchy to obtain a data sequence, constructing a data histogram corresponding to the historical environment data by utilizing a hidden layer in the decision network, and carrying out decision analysis on the historical environment data by utilizing a decision layer in the decision network in combination with the data sequence and the data histogram to obtain an analysis result.

The input layer is a neural network for performing hierarchical analysis on the historical environment data, the data hierarchy represents a level corresponding to each data in the historical environment data, the data sequence is a priority sequence corresponding to the historical environment data when performing decision analysis, the hidden layer is a neural network for converting the historical environment data into a corresponding image form, the data histogram is a data image expression form corresponding to the historical environment data, and the decision layer is a neural network for performing decision analysis on the historical environment data.

Furthermore, the hierarchical division of the historical environment data can be achieved through an input function in the input layer, such as an input () function, the sorting of the historical environment data can be achieved through a sorting algorithm, such as a bubbling sorting algorithm, the construction of the data histogram corresponding to the historical environment data can be achieved through a single hidden layer neural network in the hidden layer, and the decision analysis of the historical environment data can be achieved through a decision tree algorithm in the decision layer.

According to the analysis result, the historical environment curve graph of the target area is constructed, the historical environment change condition of the target area can be known through the historical environment curve graph, wherein the historical environment curve graph is a circuit diagram of the historical environment change of the target area constructed according to the analysis result, and further, the construction of the historical environment curve graph of the target area can be realized through the visio tool.

According to the invention, the environmental change trend of the target area is analyzed according to the historical environmental graph and the environmental factors, so that the situation of the historical environmental change of the target area can be conveniently known, wherein the second analysis result is the result of the historical environmental change analysis of the target area, and further, the analysis of the environmental change trend of the target area can be realized through the linear regression analysis method.

And S5, summarizing the first analysis result and the second analysis result to obtain a final analysis result, and generating a detection report of the environmental change trend of the target area according to the final analysis result.

According to the invention, the result summarization is carried out on the first analysis result and the second analysis result, so that the accuracy of the environmental change trend analysis of the target area can be improved, and a more accurate environmental change analysis result can be obtained conveniently, wherein the final analysis result is a result obtained by fusion summarization of the first analysis result and the second analysis result, and further, the result summarization of the first analysis result and the second analysis result can be realized through a CONCATENATE function.

According to the invention, the detection report of the environmental change trend of the target area is generated according to the final analysis result, so that the analysis report of the environmental change trend of the target area can be intuitively known.

Fig. 2 is a functional block diagram of an intelligent detection system for realizing environmental change trend based on decision network combined with big data according to an embodiment of the present invention.

The intelligent detection system 100 for realizing the environmental change trend based on the combination of the decision network and the big data can be installed in electronic equipment. Depending on the implementation function, the decision network-based environment change trend intelligent detection system 100 implemented by combining big data may include a data acquisition module 101, a feature extraction module 102, a linear analysis module 103, a change analysis module 104, and a report generation module 105. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

In the present embodiment, the functions concerning the respective modules/units are as follows:

the data acquisition module 101 is configured to acquire a target area of an environment to be analyzed, acquire current environmental data of the target area by using a preset environmental collector, and calculate a similarity coefficient of each data in the current environmental data according to the following formula:

the feature extraction module 102 is configured to perform data classification on the current environmental data according to the similarity coefficient to obtain classified environmental data, and perform feature extraction on the classified environmental data to obtain environmental data features;

the linear analysis module 103 is configured to determine an environmental factor corresponding to each type of data in the classified environmental data according to the classified environmental data, analyze a linear relationship between the environmental factor and the environmental data feature, and analyze an environmental variation trend of the target area according to the linear relationship to obtain a first analysis result;

the change analysis module 104 is configured to take historical environmental data of the target area, perform decision analysis on environmental change trends in the historical environmental data by using a preset decision network to obtain an analysis result, construct a historical environmental graph of the target area according to the analysis result, and analyze the environmental change trends of the target area according to the historical environmental graph and the environmental factor to obtain a second analysis result;

The report generating module 105 is configured to perform result aggregation on the first analysis result and the second analysis result, obtain a final analysis result, and generate a detection report of the environmental change trend of the target area according to the final analysis result.

In detail, each module in the system 100 for implementing the intelligent detection of the environmental change trend based on the decision network in combination with big data in the embodiment of the present application adopts the same technical means as the method for implementing the intelligent detection of the environmental change trend based on the decision network in combination with big data in fig. 1, and can produce the same technical effects, which are not described herein again.

Fig. 3 is a schematic structural diagram of an electronic device 1 for implementing an intelligent detection method for environmental change trend based on a decision network combined with big data according to an embodiment of the present invention.

The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a program for implementing an intelligent detection method of environmental change trend based on a decision network in combination with big data.

The processor 10 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing Unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and so on. The processor 10 is a Control Unit (Control Unit) of the electronic device 1, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory 11 (for example, executes a program for implementing an intelligent detection method of environmental change trend based on decision network in combination with big data, etc.), and invokes data stored in the memory 11 to perform various functions of the electronic device and process data.

The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used to store not only application software installed in an electronic device and various data, for example, code for implementing an intelligent detection method program for environmental change trend based on a decision network in combination with big data, but also temporarily store data that has been output or is to be output.

The communication bus 12 may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.

The communication interface 13 is used for communication between the electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.

Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.

For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.

It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.

The intelligent detection method program for realizing the environmental change trend based on the decision network and big data stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, and when running in the processor 10, the method program can realize:

In particular, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.

Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).

