CN107944180A - Suitable for the system of big data analysis - Google Patents
Suitable for the system of big data analysis Download PDFInfo
- Publication number
- CN107944180A CN107944180A CN201711294509.1A CN201711294509A CN107944180A CN 107944180 A CN107944180 A CN 107944180A CN 201711294509 A CN201711294509 A CN 201711294509A CN 107944180 A CN107944180 A CN 107944180A
- Authority
- CN
- China
- Prior art keywords
- connection
- mark
- module
- data
- neutral net
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the system suitable for big data analysis, including：Modeling module for the neutral net for establishing Weight；For being randomized all weighted values, and the data in database are output to the assignment module in neutral net；The study module for the data being input to for neural network learning in neutral net；Connection for the effect to having produced assigns high-quality mark, and the mark module of mark inferior is assigned to the connection for producing bad effect；The corresponding weighted value of connection of high-quality mark is endowed for improving, reduces the adjustment module of the weighted value for the connection for being endowed mark inferior.The system that the present invention is suitable for big data analysis, data are attached by neutral net, and assign weight to connection, the result produced at the same time according to connection adjusts weighted value, so that data analysis expands to whole database from single aspect, so that all data become an organism by the connection between data, the reliability of data results is improved.
Description
Technical field
The present invention relates to field of computer technology, and in particular to suitable for the system of big data analysis.
Background technology
Data analysis refer to appropriate statistical analysis technique to collect come mass data analyze, extract useful letter
Cease and form conclusion and data are subject to the process of research and summary in detail.This process is also the branch of quality management system
Hold process.In practicality, data analysis can help people to judge, to take appropriate action.The mathematics base of data analysis
Plinth has just been established in early stage in 20th century, but until the appearance of computer just make it possible practical operation, and so that data are divided
Analysis is promoted.Data analysis is the product that mathematical and computer sciences are combined.
With the development of big data technology, in order to obtain product developing direction, it is necessary to product manufacturing, sale and using production
Raw big data is analyzed, but existing data analysis technique, can only be analyzed from single aspect, can not tie analysis
Fruit, which derives, arrives other aspects, causes analysis result deviation very big.
The content of the invention
The technical problems to be solved by the invention are existing data analysis techniques, can only be analyzed from single aspect,
Analysis result can not be derived and arrive other aspects, cause analysis result deviation very big, and it is an object of the present invention to provide suitable for big data point
The system of analysis, solves the above problems.
The present invention is achieved through the following technical solutions：
Suitable for the system of big data analysis, including：Modeling module for the neutral net for establishing Weight；The god
Through the corresponding respective weighted value of each connection in network；Exported for being randomized all weighted values, and by the data in database
Assignment module into neutral net；The study module for the data being input to for neural network learning in neutral net；For
The connection of effect to having produced assigns high-quality mark, and the mark module of mark inferior is assigned to the connection for producing bad effect；
The corresponding weighted value of connection of high-quality mark is endowed for improving, reduces the tune of the weighted value for the connection for being endowed mark inferior
Mould preparation block.
In the prior art, data analysis technique, can only be analyzed from single aspect, can not be derived analysis result and be arrived it
His aspect, causes analysis result deviation very big.The present invention is in application, first establish the neutral net of Weight；The neutral net
In each corresponding respective weighted value of connection；All weighted values are randomized again, and the data in database are output to nerve net
In network；Then neural network learning is input to the data in neutral net；Subsequently the connection of the effect to having produced assigns excellent
Qualitative character, mark inferior is assigned to the connection for producing bad effect；Subsequently improve be endowed high-quality mark connection it is corresponding
Weighted value, reduces the weighted value for the connection for being endowed mark inferior.Data are attached by the present invention by neutral net, and right
Connection assigns weight, while the result produced according to connection adjusts weighted value so that data analysis expands to whole from single aspect
A database so that all data become an organism by the connection between data, and improve data results can
By property.
Further, the assignment module be additionally operable to by freshly harvested data add neutral net and by mark module again
It is identified.
Further, the weighted value is less than 1.
Further, the study module uses deep learning.
