CN116703004B - Water system river basin intelligent patrol method and device based on pre-training model - Google Patents

Water system river basin intelligent patrol method and device based on pre-training model Download PDF

Info

Publication number
CN116703004B
CN116703004B CN202310884749.6A CN202310884749A CN116703004B CN 116703004 B CN116703004 B CN 116703004B CN 202310884749 A CN202310884749 A CN 202310884749A CN 116703004 B CN116703004 B CN 116703004B
Authority
CN
China
Prior art keywords
data
water quality
geographic information
abnormal
quality data
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
Application number
CN202310884749.6A
Other languages
Chinese (zh)
Other versions
CN116703004A (en
Inventor
伍满禁
李伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shared Data Fujian Technology Co ltd
Original Assignee
Shared Data Fujian Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shared Data Fujian Technology Co ltd filed Critical Shared Data Fujian Technology Co ltd
Priority to CN202310884749.6A priority Critical patent/CN116703004B/en
Publication of CN116703004A publication Critical patent/CN116703004A/en
Application granted granted Critical
Publication of CN116703004B publication Critical patent/CN116703004B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
    • 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
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use
    • Y02A20/152—Water filtration

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Computational Linguistics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a water system basin intelligent patrol method based on a pre-training model, which is used for acquiring geographic information, water quality data and meteorological data of a plurality of positions in a water system basin area in a historical time period; obtaining geographic information, water quality data and meteorological data of a plurality of positions in the area in a future set time period; evaluating the abnormal risk levels of the plurality of locations; screening out abnormal points; the abnormal region is patrolled and protected, and the water area change in the abnormal region is monitored in real time; judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment; the prediction result of the water system river basin has interpretability, and can explain the reason generated by the prediction result and the internal rule of time sequence data fluctuation in the face of the topography situation of the complex water system river basin, and can improve the accuracy of monitoring a plurality of positions in the area, thereby improving the efficiency and accuracy of water system river basin inspection.

