CN113284006A - Independent water supply network metering and partitioning method based on graph convolution - Google Patents
Independent water supply network metering and partitioning method based on graph convolution Download PDFInfo
- Publication number
- CN113284006A CN113284006A CN202110525659.9A CN202110525659A CN113284006A CN 113284006 A CN113284006 A CN 113284006A CN 202110525659 A CN202110525659 A CN 202110525659A CN 113284006 A CN113284006 A CN 113284006A
- Authority
- CN
- China
- Prior art keywords
- node
- water supply
- nodes
- supply network
- water
- 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.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000000638 solvent extraction Methods 0.000 title description 22
- 238000005192 partition Methods 0.000 claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 11
- 239000006185 dispersion Substances 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- 238000013316 zoning Methods 0.000 claims description 5
- 230000004931 aggregating effect Effects 0.000 claims description 2
- 238000006116 polymerization reaction Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
- G06F17/153—Multidimensional correlation or convolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computational Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Pipeline Systems (AREA)
Abstract
A water supply network independent metering partition method based on graph convolution comprises the following steps: step 1: for a water supply network to be partitioned containing n water demand nodes, establishing an initial graph G containing the self characteristics V of the nodes and the relation L between the nodes0=(V0L); step 2: k times convolution is carried out on the initial image to establish a k layer image Gk=(VkL); and step 3: according to VkPerforming unsupervised partition training on a water supply network to form m independent metering areas; and 4, step 4: DMA (direct memory access) for outputting independent metering partition results1,DMA2,…,DMAm. The invention solves the problem of isolated water demand node characteristics when the water supply network is partitioned in the prior art, and realizes the characteristic interaction of the water demand nodes of the water supply network, thereby realizing the automatic independent metering partition with high reliability of the water supply network.
Description
Technical Field
The invention relates to the field of municipal engineering and urban water supply networks, in particular to a water supply network independent metering and partitioning method based on graph convolution.
Background
The water supply management systems (WMSs) are used for distribution and scheduling of urban water supply resources and alarming and locating of abnormal situations, however, the operation of the water supply distribution system is difficult to achieve due to the large and complicated urban water supply network. The water supply network independent metering (DMA) technology is that the water supply network is divided into a plurality of independent metering areas for metering, so that leakage monitoring, water pressure optimization and water supply balance are realized, the technology provides great convenience for management of a water supply management system, the leakage rate of a pipe network is reduced, and the service life of the pipe is prolonged. However, in the DMA partitioning of the existing water supply network, many factors such as the length of a pipe section, the node relationship, the node water consumption and the like need to be considered, objective DMA partitioning is difficult to achieve by using the traditional manual partitioning method, and how to perform reasonable DMA partitioning on the water supply network becomes one of the key problems to be solved urgently in the industry.
In the prior art, methods related to independent metering and partitioning of a water supply network are limited, a leakage detection method for the independent metering and partitioning combined with a leakage recorder is disclosed in Chinese invention patent CN200910238223.0, and a water quantity component analysis method for the independent metering and partitioning in an urban water supply system is disclosed in Chinese invention patent CN201811181755.0, however, the method realizes the independent metering and partitioning of the water supply network through manpower, and has the following two problems: firstly, the independent metering and partitioning of the water supply network are manually realized, so that the partitioning of the water supply network is unreasonable; and secondly, the difficulty of large-scale water supply networks is high by manually realizing independent metering and partitioning of the water supply networks. In addition, chinese patent CN201911300313.8 discloses a DMA automatic partitioning method for water supply network based on graph partitioning, and chinese patent CN201810864065.9 discloses a method and system for assisting DMA partitioning for water supply network based on graph theory, however, such method considers the characteristics of water demand nodes in isolation when automatic independent metering partitioning, and the interaction of the characteristics of water demand nodes of water supply network cannot be realized, resulting in unreasonable partitioning result.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a water supply network independent metering partition method based on graph convolution, which aims to solve the problem of isolated water demand node characteristics when a water supply network is partitioned in the prior art background, and realize the characteristic interaction of water demand nodes of the water supply network, thereby realizing the automatic independent metering partition with high reliability of the water supply network.
