CN110471917A - It is a kind of based on historical data excavate customs declaration list intelligently make a report on method - Google Patents
It is a kind of based on historical data excavate customs declaration list intelligently make a report on method Download PDFInfo
- Publication number
- CN110471917A CN110471917A CN201910617724.3A CN201910617724A CN110471917A CN 110471917 A CN110471917 A CN 110471917A CN 201910617724 A CN201910617724 A CN 201910617724A CN 110471917 A CN110471917 A CN 110471917A
- Authority
- CN
- China
- Prior art keywords
- field
- node
- data
- value
- report
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2246—Trees, e.g. B+trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of customs declaration lists excavated based on historical data intelligently to make a report on method.This method comprises: being pre-processed to the historical data of customs declaration list, gauge outfit is merged with table volume data, removes unrelated field；Design and Implement each field correlation analysis algorithm based on occurrence；Tree structure is designed, dynamic tree is constructed based on each field correlation and is stored；According to the dynamic tree of generation, intelligent recommendation makes a report on content；Data maintaining and updating is periodically carried out automatically according to new logging data.The correlation analysis algorithm and dynamic tree that the present invention designs preferably can carry out the intelligence that remaining fills in field according to the current typing content dynamic of user and make a report on, and accuracy rate is higher.With stronger extensive and self-learning capability, customs declaration efficiency can be greatlyd improve, is used manpower and material resources sparingly for declaration mechanism and customs broker.
Description
Technical field:
The present invention relates to customs declaration information to make a report on field more particularly to a kind of customs declaration excavated based on historical data
Single intelligence makes a report on method.
Background technique:
Customs office of the People's Republic of China passes in and out supervision and management organ as China, and it is its day that import-export commodity, which declares management,
An important and basic job in normal business.Import-export commodity, which is declared, at present mainly declares company for all related papery lists
According to rear typing customs related system is aggregated, since typing field is various and content asks that contiguity is smaller, efficiency of inputting is low,
Error rate is high, wasting manpower and material resources.
Summary of the invention:
The present invention proposes that a kind of customs declaration list excavated based on historical data intelligently makes a report on method.The present invention fully considers
Each field in information is made a report on intelligence is provided and makes a report on strategy, compared with traditional complete people based on the correlativity between occurrence
Work typing has the characteristics that higher efficiency and higher accuracy.
The present invention provides following scheme, it is a kind of based on historical data excavate customs declaration list intelligently make a report on method, wrap
Include following steps:
S1: pre-processing the historical data of customs declaration list, and gauge outfit is merged with table volume data, removes unrelated word
Section.
S1.1: Spark distributed computing merging data is used
True declaration forms data is divided into gauge outfit data and table volume data, is stored respectively in two tables of data, wherein gauge outfit
Data describe a certain order information, such as pass in and out port, declare unit, conclusion of the business mode；Table volume data describes quotient in a certain order
Product specifying information, such as goods number, product name, declare unit price.The present invention uses Spark distributed computing method, passes through
Two tables are attached by order number as major key, are obtained comprising all tables of data for making a report on information field, and be stored in Hive number
According in library.
S1.2: each field null value situation is counted, unrelated field is removed.
During customs declaration, certain fields belong to user's selection and fill in item, so will appear field is air situation condition, lead to
It crosses in preprocessing process and counts a certain field assigning null data item number and account for total data percentage, such as larger than 90% or more then removal should
Field.Time, serial number, handbook number etc. are removed without actual recommendation value field simultaneously.
By pre-processing above, obtain with the field data table for recommending value.
S2: each field correlation analysis algorithm based on occurrence is designed and Implemented.
Traditional correlation discovery algorithm only relies only on the inner link between field itself and determines correlation between certain fields
Property size.The present invention will really declare at customs data in conjunction with field, judge when the value of a certain field has determined that, the field with
Correlation size between other fields, so that simulation is actually typing the continuous interactive process in scene with user.
Defining correlation is to give field A and its value a, after the value of certain field B determines, so that other are needed in addition to A, B
It wants that the value of typing field is unique or options is minimum, then claims correlation maximum between field A and field B.