Description

Water system river basin intelligent patrol method and device based on pre-training model
Technical Field
The application relates to the technical field of intelligent patrol, in particular to a water system river basin intelligent patrol method and device based on a pre-training model.
Background
Water-based watershed is an important component of human life and ecosystem, and its protection and management are critical to sustainable development. However, the traditional inspection method often depends on manual and limited monitoring means, and the inspection method has the problems of waste of human resources, low inspection efficiency, easy occurrence of missed detection and erroneous judgment and the like. How to improve the efficiency and accuracy of water system drainage basin inspection becomes a urgent problem to be solved. Therefore, the improvement of the water system river basin inspection method by utilizing the advanced artificial intelligence technology has important research and application values.
Meanwhile, with the continuous development of computer technology, particularly the application of deep learning technology, the intelligent patrol system based on the pre-training model is widely applied. However, the intelligent patrol system in the market at present is basically aimed at the patrol of the flat ground such as urban roads, and cannot adapt to the complex terrain such as water system watershed.
Therefore, the application aims to provide a water system river basin intelligent patrol method and device based on a pre-training model, so as to solve the problems in the prior art.
Disclosure of Invention
The application aims to provide a water system drainage basin intelligent patrol method and device based on a pre-training model, so as to strengthen the accuracy of monitoring the water system drainage basin, and the method and device are more suitable for the complex topography of the water system drainage basin, thereby improving the efficiency and accuracy of water system drainage basin patrol.
In a first aspect, an embodiment of the present application provides a water system drainage basin intelligent patrol method based on a pre-training model, including the following steps:
obtaining geographic information, water quality data and meteorological data of a plurality of positions in a water system river basin area in a historical time period;
after preprocessing the geographic information, the water quality data and the meteorological data, inputting a pre-trained water system river basin prediction model to obtain the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period;
the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area;
evaluating abnormal risk levels of the plurality of positions according to geographic information, water quality data and meteorological data of the plurality of positions in the area in a future set time period;
screening out abnormal points based on the evaluation result of the abnormal risk level;
constructing the abnormal region according to the abnormal point positions;
the abnormal region is patrolled by using patrolling equipment, the water area change in the abnormal region is monitored in real time, and the steps are repeated;
judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment;
if the change trend is increased, generating and sending early warning information;
and if the change trend is reduced, continuing to maintain the patrol and monitor.
The watershed predictive model is pre-trained as follows:
acquiring historical geographic information, water quality data and meteorological data of a plurality of positions in an area, and counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time interval to obtain historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area;
after the historical geographic information, water quality data and meteorological data samples are subjected to the preprocessing, the historical geographic information, water quality data and meteorological data samples are converted into geographic information, water quality data and meteorological data supervision data;
and setting an objective function, inputting the geographic information, the water quality data and the meteorological data into the interpretable graphic neural network for training, and obtaining the water system river basin prediction model after reaching a preset training cut-off condition.
Converting the historical geographic information, water quality data and meteorological data samples into geographic information, water quality data and meteorological data supervised data, comprising:
and aggregating the previous variables in the historical geographic information, the water quality data and the meteorological data samples as input variables of the model, and the latter variables as output of the model to obtain the geographic information, the water quality data and the meteorological data supervision data.
The constructing the abnormal region according to the abnormal point location includes:
collecting all known abnormal points;
for each anomaly point location, determining its position in space and other related attributes, including coordinates, values and time stamps;
selecting a K neighbor algorithm to construct an abnormal region according to the attribute of the abnormal point location, and setting the value of K;
clustering the abnormal point positions into abnormal areas according to the selected K neighbor algorithm and the value of K, namely classifying the adjacent abnormal point positions into one type by using a clustering algorithm;
and visualizing the constructed abnormal region.
And placing a feature code at a specific position of the early warning information, and withdrawing the early warning information if the position or the content of the feature code is changed.
The feature code is generated according to the serial number of the patrol equipment.
The evaluating the abnormal risk level of the plurality of positions according to the geographic information, the water quality data and the meteorological data of the plurality of positions in the area in a future set time period comprises the following steps:
preprocessing geographic information, water quality data and meteorological data of a plurality of positions in the area in a future set time period;
extracting a geographic information characteristic value, a water quality characteristic value and a meteorological characteristic value from geographic information, water quality data and meteorological data respectively;
determining the weight of each characteristic value;
multiplying the geographic information characteristic value, the water quality characteristic value and the meteorological characteristic value by corresponding weights, and then carrying out weighted fusion to obtain a comprehensive risk value;
and establishing abnormal risk levels of different levels according to the comprehensive risk values.
In a second aspect, an embodiment of the present application provides a water system drainage basin intelligent patrol system based on a pre-training model, including:
the acquisition module is used for acquiring geographic information, water quality data and meteorological data of a plurality of positions in the water system river basin area in a historical time period;
the prediction module is used for preprocessing the geographic information, the water quality data and the meteorological data, inputting a pre-trained water system drainage basin prediction model, and obtaining the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period;
the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area;
the evaluation module is used for evaluating abnormal risk levels of the plurality of positions according to geographic information, water quality data and meteorological data of the plurality of positions in the area in a future set time period;
the screening module is used for screening out abnormal points based on the evaluation result of the abnormal risk level;