In order to achieve the purpose, the invention adopts the following technical scheme:
a water supply network independent metering partition method based on graph convolution comprises the following steps:
step 1: for a water supply network to be partitioned containing n water demand nodes, establishing an initial graph G containing the self characteristics V of the nodes and the relation L between the nodes0=(V0,L);
Step 2: k times convolution is carried out on the initial image to establish a k layer image Gk=(Vk,L);
And step 3: according to VkPerforming unsupervised partition training on a water supply network to form m independent metering areas;
and 4, step 4: DMA (direct memory access) for outputting independent metering partition results1,DMA2,…,DMAm。
Further, in the step 1, the node P for containing n water-demand nodes1,P2,…,PnThe regional water supply network to be independently metered collects the water consumption C ═ C of each node1,C2,…,CnElevation E ═ E1,E2,…,EnAnd the lateral relative position X ═ X of the node in the network of tubes1,X2,…,XnY is the longitudinal relative position with the plane1,Y2,…,YnRespectively standardizing the four items of data, combining to obtain self characteristics V of the water-requiring nodes, namely { C, E, X, Y }, recording the connection relationship among the nodes of the pipe network to form an adjacency matrix L, and finally establishing a graph G containing the self characteristics of the nodes and the relationship among the nodes0=(V0L), and defining the graph as an initial graph.
Further, in the step 2, k times of convolution is carried out on the initial image to establish a k-th layer image Gk=(VkL), comprising the steps of:
step 2.1: for any water-requiring node, carrying out characteristic data sampling on the adjacent node according to the adjacency matrix L, and recording the self characteristics of the nodeAnd the characteristics of q nodes adjacent to it
Step 2.2: for the water-requiring node, aggregating according to the characteristics of the node itself and q nodes adjacent to the node itself to form the node characteristics of the next layer:
step 2.3: for each water-requiring node, calculating the characteristic value of the node at the next layer according to the step 2.1 and the step 2.2, and establishing a next layer graph G containing the relation between all node characteristics and the nodes0+1=(V0+1,L);
Step 2.4: repeating the steps 2.1 to 2.3, carrying out sampling polymerization for k times, and establishing a k layer graph Gk=(VkL), the graph shows that each water-requiring node contains k-order neighborhood characteristic information.
Further, in said step 3, according to VkThe unsupervised partition training is carried out on the water supply network to form m independent metering areas, and the unsupervised partition training method comprises the following steps of:
step 3.1: establishing a random parameter matrixAccording to VkObtaining a water demand node feature matrix
Step 3.2: calculating the node classification prediction probability and classifying the water-demand nodes into m independent metering areas according to the maximum probability:
Class(DMA1,DMA2,…,DMAm)=max(A*w)
Step 3.4: calculating an evaluation function J of the independent metering partition dispersion:
wherein N isiRepresenting the number of water demand nodes in the ith independent metering area;
step 3.5: and optimizing the parameter matrix w by using gradient descent and taking the reduction dispersion evaluation function J as a target until the model converges to obtain the optimal solution of w and obtain an independent metering partition result in the optimal solution.
The beneficial effects of the invention are as follows: the method comprises the steps of collecting four data of water consumption, altitude, transverse position and longitudinal position of water-requiring nodes of the water supply network to form node characteristics, recording connection relations among the nodes, carrying out convolution on the node characteristics according to the node connection relations, giving weights to the node characteristics after convolution, and carrying out independent metering and zoning on the water supply network as a zoning evaluation basis, so that a plurality of independent metering areas are formed. The proposed method for enabling the water-demand nodes to contain the characteristics of the neighborhood nodes by using graph convolution has great reference value for independent metering subareas of the water supply network.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a water supply pipe network in market A according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a graph convolution according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a partitioning result according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 to 4, a water supply network independent metering partition method based on graph convolution comprises the following steps:
step 1: and collecting the relationship between the node characteristics and the nodes to establish an initial graph.