Algorithm input is history data set, user typing field A and field value a, and it is related in the case of current typing for exporting
Property largest field B.Algorithm is accomplished by
5, cutting is carried out to history data set according to typing field A and field value a, obtains subnumber in the case of the specific typing
According to collection；
6, subdata sets carry out duplicate removal processing；
7, remaining correlation size for needing typing field with field A, the field of selection and field A correlation maximum are calculated
B
8, output field B.
S3: design tree structure constructs dynamic tree based on each field correlation and stores.
The present invention is based on historical datas to excavate the realization for carrying out declaration intelligence and making a report on method, is found by S2 based on value
After field correlative relationship, tree structure is designed, building one has the most short tree for making a report on path of history.
S3.1: tree structure design
Tree construction includes node and side.Wherein node, which is divided into, divides node (n omicronn-leaf child node) and recommendation node (leaf knot
Point).Dividing node is a certain field attribute name and the field frequency of occurrence highest attribute value, and recommendation node is Map structure, storage
Field name and corresponding attribute value；It is attached between each node by side, side stores the corresponding attribute value of father node field.
S3.2: dynamic tree generates
The pretreated field data table of S1 is read in first, and it is to declare that first layer, which is divided node (root node) field definition,
Row, second, third layer divide node and are respectively defined as operating unit and product name, are saved between each layer node and node by father
Each value of making a report on of point corresponding field is attached.
4th layer and each layer node selection according to upper layer node and side correspond to attribute value as input, selection correlation later
Largest field is as lower layer's node, until other typing field values are unique after certain node or all field typings are completed, it is raw
At node (leaf node) is recommended, stores remaining typing field and field value or generate empty node.
By above step, generating one has the most short dynamic tree for making a report on path of history.
S3.3: dynamic tree storage
The S3.2 dynamic tree generated is stored in MySql database, wherein table structure is as shown in the table.
Table 1 divides node table structure
| Field name | Field type | Explanation |
| id | int | Self-propagation, major key |
| Field_name | String | Make a report on field name |
| Best_value | String | Frequency of occurrence highest field value |
| Name | String | Node title, uniquely |
| Level | int | Locating tree construction level |
| Agent_code | String | Correspondence declares row title |
| Date | Date | The record is inserted into the time |
2 leaf node table structure of table
| Field name | Field type | Explanation |
| id | int | Self-propagation, major key |
| Value | String | Field name+field value splicing |
| Level | int | Locating tree construction level |
| Agent_code | String | Correspondence declares row title |
| Date | Date | The record is inserted into the time |
3 side table structure of table
| Field name | Field type | Explanation |
| id | int | Self-propagation, major key |
| Father | String | Father node field name |
| Son | String | Child node field name |
| Value | String | Father node some make a report on value |
| Agent_code | String | Correspondence declares row title |
| Date | Date | The record is inserted into the time |
S4: according to the dynamic tree of generation, intelligent recommendation makes a report on content.
Each structure of dynamic tree in MySql database will be stored in and read in memory, and deposit the corresponding dynamic tree of building inside again.
Dynamic tree is searched for according to declare row, operating unit and the product name of user's typing first, then according to the storage of each node
BestValue attribute carries out depth-first search, and value is made a report in remaining all field of order output and recommendation；Then it is carried out with user
Interaction carries out the modification of part field or typing, is finally as above searched for and recommended again according to new entry values, until meeting
Typing is expected.
S5: data maintaining and updating is periodically carried out automatically according to new logging data.
By user, typing situation stores into database and adds time tag each time first, then when fixing weekly
Between according to time tag new data is added into history data set, construct new dynamic tree according to newly-generated history data set and deposit
Storage, to realize that data are safeguarded automatically and updated.
The present invention has following technical effect that
It is made a report on 1. the present invention preferably can carry out the intelligence that remaining fills in field according to the current typing content dynamic of user,
Accuracy rate is higher；
2. have stronger extensive and self-learning capability, customs declaration efficiency can be greatlyd improve, for declaration mechanism and
Customs broker uses manpower and material resources sparingly；
3. the present invention has regular automatically updating function.