the construction module is used for constructing the abnormal region according to the abnormal point positions;
the monitoring module is used for carrying out patrol on the abnormal area by using patrol equipment, monitoring the water area change in the abnormal area in real time and repeating the steps;
the judging module is used for judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment;
if the change trend is changed from decrease to increase, generating early warning information;
if the change trend is changed from increasing to decreasing, the patrol and monitoring are continued.
In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when running the computer program implementing the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon computer readable instructions executable by a processor to implement the method according to the first aspect.
Compared with the prior art, the intelligent water system river basin patrolling method based on the pre-training model,
obtaining geographic information, water quality data and meteorological data of a plurality of positions in a water system river basin area in a historical time period; after preprocessing the geographic information, the water quality data and the meteorological data, inputting a pre-trained water system river basin prediction model to obtain the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period; the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area; evaluating abnormal risk levels of the plurality of positions according to geographic information, water quality data and meteorological data of the plurality of positions in the area in a future set time period; screening out abnormal points based on the evaluation result of the abnormal risk level; constructing the abnormal region according to the abnormal point positions; the abnormal region is patrolled by using patrolling equipment, the water area change in the abnormal region is monitored in real time, and the steps are repeated; judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment; if the change trend is increased, generating and sending early warning information; and if the change trend is reduced, continuing to maintain the patrol and monitor. Therefore, the water system drainage basin prediction result has interpretability, can explain the cause of the prediction result and the internal rule of time sequence data fluctuation in the face of the topography condition of the complex water system drainage basin, and can improve the accuracy of monitoring a plurality of positions in the area compared with the traditional prediction method, thereby improving the efficiency and accuracy of water system drainage basin inspection.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 shows a flow chart of a water system river basin intelligent patrol method based on a pre-training model;
FIG. 2 shows a schematic diagram of a water system basin intelligent patrol system based on a pre-training model;
fig. 3 shows a schematic diagram of an electronic device provided by the application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.
In addition, the terms "first" and "second" etc. are used to distinguish different objects and are not used to describe a particular order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, fig. 1 is a flowchart of a water system basin intelligent patrol method based on a pre-training model according to an embodiment of the present application, including the following steps S101 to S107:
s101, geographic information, water quality data and meteorological data of a plurality of positions in a water system river basin area in a historical time period are acquired.
The historical time period can be set according to actual conditions.
S102, preprocessing the geographic information, the water quality data and the meteorological data, and inputting a pre-trained water system drainage basin prediction model to obtain the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period;
the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area.
Optionally, preprocessing the collected geographic information, water quality data and meteorological data, including data cleaning, missing value processing and feature extraction.
S103, evaluating abnormal risk levels of the multiple positions according to geographic information, water quality data and meteorological data of the multiple positions in the area in a future set time period;
in this embodiment, the evaluating the abnormal risk level of the plurality of locations according to the geographic information, the water quality data and the meteorological data of the plurality of locations in the area in the future set time period includes the following steps:
s301, preprocessing geographic information, water quality data and meteorological data of a plurality of positions in the area in a future set time period;
s302, respectively extracting a geographic information characteristic value, a water quality characteristic value and a meteorological characteristic value from geographic information, water quality data and meteorological data;
in some embodiments, this step may be implemented as: longitude and latitude, flow, water depth and soil fertility characteristics are extracted from geographic information, pH value, dissolved oxygen and COD characteristics are extracted from water quality data, and air temperature, rainfall and wind speed characteristics are extracted from meteorological data.
S303, determining the weight of each characteristic value; weight calculation can be performed, for example, by Analytic Hierarchy Process (AHP): and determining the weight of each feature according to factors such as importance, influence degree and the like of the feature.
S304, multiplying the geographic information characteristic value, the water quality characteristic value and the weather characteristic value by corresponding weights, and then carrying out weighted fusion to obtain a comprehensive risk value;
s305, establishing abnormal risk levels of different levels according to the comprehensive risk values.
In some embodiments it may be implemented as: the characteristics of the geographic information, the water quality data and the meteorological data can be multiplied by the corresponding weights respectively, and then weighted fusion is carried out according to the following formula:
such as: composite risk value = 0.3 geographical information eigenvalue + 0.3 water quality eigenvalue + 0.4 weather eigenvalue.
S104, screening out abnormal points based on the evaluation result of the abnormal risk level;
in this embodiment, the constructing the abnormal area according to the abnormal point location includes the following steps:
s401, collecting all known abnormal points;
s402, for each abnormal point position, determining the position of the abnormal point position in space and other related attributes, wherein the attributes can specifically comprise coordinates, numerical values and time stamps;
s403, selecting a K neighbor algorithm to construct an abnormal region according to the attribute of the abnormal point location, and setting the value of K;
s404, clustering the abnormal points into an abnormal area according to the selected K neighbor algorithm and the value of K, namely classifying the adjacent abnormal points into one type by using a clustering algorithm;
s405, visualizing the constructed abnormal region;
to better understand and analyze the anomaly, a map, chart, or other visualization tool may be used in particular, as well as in conjunction with a GIS system, to present the anomaly.
The application then proceeds to the following steps:
s105, constructing the abnormal region according to the abnormal point positions;
s106, carrying out patrol on the abnormal region by using patrol equipment, monitoring the water area change in the abnormal region in real time, and repeating the steps; the patrol equipment is preferably an unmanned aerial vehicle;