Further, the high-quality mark and mark inferior use Hash codes.
Compared with prior art, the present invention have the following advantages and advantages：
The system that the present invention is suitable for big data analysis, data are attached by neutral net, and connection is assigned
Weight, while the result produced according to connection adjusts weighted value so that data analysis expands to whole database from single aspect,
So that all data become an organism by the connection between data, the reliability of data results is improved.
Brief description of the drawings
Attached drawing described herein is used for providing further understanding the embodiment of the present invention, forms one of the application
Point, do not form the restriction to the embodiment of the present invention.In the accompanying drawings：
Fig. 1 is present system structure diagram.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, with reference to embodiment and attached drawing, to this
Invention is described in further detail, and exemplary embodiment of the invention and its explanation are only used for explaining the present invention, do not make
For limitation of the invention.
Embodiment
As shown in Figure 1, the present invention is suitable for the system of big data analysis, including：For establishing the neutral net of Weight
Modeling module；Each corresponding respective weighted value of connection in the neutral net；For being randomized all weighted values, and by number
The assignment module being output to according to the data in storehouse in neutral net；The data being input to for neural network learning in neutral net
Study module；Connection for the effect to having produced assigns high-quality mark, the connection for producing bad effect is assigned inferior
The mark module of mark；The corresponding weighted value of connection of high-quality mark is endowed for improving, reduces and is endowed mark inferior
The adjustment module of the weighted value of connection.The assignment module is additionally operable to freshly harvested data adding neutral net and by mark mould
Block is identified again.The weighted value is less than 1.The study module uses deep learning.The high-quality mark and mark inferior
Knowledge uses Hash codes.
When the present embodiment is implemented, the neutral net of Weight is first established；Each connection is corresponding respective in the neutral net
Weighted value；All weighted values are randomized again, and the data in database are output in neutral net；Then Neural Network Science
Practise the data being input in neutral net；Subsequently the connection of the effect to having produced assigns high-quality mark, to producing bad effect
The connection of fruit assigns mark inferior；The corresponding weighted value of connection for being endowed high-quality mark is subsequently improved, reduction is endowed bad
The weighted value of the connection of qualitative character.Data are attached by the present invention by neutral net, and weight, while root are assigned to connection
The result produced according to connection adjusts weighted value so that data analysis expands to whole database from single aspect so that all numbers
Become an organism according to by the connection between data, improve the reliability of data results.
Above-described embodiment, has carried out the purpose of the present invention, technical solution and beneficial effect further
Describe in detail, it should be understood that the foregoing is merely the embodiment of the present invention, be not intended to limit the present invention
Protection domain, within the spirit and principles of the invention, any modification, equivalent substitution, improvement and etc. done, should all include
Within protection scope of the present invention.
Claims (5)
1. suitable for the system of big data analysis, it is characterised in that including：
Modeling module for the neutral net for establishing Weight；Each corresponding respective weight of connection in the neutral net
Value；
For being randomized all weighted values, and the data in database are output to the assignment module in neutral net；
The study module for the data being input to for neural network learning in neutral net；
Connection for the effect to having produced assigns high-quality mark, and the mark of mark inferior is assigned to the connection for producing bad effect
Know module；
The corresponding weighted value of connection of high-quality mark is endowed for improving, reduces the weighted value for the connection for being endowed mark inferior
Adjustment module.
2. the system according to claim 1 suitable for big data analysis, it is characterised in that the assignment module is additionally operable to
Freshly harvested data are added into neutral net and are identified again by mark module.
3. the system according to claim 1 suitable for big data analysis, it is characterised in that the weighted value is less than 1.
4. the system according to claim 1 suitable for big data analysis, it is characterised in that the study module is using deep
Degree study.
