CN111914014A - Big data platform and application thereof - Google Patents
Big data platform and application thereof Download PDFInfo
- Publication number
- CN111914014A CN111914014A CN202010826303.4A CN202010826303A CN111914014A CN 111914014 A CN111914014 A CN 111914014A CN 202010826303 A CN202010826303 A CN 202010826303A CN 111914014 A CN111914014 A CN 111914014A
- Authority
- CN
- China
- Prior art keywords
- data
- platform
- sub
- module
- model
- 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
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
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- 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
-
- 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
- G06F16/26—Visual data mining; Browsing structured data
Abstract
The application belongs to the technical field of data analysis, and particularly relates to a big data platform and application thereof. In the oil industry, no corresponding data analysis platform exists for the subdivision direction of the multiphase flow. The application provides a big data platform, which comprises an interface sub-platform, a service mode sub-platform, a cluster sub-platform and a data layer sub-platform; the interface sub-platform is used for displaying different dimensional data by using the big data platform and comparing the dimensional data; the business mode sub-platform is used for feeding back the calculation result of the data layer sub-platform to the outside in real time; the cluster sub-platform is used for processing data from different enterprises in real time and off line by using the existing big data analysis platform, performing different machine learning algorithms on the data, and calling an externally trained model to process the data according to the requirement; and the data layer sub-platform is used for respectively storing the real-time data and the historical data and cleaning partial data. A reasonable storage mode is designed at a platform level aiming at the characteristics of data.
Description
Technical Field
The application belongs to the technical field of data analysis, and particularly relates to a big data platform and application thereof.
Background
With the rapid development of artificial intelligence and big data technology in recent years, various industries have rapidly upgraded the technology in the aspect of data information technology processing, and especially have great technical changes in the traditional industry. In the field of petroleum, the wide use of business systems in large petroleum enterprises puts higher demands on data processing, such as improving the operation efficiency of a single well, reasonably planning the productivity of the oil field, reducing the transportation cost, improving the production efficiency, managing the data of the oil field of the enterprise and providing high-level decision support. For example, in oil field multiphase flow measurement, the data of ECT, microwave, Venturi and the like of a multiphase flowmeter in one day is nearly 1G, the oil and gas content data related to the multiphase flow directly or indirectly represents the yield of a certain oil well and the oil quality, and because the data volume is very large, the traditional data analysis method cannot meet the current requirements, so that higher requirements are needed for data mining of oil and gas large data of the multiphase flow. Meanwhile, a great deal of data is applied to deep learning, and the data is directly collected from a multiphase flowmeter, and the data has the problems of loss, error, redundancy and the like and cannot be directly used for training a deep learning model, so that the data needs to be preprocessed by a large data platform, and then the processed data is used for training and predicting the deep learning model.
Oil field enterprises have a lot of production data, and certain difficulty exists in application of mass production data, especially certain privacy exists in different enterprise data, and data interaction is impossible, so that the data are delivered to third-party companies, data analysis is carried out by using a large data platform of a third party, the fused data are applied to training of various models, and then the data analysis result and the trained models are returned to different enterprises to improve the reliability of the models.
At present, a plurality of oil enterprises such as shell, chevrons, saudi amai, schlumberger and the like establish own big data platforms in the enterprises, but the big data platforms establish different business modules according to different requirements, utilize data to analyze the data and give decision support to field personnel, reduce the possibility of manual intervention through automatic decision, reduce the workload of data analyzers, and do not have corresponding data analysis platforms for the subdivision direction of multiphase flow in the oil industry, and in addition, the data of the data platforms of the big companies can not be handed to a third party company to perform data analysis but are the data analysis platforms in the enterprises.
Disclosure of Invention
1. Technical problem to be solved
Based on the fact that a plurality of current oil enterprises such as shell brand, Chevron, Saudi, Schlumberger and the like establish own big data platforms in the enterprises, but the big data platforms establish different business modules according to different requirements, data are used for data analysis, decision support is provided for field personnel, the possibility of manual intervention is reduced through automatic decision, the workload of data analysts is reduced, no corresponding data analysis platform exists in the oil industry for the subdivision direction of multiphase flow, and besides, the data of the data platforms of the big companies cannot be handed to a third party company for data analysis but are used as the data analysis platform in the enterprises.
