CN112000651A - Sliding orientation data processing method - Google Patents
Sliding orientation data processing method Download PDFInfo
- Publication number
- CN112000651A CN112000651A CN202010801808.5A CN202010801808A CN112000651A CN 112000651 A CN112000651 A CN 112000651A CN 202010801808 A CN202010801808 A CN 202010801808A CN 112000651 A CN112000651 A CN 112000651A
- Authority
- CN
- China
- Prior art keywords
- data
- processing method
- mwd
- sliding
- invalid
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000005553 drilling Methods 0.000 claims abstract description 32
- 238000004140 cleaning Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000012216 screening Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 abstract description 11
- 238000012545 processing Methods 0.000 abstract description 10
- 238000010606 normalization Methods 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000011425 standardization method Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013523 data management Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
Abstract
The invention discloses a sliding orientation data processing method, which comprises the following steps: (1) acquiring a single-row timestamp by taking the data table of the torsional pendulum system as a reference table; (2) traversing data tables of the MWD system and the logging system according to the timestamps, and merging and storing the traversed data to obtain an integrated data summary table of the torsional pendulum system, the MWD system and the logging system; (3) traversing the integrated data summary table, cleaning messy codes, redundant numbers and invalid data, updating the data table and realizing data cleaning; (4) and (6) standardizing the data to form an effective data set. The method can realize multi-system data integration management, and carry out data cleaning on integrated data, delete messy codes, redundant numbers and invalid data, improve the data quality, and carry out standardized processing on the original index data after the data cleaning on the basis, thereby improving the normalization and the applicability of the sliding drilling data.
Description
Technical Field
The invention relates to a sliding directional data processing method, and belongs to the field of petroleum and gas drilling data processing.
Background
The sliding drilling gradually develops towards digitization and intellectualization, sliding directional operation is guided by depending on engineering data, the quality of sample data is particularly important, in the sliding drilling process, data acquired on a drilling site mainly comes from three systems of logging, MWD and torsional pendulum, however, the three systems are mutually independent and usually have different dimensions and orders of magnitude, and the aspects of different acquisition frequencies and the like have larger difference, when the level difference among the indexes is large, the original index value is directly used for analysis, the function of the index with higher value in comprehensive analysis can be highlighted, the function of the index with lower value level can be relatively weakened, the reliability of the data is influenced, the data directly combined is not suitable for being directly used for calculation and model training, and a large amount of data generated by the systems are difficult to realize fusion, sharing and integrated management, direct comparative analysis is not possible. Meanwhile, due to the fact that factors such as collection software restart and communication faults easily cause the problems of code loss, messy codes and the like, the accurate determination and the reliability of data are greatly influenced. Therefore, the collected data must be preprocessed to develop the maximum value for guiding the sliding drilling operation.
Disclosure of Invention
The present invention is directed to overcoming the above problems in the prior art and providing a method for processing sliding orientation data. The method can realize multi-system data integration management, and carry out data cleaning on integrated data, delete messy codes, redundant numbers and invalid data, improve the data quality, and carry out standardized processing on the original index data after the data cleaning on the basis, thereby improving the normalization and the applicability of the sliding drilling data.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a sliding orientation data processing method is characterized by comprising the following steps:
(1) acquiring a single-row timestamp by taking the data table of the torsional pendulum system as a reference table;
(2) traversing data tables of the MWD system and the logging system according to the timestamps, and merging and storing the traversed data to obtain an integrated data summary table of the torsional pendulum system, the MWD system and the logging system;
(3) traversing the integrated data summary table, cleaning messy codes, redundant numbers and invalid data, updating the data table and realizing data cleaning;
(4) and (6) standardizing the data to form an effective data set.
In the step (1), the time stamp (n is 1,2,3 … n) of the nth row of the torsion pendulum system data table is cyclically acquired by using the torsion pendulum system data table as a reference table.
