CN112070107A - Electronic port ship harboring control method - Google Patents
Electronic port ship harboring control method Download PDFInfo
- Publication number
- CN112070107A CN112070107A CN202010683101.9A CN202010683101A CN112070107A CN 112070107 A CN112070107 A CN 112070107A CN 202010683101 A CN202010683101 A CN 202010683101A CN 112070107 A CN112070107 A CN 112070107A
- Authority
- CN
- China
- Prior art keywords
- data
- ship
- decision tree
- current
- port
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000003066 decision tree Methods 0.000 claims abstract description 79
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000008676 import Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an electronic port ship harboring control method, which comprises the following steps: acquiring and analyzing historical declaration form data to obtain historical ship category data, and combining corresponding historical ship port entry data to jointly form a sample data set; constructing a decision tree, inputting a sample data set into a decision number for training to obtain a trained decision tree; acquiring current customs declaration form data, and preprocessing the current customs declaration form data; inputting the preprocessed data of the current declaration form into a trained decision tree to obtain a current ship harboring prediction result; and controlling the current harboring operation of the ship according to the current harboring prediction result of the ship. Compared with the prior art, the ship entry prediction method and the system have the advantages that ship category data and split standard data are obtained by analyzing and extracting data relation of the declaration form data, so that a decision tree with various decision prediction rules is constructed, a ship entry prediction result can be rapidly and accurately obtained, and the efficiency of electronic port ship entry control is improved.
Description
Technical Field
The invention relates to the technical field of electronic port big data processing, in particular to an electronic port ship harboring control method.
Background
The international trade single window in China, namely the electronic port, it uses modern information technology, with the help of the public network of the national telecommunications, deposit all kinds of import and export business electronic basic account data to the public data center in a centralized manner, the government function administration department can carry on the cross-department, cross-industry networking data check, the enterprise can handle all kinds of import and export business on the network, the electronic port has electronic ports of China and all places at present, the local electronic port depends on all kinds of data interfaces of the government department, in the course of setting up, except meeting the normal customs declaration demand of the enterprise, also through the user data that self accumulates, provide comprehensive guidance and warning for the enterprise, make the enterprise handle all kinds of import and export business simpler, more convenient.
In recent years, with the extensive and deep work of environmental construction, project development, information safety, operation maintenance, technical support and the like of the electronic port in China, the ship industry information technology of the electronic port is also vigorously developed. In the high-speed stage of internet development, the traditional management and control mode is difficult to meet the actual development requirement of the electronic port ship industry, the data volume generated by the information management system is increasing explosively, and people face the dilemma of data explosion and knowledge shortage in the process of ship management, trade and customs clearance. Until now, big data continuously drives the fields of internet +, internet of things, smart cities, intelligent manufacturing and the like, global data also presents a rapid development trend, and on the basis, a big data technology is needed to be scientifically applied to analyze and predict various mass data of electronic port ships, so that data support and powerful basis are provided for making various decisions, and timeliness, accuracy and reliability of various works are finally improved. At present, the traditional electronic port ship harbor control is carried out in a mode of declaration in advance and manual examination and approval, so that the problem of low efficiency exists, and the phenomenon of control error is likely to occur only by means of decision-making actions of people, so that the ship harbor is disordered, and the efficient and orderly harbor of the electronic port ship is not facilitated.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an electronic port ship harboring control method, which aims to realize the purpose of efficiently and accurately controlling the harboring of a ship by analyzing and predicting ship data.
The purpose of the invention can be realized by the following technical scheme: an electronic port ship harboring control method comprises the following steps:
s1, acquiring historical declaration form data and corresponding ship entry data;
s2, analyzing the historical declaration form data to obtain ship type data, and combining corresponding ship port entry data to form a sample data set;
s3, constructing a decision tree, inputting a sample data set into a decision number for training to obtain a trained decision tree;
s4, acquiring data of the current declaration form, and preprocessing the data of the current declaration form;
s5, inputting the preprocessed data of the current declaration form into a trained decision tree to obtain a current ship harboring prediction result;
and S6, controlling the port entering operation of the current ship according to the current ship port entering prediction result.
Further, the ship category data comprises four attributes of ship number, ship tonnage, cargo capacity and existence of dangerous goods.