As shown in fig. 2, a water supply network in city a has 183 main water supply nodes and 275 pipe sections, and the water consumption C ═ C of each node P is collected1,C2,…,C183Elevation E ═ E1,E2,…,E183And the lateral relative position X ═ X of the node in the network of tubes1,X2,…,X183Y is the longitudinal relative position with the plane1,Y2,…,Y183The characteristics V of the water demand nodes are obtained after standardization, wherein the characteristics V is { C, E, X and Y } are shown in table 1, and the table 1 is characteristic data of the water demand nodes of the water supply network;
table 1 in addition, the connection relationship between the nodes of the pipe network is recorded to form an adjacency matrix L:
further establishing a graph G containing the self characteristics of the nodes and the relationship between the nodes0=(V0L), and defining the graph as an initial graph.
Step 2: the initial map is subjected to a map convolution.
Performing convolution 3 times on the initial diagram of a water supply network in the city A to establish a third layer diagram G3=(V3L) to the water demand node P in the pipe network1For example, the convolution process is shown in fig. 3, and specifically includes the following steps:
step 2.1: for any water-requiring node, carrying out characteristic data sampling on the adjacent node according to the adjacency matrix L, and recording the node selfPhysical characteristicsAnd the characteristics of q nodes adjacent to itWith water demand node P1For example, record the characteristics of the node itself and 2 nodes P adjacent to the node itself8、P9Is characterized in that the characteristics of (1) are shown in Table 2, and the water-requiring node P in Table 21Own and adjacent node characteristics;
TABLE 2
Step 2.2: for the water-requiring node, the characteristics of the node and the adjacent nodes are aggregated to form the characteristics of the node at the next layer:
Step 2.3: for each water demand node, calculating the characteristic value of the node at the next layer according to the step 2.1 and the step 2.2, taking a certain water supply network in the city A as an example, calculating to obtain a first layer characteristic V of the water demand node1As shown in Table 3, Table 3 shows the first layer characteristic data of a water supply network in market A;
TABLE 3
Establishing a first-level graph G containing all node characteristics and relationships between nodes1=(V1,L);
Step 2.4: repeating the steps 2.1 to 2.3, carrying out sampling aggregation on the node characteristics of a certain water supply pipe network in the city A for 3 times, and establishing a third layer graph G3=(V3L), the graph shows that each water-requiring node contains 3-order neighborhood characteristics of the node, and the characteristic V of the water-requiring node after 3 times of convolution3As shown in Table 4, the data of the third layer of a water supply network in market A are shown in Table 4.
TABLE 4
And step 3: and training and partitioning the water supply network.
According to V3The method comprises the following steps of carrying out unsupervised partition training on a water supply network to form 5 independent metering areas, and specifically comprising the following steps:
step 3.1: establishing a random parameter matrixAccording to V3Obtaining a water demand node feature matrix
Step 3.2: calculating the classification prediction probability A w of the water demand nodes of the water supply network is shown in Table 5, wherein the Table 5 shows the classification prediction probability of a certain water supply network node in the city A:
TABLE 5
Classifying the nodes according to the maximum probability of each node to form 5 independent metering areas as shown in table 6, wherein the table 6 is a partition result of a certain water supply network node in city A;
TABLE 6
Step 3.3: each time of calculationCenter of independent metering zoneAs shown in table 7, table 7 is the independent metering zone center position;
table 7 step 3.4: calculating an evaluation function J of the independent metering partition dispersion:
wherein N isiRepresenting the number of water-demand nodes in the ith independent metering area, and calculating to obtain the dispersion evaluation degree of a water supply network in the city A through the initial independent metering subarea, wherein the dispersion evaluation degree is 0.284;
step 3.5: optimizing a parameter matrix w by using gradient descent with a reduced dispersion evaluation function J as a target until a model converges, wherein the optimization process of the partition dispersion evaluation function J is shown in a table 8, and the table 8 is the optimization process of the partition dispersion evaluation function of the independent metering of a certain water supply network in the city A;
TABLE 8
The final result of the partition of the water demand nodes of a water supply network in city A is shown in Table 9, and Table 9 shows the final result of the partition of the nodes of the water supply network in city A.