The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:

/>

In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. The method for realizing the intelligent detection of the environmental change trend based on the decision network and the big data is characterized by comprising the following steps:

according to the similarity coefficient, carrying out data classification on the current environment data to obtain classified environment data, carrying out attribute analysis on the classified environment data to obtain classified data attributes, and extracting a classified attribute signal corresponding to the classified data attributes; calculating the signal weight of each category in the classification attribute signals to obtain classification signal weights, and carrying out signal screening on the classification attribute signals according to the classification signal weights to obtain target classification attribute signals; extracting the characteristics of the target classification attribute signals to obtain classification signal characteristics, and constructing a signal characteristic matrix corresponding to each category of characteristics in the classification signal characteristics to obtain a classification signal characteristic matrix; according to each category, carrying out weighted summation on the classified signal feature matrixes to obtain a target feature matrix, and determining the environmental data features of the classified environmental data according to the target feature matrix;

Extracting texts in the classification environment data according to the classification environment data to obtain data texts, and performing word segmentation processing on the data texts to obtain data text word segmentation; carrying out semantic analysis on each word in the data text word segmentation to obtain word segmentation semantics, and extracting key characters in the data text word segmentation according to the word segmentation semantics; inquiring environmental factors corresponding to the key characters from a preset environmental character mapping table according to the key characters to obtain first environmental factors; analyzing the data category corresponding to the data in the classified environmental data, and analyzing the environmental factor corresponding to the classified environmental data according to the data category to obtain a second environmental factor; determining the environmental factors corresponding to each type of data in the classified environmental data by combining the first environmental factors and the second environmental factors;

analyzing the linear relation between the environmental factors and the environmental data characteristics, and analyzing the environmental change trend of the target area according to the linear relation to obtain a first analysis result;

the historical environment data of the target area are called, and hierarchical division is carried out on the historical environment data by utilizing an input layer in a preset decision network to obtain a data hierarchy; according to the data hierarchy, sequencing the historical environment data to obtain a data sequence, and constructing a data column diagram corresponding to the historical environment data by utilizing a hidden layer in the decision network; combining the data sequence and the data bar graph, utilizing a decision layer in the decision network to perform decision analysis on the historical environment data to obtain an analysis result, constructing a historical environment graph of the target area according to the analysis result, and analyzing the environment change trend of the target area according to the historical environment graph and the environment factor to obtain a second analysis result;

2. The method for implementing intelligent detection of environmental change trend based on decision network combined big data according to claim 1, wherein the step of classifying the current environmental data according to the similarity coefficient to obtain classified environmental data comprises the following steps:

3. The method for implementing intelligent detection of environmental change trend based on decision network and big data according to claim 1, wherein the calculating the signal weight of each category in the classification attribute signal to obtain the classification signal weight comprises:

4. The method for implementing intelligent detection of environmental change trend based on decision network combined with big data according to claim 1, wherein the step of performing weighted summation on the classified signal feature matrix to obtain a target feature matrix comprises the following steps:

5. The method for implementing intelligent detection of environmental change trend based on decision network combined with big data according to claim 1, wherein the analyzing the linear relation between the environmental factor and the environmental data feature comprises:

and according to the curve inclination rate, analyzing the linear relation between the environmental factor and the environmental data characteristic by using a preset linear function.

6. The method for implementing intelligent detection of environmental change trend based on decision network in combination with big data according to claim 5, wherein the calculating the association coefficient between the environmental factor and the environmental data feature comprises:

7. The intelligent detection system for realizing the environmental change trend based on the decision network and big data is characterized by comprising the following components:

the feature extraction module is used for carrying out data classification on the current environment data according to the similarity coefficient to obtain classified environment data, carrying out attribute analysis on the classified environment data to obtain classified data attributes, and extracting a classified attribute signal corresponding to the classified data attributes; calculating the signal weight of each category in the classification attribute signals to obtain classification signal weights, and carrying out signal screening on the classification attribute signals according to the classification signal weights to obtain target classification attribute signals; extracting the characteristics of the target classification attribute signals to obtain classification signal characteristics, and constructing a signal characteristic matrix corresponding to each category of characteristics in the classification signal characteristics to obtain a classification signal characteristic matrix; according to each category, carrying out weighted summation on the classified signal feature matrixes to obtain a target feature matrix, and determining the environmental data features of the classified environmental data according to the target feature matrix;

The linear analysis module is used for extracting texts in the classification environment data according to the classification environment data to obtain data texts, and performing word segmentation processing on the data texts to obtain data text word segmentation; carrying out semantic analysis on each word in the data text word segmentation to obtain word segmentation semantics, and extracting key characters in the data text word segmentation according to the word segmentation semantics; inquiring environmental factors corresponding to the key characters from a preset environmental character mapping table according to the key characters to obtain first environmental factors; analyzing the data category corresponding to the data in the classified environmental data, and analyzing the environmental factor corresponding to the classified environmental data according to the data category to obtain a second environmental factor; determining environmental factors corresponding to each type of data in the classified environmental data by combining the first environmental factors and the second environmental factors, analyzing the linear relation between the environmental factors and the environmental data characteristics, and analyzing the environmental change trend of the target area according to the linear relation to obtain a first analysis result;

the change analysis module is used for calling the historical environment data of the target area, and carrying out hierarchical division on the historical environment data by utilizing an input layer in a preset decision network to obtain a data hierarchy; according to the data hierarchy, sequencing the historical environment data to obtain a data sequence, and constructing a data column diagram corresponding to the historical environment data by utilizing a hidden layer in the decision network; combining the data sequence and the data bar graph, utilizing a decision layer in the decision network to perform decision analysis on the historical environment data to obtain an analysis result, constructing a historical environment graph of the target area according to the analysis result, and analyzing the environment change trend of the target area according to the historical environment graph and the environment factor to obtain a second analysis result;