s107, judging the change trend of the area of the abnormal region at the current moment and the area of the abnormal region at the adjacent historical moment; if the change trend is increased, generating and sending early warning information; and if the change trend is reduced, continuing to maintain the patrol and monitor.
In some embodiments, the application can place the feature code at the specific position of the early warning information, if the position or the content of the feature code is changed, the early warning information is withdrawn, which is helpful for improving the accuracy of patrol and early warning. In order to further enhance the security of the early warning, the feature code of this embodiment is generated according to the serial number of the patrol equipment.
The following describes how to pre-train the water system drainage basin prediction model, specifically, the water system drainage basin prediction model may be pre-trained in the following manner, including steps S201 to S203:
s201, acquiring historical geographic information, water quality data and meteorological data of a plurality of positions in an area, and counting the historical geographic information, the water quality data and the meteorological data into time sequences within the same time interval to obtain historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area;
the method comprises the steps of collecting historical geographic information, water quality data and meteorological data of a plurality of positions in an area, setting time intervals, and statistically counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time intervals according to time sequences to obtain initial multi-element time sequence data, wherein the multi-element time sequence data are historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area, and specifically comprises the following steps of:
determining a time interval: the time interval is determined according to the time span of the data and the time granularity required to be counted, and can be set as hours, days, weeks or months, etc. Time-aligning the original data: for the historical geographic information, water quality data and meteorological data of each position, aligning the historical geographic information, the water quality data and the meteorological data according to time intervals, namely filling the data into corresponding time points; combining data of multiple clients: and merging the data of all the positions according to the time sequence to obtain a multi-element time sequence data set, wherein each time point comprises the historical geographic information, the water quality data and the air image data of each position.
S202, after the historical geographic information, water quality data and meteorological data samples are subjected to the preprocessing, the historical geographic information, water quality data and meteorological data samples are converted into geographic information, water quality data and meteorological data supervision data; specifically, the method comprises the following steps: and aggregating the previous variables in the historical geographic information, the water quality data and the meteorological data samples as input variables of the model, and the latter variables as output of the model to obtain the geographic information, the water quality data and the meteorological data supervision data.
S203, setting an objective function, inputting the geographic information, the water quality data and the meteorological data into the interpretable graphic neural network for training, and obtaining the water system river basin prediction model after reaching a preset training cut-off condition.
Specifically, the interpretable graph neural network includes the following components:
node feature extractor: for extracting features from geographical information, water quality data and meteorological data and representing them as feature vectors for the nodes.
An adjacency modeler: for modeling adjacency between geographical information, water quality data and meteorological data supervised data.
Graph convolution neural network: for learning the relationship between the node feature vector and the adjacency matrix and extracting useful information therefrom.
Full tie layer: and the node characteristic vector is used for mapping the node characteristic vector output by the graph convolution neural network to a final prediction result.
Activation function: for non-linearly transforming the output of the fully connected layers to produce a final prediction result.
Loss function: the method is used for measuring the difference between the predicted result and the actual result and optimizing the weight of the neural network.
An optimizer: for optimizing the weights of the neural network based on the result of the loss function.
In order to provide real-time and accurate prediction for an area, the application provides a water system drainage basin intelligent patrol method based on a pre-training model.
The method provided by the embodiment of the application has the following beneficial effects:
according to the intelligent water system drainage basin patrolling method based on the pre-training model, geographic information, water quality data and meteorological data of a plurality of positions in a water system drainage basin area in a historical time period are obtained; after preprocessing the geographic information, the water quality data and the meteorological data, inputting a pre-trained water system river basin prediction model to obtain the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period; the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area; evaluating abnormal risk levels of the plurality of positions according to geographic information, water quality data and meteorological data of the plurality of positions in the area in a future set time period; screening out abnormal points based on the evaluation result of the abnormal risk level; constructing the abnormal region according to the abnormal point positions; the abnormal region is patrolled by using patrolling equipment, the water area change in the abnormal region is monitored in real time, and the steps are repeated; judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment; if the change trend is increased, generating and sending early warning information; and if the change trend is reduced, continuing to maintain the patrol and monitor. Therefore, the water system drainage basin prediction result has interpretability, can explain the cause of the prediction result and the internal rule of time sequence data fluctuation in the face of the topography condition of the complex water system drainage basin, and can improve the accuracy of monitoring a plurality of positions in the area compared with the traditional prediction method, thereby improving the efficiency and accuracy of water system drainage basin inspection.
In the embodiment, the application provides the intelligent water system drainage basin patrolling method based on the pre-training model, and correspondingly, the intelligent water system drainage basin patrolling system based on the pre-training model. The intelligent water system drainage basin inspection system based on the pre-training model can implement the intelligent water system drainage basin inspection method, and the intelligent water system drainage basin inspection system based on the pre-training model can be realized in a mode of software, hardware or combination of software and hardware. For example, the pretrained model-based watershed intelligent patrol system may include integrated or separate functional modules or units to perform the corresponding steps in the methods described above, including:
an acquisition module 101 for acquiring geographical information, water quality data, and meteorological data of a plurality of locations within a water system basin area over a historical period of time;
the prediction module 102 is configured to pre-process the geographic information, the water quality data and the meteorological data, and then input a pre-trained water system drainage basin prediction model to obtain geographic information, water quality data and meteorological data of a plurality of positions in the area within a future set time period;