In the step (2), for the nth data of the torsional pendulum system, traversing the data tables of the MWD and the logging system according to the timestamps, namely, screening other system data according to the timestamps, searching the same and similar timestamps in the data tables of the MWD and the logging system, and judging the basis: and if the time difference between the timestamp of the n rows in the torsional pendulum data table and the timestamp of other system data tables is 1 second, judging whether the time difference is smaller than the latest value of the time.
In the step (2), since the data is from a plurality of systems, the data has different structures and attributes, the data types should be divided according to the data structures and attributes during data merging, and the data of the same type are merged according to the timestamps to form an effective data column.
And (2) merging the data of the data stamps meeting the screening conditions of the three data tables, storing the data into a data summary table, repeating the steps (1) to (2), traversing all the single-row time stamps, and finishing traversal to obtain the integrated data summary table of the three systems of the torsional pendulum, the MWD and the logging.
In the step (3), traversing the data summary table, judging whether the messy codes, the redundancy numbers and the invalid data exist, screening the invalid information, deleting the messy codes, the redundancy numbers and the invalid data, and updating the data table.
In the step (3), the messy code error data mainly exists in the messy code problem caused by too fast sending frequency in the MWD transmission process, the places where the messy codes possibly exist are searched according to the keywords, and the messy code error data are modified through comparison analysis of front time and back time.
In the step (3), the redundancy number is mainly influenced by the drilling working condition, and in the sliding drilling operation process, the data irrelevant to the sliding drilling orientation under the starting and descending working conditions is the redundancy number.
In the step (3), the invalid data mainly includes: blank recording data of a logging system and an MWD system caused by equipment operation debugging and network faults; and basic data acquired by the torsional pendulum system without directional operation are taken as reference basis by the actual torque drilling speed.
In the step (3), the invalid data is screened according to the parameter variation fluctuation condition as the basis for judging whether the parameter variation fluctuation condition has the reference value.
In the step (4), in order to make the data result more standard and more convenient to use, the cleaned original index data needs to be normalized, that is, the data is standardized to form an effective data set.
In the step (4), the data standardization comprises the following steps:
a) carrying out linear transformation on the original data to enable the result to fall into a [0,1] interval, wherein the conversion formula is as follows:
wherein max is the maximum value of the sample data, min is the minimum value of the sample data, and X is the original data;
b) if it is desired to map the data to [ -1,1], then the formula is:
where mean is the sample mean.
The invention has the advantages that:
1. the invention integrates the data tables of the torsional pendulum system, the MWD system and the logging system by taking the data table of the torsional pendulum system as a reference table and taking the time stamp of the data table of the torsional pendulum system as a reference basis, thereby realizing the integrated management of multi-system data. And then, data cleaning is carried out on the integrated data, the messy codes, the redundant number and the invalid data are deleted, and the data quality is improved. On the basis, the original index data after data cleaning is subjected to standardization processing, and the normalization and the applicability of the sliding drilling data are improved.
2. The invention solves the problems that the sliding drilling field logging, MWD and torsional pendulum systems are mutually independent and data is dispersed, and a large amount of data generated by each system is difficult to realize fusion, sharing and integrated management, and provides technical support for integrated data management.
3. By carrying out data cleaning on the integrated data, messy codes, redundant data and invalid data are screened out, the data quality of the sliding drilling is improved, and the utilization value of the sliding drilling data is further improved.
4. The original index data after data cleaning is subjected to standardization processing, the normalization and the applicability of the sliding drilling data are improved, and a foundation is provided for the wide application of the sliding drilling data.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a graph of the results of training using Z-score normalized data;
FIG. 3 is a comparison of training results using Min-max normalized data.
Detailed Description
Example 1
A sliding orientation data processing method comprises the following steps:
(1) acquiring a single-row timestamp by taking the data table of the torsional pendulum system as a reference table;
(2) traversing data tables of the MWD system and the logging system according to the timestamps, and merging and storing the traversed data to obtain an integrated data summary table of the torsional pendulum system, the MWD system and the logging system;
(3) traversing the integrated data summary table, cleaning messy codes, redundant numbers and invalid data, updating the data table and realizing data cleaning;
(4) and (6) standardizing the data to form an effective data set.