TABLE 9
And 4, step 4: and outputting a partitioning result.
Taking a water supply network in market A as an example, the final partition result DMA of the water supply network1,DMA2,…,DMA5As shown in fig. 4。
The embodiments described in this specification are merely illustrative of implementations of the inventive concepts, which are intended for purposes of illustration only. The scope of the present invention should not be construed as being limited to the particular forms set forth in the examples, but rather as being defined by the claims and the equivalents thereof which can occur to those skilled in the art upon consideration of the present inventive concept.
Claims (4)
1. A water supply network independent metering zoning method based on graph convolution, which is characterized by comprising the following steps:
step 1: for a water supply network to be partitioned containing n water demand nodes, establishing an initial graph G containing the self characteristics V of the nodes and the relation L between the nodes0=(V0,L);
Step 2: k times convolution is carried out on the initial image to establish a k layer image Gk=(Vk,L);
And step 3: according to VkPerforming unsupervised partition training on a water supply network to form m independent metering areas;
and 4, step 4: DMA (direct memory access) for outputting independent metering partition results1,DMA2,…,DMAm。
2. The method as claimed in claim 1, wherein in step 1, the water supply network comprises n water demand nodes P1,P2,…,PnThe regional water supply network to be independently metered collects the water consumption C ═ C of each node1,C2,…,CnElevation E ═ E1,E2,…,EnAnd the lateral relative position X ═ X of the node in the network of tubes1,X2,…,XnY is the longitudinal relative position with the plane1,Y2,…,YnRespectively standardizing the four items of data, combining to obtain self characteristics V of the water-requiring nodes, namely { C, E, X, Y }, recording the connection relationship among the nodes of the pipe network to form an adjacency matrix L, and finally establishing a graph G containing the self characteristics of the nodes and the relationship among the nodes0=(V0,L) And defining the graph as an initial graph.
3. The method as claimed in claim 2, wherein in step 2, k convolutions are performed on the initial graph to establish a k-th layer graph Gk=(VkL), comprising the steps of:
step 2.1: for any water-requiring node, carrying out characteristic data sampling on the adjacent node according to the adjacency matrix L, and recording the self characteristics of the nodeAnd the characteristics of q nodes adjacent to it
Step 2.2: for the water-requiring node, aggregating according to the characteristics of the node itself and q nodes adjacent to the node itself to form the node characteristics of the next layer:
step 2.3: for each water-requiring node, calculating the characteristic value of the node at the next layer according to the step 2.1 and the step 2.2, and establishing a next layer graph G containing the relation between all node characteristics and the nodes0+1=(V0+1,L);
Step 2.4: repeating the steps 2.1 to 2.3, carrying out sampling polymerization for k times, and establishing a k layer graph Gk=(VkL), the graph shows that each water-requiring node contains k-order neighborhood characteristic information.
4. The graph convolution-based water supply network independent metering zoning method according to claim 3, wherein in the step 3, the water supply network independent metering zoning method is based on VkThe unsupervised partition training is carried out on the water supply network to form m independent metering areas, and the unsupervised partition training method comprises the following steps of:
step 3.1: establishing a random parameter matrixAccording to VkObtaining a water demand node feature matrix
Step 3.2: calculating the node classification prediction probability and classifying the water-demand nodes into m independent metering areas according to the maximum probability:
Class(DMA1,DMA2,…,DMAm)=max(A*w)
Step 3.4: calculating an evaluation function J of the independent metering partition dispersion:
wherein N isiRepresenting the number of water demand nodes in the ith independent metering area;
step 3.5: and optimizing the parameter matrix w by using gradient descent and taking the reduction dispersion evaluation function J as a target until the model converges to obtain the optimal solution of w and obtain an independent metering partition result in the optimal solution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110525659.9A CN113284006A (en) | 2021-05-14 | 2021-05-14 | Independent water supply network metering and partitioning method based on graph convolution |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110525659.9A CN113284006A (en) | 2021-05-14 | 2021-05-14 | Independent water supply network metering and partitioning method based on graph convolution |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113284006A true CN113284006A (en) | 2021-08-20 |