the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area;
an evaluation module 103, configured to evaluate abnormal risk levels of a plurality of locations in the area according to geographic information, water quality data, and weather data of the plurality of locations in a future set period of time;
a screening module 104, configured to screen out an abnormal point location based on the evaluation result of the abnormal risk level;
a construction module 105, configured to construct the abnormal region according to the abnormal point location;
the monitoring module 106 is configured to patrol the abnormal area by using a patrol device, monitor a water area change in the abnormal area in real time, and repeat the above steps;
a judging module 107, configured to judge a change trend of the abnormal area at the current time and the abnormal area at the adjacent historical time;
if the change trend is changed from decrease to increase, generating early warning information;
if the change trend is changed from increasing to decreasing, the patrol and monitoring are continued.
In some embodiments of the application, the system further comprises: the model training module pre-trains the water system watershed prediction model according to the following mode:
acquiring historical geographic information, water quality data and meteorological data of a plurality of positions in an area, and counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time interval to obtain historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area;
after the historical geographic information, water quality data and meteorological data samples are subjected to the preprocessing, the historical geographic information, water quality data and meteorological data samples are converted into geographic information, water quality data and meteorological data supervision data;
and setting an objective function, inputting the geographic information, the water quality data and the meteorological data into the interpretable graphic neural network for training, and obtaining the water system river basin prediction model after reaching a preset training cut-off condition.
In some embodiments of the present application, the apparatus further comprises a model training module for converting the historical geographic information, water quality data, and meteorological data samples into geographic information, water quality data, and meteorological data supervised data, comprising:
and aggregating the previous variables in the historical geographic information, the water quality data and the meteorological data samples as input variables of the model, and the latter variables as output of the model to obtain the geographic information, the water quality data and the meteorological data supervision data.
In some embodiments of the present application, the constructing the anomaly region according to the anomaly point location includes:
collecting all known abnormal points;
for each anomaly point location, determining its position in space and other related attributes, including coordinates, values and time stamps;
selecting a K neighbor algorithm to construct an abnormal region according to the attribute of the abnormal point location, and setting the value of K;
clustering the abnormal point positions into abnormal areas according to the selected K neighbor algorithm and the value of K, namely classifying the adjacent abnormal point positions into one type by using a clustering algorithm;
and visualizing the constructed abnormal region.
In some embodiments of the present application, feature codes are placed at specific positions of the early warning information, and if the positions or contents of the feature codes are changed, the early warning information is withdrawn.
In some embodiments of the application, the signature is generated from a serial number of the patrolling device.
In some embodiments of the present application, the evaluating the abnormal risk level of the plurality of locations according to the geographic information, the water quality data and the weather data of the plurality of locations in the area in the future set time period includes:
preprocessing geographic information, water quality data and meteorological data of a plurality of positions in the area in a future set time period;
extracting a geographic information characteristic value, a water quality characteristic value and a meteorological characteristic value from geographic information, water quality data and meteorological data respectively;
determining the weight of each characteristic value;
multiplying the geographic information characteristic value, the water quality characteristic value and the meteorological characteristic value by corresponding weights, and then carrying out weighted fusion to obtain a comprehensive risk value;
and establishing abnormal risk levels of different levels according to the comprehensive risk values.
The water system watershed intelligent patrol system based on the pre-training model and the water system watershed intelligent patrol method based on the pre-training model provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the same inventive concept.
The embodiment of the application also provides an electronic device corresponding to the method provided by the previous embodiment, wherein the electronic device can be an electronic device for a client, such as a mobile phone, a notebook computer, a tablet computer, a desktop computer and the like, so as to execute the prediction method.
Referring to fig. 3, a schematic diagram of an electronic device according to some embodiments of the present application is shown. As shown in fig. 3, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, the processor 200, the communication interface 203 and the memory 201 being connected by the bus 202; the memory 201 stores a computer program that can be executed on the processor 200, and when the processor 200 executes the computer program, the phishing mail tracing method provided by any one of the foregoing embodiments of the present application is executed.
The memory 201 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 203 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 202 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. The memory 201 is configured to store a program, and the processor 200 executes the program after receiving an execution instruction, and the phishing mail tracing method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 200 or implemented by the processor 200.
The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 200 or by instructions in the form of software. The processor 200 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201, and in combination with its hardware, performs the steps of the above method.
The electronic equipment provided by the embodiment of the application and the prediction method provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the electronic equipment based on the same inventive concept.
The present application also provides a computer readable storage medium corresponding to the prediction method provided in the foregoing embodiment, on which a computer program (i.e. a program product) is stored, which when executed by a processor, performs the prediction method provided in any of the foregoing embodiments.
It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.
The computer-readable storage medium provided by the above-described embodiments of the present application has the same advantageous effects as the method adopted, operated or implemented by the application program stored therein, for the same inventive concept as the prediction method provided by the embodiments of the present application.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application, and are intended to be included within the scope of the appended claims and description.