In the step (1), the time stamp (n is 1,2,3 … n) of the nth row of the torsion pendulum system data table is cyclically acquired by using the torsion pendulum system data table as a reference table.
In the step (2), for the nth data of the torsional pendulum system, traversing the data tables of the MWD and the logging system according to the timestamps, namely, screening other system data according to the timestamps, searching the same and similar timestamps in the data tables of the MWD and the logging system, and judging the basis: and if the time difference between the timestamp of the n rows in the torsional pendulum data table and the timestamp of other system data tables is 1 second, judging whether the time difference is smaller than the latest value of the time.
In the step (2), since the data is from a plurality of systems, the data has different structures and attributes, the data types should be divided according to the data structures and attributes during data merging, and the data of the same type are merged according to the timestamps to form an effective data column.
And (2) merging the data of the data stamps meeting the screening conditions of the three data tables, storing the data into a data summary table, repeating the steps (1) to (2), traversing all the single-row time stamps, and finishing traversal to obtain the integrated data summary table of the three systems of the torsional pendulum, the MWD and the logging.
In the step (3), traversing the data summary table, judging whether the messy codes, the redundancy numbers and the invalid data exist, screening the invalid information, deleting the messy codes, the redundancy numbers and the invalid data, and updating the data table.
In the step (3), the messy code error data mainly exists in the messy code problem caused by too fast sending frequency in the MWD transmission process, the places where the messy codes possibly exist are searched according to the keywords, and the messy code error data are modified through comparison analysis of front time and back time.
In the step (3), the redundancy number is mainly influenced by the drilling working condition, and in the sliding drilling operation process, the data irrelevant to the sliding drilling orientation under the starting and descending working conditions is the redundancy number.
In the step (3), the invalid data mainly includes: blank recording data of a logging system and an MWD system caused by equipment operation debugging and network faults; and basic data acquired by the torsional pendulum system without directional operation are taken as reference basis by the actual torque drilling speed.
In the step (3), the invalid data is screened according to the parameter variation fluctuation condition as the basis for judging whether the parameter variation fluctuation condition has the reference value.
In the step (4), in order to make the data result more standard and more convenient to use, the cleaned original index data needs to be normalized, that is, the data is standardized to form an effective data set.
In the step (4), the data standardization comprises the following steps:
a) carrying out linear transformation on the original data to enable the result to fall into a [0,1] interval, wherein the conversion formula is as follows:
wherein max is the maximum value of the sample data, min is the minimum value of the sample data, and X is the original data;
b) if it is desired to map the data to [ -1,1], then the formula is:
where mean is the sample mean.
The field original data processing is mainly divided into three aspects of data cleaning, data integration and data normalization. Data integration, data cleansing and data normalization.
The data integration is that the sliding drilling data is derived from a plurality of data tables of a plurality of systems, so that the data calling efficiency is seriously influenced, meanwhile, the data management is difficult, and in order to facilitate the calling and the management, the data needs to be woven into a data set so as to realize the data integration management. Data integration is a data integration process, data with different structures and different attributes are integrated and summarized together by integrating data sources of various systems, and data types are effectively divided according to the structures and the attributes to form a data set containing all data tables.
The data cleaning is that the stored data format, the value mode and the unit are different because the naming rule is different when the data source definition attributes of different data acquisition systems are different. Thus, even if two values represent the same business meaning, they do not represent that the values stored in the database are the same. Meanwhile, in the data acquisition process, because the acquisition time is long, the data transmission frequency is high, and some error data formats are inevitably generated. Thus. Data integration is required to be cleaned before, and data quality is guaranteed.