Detailed description of the invention:
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without any creative labor, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is that a kind of customs declaration list excavated based on historical data provided in an embodiment of the present invention intelligently makes a report on method
Implementation flow chart.
Fig. 2 is that a kind of customs declaration list excavated based on historical data provided in an embodiment of the present invention intelligently makes a report on method
Dynamic tree topology figure.
Specific embodiment:
The present invention provides a kind of customs declaration lists excavated based on customs declaration historical data intelligently to make a report on method.It is whole
Scheme includes:
The historical data of customs declaration list is pre-processed, gauge outfit is merged with table volume data, removes unrelated field；If
It counts and realizes each field correlation analysis algorithm based on occurrence；Tree structure is designed, it is dynamic based on the building of each field correlation
State tree simultaneously stores；According to the dynamic tree of generation, intelligent recommendation makes a report on content；Data dimension is periodically carried out automatically according to new logging data
Shield and update.Figure one is implementation flow chart of the invention.
The correlation analysis algorithm and dynamic tree that the present invention designs can be carried out preferably according to user's typing Intelligent Dynamic
Remaining fills in making a report on for field, and accuracy rate is higher.With stronger extensive and self-learning capability, customs's report can be greatlyd improve
Efficiency is closed, is used manpower and material resources sparingly for declaration mechanism and customs broker.
The embodiment illustrated the present invention:
By taking the real data set that certain domestic customs port provides as an example, including 2015, the port was complete with 2016
Portion's declaration data.14,423,930 records are shared in gauge outfit tables of data in 2015, share 36,578,318 in table volume data table
Item record；14,832,866 records are shared in gauge outfit tables of data in 2016, and 38,673,224 notes are shared in table volume data table
Record.Data are related to more than 7000 families and declare row.Wherein, gauge outfit data share 43 fields, describe a certain order information, such as import and export
Bank declares unit, conclusion of the business mode etc., and table volume data shares 15 fields, describes many commodity specifying informations in a certain order, such as
Goods number, product name declare unit price etc..
Step S1: pre-processing the historical data of customs declaration list, and gauge outfit is merged with table volume data, removes unrelated
Field.
S1.1: Spark distributed computing merging data is used
Using Spark distributed computing method, two tables are attached as major key by order number, are obtained comprising all
The tables of data of information field is made a report on, and is stored in Hive database.
S1.2: each field null value situation is counted, unrelated field is removed.
Statistics wherein field of the null value ratio greater than 90% and removal, while time, serial number, handbook number etc. being removed,
It obtains with the field data table for recommending value.
Step S2: design and each field correlation analysis algorithm of the realization based on occurrence.
Data will really be declared at customs in conjunction with field, judged when the value of a certain field has determined that, the field and other
Correlation size between field, so that simulation is actually typing the continuous interactive process in scene with user.
Realize field correlation analysis algorithm, design program inputs under a certain field name A, field value a and current input
Data set exports correlation maximum field B under the specific input condition.
Step S3: design tree structure constructs dynamic tree based on each field correlation and stores.
S3.1: tree structure design
Tree construction includes node and side.Wherein node, which is divided into, divides node (n omicronn-leaf child node) and recommendation node (leaf knot
Point).Dividing node is a certain field attribute name and the field frequency of occurrence highest attribute value, and recommendation node is Map structure, storage
Field name and corresponding attribute value；It is attached between each node by side, side stores the corresponding attribute value of father node field.
S3.2: dynamic tree generates
The tables of data generated after step S1 is read in, it is to declare row, two or three layers of division knot that building first layer, which divides node,
Point is operating unit and the dynamic tree for declaring commodity, is made a report between each layer node and node by each of father node corresponding field
Value is attached.Remainder layer divides the obtained correlation maximum field of node selection step S2, recommend node be remaining typing only
One or empty.
S3.3: dynamic tree storage
Dynamic tree after generation is respectively divided into node, node and side is recommended to be stored respectively into Mysql division ode table, leaf
In child node table and side table.
Step S4: according to the dynamic tree of generation, intelligent recommendation makes a report on content.