Claims (7)

1. The intelligent water system river basin patrolling method based on the pre-training model is characterized by comprising the following steps of:
obtaining geographic information, water quality data and meteorological data of a plurality of positions in a water system river basin area in a historical time period;
after preprocessing the geographic information, the water quality data and the meteorological data, inputting a pre-trained water system river basin prediction model to obtain the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period;
the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area;
evaluating abnormal risk levels of the plurality of positions according to geographic information, water quality data and meteorological data of the plurality of positions in the area in a future set time period;
screening out abnormal points based on the evaluation result of the abnormal risk level;
constructing an abnormal region according to the abnormal point positions;
the abnormal region is patrolled by using patrolling equipment, the water area change in the abnormal region is monitored in real time, and the steps are repeated;
judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment;
if the change trend is increased, generating and sending early warning information;
if the change trend is reduced, continuing to maintain the patrol and monitor;
the method pre-trains the water system river basin prediction model according to the following mode:
acquiring historical geographic information, water quality data and meteorological data of a plurality of positions in an area, and counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time interval to obtain historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area;
the method comprises the steps of collecting historical geographic information, water quality data and meteorological data of a plurality of positions in an area, setting time intervals, and statistically counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time intervals according to time sequences to obtain initial multi-element time sequence data, wherein the multi-element time sequence data are historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area, and specifically comprises the following steps of:
determining a time interval: determining a time interval according to the time span of the data and the time granularity to be counted, wherein the time interval can be set as an hour, a day, a week or a month; time-aligning the original data: for the historical geographic information, water quality data and meteorological data of each position, aligning the historical geographic information, the water quality data and the meteorological data according to time intervals, namely filling the data into corresponding time points; combining data of multiple clients: combining the data of all the positions according to the time sequence to obtain a multi-element time sequence data set, wherein each time point comprises historical geographic information, water quality data and meteorological data of each position;
after the historical geographic information, water quality data and meteorological data samples are subjected to the preprocessing, the historical geographic information, water quality data and meteorological data samples are converted into geographic information, water quality data and meteorological data supervision data;
setting an objective function, inputting the geographic information, the water quality data and the meteorological data into the interpretable graphic neural network for training, and obtaining the water system river basin prediction model after reaching a preset training cut-off condition;
the method converts the historical geographic information, water quality data and meteorological data samples into geographic information, water quality data and meteorological data supervised data, and comprises the following steps:
the former variables in the historical geographic information, the water quality data and the meteorological data samples are used as input variables of the model, and the latter variables are used as output of the model to be aggregated, so that geographic information, water quality data and meteorological data supervision data are obtained;
the constructing the abnormal region according to the abnormal point location includes:
collecting all known abnormal points;
for each anomaly point location, determining its position in space and other related attributes, including coordinates, values and time stamps;
selecting a K neighbor algorithm to construct an abnormal region according to the attribute of the abnormal point location, and setting the value of K;
clustering the abnormal point positions into abnormal areas according to the selected K neighbor algorithm and the value of K, namely classifying the adjacent abnormal point positions into one type by using a clustering algorithm;
and visualizing the constructed abnormal region.
2. The method of claim 1, wherein the feature code is placed at a specific location of the pre-warning information, and the pre-warning information is withdrawn if the location or content of the feature code is altered.
3. The method of claim 2, wherein the signature is generated based on a serial number of the patrolling device.
4. The method of claim 1, wherein evaluating the abnormal risk level for the plurality of locations based on the geographic information, the water quality data, and the weather data for the plurality of locations within the area over a future set period of time comprises:
preprocessing geographic information, water quality data and meteorological data of a plurality of positions in the area in a future set time period;
extracting a geographic information characteristic value, a water quality characteristic value and a meteorological characteristic value from geographic information, water quality data and meteorological data respectively;
determining the weight of each characteristic value;
multiplying the geographic information characteristic value, the water quality characteristic value and the meteorological characteristic value by corresponding weights, and then carrying out weighted fusion to obtain a comprehensive risk value;
and establishing abnormal risk levels of different levels according to the comprehensive risk values.
5. Water system river basin wisdom system of patrolling and protecting based on training model in advance, characterized in that includes:
the acquisition module is used for acquiring geographic information, water quality data and meteorological data of a plurality of positions in the water system river basin area in a historical time period;
the prediction module is used for preprocessing the geographic information, the water quality data and the meteorological data, inputting a pre-trained water system drainage basin prediction model, and obtaining the geographic information, the water quality data and the meteorological data of a plurality of positions in the area in a future set time period;
the water system river basin prediction model is obtained by training an interpretable graphic neural network through historical geographic information, water quality data and meteorological data samples of a plurality of positions in an area;
the evaluation module is used for evaluating abnormal risk levels of the plurality of positions according to geographic information, water quality data and meteorological data of the plurality of positions in the area in a future set time period;
the screening module is used for screening out abnormal points based on the evaluation result of the abnormal risk level;
the construction module is used for constructing an abnormal region according to the abnormal point positions;
the monitoring module is used for carrying out patrol on the abnormal area by using patrol equipment, monitoring the water area change in the abnormal area in real time and repeating the steps;
the judging module is used for judging the change trend of the abnormal area at the current moment and the abnormal area at the adjacent historical moment;
if the change trend is changed from decrease to increase, generating early warning information;
if the change trend is changed from increasing to decreasing, continuing to maintain the patrol and monitor;
the model training module is used for training the water system river basin prediction model in advance according to the following mode:
acquiring historical geographic information, water quality data and meteorological data of a plurality of positions in an area, and counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time interval to obtain historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area;
the method comprises the steps of collecting historical geographic information, water quality data and meteorological data of a plurality of positions in an area, setting time intervals, and statistically counting the historical geographic information, the water quality data and the meteorological data into time sequences in the same time intervals according to time sequences to obtain initial multi-element time sequence data, wherein the multi-element time sequence data are historical geographic information, water quality data and meteorological data samples of the plurality of positions in the area, and specifically comprises the following steps of:
determining a time interval: determining a time interval according to the time span of the data and the time granularity to be counted, wherein the time interval can be set as an hour, a day, a week or a month; time-aligning the original data: for the historical geographic information, water quality data and meteorological data of each position, aligning the historical geographic information, the water quality data and the meteorological data according to time intervals, namely filling the data into corresponding time points; combining data of multiple clients: combining the data of all the positions according to the time sequence to obtain a multi-element time sequence data set, wherein each time point comprises historical geographic information, water quality data and meteorological data of each position;
after the historical geographic information, water quality data and meteorological data samples are subjected to the preprocessing, the historical geographic information, water quality data and meteorological data samples are converted into geographic information, water quality data and meteorological data supervision data;
setting an objective function, inputting the geographic information, the water quality data and the meteorological data into the interpretable graphic neural network for training, and obtaining the water system river basin prediction model after reaching a preset training cut-off condition;
wherein converting the historical geographic information, water quality data and meteorological data samples into geographic information, water quality data and meteorological data supervised data comprises:
the former variables in the historical geographic information, the water quality data and the meteorological data samples are used as input variables of the model, and the latter variables are used as output of the model to be aggregated, so that geographic information, water quality data and meteorological data supervision data are obtained;
the constructing the abnormal region according to the abnormal point location includes:
collecting all known abnormal points;
for each anomaly point location, determining its position in space and other related attributes, including coordinates, values and time stamps;
selecting a K neighbor algorithm to construct an abnormal region according to the attribute of the abnormal point location, and setting the value of K;
clustering the abnormal point positions into abnormal areas according to the selected K neighbor algorithm and the value of K, namely classifying the adjacent abnormal point positions into one type by using a clustering algorithm;
and visualizing the constructed abnormal region.
6. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor runs the computer program to implement the method according to any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon computer readable instructions executable by a processor to implement the method of any one of claims 1 to 4.
CN202310884749.6A 2023-07-19 2023-07-19 Water system river basin intelligent patrol method and device based on pre-training model Active CN116703004B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310884749.6A CN116703004B (en) 2023-07-19 2023-07-19 Water system river basin intelligent patrol method and device based on pre-training model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310884749.6A CN116703004B (en) 2023-07-19 2023-07-19 Water system river basin intelligent patrol method and device based on pre-training model