The data normalization is due to the fact that in a multi-index evaluation system, different dimensions and orders of magnitude are generally achieved due to different properties of evaluation indexes. When the levels of the indexes are greatly different, if the original index values are directly used for analysis, the function of the indexes with higher numerical values in the comprehensive analysis is highlighted, and the function of the indexes with lower numerical levels is relatively weakened. Therefore, in order to ensure the reliability of the result, the raw index data needs to be normalized. The normalization method has two forms, one is to change a number to a decimal between (0, 1), and the other is to change a dimensional expression to a dimensionless expression. The method mainly aims to provide data processing convenience, maps data into a range of 0-1 for processing, and is more convenient and faster.
Example 2
In the step (1), the time stamp (n is 1,2,3 … n) of the nth row of the torsion pendulum system data table is cyclically acquired by using the torsion pendulum system data table as a reference table.
And (2) traversing the data tables of the MWD and the logging system according to the time stamp, and merging and storing the traversed data to realize data integration.
Further, in the step (2), for the nth data of the torsional pendulum system, traversing the MWD and logging system data tables according to the timestamp, namely, screening other system data according to the timestamp, searching the same and similar timestamps in the MWD and logging system data tables, and judging the basis: and if the time difference between the timestamp of the n rows in the torsional pendulum data table and the timestamp of other system data tables is 1 second, judging whether the time difference is smaller than the latest value of the time.
Further, in the step (2), since the data is from a plurality of systems, the data has different structures and attributes, and the data types should be divided according to the data structures and attributes during data merging, so that the data merging of the same type according to the timestamps is realized, and an effective data column is formed.
Further, in the step (2), for the data stamps meeting the screening conditions of the three data tables, data of data where the respective time stamps of the three data tables are located are combined and stored in the data summary table, the steps (1) to (2) are repeated, all the time stamps of a single line are traversed, the traversal is finished, and finally the data summary table containing the three systems of the torsional pendulum, the MWD and the logging is obtained, so that the purpose of data integration of the three systems of the data is achieved.
In the step (3), traversing the data summary table, judging whether the messy codes, the redundancy numbers and the invalid data exist, screening the invalid information, deleting the messy codes, the redundancy numbers and the invalid data, and updating the data table.
Further, in the step (3), the garbled error data mainly exists in the garbled problem caused by too fast sending frequency in the transmission process of the MWD. And searching a place where a messy code possibly exists according to the keywords, and modifying through front-back time comparison analysis.
Furthermore, in the step (3), the redundancy number is mainly influenced by the drilling working condition, and in the sliding drilling operation process, the data irrelevant to the sliding drilling orientation under the working conditions of starting, descending and the like is the redundancy number.
Further, in step (3), the invalid data mainly includes: blank recording data of a logging system and an MWD system caused by equipment operation debugging and network faults; and basic data acquired by the torsional pendulum system without directional operation are taken as reference basis by the actual torque drilling speed.
Further, in the step (3), the screening of invalid information is performed according to whether the parameter variation fluctuation condition is taken as a basis for having a reference value, so that invalid data are screened, and invalid parameters participating in the screening are reduced.
In the step (4), in order to make the data result more standard and more convenient to use, the cleaned original index data needs to be normalized, that is, the data is standardized to form an effective data set.
Further, in the step (4), Min-max standardization is selected as a method for processing the standardization of the sliding drilling raw data, and the Min-max standardization step is as follows:
a) carrying out linear transformation on the original data to enable the result to fall into a [0,1] interval, wherein the conversion formula is as follows:
wherein max is the maximum value of the sample data, min is the minimum value of the sample data, and X is the original data;
b) if it is desired to map the data to [ -1,1], then the formula is:
where mean is the sample mean.
The common data preprocessing methods comprise Min-max standardization, Z-score standardization, Log function conversion and other common data preprocessing methods, the Min-max standardization and the Z-score standardization are both realized, data with different magnitudes are unified into the same magnitude, and the Z-score standardization and the Min-max standardization methods are compared by utilizing the sliding drilling data zero.