Further, the step S3 specifically includes the following steps:
s31, calculating the information gain of each attribute in the sample data set;
s32, sequentially taking each attribute as a root node and a branch node of the decision tree according to the relationship of the information gain numerical values from large to small, wherein when the output of the leaf node of the decision tree is 0, the situation that the ship cannot enter the port is indicated; when the leaf node output of the decision tree is 1, indicating that the ship can enter the port;
and S33, dividing the sample data set into a training set and a test set according to the proportion, and finishing the training of the decision tree by utilizing the training set and the test set.
Further, the information gain of the attribute in step S31 is specifically:
wherein P (M, attribute) is information gain of attribute, M is sample data set, Q (M) is information entropy, D is sample number of attribute in sample data set M, N isiIs the probability of occurrence of sample i, M is the total number of samples in the sample data set, MrIs a sample with the value r in the attribute.
Further, the root node of the decision tree in the step S32 is a ship, and the sub-nodes are the ship tonnage, the cargo capacity and whether dangerous goods exist in turn.
Further, the step S33 specifically includes the following steps:
s331, dividing a sample data set into a training set and a test set according to a preset division ratio;
s332, extracting data relation of the training set data to obtain splitting characteristic data serving as a splitting standard of each branch node of the decision tree;
s333, inputting the training set data into a decision tree, and training a decision tree model according to preset iteration times;
and S334, inputting the data of the report form in the test set into the decision tree to obtain a ship entry prediction result corresponding to the test set, comparing the prediction result with the ship entry data in the test set one by one, stopping the training of the decision tree if the matching rate of the prediction result and the ship entry data in the test set is greater than or equal to a preset threshold value to obtain a trained decision tree, and otherwise, returning to the step S333.
Further, the splitting characteristic data comprises the year of the ship, the country of the ship and a ship customs port.
Further, the division ratio is specifically 1: 1.
Further, the step S4 specifically includes the following steps:
s41, deleting or filling incomplete data in the current declaration form data;
s42, removing the repeated data in the current declaration form data;
and S43, carrying out format unification processing on the current declaration form data.
Further, the step S5 specifically includes the following steps:
s51, analyzing the preprocessed current declaration form data to obtain current ship category data;
s52, screening abnormal values in the current ship category data based on a preset attribute threshold, and deleting the abnormal values;
s53, extracting the data relation of the preprocessed current customs declaration form data, and extracting to obtain the year, the country and the customs declaration port data of the current ship;
and S54, inputting the current ship type data processed in the step S52 and the year, the country and the customs port data of the current ship extracted in the step S53 into a trained decision tree model, and outputting to obtain a current ship entry prediction result.
Compared with the prior art, the invention has the following advantages:
the method comprises the steps of analyzing data of a clearance form and extracting data relation to construct a decision tree model, using ship times, ship tonnage, cargo quantity and whether dangerous goods exist as root nodes and branch nodes of the decision tree, and using ship year, country and clearance port as node splitting standards of the decision tree, so that accurate analysis and prediction of ship entering the port are achieved, and ship entering prediction results can be rapidly obtained even under the condition of large data volume, and therefore the efficiency of electronic port ship entering control is guaranteed.
Secondly, when the decision tree is constructed, the information gain of each attribute is calculated, the attribute with the maximum information gain is selected as the root node of the decision tree, and each sub-node of the decision tree is respectively set according to the relation that the information gain is reduced in sequence, so that the decision tree can have more decision prediction rules, the height and the depth of the decision tree are considered, the accuracy of the output result of the decision tree is improved, and the accuracy of the ship harbor entry prediction result is guaranteed.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a diagram illustrating a process of constructing a decision tree according to an embodiment;
FIG. 3 is a diagram illustrating an application architecture according to an embodiment.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
Examples
As shown in fig. 1, an electronic port ship harboring control method includes the following steps:
s1, acquiring historical declaration form data and corresponding ship entry data;
s2, analyzing the historical declaration form data to obtain ship category data, and combining corresponding ship port entry data to jointly form a sample data set, wherein the ship category data comprise four attributes of ship number, ship tonnage, cargo quantity and existence of dangerous goods;
s3, constructing a decision tree, inputting a sample data set into a decision number for training to obtain a trained decision tree;
s4, acquiring data of the current declaration form, and preprocessing the data of the current declaration form;
s5, inputting the preprocessed data of the current declaration form into a trained decision tree to obtain a current ship harboring prediction result;
and S6, controlling the port entering operation of the current ship according to the current ship port entering prediction result.
Specifically, when a decision tree is constructed, the information gain of each attribute in a sample data set is calculated:
wherein P (M, attribute) is information gain of attribute, M is sample data set, Q (M) is information entropy, D is sample number of attribute in sample data set M, N isiIs the probability of occurrence of sample i, M is the total number of samples in the sample data set, MrA sample with the value r in the attribute is obtained;
then, according to the relationship of the information gain numerical value from large to small, all attributes are sequentially used as a root node and branch nodes of the decision tree, in the embodiment, the root node of the decision tree is the ship for several times, the branch nodes are the ship tonnage, the cargo quantity and whether dangerous goods exist or not, and when the output of the leaf node of the decision tree is 0, the fact that the ship cannot enter a port is indicated; when the output of the leaf node of the decision tree is 1, indicating that the ship can enter the port;
and finally, dividing the sample data set into a training set and a testing set according to the proportion of 1:1, and finishing the training of the decision tree by utilizing the training set and the testing set:
performing data relation extraction on the training set data to obtain splitting characteristic data serving as a splitting standard of each branch node of the decision tree, wherein the splitting characteristic data comprises the year of the ship, the country of the ship and a ship customs declaration port;
inputting training set data into a decision tree, and training a decision tree model according to preset iteration times;
inputting the data of the report form in the test set into the decision tree to obtain a ship entry prediction result corresponding to the test set, comparing the prediction result with the ship entry data in the test set one by one, stopping the training of the decision tree if the matching rate of the prediction result and the ship entry data in the test set is greater than or equal to a preset threshold value to obtain a trained decision tree, and returning to the training set for continuously training the decision tree model.
After the decision tree is trained, preprocessing the acquired data of the current declaration form:
deleting or filling incomplete data in the current customs declaration form data;
removing repeated data in the data of the current declaration form;
and carrying out format unification processing on the current report form data.
Finally, analyzing the preprocessed current declaration form data to obtain current ship category data;
screening abnormal values in the current ship category data based on a preset attribute threshold, and deleting the abnormal values;
extracting the data relation of the preprocessed current customs declaration form data, and extracting to obtain the data of the current ship year, the country of the ship and a customs declaration port;
and inputting the processed current ship category data and the extracted year, country and customs port data of the current ship into a trained decision tree model, and outputting to obtain a current ship entry prediction result.
The method is not limited to the simple analysis of the data of domestic ships or ports, but the analysis of the data of international ship dynamics, crew information, the import and export of trade goods in the country along the ship driving, the number of times and tonnage of the ship and the like is deeply researched, and then the classification of elements such as year, country and ports is carried out to help the electronic port to predict the ship data, so that the ship entering operation can be controlled better and more practically, and in the practical application, the main process is as follows:
(1) when the electronic port system server end receives the customs declaration form data transmitted by the personal terminal, analyzing the customs declaration form data to obtain the number of times of the ship, the number of crew members, the national trade volume along the running line of the ship, the volume of goods in and out, the tonnage of the ship and the category data of whether dangerous goods exist or not;
(2) the electronic port system server side sends a customs declaration request to the data interface to which each customs declaration project category belongs, and counts the number of times of customs declaration ships, the number of crew members, the national trade volume along the running line of the ships, the ship tonnage of import and export goods and whether dangerous goods exist to the electronic port system server side;
(3) when the data interface to which the ship data category belongs is abnormal or returns a result that customs declaration audit fails, the personal terminal sends a customs declaration request to the system again, so that the data of each category of the ship is obtained again;
(4) when the data interface to which the ship data category belongs returns a result of passing customs clearance examination, the acquired data is directly cleaned and sorted, firstly, thresholds are preset for various types of ship data, missing values and abnormal values are processed independently, and finally, data formats are unified and the data are summarized;
(5) constructing a decision tree model based on ID3, establishing a sample data set, effectively classifying the data by a certain method, wherein the concept of information entropy is used, finally obtaining information gains of various attributes, and classifying the data with the maximum information gain as a root node: since the ID3 algorithm can only be considered from local optimization, only the optimal situation at each step is considered, but global optimization cannot be obtained due to the influence of noise data, etc., the concept of attribute kernel is introduced to consider the optimization problem, and it can be found by comparison that a decision tree model made by using the ID3 algorithm has a significant defect that the decision tree is generally very large in height but very small in width, so that the decision tree becomes very complicated and difficult to interpret. However, the decision tree made by the optimized algorithm takes into account the height of the decision tree and the depth of the decision tree, so that a user can better understand and interpret the result of the decision tree, and the practical requirement of the electronic port on the analysis and prediction of the ship can be better met.
As shown in fig. 2, in order to analyze the accuracy of the model after training the decision tree model, partition nodes are added to divide the sample data into 50% training data and 50% testing data, so that after the decision tree model is generated, two classification models, i.e., C5.0 and CHAID, can be established to set and analyze the nodes, the completed decision tree model is streamed, data relationship extraction is performed through a source program, data of classification elements, i.e., year, country and port, are extracted, a node space is calculated, a classification algorithm model is established through C4.5, decision tree, naive bayes, Logistic regression, and the like, and a classification model which is more suitable for modeling the current ID3 data is selected through comparative analysis. Before data is input into a model, preprocessing of the data is needed, namely, noise interference data removal including data integration, data cleaning, data transformation and data reduction is needed for sampling and screening, and the data not only contains abnormal data, but also has the problems of incomplete information, wrong information and the like. On one hand, the data preprocessing is to process the incomplete data, and two processing methods are available, wherein one method is to directly delete the incomplete data, and the other method is to fill the incomplete data according to related information; another aspect is to remove duplicate data and unify the format of the data so that the software can directly process the data.
By building the decision tree model in a big data environment, the data stored in advance can be found in the database, and then the decision tree model interpretation based on the big data can be finally realized by selecting the input attribute and outputting the attribute. In addition, the invention is applied to practice, and can also be combined with a ship big data system display platform (as shown in figure 3): the webpage end is logged in by using a Chrome browser, a carrier for displaying the effect of big data application is a spliced big screen, a display module of a chart is developed by combining data visualization tools such as Echarts and a Python graphical library, and finally a display interface for big data of an electronic port ship is formed, wherein the display contents of a main analysis and prediction module are as follows: (1) analyzing the total number of the shippers entering the country, the number of the shippers entering the country in the past year and the number of the shippers entering the port; (2) analyzing the ship entry and exit amount of the ship in the country along the running line and the ship entry and exit of the main country in the past year for a plurality of times; (3) the tonnage change of the inbound ship at each port in the past year, including the change trend of the number of inbound ships in the past year and the total tonnage and the change of the type of inbound ship in the past year; (4) the proportion analysis of Chinese nationality ships going in and out for a time in the past year, and the proportion analysis of import and export of main cargo types of all ports in China; (5) analyzing the number of ships passing in and out of the domestic port and the occupation ratio of the ships in the past year, and analyzing the number of ships passing in and out of the important economic port in a specific year independently; (6) the forecast of ships entering and leaving the port of China in important trade countries.
To sum up, after the method provided by the invention is applied, various data of ship shipping can be analyzed and predicted through the decision tree model, so that the decision tree model is better and more widely applicable to various situations, and an improved decision tree algorithm is researched by using sample data, so that an electronic port can be better managed;
the embodiment judges the ship traffic situation of countries and regions along the running line of the ship through mass data, thereby better controlling import and export trades of the countries and China;
the individual requirements that ship data can be obtained and stored through big data are systematically analyzed through the existing ship big data, so that the ship data management system has the one-to-many relationship management advantages again, and further value creation by taking electronic port ship data management as a center is realized;
in addition, the method can comprehensively analyze factors such as port cargo weight change, port cargo price change, import and export category change and the like through a big data prediction process and introducing more influence factor data, and analyze the change of the import and export quantity of the port cargo through data correlation analysis, so that the whole model forms a dynamic and interactive self-feedback system.
Claims (10)
1. An electronic port ship harboring control method is characterized by comprising the following steps:
s1, acquiring historical declaration form data and corresponding ship entry data;
s2, analyzing the historical declaration form data to obtain ship type data, and combining corresponding ship port entry data to form a sample data set;
s3, constructing a decision tree, inputting a sample data set into a decision number for training to obtain a trained decision tree;
s4, acquiring data of the current declaration form, and preprocessing the data of the current declaration form;
s5, inputting the preprocessed data of the current declaration form into a trained decision tree to obtain a current ship harboring prediction result;
and S6, controlling the port entering operation of the current ship according to the current ship port entering prediction result.
2. The electronic port ship harbor entrance control method according to claim 1, wherein the ship classification data includes four attributes of ship number, ship tonnage, cargo capacity and existence of dangerous goods.
3. The electronic port ship harbor control method according to claim 2, wherein the step S3 specifically comprises the steps of:
s31, calculating the information gain of each attribute in the sample data set;
s32, sequentially taking each attribute as a root node and a branch node of the decision tree according to the relationship of the information gain numerical values from large to small, wherein when the output of the leaf node of the decision tree is 0, the situation that the ship cannot enter the port is indicated; when the leaf node output of the decision tree is 1, indicating that the ship can enter the port;
and S33, dividing the sample data set into a training set and a test set according to the proportion, and finishing the training of the decision tree by utilizing the training set and the test set.
4. The electronic port ship harbor entry control method according to claim 3, wherein the information gain of the attributes in step S31 is specifically:
wherein P (M, attribute) is information gain of attribute, M is sample data set, Q (M) is information entropy, D is sample number of attribute in sample data set M, N isiIs the probability of occurrence of sample i, M is the total number of samples in the sample data set, MrIs a sample with the value r in the attribute.
5. The method as claimed in claim 3, wherein the root node of the decision tree in step S32 is a ship, and the sub-nodes are ship tonnage, cargo capacity and existence of dangerous goods.
6. The electronic port ship harbor control method according to claim 3, wherein the step S33 specifically comprises the steps of:
s331, dividing a sample data set into a training set and a test set according to a preset division ratio;
s332, extracting data relation of the training set data to obtain splitting characteristic data serving as a splitting standard of each branch node of the decision tree;
s333, inputting the training set data into a decision tree, and training a decision tree model according to preset iteration times;
and S334, inputting the data of the report form in the test set into the decision tree to obtain a ship entry prediction result corresponding to the test set, comparing the prediction result with the ship entry data in the test set one by one, stopping the training of the decision tree if the matching rate of the prediction result and the ship entry data in the test set is greater than or equal to a preset threshold value to obtain a trained decision tree, and otherwise, returning to the step S333.
7. The electronic port ship harbor entrance control method according to claim 6, wherein the split feature data includes a ship year, a country of the ship, and a ship customs port.
8. The electronic port ship harbor entry control method according to claim 6, wherein the division ratio is 1: 1.
9. The electronic port ship harbor control method according to claim 1, wherein the step S4 specifically comprises the steps of:
s41, deleting or filling incomplete data in the current declaration form data;
s42, removing the repeated data in the current declaration form data;
and S43, carrying out format unification processing on the current declaration form data.
10. The electronic port ship harbor control method according to claim 6, wherein the step S5 specifically comprises the steps of:
s51, analyzing the preprocessed current declaration form data to obtain current ship category data;
s52, screening abnormal values in the current ship category data based on a preset attribute threshold, and deleting the abnormal values;
s53, extracting the data relation of the preprocessed current customs declaration form data, and extracting to obtain the year, the country and the customs declaration port data of the current ship;
and S54, inputting the current ship type data processed in the step S52 and the year, the country and the customs port data of the current ship extracted in the step S53 into a trained decision tree model, and outputting to obtain a current ship entry prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683101.9A CN112070107A (en) | 2020-07-15 | 2020-07-15 | Electronic port ship harboring control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683101.9A CN112070107A (en) | 2020-07-15 | 2020-07-15 | Electronic port ship harboring control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112070107A true CN112070107A (en) | 2020-12-11 |
Family
ID=73657780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010683101.9A Pending CN112070107A (en) | 2020-07-15 | 2020-07-15 | Electronic port ship harboring control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070107A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948353A (en) * | 2021-03-01 | 2021-06-11 | 北京寄云鼎城科技有限公司 | Data analysis method, system and storage medium applied to DAstudio |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095238A (en) * | 2014-05-04 | 2015-11-25 | ***股份有限公司 | Decision tree generation method used for detecting fraudulent trade |
| CN108389015A (en) * | 2018-01-22 | 2018-08-10 | 福建省数字福建云计算运营有限公司 | A kind of electronic port data monitoring method and system |
| CN108710979A (en) * | 2018-03-31 | 2018-10-26 | 西安电子科技大学 | A kind of Internet of Things yard craft dispatching method based on decision tree |
| CN108985718A (en) * | 2018-07-10 | 2018-12-11 | 江苏宏坤供应链管理有限公司 | Based on the single declaration data processing method of customs declaration grass |
| CN109522957A (en) * | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
| CN110128345A (en) * | 2019-05-13 | 2019-08-16 | 上海大学 | A kind of preparation method of e derivatives |
| CN110598730A (en) * | 2019-07-29 | 2019-12-20 | 南京理工大学 | Flight path association algorithm based on decision tree |
| CN111030941A (en) * | 2019-10-29 | 2020-04-17 | 武汉瑞盈通网络技术有限公司 | Decision tree-based HTTPS encrypted flow classification method |
| CN111144373A (en) * | 2019-12-31 | 2020-05-12 | 广州市昊链信息科技股份有限公司 | Information identification method and device, computer equipment and storage medium |
-
2020
- 2020-07-15 CN CN202010683101.9A patent/CN112070107A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095238A (en) * | 2014-05-04 | 2015-11-25 | ***股份有限公司 | Decision tree generation method used for detecting fraudulent trade |
| CN108389015A (en) * | 2018-01-22 | 2018-08-10 | 福建省数字福建云计算运营有限公司 | A kind of electronic port data monitoring method and system |
| CN108710979A (en) * | 2018-03-31 | 2018-10-26 | 西安电子科技大学 | A kind of Internet of Things yard craft dispatching method based on decision tree |
| CN108985718A (en) * | 2018-07-10 | 2018-12-11 | 江苏宏坤供应链管理有限公司 | Based on the single declaration data processing method of customs declaration grass |
| CN109522957A (en) * | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
| CN110128345A (en) * | 2019-05-13 | 2019-08-16 | 上海大学 | A kind of preparation method of e derivatives |
| CN110598730A (en) * | 2019-07-29 | 2019-12-20 | 南京理工大学 | Flight path association algorithm based on decision tree |
| CN111030941A (en) * | 2019-10-29 | 2020-04-17 | 武汉瑞盈通网络技术有限公司 | Decision tree-based HTTPS encrypted flow classification method |
| CN111144373A (en) * | 2019-12-31 | 2020-05-12 | 广州市昊链信息科技股份有限公司 | Information identification method and device, computer equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948353A (en) * | 2021-03-01 | 2021-06-11 | 北京寄云鼎城科技有限公司 | Data analysis method, system and storage medium applied to DAstudio |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106067094A (en) | A kind of dynamic assessment method and system | |
| US20090018983A1 (en) | Method and system for detecting anomalous process behavior | |
| CN108170769A (en) | A kind of assembling manufacturing qualitative data processing method based on decision Tree algorithms | |
| CN109961248A (en) | Waybill complains prediction technique, device, equipment and its storage medium | |
| CN112558931A (en) | Intelligent model construction and operation method for user workflow mode | |
| Gontareva et al. | Efficiency of Information Management and Analysis for Industrial Entrepreneurship | |
| CN114723287A (en) | Quantitative statistical method for risk formation based on enterprise characteristics and operation behaviors | |
| Naidu et al. | Classification of defects in software using decision tree algorithm | |
| JP2012014291A (en) | Job process analysis method, system and program | |
| US11494850B1 (en) | Applied artificial intelligence technology for detecting anomalies in payroll data | |
| CN114298412A (en) | Enterprise safety standardized operation method based on artificial intelligence and big data | |
| CN117453764A (en) | Data mining analysis method | |
| CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
| CN115757660A (en) | Method, system, electronic equipment and program product for automatically generating incidence relation between database tables | |
| CN112070107A (en) | Electronic port ship harboring control method | |
| Al-Bahri et al. | Evaluate the role of big data in enhancing strategic decision making for E-governance in E-Oman portal | |
| CN113176873B (en) | Method and device for information management, electronic equipment and medium | |
| CN115936217A (en) | Method and device for judging maturity of business opportunity, storage medium and electronic equipment | |
| Shah et al. | Predictive Analytic Modeling: A Walkthrough | |
| CN114066631A (en) | Anti-money laundering data monitoring method and system, storage medium and intelligent terminal | |
| Razali et al. | Big data analytics for preventive maintenance management | |
| CN112100165A (en) | Traffic data processing method, system, device and medium based on quality evaluation | |
| CN111612302A (en) | Group-level data management method and equipment | |
| Kumar et al. | Student’s Performance Analysis with EDA and Machine Learning Models | |
| Afzal | NNBI: A Neural Network based Business Intelligence Dashboard for a Clothing Store |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201211 |