Publications (2)

Publication Number Publication Date
CN116703004A CN116703004A (en) 2023-09-05
CN116703004B true CN116703004B (en) 2023-09-29

Family

ID=87843463

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310884749.6A Active CN116703004B (en) 2023-07-19 2023-07-19 Water system river basin intelligent patrol method and device based on pre-training model

Country Status (1)

Country Link
CN (1) CN116703004B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117195135B (en) * 2023-11-01 2024-02-27 潍坊德瑞生物科技有限公司 Water pollution anomaly traceability detection method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109844832A (en) * 2016-12-30 2019-06-04 同济大学 A kind of multi-modal accident detection method based on journey time distribution
CN109858647A (en) * 2018-12-21 2019-06-07 河海大学 A kind of Regional Flooding Hazard Risk Assessment and predictor method coupling GIS and GBDT algorithm
CN109991685A (en) * 2019-04-03 2019-07-09 北京市天元网络技术股份有限公司 A kind of precipitation prediction technique and device based on more LSTM Model Fusions
CN115410114A (en) * 2022-08-02 2022-11-29 南京熊猫电子股份有限公司 Urban rail flood prevention early warning method and system based on multiple characteristics
CN116308952A (en) * 2023-03-08 2023-06-23 浪潮智慧科技有限公司 Water quality monitoring method and device based on unmanned ship

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909722B (en) * 2017-02-10 2019-07-26 广西壮族自治区气象减灾研究所 A kind of accurate inversion method of large area of temperature near the ground
US10802136B2 (en) * 2017-07-19 2020-10-13 Rezatec Limited Water network monitoring system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109844832A (en) * 2016-12-30 2019-06-04 同济大学 A kind of multi-modal accident detection method based on journey time distribution
CN109858647A (en) * 2018-12-21 2019-06-07 河海大学 A kind of Regional Flooding Hazard Risk Assessment and predictor method coupling GIS and GBDT algorithm
CN109991685A (en) * 2019-04-03 2019-07-09 北京市天元网络技术股份有限公司 A kind of precipitation prediction technique and device based on more LSTM Model Fusions
CN115410114A (en) * 2022-08-02 2022-11-29 南京熊猫电子股份有限公司 Urban rail flood prevention early warning method and system based on multiple characteristics
CN116308952A (en) * 2023-03-08 2023-06-23 浪潮智慧科技有限公司 Water quality monitoring method and device based on unmanned ship

Also Published As

Publication number Publication date
CN116703004A (en) 2023-09-05

Similar Documents

Publication Publication Date Title
Dadhich et al. Spatio-temporal urban growth modeling of Jaipur, India
Feng et al. Incorporation of spatial heterogeneity-weighted neighborhood into cellular automata for dynamic urban growth simulation
CN116703004B (en) Water system river basin intelligent patrol method and device based on pre-training model
Mubea et al. Assessing application of Markov chain analysis in predicting land cover change: a case study of Nakuru municipality
CN109636171A (en) A kind of comprehensive diagnos and risk evaluating method that regional vegetation restores
CN106373070A (en) Four-prevention method for responding to city rainstorm waterlogging
CN114663764A (en) Method, device, medium and terminal equipment for zoning soil environment quality of cultivated land
Feng et al. Calibrating nonparametric cellular automata with a generalized additive model to simulate dynamic urban growth
CN115730684A (en) Air quality detection system based on LSTM-CNN model
CN114881381A (en) Urban ponding water level prediction method and system based on improved convolutional neural network
Hashemi Forecasting El Niño and La Niña using spatially and temporally structured predictors and a convolutional neural network
CN110633853A (en) Training method and device of space-time data prediction model and electronic equipment
CN117332291B (en) Distributed photovoltaic-oriented regional resource monitoring layout method and system
CN116758707B (en) Geological disaster monitoring system and method based on big data
CN116340863B (en) Air pollutant prediction method and device, electronic equipment and readable storage medium
CN117091675A (en) Dam water level monitoring and early warning method, system, electronic equipment and storage medium
CN115600047B (en) Small watershed surface average rainfall measurement and calculation method and system based on grid analysis
Zhang et al. Modeling and mapping high water table for a coastal region in Florida using Lidar DEM data
CN110968929A (en) Wind power plant wind speed prediction method and device and electronic equipment
CN113901043A (en) Pollution source intelligent supervision and data fusion analysis method and system
CN113496305A (en) Data processing method and device
CN117058888B (en) Traffic big data processing method and system thereof
CN117434624B (en) Strong convection weather identification and development prejudgment method based on semantic segmentation
Balamurugan et al. Implementation of Effective Rainfall Forecast Model using Machine Learning
Benchelha et al. Modeling Dynamic Urban Growth Using Cellular Automata and Geospatial Technique: Case of Casablanca in Morocco

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