Family
ID=77278981
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110525659.9A Pending CN113284006A (en) | 2021-05-14 | 2021-05-14 | Independent water supply network metering and partitioning method based on graph convolution |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113284006A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807012A (en) * | 2021-09-14 | 2021-12-17 | 杭州莱宸科技有限公司 | Water supply network division method based on connection strengthening |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214549A (en) * | 2018-08-01 | 2019-01-15 | 武汉众智鸿图科技有限公司 | A kind of water supply network auxiliary DMA partition method and system based on graph theory |
CN111080483A (en) * | 2019-12-17 | 2020-04-28 | 上海市城市建设设计研究总院(集团)有限公司 | DMA automatic partitioning method for water supply network based on graph division |
CN112464057A (en) * | 2020-11-18 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Network data classification method, device, equipment and readable storage medium |
-
2021
- 2021-05-14 CN CN202110525659.9A patent/CN113284006A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214549A (en) * | 2018-08-01 | 2019-01-15 | 武汉众智鸿图科技有限公司 | A kind of water supply network auxiliary DMA partition method and system based on graph theory |
CN111080483A (en) * | 2019-12-17 | 2020-04-28 | 上海市城市建设设计研究总院(集团)有限公司 | DMA automatic partitioning method for water supply network based on graph division |
CN112464057A (en) * | 2020-11-18 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Network data classification method, device, equipment and readable storage medium |
Non-Patent Citations (2)
Title |
---|
刘俊等: "谱聚类在给水管网分区优化中的应用", 《土木建筑与环境工程》 * |
姜东明等: "融合图卷积网络模型的无监督社区检测算法", 《计算机工程与应用》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807012A (en) * | 2021-09-14 | 2021-12-17 | 杭州莱宸科技有限公司 | Water supply network division method based on connection strengthening |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108366386B (en) | Method for realizing wireless network fault detection by using neural network | |
CN110703057A (en) | Power equipment partial discharge diagnosis method based on data enhancement and neural network | |
CN110134907B (en) | Rainfall missing data filling method and system and electronic equipment | |
CN113284006A (en) | Independent water supply network metering and partitioning method based on graph convolution | |
CN106126328B (en) | A kind of traffic metadata management method and system based on event category | |
CN116384746A (en) | Urban pipe network danger early warning method and system based on graph algorithm and application thereof | |
CN103945238A (en) | Community detection method based on user behaviors | |
CN115996249A (en) | Data transmission method and device based on grading | |
CN116777284A (en) | Space and attribute data integrated quality inspection method | |
CN109165207B (en) | Drinking water mass data storage management method and system based on Hadoop | |
Tang et al. | A novel method for road intersection construction from vehicle trajectory data | |
CN116703132B (en) | Management method and device for dynamic scheduling of shared vehicles and computer equipment | |
WO2019104952A1 (en) | Scene intelligent analysis system and method based on metropolitan area level internet of things perceptual data | |
CN110659774B (en) | Big data method driven parking demand prediction method | |
CN107729942A (en) | A kind of sorting technique of structured view missing data | |
CN115100847B (en) | Queuing service time estimation method for low-permeability network-connected track data | |
CN114866301B (en) | Encryption traffic identification and classification method and system based on direct push graph | |
CN113516850B (en) | Pipeline traffic flow data acquisition method based on space syntactic analysis | |
CN115545240A (en) | Method, system, equipment and medium for diagnosing abnormal line loss of low-voltage distribution network transformer area | |
CN108429771A (en) | Software defined network secure state evaluating method based on catastrophe theory and device | |
CN102652425B (en) | Data acquisition method of large-scale network and network node | |
CN113674104B (en) | Independent metering and partitioning method for water supply network based on spectrum analysis | |
CN113886592A (en) | Quality detection method for operation and maintenance data of power information communication system | |
CN111797281A (en) | Two-layer dissimilarity community discovery algorithm research based on central node | |
CN107688629B (en) | Visual compression method for interactive architecture among multiple types of networks |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210820 |
|
RJ01 | Rejection of invention patent application after publication |