By above-mentioned steps, the dynamic tree excavated based on historical data and correlation discovery algorithm obtains is stored in
In Mysql database.Database data is read in memory and reconstructs dynamic tree by this step.Declaring according to user's typing first
Row, operating unit and product name search for dynamic tree, and it is excellent then to carry out depth according to the BestValue attribute of each node storage
It first searches for, value is made a report in remaining all field of order output and recommendation；Then interacted with user, carry out the modification of part field or
Typing is finally as above searched for and is recommended again according to new entry values, until it is expected to meet typing.
Step S5: data maintaining and updating is periodically carried out automatically according to new logging data.
By user, typing situation stores into database and adds time tag each time first, then when fixing weekly
Between according to time tag new data is added into history data set, construct new dynamic tree according to newly-generated history data set and deposit
Storage.
Claims (2)
1. a kind of customs declaration list excavated based on historical data intelligently makes a report on method, which comprises the following steps:
S1: pre-processing the historical data of customs declaration list, and gauge outfit is merged with table volume data, removes unrelated field:
S1.1: Spark distributed computing merging data is used
True declaration forms data is divided into gauge outfit data and table volume data, is stored respectively in two tables of data, wherein gauge outfit data
A certain order information is described, port is such as passed in and out, declares unit, conclusion of the business mode；It is specific that table volume data describes commodity in a certain order
Information such as goods number, product name, declares unit price；The present invention uses Spark distributed computing method, is made by order number
Two tables are attached for major key, are obtained comprising all tables of data for making a report on information field, and be stored in Hive database；
S1.2: each field null value situation is counted, unrelated field is removed
Total data percentage is accounted for by counting a certain field assigning null data item number in preprocessing process, such as larger than 90% or more then
Remove the field；Time, serial number, handbook number etc. are removed without actual recommendation value field simultaneously；
By pre-processing above, obtain with the field data table for recommending value；
S2: each field correlation analysis algorithm based on occurrence is designed and Implemented
By will really declare at customs data in conjunction with field, judge when the value of a certain field has determined that, the field and other
Correlation size between field, so that simulation is actually typing the continuous interactive process in scene with user；
Defining correlation is to give field A and its value a, after the value of certain field B determines, so that other need to record in addition to A, B
The value for entering field is unique or options is minimum, then claims correlation maximum between field A and field B；
Algorithm input is history data set, user typing field A and field value a, is exported as correlation in the case of current typing most
Big field B, algorithm are accomplished by
1, cutting is carried out to history data set according to typing field A and field value a, obtains subdata in the case of the specific typing
Collection；
2, subdata sets carry out duplicate removal processing；
3, remaining correlation size for needing typing field with field A, the field B of selection and field A correlation maximum are calculated；
4, output field B；
S3: design tree structure constructs dynamic tree based on each field correlation and stores
After finding the field correlative relationship based on occurrence by S2, tree structure is designed, building one has history most short
Make a report on the tree in path:
S3.1: tree structure design
Tree construction includes node and side, and wherein node, which is divided into, divides node and recommend node, and division node is a certain field attribute
Name and the field frequency of occurrence highest attribute value, recommendation node are Map structure, store field name and corresponding attribute value；Each node
Between be attached by side, side stores the corresponding attribute value of father node field；
S3.2: dynamic tree generates
The pretreated field data table of S1 is read in first, it is to declare row that first layer, which is divided node field definition, second, third
Layer divides node and is respectively defined as operating unit and product name, passes through father node corresponding field between each layer node and node
Each value of making a report on is attached；
4th layer and each layer node selection according to upper layer node and side correspond to attribute value as input, selection correlation maximum later
Field is as lower layer's node, until other typing field values are unique after certain node or all field typings are completed, generation is pushed away
Node is recommended, remaining typing field and field value are stored or generates empty node；
By above step, generating one has the most short dynamic tree for making a report on path of history；
S3.3: dynamic tree storage
The S3.2 dynamic tree generated is stored in MySql database；
S4: according to the dynamic tree of generation, intelligent recommendation makes a report on content
Each structure of dynamic tree in MySql database will be stored in and read in memory, and deposit the corresponding dynamic tree of building inside again: first
Row, operating unit and product name search dynamic tree are declared according to user's typing, then according to the storage of each node
BestValue attribute carries out depth-first search, and value is made a report in remaining all field of order output and recommendation；Then it is carried out with user
Interaction carries out the modification of part field or typing, is finally as above searched for and recommended again according to new entry values, until meeting
Typing is expected；
S5: data maintaining and updating is periodically carried out automatically according to new logging data
By user, typing situation stores into database and adds time tag each time first, then the set time weekly according to
New data is added into history data set according to time tag, constructs new dynamic tree and storage according to newly-generated history data set,
To realize that data are safeguarded and update automatically.