The application provides a big data platform and application thereof.
2. Technical scheme
In order to achieve the above object, the present application provides a big data platform, where the platform includes an interface sub-platform, a service mode sub-platform, a cluster sub-platform, and a data layer sub-platform;
the interface sub-platform is used for displaying different dimensional data by using the big data platform and comparing the dimensional data;
the business mode sub-platform is used for feeding back the calculation result of the data layer sub-platform to the outside in real time;
the cluster sub-platform is used for processing data from different enterprises in real time and off-line by using the existing big data analysis platform, performing different machine learning algorithms on the data, and calling an externally trained model to process the data according to needs;
and the data layer sub-platform is used for respectively storing the real-time data and the historical data and cleaning partial data.
Another embodiment provided by the present application is: the interface sub-platform, the service mode sub-platform, the cluster sub-platform and the data layer sub-platform are in communication connection.
Another embodiment provided by the present application is: the interface sub-platform comprises a data display module and a model management module;
the data display module is used for displaying total data, supporting a two-dimensional or three-dimensional visual chart to display each key index, and displaying a data mining result or an intermediate result;
and the model management module is used for comparing the specific model results and selecting the optimal model.
Another embodiment provided by the present application is: the business mode sub-platform comprises a data transmission module and a business processing module, wherein the data transmission module is used for managing different data sources, and automatically transferring partial data to another storage device in different storage modes, so that each calculation engine can calculate conveniently;
the business processing module is used for analyzing each business index or analyzing and summarizing the automatic script.
Another embodiment provided by the present application is: the cluster sub-platform comprises a data processing module, an algorithm module and a model coordination module;
the data processing module is used for performing off-line processing and real-time processing on the data according to different data sources and data formats;
the algorithm module is used for carrying out different machine learning algorithms on the data;
and the model coordination module is used for calling an externally trained model to process data according to the requirement.
Another embodiment provided by the present application is: the data layer sub-platform comprises a data life cycle management module and a data storage module;
the data life cycle management module is used for carrying out data mining and model training on data, and downloading and screening a large amount of data to meet the requirements;
and the data storage module is used for storing the classified data respectively.
Another embodiment provided by the present application is: the interface sub-platform also comprises an authority management module, wherein the authority management module is used for establishing corresponding authorities for employees of different departments in the company and employees of other operating parties, and establishing different authorities for different roles.
Another embodiment provided by the present application is: the algorithm module comprises a machine learning algorithm submodule, and the machine learning algorithm submodule comprises a regression model, a classification model, a cluster analysis model and a time sequence model.
The application also provides application of the big data platform, and the big data platform is applied to analysis of oil and gas big data. Another embodiment provided by the present application is: the system also comprises an oil-gas well fault monitoring module and an oil well development scheme evaluation module; the oil-gas well fault monitoring module is used for monitoring the breakage of the sucker rod, the blockage of the piston, the oil leakage of an oil pipe or a pump, the wax deposition or the sand production and the insufficient liquid supply;
the oil well development scheme evaluation module is used for providing a production allocation and injection allocation scheme, evaluating the adaptation degree of the development scheme and providing an adjustment scheme; and predicting the yield, pressure and water content change trend of the partitioned wells and the water flooding rule of the oil well.
3. Advantageous effects
Compared with the prior art, the big data platform and the application thereof have the advantages that:
the big data platform provided by the application is based on oil-gas static and dynamic multi-dimensional big data production of multi-sensing technical means, provides a set of scheme for solving the problems by supporting intelligent management of oil-gas production, and establishes a set of third party system for analyzing the big data production and deploys the third party system in an actual production environment.
The big data platform provided by the application collects oil and gas production data of each big petroleum company by using the current big data platform, then carries out data preprocessing on the data of each petroleum company and analyzes the data, and finally, the data needing visualization is displayed.
The big data platform provided by the application utilizes the mainstream big data analysis technology spark, and is faster in speed and stronger in data processing capacity compared with the traditional Hadoop processing mode.
According to the big data platform, the data analysis of the big data platform can be predicted on the platform by using a machine learning model and a deep learning model.
The big data platform provided by the application is specifically transmitted to the inside of the big data platform aiming at the characteristic that data are stored on the Aliyun.
The big data platform provided by the application aims at the storage mode with reasonable design on the platform level according to the data characteristics.
Drawings
FIG. 1 is a schematic diagram of a big data platform architecture of the present application;
FIG. 2 is a schematic data processing flow diagram of the present application;
FIG. 3 is a schematic representation of the SSH architecture of the present application;
FIG. 4 is a historical data review schematic of the present application;
FIG. 5 is a schematic illustration of hydrocarbon production data presentation of the present application;
FIG. 6 is a big data frame diagram of the present application.
Detailed Description
Hereinafter, specific embodiments of the present application will be described in detail with reference to the accompanying drawings, and it will be apparent to those skilled in the art from this detailed description that the present application can be practiced. Features from different embodiments may be combined to yield new embodiments, or certain features may be substituted for certain embodiments to yield yet further preferred embodiments, without departing from the principles of the present application.
Clustering: a computer cluster, referred to as a cluster for short, is a computer system that cooperates with each other to a high degree of closeness to perform computing tasks by connecting a set of loosely integrated computer software or hardware.
Distributed: refers to a system of multiple, distributed computers connected via an interconnection network, with the processing and control functions of the system being distributed among the computers.
Data mining refers to a process of searching information hidden in a large amount of data through an algorithm
A big data platform: the method is a set of infrastructure mainly used for processing scenes such as mass data storage, calculation, uninterrupted stream data real-time calculation and the like. Typically include clusters of Hadoop series, Spark, Storm, Flink, and Flume/Kafka.
For predicting production over a future period of time using time series, the following problems exist:
(1) the current big data platform is a data platform aiming at the interior of an enterprise, and no complete data analysis platform exists for oil and gas big data analysis of specific industries.
(2) Most of the current data analysis platforms do not consider collecting data of a plurality of oil fields for data analysis, and data sharing cannot be achieved in enterprises.
(3) The data acquisition mode of the current data analysis platform is single, and the data acquisition mode of the platform is multiple.
(4) Multidimensional data is not explicitly materialized in the data storage schema of the platform.
(5) Most current technology platforms select the older technology framework Hadoop more, so that the computing speed is slower.
Referring to fig. 1 to 6, the present application provides a big data platform, where the platform includes an interface sub-platform, a service mode sub-platform, a cluster sub-platform, and a data layer sub-platform;
the interface sub-platform is used for displaying different dimensional data by using the big data platform and comparing the dimensional data;
the business mode sub-platform is used for feeding back the calculation result of the data layer sub-platform to the outside in real time;
the cluster sub-platform is used for processing data from different enterprises in real time and off-line by using the existing big data analysis platform, performing different machine learning algorithms on the data, and calling an externally trained model to process the data according to needs;
and the data layer sub-platform is used for respectively storing the real-time data and the historical data and cleaning partial data.
Firstly, data enters a data storage sub-platform, the data is acquired from a data storage layer according to the service requirement and then calculated by using cluster hardware, the calculated result is stored in a disk or a database, and finally, the data is displayed by using a webpage.
Partial data can be directly displayed from the data layer to the interface, partial data can be directly transmitted from the external interface to the interface for display, and partial data can be directly displayed according to the calculation result of the cluster.
The parameters of part of service layers can be directly set through the interface, and then calculation and storage are carried out.
Part of the service layer can be started by timing starting or script mode.
Friendly interaction: the platform design can be dragged, pulled and the like again to adjust the complex interface.
Further, the interface sub-platform, the service mode sub-platform, the cluster sub-platform and the data layer sub-platform are in communication connection.
Further, the interface sub-platform comprises a data display module and a model management module;
the data display module is used for displaying total data, supporting a two-dimensional or three-dimensional visual chart to display each key index, and displaying a data mining result or an intermediate result; friendly visual interface: the interface can display the summarized data through a Baidu Echarts plug-in, and supports a two-dimensional or three-dimensional visual chart to display each key index, such as a line chart, a curve chart, a radar chart and a map to display the oil well yield of each area.
And the model management module is used for comparing the specific model results and selecting the optimal model. The comparison of specific model results can be realized through a Web interface, and an optimal model is selected.
Further, the service mode sub-platform comprises a data transmission module and a service processing module, wherein the data transmission module is used for managing different data sources, such as historical data, real-time data, data of an ariloc cloud and local disk data; for different storage modes, partial data can be automatically migrated to another storage device, so that each calculation engine can calculate conveniently; the business processing module mainly analyzes each business index by means of a web page, or analyzes, summarizes and the like by means of a back-end automatic script.
Further, the cluster sub-platform comprises a data processing module, an algorithm module and a model coordination module;
the data processing module is used for performing off-line processing and real-time processing on the data according to different data sources and data formats; according to different data sources and data formats, a large amount of data is processed in an off-line mode and oil and gas data from the transmission interface is processed in real time.
The algorithm module is used for carrying out different machine learning algorithms on the data;
and the model coordination module is used for calling an externally trained model to process data according to the requirement.
The data can be correspondingly preprocessed through the scripting language, and the files can also be automatically processed through the platform codes; data processing from different sources is supported, such as interface data, Aliyun data, local data, real-time data and the like; various data formats are supported, such as CSV, Excel, TXT text, json and Xml format data, database data, HDFS, Hive, Hbase, etc.
Further, the data layer sub-platform comprises a data life cycle management module and a data storage module;
the data life cycle management module is used for carrying out data mining and model training on data, and downloading and screening a large amount of data to meet the requirements;
and the data storage module is used for storing the classified data respectively.
The method supports data mining and model training on all oil and gas data, wherein the data mining and model training comprises data cleaning, data standardization, data visualization and the like. And the downloading of a large amount of data through the platform is supported, and the data meeting the requirements are screened.
Furthermore, the interface sub-platform also comprises an authority management module, wherein the authority management module is used for establishing corresponding authorities for employees of different departments and employees of other operation parties in the company and establishing different authorities for different roles.
Further, the algorithm module comprises a machine learning algorithm submodule which comprises a regression model, a classification model, a cluster analysis model and a time series model.
TensorFlow can also be used for training and presenting the results on the platform and comparing the parameters of various same models or with different AI models.
The application also provides application of the big data platform, and the big data platform is applied to analysis of oil and gas big data. Further, the system also comprises an oil-gas well fault monitoring module and an oil well development scheme evaluation module;
the oil-gas well fault monitoring module is used for monitoring the breakage of the sucker rod, the blockage of the piston, the oil leakage of an oil pipe or a pump, the wax deposition or the sand production and the insufficient liquid supply;
the oil well development scheme evaluation module is used for providing a production allocation and injection allocation scheme, evaluating the adaptation degree of the development scheme and providing an adjustment scheme; and predicting the yield, pressure and water content change trend of the partitioned wells and the water flooding rule of the oil well.
The platform data processing flow needs to be processed in stages, each stage can provide corresponding data processing service according to the requirement of actual business, and the overall flow is shown in fig. 2:
the process of the warehouse is actually data integration; converting the data into a form suitable for data mining in the modes of smooth aggregation, data generalization, normalization and the like; data mining tends to be very large in data volume, long time is required for mining analysis on a small amount of data, data reduction techniques can be used to obtain a reduced representation of a data set, the data after reduction is much smaller but still close to maintaining the integrity of the original data, and the result is the same or nearly the same as the result before reduction.
And (3) selecting a data mining algorithm: and selecting an algorithm to be used and an algorithm result comparison mode according to the actual service requirement or laboratory requirement of the corresponding oil field, and displaying the result through the web.
Training and data mining of the model: and selecting the optimal parameter and the most available parameter according to the comparison of results of different models. And the corresponding data mining requirements are completed by utilizing a platform machine learning algorithm library, a deep learning library and the like.
Data visualization: the result of data mining or the intermediate result can be displayed by means of the front-end page of the platform web, and a proper preprocessing algorithm can be selected according to the data statistical analysis visualization result.
For the platform main functions:
oil and gas production data management, which aims at different data sources and can be divided into historical data and real-time data for processing; the data types can be divided into ECT, Venturi and microwave data for processing; the data granularity can be divided into detail data and summarized data processing.
And dynamic production analysis, which comprises production analysis, measure effect analysis, single-well change reason analysis, single-well oil and gas dynamic production analysis change reason, oil and gas dynamic production analysis-level (total five levels) and well group dynamic analysis change reason.
The fault monitoring of oil-gas well includes breaking sucker rod, blocking piston, leaking oil from oil pipe or pump, deposition of wax or sand and insufficient liquid supply. Evaluating an oil well development scheme, determining a reasonable injection-production ratio of a block and a small layer, a reasonable production pressure difference and a reasonable injection-production strength, and providing a production allocation and injection allocation scheme; analyzing and mastering the oil well effect, water breakthrough and water flooding rules after water injection, and formulating a working system to ensure stable production of the oil well; verifying the cognitive stratification degree of the static condition (oil layer together with the condition, fault position, property and shielding effect) of the oil field through the actual condition and the dynamic analysis result of the oil field development, evaluating the adaptation degree of the development scheme and providing an adjustment scheme; and predicting the yield, pressure and water content change trend of the partitioned wells and the water flooding rule of the oil well.
The prediction can be carried out by utilizing a platform machine learning library, and a deep learning model can be deployed to the platform and then predicted.
Platform technology implementation and platform deployment:
in the background part of the whole Web part, Struts, Spring and Hibernate are adopted to perform data processing and authority control of the background. The Struts are a good MVC framework, servlets and Jsp are main technologies, and the MVC design of the Struts can make the logic of the Struts clear, so that the written program is clear, and the Struts play a core control role in the whole MVC; spring provides a consistent method of managing business objects and encourages injection into a good habit of programming interfaces rather than classes, decoupling our products to the greatest extent; hibernate is used to persist data, providing fully object-oriented database operations, and it encapsulates JDBC very lightweight, making interaction with relational databases very easy. The entire SSH architecture is shown in fig. 3.
The front end of the Web adopts HTML, css, javascript and the like as a main page frame, and HTML determines the structure and content of a webpage in the whole front end; CSS sets the expression style of the web page; JavaScript controls the behavior of the web page. Besides, third-party plug-ins such as hundred-degree Echarts and jQuery are needed to realize special functions of the page and beautify the page. The built front end can be used for displaying part of data, the data is realized through the back end, and part of pages are realized as shown in the following fig. 4 and fig. 5.
In the whole big data platform level, Apache Spark is selected as a computing core, and Spark can process historical data and real-time data. The whole platform data can be divided into two types of dynamic data and static data, the dynamic data and the static data need different processing modes, a large amount of historical data can be stored in HBase in the platform, the historical data of each day are temporarily stored through the Ali cloud, then the data are downloaded and stored in the HBase by using a scripting language, real-time data can be transmitted through an interface and calculated by using a Spark calculation frame, an intermediate result is stored in a Redis memory database, the calculation result is stored in a MySQL database and displayed on a page through a web, the big data can be analyzed by using Hive, the whole platform has a plurality of jobs, so that Azkaban is needed for operation scheduling, and the whole data platform provides an interface for external calling. The overall big data platform system architecture diagram is shown in FIG. 6.
Other framework substitutions may be made for the transmission of portions of data to achieve the effect of the transmission.
Other algorithms may be used instead for some of the predictive algorithms used within the platform.
Although the present application has been described above with reference to specific embodiments, those skilled in the art will recognize that many changes may be made in the configuration and details of the present application within the principles and scope of the present application. The scope of protection of the application is determined by the appended claims, and all changes that come within the meaning and range of equivalency of the technical features are intended to be embraced therein.
Claims (10)
1. A big data platform, comprising: the platform comprises an interface sub-platform, a service mode sub-platform, a cluster sub-platform and a data layer sub-platform;
the interface sub-platform is used for displaying different dimensional data by using the big data platform and comparing the dimensional data;
the business mode sub-platform is used for feeding back the calculation result of the data layer sub-platform to the outside in real time;
the cluster sub-platform is used for processing data from different enterprises in real time and off-line by using the existing big data analysis platform, performing different machine learning algorithms on the data, and calling an externally trained model to process the data according to needs;
and the data layer sub-platform is used for respectively storing the real-time data and the historical data and cleaning partial data.
2. The big data platform of claim 1, wherein: the interface sub-platform, the service mode sub-platform, the cluster sub-platform and the data layer sub-platform are in communication connection.
3. The big data platform of claim 1, wherein: the interface sub-platform comprises a data display module and a model management module;
the data display module is used for displaying total data, supporting a two-dimensional or three-dimensional visual chart to display each key index, and displaying a data mining result or an intermediate result;
and the model management module is used for comparing the specific model results and selecting the optimal model.
4. The big data platform of claim 1, wherein: the business mode sub-platform comprises a data transmission module and a business processing module, wherein the data transmission module is used for managing different data sources, and automatically transferring partial data to another storage device in different storage modes, so that each calculation engine can calculate conveniently;
the business processing module is used for analyzing each business index or analyzing and summarizing the automatic script.
5. The big data platform of claim 1, wherein: the cluster sub-platform comprises a data processing module, an algorithm module and a model coordination module;
the data processing module is used for performing off-line processing and real-time processing on the data according to different data sources and data formats;
the algorithm module is used for carrying out different machine learning algorithms on the data;
and the model coordination module is used for calling an externally trained model to process data according to the requirement.
6. The big data platform of claim 1, wherein: the data layer sub-platform comprises a data life cycle management module and a data storage module;
the data life cycle management module is used for carrying out data mining and model training on data, and downloading and screening a large amount of data to meet the requirements;
and the data storage module is used for storing the classified data respectively.
7. The big data platform of claim 3, wherein: the interface sub-platform also comprises an authority management module, wherein the authority management module is used for establishing corresponding authorities for employees of different departments in the company and employees of other operating parties, and establishing different authorities for different roles.
8. The big data platform of claim 5, wherein: the algorithm module comprises a machine learning algorithm submodule, and the machine learning algorithm submodule comprises a regression model, a classification model, a cluster analysis model and a time sequence model.
9. An application of a big data platform, which is characterized in that: applying the big data platform of any one of claims 1-8 to analysis of oil and gas big data.
10. The use of the big data platform of claim 9, wherein: the system also comprises an oil-gas well fault monitoring module and an oil well development scheme evaluation module;
the oil-gas well fault monitoring module is used for monitoring the breakage of the sucker rod, the blockage of the piston, the oil leakage of an oil pipe or a pump, the wax deposition or the sand production and the insufficient liquid supply;
the oil well development scheme evaluation module is used for providing a production allocation and injection allocation scheme, evaluating the adaptation degree of the development scheme and providing an adjustment scheme; and predicting the yield, pressure and water content change trend of the partitioned wells and the water flooding rule of the oil well.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010826303.4A CN111914014A (en) | 2020-08-17 | 2020-08-17 | Big data platform and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010826303.4A CN111914014A (en) | 2020-08-17 | 2020-08-17 | Big data platform and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914014A true CN111914014A (en) | 2020-11-10 |
Family
ID=73279636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010826303.4A Pending CN111914014A (en) | 2020-08-17 | 2020-08-17 | Big data platform and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914014A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049515A (en) * | 2022-04-28 | 2022-09-13 | 中国石油大学(华东) | Method and device for establishing sample database and plate map of oil well production increase measure |
| CN115268937A (en) * | 2022-09-27 | 2022-11-01 | 中国空气动力研究与发展中心计算空气动力研究所 | Multi-phase flow field initialization method, device, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102520787A (en) * | 2011-11-09 | 2012-06-27 | 浙江大学 | Real-time spatial three-dimensional presentation system and real-time spatial three-dimensional presentation method |
| CN104731079A (en) * | 2015-04-09 | 2015-06-24 | 沈阳日明自动化工程系统有限公司 | Oil field data monitoring system and method |
| CN104915793A (en) * | 2015-06-30 | 2015-09-16 | 北京西塔网络科技股份有限公司 | Public information intelligent analysis platform based on big data analysis and mining |
| CN109582709A (en) * | 2018-11-20 | 2019-04-05 | 中国石油大学(华东) | A kind of data digging method of the oil-gas mining big data based on Spark |
| CN110298601A (en) * | 2019-07-05 | 2019-10-01 | 上海观安信息技术股份有限公司 | A kind of real time business air control system of rule-based engine |
| CN111090646A (en) * | 2019-10-21 | 2020-05-01 | 中国科学院信息工程研究所 | Electromagnetic data processing platform |
| CN111240662A (en) * | 2020-01-16 | 2020-06-05 | 同方知网(北京)技术有限公司 | Spark machine learning system and learning method based on task visual dragging |
| CN111538494A (en) * | 2020-07-09 | 2020-08-14 | 南京红松信息技术有限公司 | Big data automatic modeling and verification engine system and method |
-
2020
- 2020-08-17 CN CN202010826303.4A patent/CN111914014A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102520787A (en) * | 2011-11-09 | 2012-06-27 | 浙江大学 | Real-time spatial three-dimensional presentation system and real-time spatial three-dimensional presentation method |
| CN104731079A (en) * | 2015-04-09 | 2015-06-24 | 沈阳日明自动化工程系统有限公司 | Oil field data monitoring system and method |
| CN104915793A (en) * | 2015-06-30 | 2015-09-16 | 北京西塔网络科技股份有限公司 | Public information intelligent analysis platform based on big data analysis and mining |
| CN109582709A (en) * | 2018-11-20 | 2019-04-05 | 中国石油大学(华东) | A kind of data digging method of the oil-gas mining big data based on Spark |
| CN110298601A (en) * | 2019-07-05 | 2019-10-01 | 上海观安信息技术股份有限公司 | A kind of real time business air control system of rule-based engine |
| CN111090646A (en) * | 2019-10-21 | 2020-05-01 | 中国科学院信息工程研究所 | Electromagnetic data processing platform |
| CN111240662A (en) * | 2020-01-16 | 2020-06-05 | 同方知网(北京)技术有限公司 | Spark machine learning system and learning method based on task visual dragging |
| CN111538494A (en) * | 2020-07-09 | 2020-08-14 | 南京红松信息技术有限公司 | Big data automatic modeling and verification engine system and method |
Non-Patent Citations (1)
| Title |
|---|
| 郭燚等: "基于微服务的石油大数据挖掘平台", 《计算机与现代化》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049515A (en) * | 2022-04-28 | 2022-09-13 | 中国石油大学(华东) | Method and device for establishing sample database and plate map of oil well production increase measure |
| CN115268937A (en) * | 2022-09-27 | 2022-11-01 | 中国空气动力研究与发展中心计算空气动力研究所 | Multi-phase flow field initialization method, device, equipment and medium |
| CN115268937B (en) * | 2022-09-27 | 2023-02-17 | 中国空气动力研究与发展中心计算空气动力研究所 | Multi-phase flow field initialization method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10936479B2 (en) | Pluggable fault detection tests for data pipelines | |
| US10275502B2 (en) | System and method for interactive reporting in computerized data modeling and analysis | |
| US20220075515A1 (en) | Interactive graphical user interfaces for simulated systems | |
| CN103336790B (en) | Hadoop-based fast neighborhood rough set attribute reduction method | |
| US20170351511A1 (en) | System and Method for Code and Data Versioning in Computerized Data Modeling and Analysis | |
| CN112181960B (en) | Intelligent operation and maintenance framework system based on AIOps | |
| CN106651188A (en) | Electric transmission and transformation device multi-source state assessment data processing method and application thereof | |
| CN104915793A (en) | Public information intelligent analysis platform based on big data analysis and mining | |
| CN105139281A (en) | Method and system for processing big data of electric power marketing | |
| US11947934B2 (en) | Auto-generating interactive workflow user interfaces for simulated systems | |
| CN104205039A (en) | Interest-driven business intelligence systems and methods of data analysis using interest-driven data pipelines | |
| CN103853818A (en) | Multidimensional data processing method and device | |
| CN112100800B (en) | Space-time information intelligent analysis system architecture design method oriented to earth edge environment | |
| CN111914014A (en) | Big data platform and application thereof | |
| CN109977125A (en) | A kind of big data safety analysis plateform system based on network security | |
| CN115640300A (en) | Big data management method, system, electronic equipment and storage medium | |
| Hongliang et al. | Management and instant query of distributed oil and gas production dynamic data | |
| Hu | E-commerce big data computing platform system based on distributed computing logistics information | |
| CN112163017B (en) | Knowledge mining system and method | |
| Lv | Real estate marketing adaptive decision-making algorithm based on big data analysis | |
| CN109213909A (en) | A kind of big data analysis system and its analysis method fusion search and calculated | |
| Shouaib et al. | Survey on iot-based big data analytics | |
| EP3878143A1 (en) | Pipeline network solving using decomposition procedure | |
| Kongkiatpaiboon et al. | Advancing Well and Remote Compressor Performance Through Data Analytics | |
| Sun et al. | Development of a Framework for Data Integration, Assimilation, and Learning for Geological Carbon Sequestration (DIAL-GCS) |
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 |