Comparing fig. 2 and fig. 3, it can be known that the loss value of the Z-score normalization method tends to be stable along with the increase of the training rounds, the fitting effect on the forward torque and the reverse torque is good, but the difference between the predicted value and the true value of the forward rotating speed and the reverse rotating speed is large, which indicates that the normalization effect of the method on partial sliding orientation data is not good. Besides good fitting effect on forward torque and reverse torque, the Min-max standardization method has good fitting effect on predicted values and real values of forward rotating speed and reverse rotating speed, so that the Min-max standardization method has good suitability as a standardization method for sliding orientation.
Claims (10)
1. A sliding orientation data processing method is characterized by comprising the following steps:
(1) acquiring a single-row timestamp by taking the data table of the torsional pendulum system as a reference table;
(2) traversing data tables of the MWD system and the logging system according to the timestamps, and merging and storing the traversed data to obtain an integrated data summary table of the torsional pendulum system, the MWD system and the logging system;
(3) traversing the integrated data summary table, cleaning messy codes, redundant numbers and invalid data, updating the data table and realizing data cleaning;
(4) and (6) standardizing the data to form an effective data set.
2. A sliding orientation data processing method according to claim 1, wherein: in the step (1), the time stamp (n is 1,2,3 … n) of the nth row of the torsion pendulum system data table is cyclically acquired by using the torsion pendulum system data table as a reference table.
3. A sliding orientation data processing method according to claim 2, wherein: in the step (2), for the nth data of the torsional pendulum system, traversing the data tables of the MWD and the logging system according to the timestamps, namely, screening other system data according to the timestamps, searching the same and similar timestamps in the data tables of the MWD and the logging system, and judging the basis: and if the time difference between the timestamp of the n rows in the torsional pendulum data table and the timestamp of other system data tables is 1 second, judging whether the time difference is smaller than the latest value of the time.
4. A sliding orientation data processing method according to claim 3, wherein: in the step (2), since the data is from a plurality of systems, the data has different structures and attributes, the data types should be divided according to the data structures and attributes during data merging, and the data of the same type are merged according to the timestamps to form an effective data column.
5. A sliding orientation data processing method according to claim 4, wherein: and (2) merging the data of the data stamps meeting the screening conditions of the three data tables, storing the data into a data summary table, repeating the steps (1) to (2), traversing all the single-row time stamps, and finishing traversal to obtain the integrated data summary table of the three systems of the torsional pendulum, the MWD and the logging.
6. A sliding orientation data processing method according to claim 5, wherein: in the step (3), traversing the data summary table, judging whether the messy codes, the redundancy numbers and the invalid data exist, screening the invalid information, deleting the messy codes, the redundancy numbers and the invalid data, and updating the data table.
7. A sliding orientation data processing method according to claim 6, wherein: in the step (3), the messy code error data mainly exists in the messy code problem caused by the excessively fast sending frequency in the MWD transmission process, the part possibly having the messy code is searched according to the keyword, and the part is analyzed and modified through the comparison of the front time and the back time; the redundancy number is mainly influenced by the drilling working condition, and in the sliding drilling operation process, the data irrelevant to the sliding drilling orientation under the starting and descending working conditions is the redundancy number; the invalid data mainly includes: blank recording data of a logging system and an MWD system caused by equipment operation debugging and network faults; and basic data acquired by the torsional pendulum system without directional operation are taken as reference basis by the actual torque drilling speed.
8. A sliding orientation data processing method according to claim 7, wherein: in the step (3), the invalid data is screened according to the parameter variation fluctuation condition as the basis for judging whether the parameter variation fluctuation condition has the reference value.
9. A sliding orientation data processing method according to claim 8, wherein: in the step (4), in order to make the data result more standard and more convenient to use, the cleaned original index data needs to be normalized, that is, the data is standardized to form an effective data set.
10. A sliding orientation data processing method according to claim 9, wherein: in the step (4), the data standardization comprises the following steps:
a) carrying out linear transformation on the original data to enable the result to fall into a [0,1] interval, wherein the conversion formula is as follows:
wherein max is the maximum value of the sample data, min is the minimum value of the sample data, and X is the original data;
b) if it is desired to map the data to [ -1,1], then the formula is:
where mean is the sample mean.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010801808.5A CN112000651A (en) | 2020-08-11 | 2020-08-11 | Sliding orientation data processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010801808.5A CN112000651A (en) | 2020-08-11 | 2020-08-11 | Sliding orientation data processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112000651A true CN112000651A (en) | 2020-11-27 |
Family
ID=73463808
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010801808.5A Pending CN112000651A (en) | 2020-08-11 | 2020-08-11 | Sliding orientation data processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112000651A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107038202A (en) * | 2016-12-28 | 2017-08-11 | 阿里巴巴集团控股有限公司 | Data processing method, device and equipment, computer-readable recording medium |
CN110500034A (en) * | 2019-08-30 | 2019-11-26 | 中国石油集团川庆钻探工程有限公司 | It establishes neural network model, determine the method for rocking drill string parameters and directed drilling |
-
2020
- 2020-08-11 CN CN202010801808.5A patent/CN112000651A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107038202A (en) * | 2016-12-28 | 2017-08-11 | 阿里巴巴集团控股有限公司 | Data processing method, device and equipment, computer-readable recording medium |
CN110500034A (en) * | 2019-08-30 | 2019-11-26 | 中国石油集团川庆钻探工程有限公司 | It establishes neural network model, determine the method for rocking drill string parameters and directed drilling |
Non-Patent Citations (2)
Title |
---|
张鑫: "滑动定向钻探过程的智能决策算法研究与实", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》, no. 07, 15 July 2020 (2020-07-15), pages 11 - 14 * |
韩烈祥;张继川;刘伟;: "PIPE ROCK钻柱扭摆系统应用评价", 天然气工业, no. 11, 27 November 2018 (2018-11-27), pages 73 - 78 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111639237B (en) | Electric power communication network risk assessment system based on clustering and association rule mining | |
US6389412B1 (en) | Method and system for constructing integrated metadata | |
CN109213756B (en) | Data storage method, data retrieval method, data storage device, data retrieval device, server and storage medium | |
JP5092165B2 (en) | Data construction method and system | |
CN102306176B (en) | On-line analytical processing (OLAP) keyword query method based on intrinsic characteristic of data warehouse | |
CN111324602A (en) | Method for realizing financial big data oriented analysis visualization | |
EP1065606A2 (en) | Method and apparatus for identifying preferred indexes for databases | |
CN102098175A (en) | Alarm association rule obtaining method of mobile internet | |
CN112231333A (en) | Ecological environment data sharing and exchanging method and system | |
CN112199433A (en) | Data management system for city-level data middling station | |
CN110442620B (en) | Big data exploration and cognition method, device, equipment and computer storage medium | |
CN110389950B (en) | Rapid running big data cleaning method | |
CN114218218A (en) | Data processing method, device and equipment based on data warehouse and storage medium | |
CN110163511A (en) | A kind of Manufacture quality control method based on association rule mining and fuzzy decision | |
CN111241129A (en) | Industrial production enterprise index data acquisition and calculation system | |
CN106484815B (en) | A kind of automatic identification optimization method based on mass data class SQL retrieval scene | |
CN113553312A (en) | Digital twin construction method based on elevator production process | |
CN112000651A (en) | Sliding orientation data processing method | |
CN111292201A (en) | Method for pushing field operation and maintenance information of power communication network based on Apriori and RETE | |
KR101985961B1 (en) | Similarity Quantification System of National Research and Development Program and Searching Cooperative Program using same | |
CN112967759B (en) | DNA material evidence identification STR typing comparison method based on memory stack technology | |
CN109976271B (en) | Method for calculating information structure order degree by using information representation method | |
CN106547860B (en) | Method for positioning performance fault of distributed database | |
CN108280790A (en) | Policy information service system based on big data analysis | |
CN114185875A (en) | Big data unified analysis and processing system based on cloud computing |
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 |