2. a kind of customs declaration list excavated as described in claim 1 based on historical data intelligently makes a report on method, it is characterised in that:
Table structure is as shown in the table in S3.3:
Table 1 divides node table structure
2 leaf node table structure of table
3 side table structure of table
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910617724.3A CN110471917B (en) | 2019-07-10 | 2019-07-10 | Intelligent customs declaration and customs clearance filling method based on historical data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910617724.3A CN110471917B (en) | 2019-07-10 | 2019-07-10 | Intelligent customs declaration and customs clearance filling method based on historical data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110471917A true CN110471917A (en) | 2019-11-19 |
| CN110471917B CN110471917B (en) | 2021-01-15 |
Family
ID=68507571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910617724.3A Active CN110471917B (en) | 2019-07-10 | 2019-07-10 | Intelligent customs declaration and customs clearance filling method based on historical data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110471917B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111047299A (en) * | 2019-12-17 | 2020-04-21 | 苏州工业园区报关有限公司 | Application of two-dimensional code in customs two-step declaration and customs declaration system |
| CN111461072A (en) * | 2020-05-06 | 2020-07-28 | 深圳市慧通关网络科技有限公司 | AI (Artificial intelligence) identification importing method for quickly identifying imported form data |
| CN112633833A (en) * | 2020-12-23 | 2021-04-09 | 云汉芯城（上海）互联网科技股份有限公司 | Data acquisition method and device and computer storage medium |
| CN113296613A (en) * | 2021-03-12 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Customs clearance information processing method and device and electronic equipment |
| CN114356115A (en) * | 2021-12-31 | 2022-04-15 | 阿里巴巴（中国）有限公司 | Method for intelligently inputting form, electronic equipment and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102364512A (en) * | 2011-10-11 | 2012-02-29 | 中华人民共和国宁波出入境检验检疫局 | Method for realizing automatically sampling inspection of computer during product inspection and quarantine |
| US20130297488A1 (en) * | 2012-04-12 | 2013-11-07 | PGB Solutions, Inc. | System, method, service and computer readable medium for taking and processing paperless mortgage loan applications |
| CN103996112A (en) * | 2014-04-18 | 2014-08-20 | 青岛诚业国际物流有限公司 | Custom declaration data process system and method |
| CN104376068A (en) * | 2014-11-07 | 2015-02-25 | 北京思特奇信息技术股份有限公司 | Data representation system and method based on dynamic report template |
| CN108197796A (en) * | 2017-12-28 | 2018-06-22 | 云南路普斯数据科技有限公司 | A kind of data management and statistical analysis busincess intelligence platform |
| CN109409430A (en) * | 2018-10-26 | 2019-03-01 | 江苏智通交通科技有限公司 | Traffic accident intelligent data analysis and comprehensive application system |
-
2019
- 2019-07-10 CN CN201910617724.3A patent/CN110471917B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102364512A (en) * | 2011-10-11 | 2012-02-29 | 中华人民共和国宁波出入境检验检疫局 | Method for realizing automatically sampling inspection of computer during product inspection and quarantine |
| US20130297488A1 (en) * | 2012-04-12 | 2013-11-07 | PGB Solutions, Inc. | System, method, service and computer readable medium for taking and processing paperless mortgage loan applications |
| CN103996112A (en) * | 2014-04-18 | 2014-08-20 | 青岛诚业国际物流有限公司 | Custom declaration data process system and method |
| CN104376068A (en) * | 2014-11-07 | 2015-02-25 | 北京思特奇信息技术股份有限公司 | Data representation system and method based on dynamic report template |
| CN108197796A (en) * | 2017-12-28 | 2018-06-22 | 云南路普斯数据科技有限公司 | A kind of data management and statistical analysis busincess intelligence platform |
| CN109409430A (en) * | 2018-10-26 | 2019-03-01 | 江苏智通交通科技有限公司 | Traffic accident intelligent data analysis and comprehensive application system |
Non-Patent Citations (1)
| Title |
|---|
| 崔建高: "数据智慧：开启智慧海关建设的关键密钥", 《海关与经贸研究》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111047299A (en) * | 2019-12-17 | 2020-04-21 | 苏州工业园区报关有限公司 | Application of two-dimensional code in customs two-step declaration and customs declaration system |
| CN111461072A (en) * | 2020-05-06 | 2020-07-28 | 深圳市慧通关网络科技有限公司 | AI (Artificial intelligence) identification importing method for quickly identifying imported form data |
| CN111461072B (en) * | 2020-05-06 | 2023-04-18 | 深圳市慧通关网络科技有限公司 | AI (Artificial intelligence) identification importing method for quickly identifying imported form data |
| CN112633833A (en) * | 2020-12-23 | 2021-04-09 | 云汉芯城（上海）互联网科技股份有限公司 | Data acquisition method and device and computer storage medium |
| CN113296613A (en) * | 2021-03-12 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Customs clearance information processing method and device and electronic equipment |
| CN114356115A (en) * | 2021-12-31 | 2022-04-15 | 阿里巴巴（中国）有限公司 | Method for intelligently inputting form, electronic equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110471917B (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110471917A (en) | It is a kind of based on historical data excavate customs declaration list intelligently make a report on method | |
| US10936668B2 (en) | Systems and methods for querying databases | |
| Sahoo et al. | An efficient approach for mining association rules from high utility itemsets | |
| EP3617898A1 (en) | Scalable indexing architecture | |
| Romero et al. | GEM: Requirement-driven generation of ETL and multidimensional conceptual designs | |
| Deutsch et al. | Aggregation support for modern graph analytics in TigerGraph | |
| US9547646B2 (en) | User-created members positioning for OLAP databases | |
| JP2008523473A (en) | Computer system and method for visualizing data using mark generation | |
| JP2006526840A (en) | Computer System and Method for Multidimensional Database Query and Visualization The present invention relates to the Ministry of Energy ASCI Level 1 Partnership LLL-B523835 with Stanford University ("Center for Integrated Turbulence Simulation"). As well as by the Defense Advanced Research Projects Agency (“Visualization of Complex Systems and Environments”), APRA order number E269. The US government may have rights in the invention. | |
| EP3678032A1 (en) | Computer implemented methods and systems for improved data retrieval | |
| Morrison et al. | Solving the pricing problem in a branch-and-price algorithm for graph coloring using zero-suppressed binary decision diagrams | |
| EP3678033A1 (en) | A computer implemented method for indexlet based aggregation | |
| Mota et al. | A compact timed state space approach for the analysis of manufacturing systems: key algorithmic improvements | |
| Yang et al. | K-truss community most favorites query based on top-t | |
| Al Aghbari et al. | Geosimmr: A mapreduce algorithm for detecting communities based on distance and interest in social networks | |
| US10922278B2 (en) | Systems and methods for database compression and evaluation | |
| CN107609110B (en) | Mining method and device for maximum multiple frequent patterns based on classification tree | |
| CN105389337A (en) | Method for searching big data space for statistical significance mode | |
| Wang et al. | Considering high utilities for time interval sequential pattern mining | |
| CN115359844A (en) | Non-overlapping condition negative sequence pattern mining method | |
| Anuradha et al. | Mining generalized positive and negative inter-cross fuzzy multiple-level coherent rules | |
| CN101401100B (en) | Data mining by determining patterns in input data | |
| El-Hajj et al. | Parallel association rule mining with minimum inter-processor communication | |
| Murali et al. | A Novel Mining Algorithm for High Utility Itemsets from Transactional Databases | |
| CN104102654A (en) | Vocabulary clustering method and device |
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 |