5. the system according to claim 1 suitable for big data analysis, it is characterised in that the high-quality mark and poor quality
Mark uses Hash codes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711294509.1A CN107944180A (en) | 2017-12-08 | 2017-12-08 | Suitable for the system of big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711294509.1A CN107944180A (en) | 2017-12-08 | 2017-12-08 | Suitable for the system of big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107944180A true CN107944180A (en) | 2018-04-20 |
Family
ID=61945333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711294509.1A Pending CN107944180A (en) | 2017-12-08 | 2017-12-08 | Suitable for the system of big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944180A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104897583A (en) * | 2015-06-18 | 2015-09-09 | 重庆理工大学 | Trace bloodstain nondestructive testing device and method |
| CN105512273A (en) * | 2015-12-03 | 2016-04-20 | 中山大学 | Image retrieval method based on variable-length depth hash learning |
| CN106302522A (en) * | 2016-09-20 | 2017-01-04 | 华侨大学 | A kind of network safety situations based on neutral net and big data analyze method and system |
| CN106408343A (en) * | 2016-09-23 | 2017-02-15 | 广州李子网络科技有限公司 | Modeling method and device for user behavior analysis and prediction based on BP neural network |
| WO2017141997A1 (en) * | 2016-02-15 | 2017-08-24 | 国立大学法人電気通信大学 | Characteristic amount conversion module, pattern identification device, pattern identification method, and program |
-
2017
- 2017-12-08 CN CN201711294509.1A patent/CN107944180A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104897583A (en) * | 2015-06-18 | 2015-09-09 | 重庆理工大学 | Trace bloodstain nondestructive testing device and method |
| CN105512273A (en) * | 2015-12-03 | 2016-04-20 | 中山大学 | Image retrieval method based on variable-length depth hash learning |
| WO2017141997A1 (en) * | 2016-02-15 | 2017-08-24 | 国立大学法人電気通信大学 | Characteristic amount conversion module, pattern identification device, pattern identification method, and program |
| CN106302522A (en) * | 2016-09-20 | 2017-01-04 | 华侨大学 | A kind of network safety situations based on neutral net and big data analyze method and system |
| CN106408343A (en) * | 2016-09-23 | 2017-02-15 | 广州李子网络科技有限公司 | Modeling method and device for user behavior analysis and prediction based on BP neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bornmann et al. | BRICS countries and scientific excellence: A bibliometric analysis of most frequently cited papers | |
| EP3575980A3 (en) | Intelligent data quality | |
| Chen et al. | Testing the relationships between globalization, regionalization and the regional hubness of the BRICs | |
| CN104504086B (en) | The clustering method and device of Webpage | |
| CN106408132A (en) | Method and device of crop yield prediction based on plantation device | |
| WO2023112013A3 (en) | Balancing of environmental attributes in chemical production networks | |
| CN113452802A (en) | Equipment model identification method, device and system | |
| CN107885714A (en) | A kind of method prepared lessons online based on big data | |
| Trajanovski et al. | From epidemics to information propagation: Striking differences in structurally similar adaptive network models | |
| SA522440513B1 (en) | A system, method, and computer program product for improving a manufacturing process | |
| CN105101228B (en) | The pre- addressing algorithm of the modified multi-operator of quadruple | |
| CN109257160A (en) | A kind of side channel template attack method based on decision tree | |
| CN107944549A (en) | Data analysing method based on artificial intelligence | |
| CN107944180A (en) | Suitable for the system of big data analysis | |
| CN102982011B (en) | A kind of method and apparatus for recognizing out-of-sequence text | |
| CN105233486A (en) | Bodybuilding-assisting information acquiring system and method | |
| CN109472115A (en) | Large-scale complex network modeling method and device based on geographic information | |
| CN106203632B (en) | A kind of limited knowledge collection recombinant and study and the application system method for being distributed extraction | |
| Zhao et al. | A social network model with proximity prestige property | |
| Tedeschi et al. | A New Common Knowledge in Agronomics: the network of the European Agrarian Reviews and Congresses during the first half of the 19th century | |
| CN104090950A (en) | Data flow clustering method integrating cluster existence strength | |
| Ragozini et al. | Prototyping and comparing networks through Archetypal Analysis | |
| CN104572854A (en) | Decision-tree-based translator classification method | |
| CN103780459B (en) | With the network evolution method of Connection Density in class between a kind of invariance class | |
| CN109522476A (en) | The static prediction method of client properties discretization index conversion ratio |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |