CN112579582A - Data exploration method and system of data analysis engine - Google Patents
Data exploration method and system of data analysis engine Download PDFInfo
- Publication number
- CN112579582A CN112579582A CN202011381625.9A CN202011381625A CN112579582A CN 112579582 A CN112579582 A CN 112579582A CN 202011381625 A CN202011381625 A CN 202011381625A CN 112579582 A CN112579582 A CN 112579582A
- Authority
- CN
- China
- Prior art keywords
- data
- exploration
- dimensions
- structured
- characteristic value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000007405 data analysis Methods 0.000 title claims abstract description 28
- 238000004140 cleaning Methods 0.000 claims abstract description 33
- 238000013499 data model Methods 0.000 claims abstract description 13
- 238000013135 deep learning Methods 0.000 claims abstract description 13
- 238000012512 characterization method Methods 0.000 claims description 47
- 238000013527 convolutional neural network Methods 0.000 claims description 18
- 230000009193 crawling Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011985 exploratory data analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007619 statistical method 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
- G06F16/24—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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Abstract
The invention relates to a data exploration method and a data exploration system of a data analysis engine, wherein the method comprises the steps of collecting external big data, and cleaning and structuring the external big data to obtain a structured data set; characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set; and performing data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result. According to the method, data is firstly cleaned once in a data acquisition stage, and then data is filtered once in a data characteristic stage, so that useless data which cannot be searched are eliminated, the useless data are prevented from occupying data searching time, and the data searching efficiency is improved; before data exploration, data is structured and then characterized, so that data characteristics are easy to identify, and forward exploration weight is converged by reverse exploration, and the accuracy of data exploration is improved.
Description
Technical Field
The invention relates to the field of data exploration, in particular to a data exploration method and system of a data analysis engine.
Background
Data exploration generally refers to exploratory data analysis. With the development of big data, the difficulty and complexity of data analysis are increasing. The abundant data volume contains a great deal of valuable information, but the data needs complex statistical analysis exploration to extract meaningful results from the data. The existing data exploration method is too conservative, so that the precision of data exploration is poor and satisfactory, and the exploration efficiency of the existing data exploration method cannot meet the practical requirement in the face of a large amount of data.
Disclosure of Invention
The invention aims to provide a data exploration method and a data exploration system of a data analysis engine, which can provide data exploration efficiency and data exploration precision.
The technical scheme for solving the technical problems is as follows: a data exploration method of a data analysis engine comprises the following steps,
s1, collecting external big data, and cleaning and structuring the external big data to obtain a structured data set;
s2, characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set;
and S3, performing data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, in S1, a data crawler is used to collect the external big data and perform cleaning and structuring processing on the external big data, and a data crawling assembly, a data cleaning assembly, and a data structuring assembly are embedded in the data crawler; s1 specifically comprises the steps of collecting external big data by the data crawling component, cleaning the external big data by the data cleaning component, and structuring the cleaned external big data by the data structuring component to obtain a structured data set.
Further, each structured data in the structured data set comprises X, Y structural features of three dimensions of Z; specifically, the step S2 is,
s21, calculating characterization driving values corresponding to the structural features of the three dimensions X, Y and Z respectively based on preset characterization granularity;
s22, carrying out forward characterization on the structural features of the three dimensions of the structured data X, Y and Z according to characterization driving values corresponding to the structural features of the three dimensions of the structured data X, Y and Z respectively to obtain first characteristic values of the three dimensions of the structured data X, Y and Z; reversely characterizing the structural features of the three dimensions X, Y and Z of the structured data according to the structural features X, Y and the characterization driving values corresponding to the structural features of the three dimensions Z, respectively, to obtain second feature values of the three dimensions Z and X, Y of the structured data;
s23, judging whether the first characteristic value and the second characteristic value are correspondingly matched in three dimensions X, Y and Z; if the first characteristic value and the second characteristic value are matched, taking the average value of the first characteristic value and the second characteristic value in X, Y and Z dimensions as a final characteristic value of the structured data in X, Y and Z dimensions; and if not, filtering the structured data.
Further, the deep learning data model is specifically a convolutional neural network model; specifically, the step S3 is,
s31, inputting the final eigenvalues of X, Y and Z dimensions of the structured data into the convolutional neural network model, performing forward exploration according to the exploration weight in the process of positive convolution and deconvolution processing, and outputting a one-dimensional forward exploration vector;
s32, performing difference processing on the one-dimensional forward exploration vector and a preset forward exploration vector to calculate a forward exploration loss vector;
s33, performing reverse exploration on the forward exploration loss vector in a chain mode to adjust the exploration weight, and returning to repeatedly execute the S31 and the S32 until the forward exploration loss vector is a zero vector;
and S34, taking the one-dimensional forward search vector finally output by the convolutional neural network model as a data search result.
Further, after the step of S3, the method further comprises the following steps,
and S4, multimedia the data exploration result and displaying the data exploration result to the user through a display interface.
Based on the data exploration method of the data analysis engine, the invention also provides a data exploration system of the data analysis engine.
A data exploration system of a data analysis engine comprises the following modules,
the data acquisition module is used for acquiring external big data, and cleaning and structuring the external big data to obtain a structured data set;
the data characterization module is used for characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set;
and the data exploration module is used for carrying out data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result.
On the basis of the technical scheme, the invention can be further improved as follows.
Furthermore, in the data acquisition module, a data crawler is adopted to acquire the external big data and carry out cleaning and structuring processing on the external big data, and a data crawling assembly, a data cleaning assembly and a data structuring assembly are embedded in the data crawler; the data acquisition module is specifically used for acquiring external big data by using the data crawling assembly, cleaning the external big data by using the data cleaning assembly, and structuring the cleaned external big data by using the data structuring assembly to obtain a structured data set.
Further, each structured data in the structured data set comprises X, Y structural features of three dimensions of Z; the data characterisation module is particularly adapted to,
calculating characterization driving values respectively corresponding to the structural features of the three dimensions of the structured data X, Y and Z based on preset characterization granularity;
forward characterizing the structural features of the three dimensions of the structured data X, Y and Z according to characterization driving values corresponding to the structural features of the three dimensions of the structured data X, Y and Z, respectively, to obtain first feature values of the three dimensions of the structured data X, Y and Z; reversely characterizing the structural features of the three dimensions X, Y and Z of the structured data according to the structural features X, Y and the characterization driving values corresponding to the structural features of the three dimensions Z, respectively, to obtain second feature values of the three dimensions Z and X, Y of the structured data;
judging whether the first characteristic value and the second characteristic value are correspondingly matched in three dimensions of X, Y and Z; if the first characteristic value and the second characteristic value are matched, taking the average value of the first characteristic value and the second characteristic value in X, Y and Z dimensions as a final characteristic value of the structured data in X, Y and Z dimensions; and if not, filtering the structured data.
Further, the deep learning data model is specifically a convolutional neural network model; the data exploration module comprises a forward exploration unit, a loss amount calculation unit, a weight value adjustment unit and a data exploration result determination unit;
the forward exploration unit is used for inputting final characteristic values of the structured data in three dimensions of X, Y and Z into the convolutional neural network model, carrying out forward exploration according to an exploration weight in the process of positive convolution and deconvolution processing, and outputting a one-dimensional forward exploration vector;
the loss amount calculation unit is used for performing difference processing on the one-dimensional forward exploration vector and a preset forward exploration vector to calculate a forward exploration loss vector;
the weight value adjusting unit is used for adjusting the exploration weight value by performing reverse exploration on the forward exploration loss vector in a chain manner, and returning to repeatedly execute the forward exploration unit and the loss amount calculating unit until the forward exploration loss vector is a zero vector;
and the data exploration result determining unit is used for taking the one-dimensional forward exploration vector finally output by the convolutional neural network model as a data exploration result.
Further, the system also comprises a data exploration result display module,
and the data exploration result display module is used for carrying out multimedia on the data exploration result and displaying the data exploration result to a user through a display interface.
The invention has the beneficial effects that: according to the data exploration method and system of the data analysis engine, data cleaning is performed once in the data acquisition stage, data filtering is performed once in the data characteristic stage, useless data which cannot be explored are eliminated, the useless data are prevented from occupying data exploration time, and the data exploration efficiency is improved; before data exploration, data are structured and characterized, so that data characteristics are easy to identify, the characterization comprises forward characterization and reverse characterization, the forward characterization corresponds to the forward exploration and the reverse exploration in the subsequent data exploration process, the weight of the forward exploration is converged by utilizing the reverse exploration, and the precision of the data exploration is increased.
Drawings
FIG. 1 is a flow chart of a data exploration method of a data analysis engine according to the present invention;
FIG. 2 is a block diagram of a data exploration system of a data analysis engine according to the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, a data exploration method of a data analysis engine includes the steps of,
s1, collecting external big data, and cleaning and structuring the external big data to obtain a structured data set;
s2, characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set;
and S3, performing data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result.
In this embodiment, the following preferred embodiments are also provided:
preferably, in S1, a data crawler is used to collect the external big data and perform cleaning and structuring processing on the external big data, and a data crawling assembly, a data cleaning assembly, and a data structuring assembly are embedded in the data crawler; s1 specifically comprises the steps of collecting external big data by the data crawling component, cleaning the external big data by the data cleaning component, and structuring the cleaned external big data by the data structuring component to obtain a structured data set.
Preferably, each structured data in the structured data set comprises X, Y structural features of three dimensions Z; specifically, the step S2 is,
s21, calculating characterization driving values corresponding to the structural features of the three dimensions X, Y and Z respectively based on preset characterization granularity;
s22, carrying out forward characterization on the structural features of the three dimensions of the structured data X, Y and Z according to characterization driving values corresponding to the structural features of the three dimensions of the structured data X, Y and Z respectively to obtain first characteristic values of the three dimensions of the structured data X, Y and Z; reversely characterizing the structural features of the three dimensions X, Y and Z of the structured data according to the structural features X, Y and the characterization driving values corresponding to the structural features of the three dimensions Z, respectively, to obtain second feature values of the three dimensions Z and X, Y of the structured data;
s23, judging whether the first characteristic value and the second characteristic value are correspondingly matched in three dimensions X, Y and Z; if the first characteristic value and the second characteristic value are matched, taking the average value of the first characteristic value and the second characteristic value in X, Y and Z dimensions as a final characteristic value of the structured data in X, Y and Z dimensions; and if not, filtering the structured data.
In the invention, the data characterization is used for easily identifying the data characteristics in the data searching process so as to accelerate the data searching process. In the data characterization process, the three-dimensional characterization is performed, and the forward characterization and the reverse characterization are included, so that the comprehensiveness of the characterization is ensured, and a powerful guarantee condition is provided for improving the precision of subsequent data exploration.
Preferably, the deep learning data model is a convolutional neural network model; specifically, the step S3 is,
s31, inputting the final eigenvalues of X, Y and Z dimensions of the structured data into the convolutional neural network model, performing forward exploration according to the exploration weight in the process of positive convolution and deconvolution processing, and outputting a one-dimensional forward exploration vector;
s32, performing difference processing on the one-dimensional forward exploration vector and a preset forward exploration vector to calculate a forward exploration loss vector;
s33, performing reverse exploration on the forward exploration loss vector in a chain mode to adjust the exploration weight, and returning to repeatedly execute the S31 and the S32 until the forward exploration loss vector is a zero vector;
and S34, taking the one-dimensional forward search vector finally output by the convolutional neural network model as a data search result.
In the process of the invention, forward exploration is carried out according to the exploration weight, then the exploration loss vector is calculated, then reverse exploration is carried out on the exploration loss vector to adjust the exploration weight, and the converged exploration weight can ensure that the exploration loss is zero, thereby ensuring the precision of data exploration.
Preferably, after said S3, the method further comprises the following steps,
and S4, multimedia the data exploration result and displaying the data exploration result to the user through a display interface.
The multimedia can be characters, diagrams, voice and video, and provides rich display pictures.
Based on the data exploration method of the data analysis engine, the invention also provides a data exploration system of the data analysis engine.
As shown in fig. 2, a data exploration system of a data analysis engine includes the following modules,
the data acquisition module is used for acquiring external big data, and cleaning and structuring the external big data to obtain a structured data set;
the data characterization module is used for characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set;
and the data exploration module is used for carrying out data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result.
In this embodiment, the following preferred embodiments are also provided:
preferably, in the data acquisition module, a data crawler is adopted to acquire the external big data and perform cleaning and structuring processing on the external big data, and a data crawling assembly, a data cleaning assembly and a data structuring assembly are embedded in the data crawler; the data acquisition module is specifically used for acquiring external big data by using the data crawling assembly, cleaning the external big data by using the data cleaning assembly, and structuring the cleaned external big data by using the data structuring assembly to obtain a structured data set.
Preferably, each structured data in the structured data set comprises X, Y structural features of three dimensions Z; the data characterisation module is particularly adapted to,
calculating characterization driving values respectively corresponding to the structural features of the three dimensions of the structured data X, Y and Z based on preset characterization granularity;
forward characterizing the structural features of the three dimensions of the structured data X, Y and Z according to characterization driving values corresponding to the structural features of the three dimensions of the structured data X, Y and Z, respectively, to obtain first feature values of the three dimensions of the structured data X, Y and Z; reversely characterizing the structural features of the three dimensions X, Y and Z of the structured data according to the structural features X, Y and the characterization driving values corresponding to the structural features of the three dimensions Z, respectively, to obtain second feature values of the three dimensions Z and X, Y of the structured data;
judging whether the first characteristic value and the second characteristic value are correspondingly matched in three dimensions of X, Y and Z; if the first characteristic value and the second characteristic value are matched, taking the average value of the first characteristic value and the second characteristic value in X, Y and Z dimensions as a final characteristic value of the structured data in X, Y and Z dimensions; and if not, filtering the structured data.
Preferably, the deep learning data model is a convolutional neural network model; the data exploration module comprises a forward exploration unit, a loss amount calculation unit, a weight value adjustment unit and a data exploration result determination unit;
the forward exploration unit is used for inputting final characteristic values of the structured data in three dimensions of X, Y and Z into the convolutional neural network model, carrying out forward exploration according to an exploration weight in the process of positive convolution and deconvolution processing, and outputting a one-dimensional forward exploration vector;
the loss amount calculation unit is used for performing difference processing on the one-dimensional forward exploration vector and a preset forward exploration vector to calculate a forward exploration loss vector;
the weight value adjusting unit is used for adjusting the exploration weight value by performing reverse exploration on the forward exploration loss vector in a chain manner, and returning to repeatedly execute the forward exploration unit and the loss amount calculating unit until the forward exploration loss vector is a zero vector;
and the data exploration result determining unit is used for taking the one-dimensional forward exploration vector finally output by the convolutional neural network model as a data exploration result.
Preferably, the data exploration result display module is further included,
and the data exploration result display module is used for carrying out multimedia on the data exploration result and displaying the data exploration result to a user through a display interface.
According to the data exploration method and system of the data analysis engine, data cleaning is performed once in the data acquisition stage, data filtering is performed once in the data characteristic stage, useless data which cannot be explored are eliminated, the useless data are prevented from occupying data exploration time, and the data exploration efficiency is improved; before data exploration, data are structured and characterized, so that data characteristics are easy to identify, the characterization comprises forward characterization and reverse characterization, the forward characterization corresponds to the forward exploration and the reverse exploration in the subsequent data exploration process, the weight of the forward exploration is converged by utilizing the reverse exploration, and the precision of the data exploration is increased.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A data exploration method of a data analysis engine is characterized in that: comprises the following steps of (a) carrying out,
s1, collecting external big data, and cleaning and structuring the external big data to obtain a structured data set;
s2, characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set;
and S3, performing data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result.
2. The data exploration method for a data analysis engine according to claim 1, wherein: in the step S1, a data crawler is adopted to collect the external big data and perform cleaning and structuring processing on the external big data, and a data crawling assembly, a data cleaning assembly and a data structuring assembly are embedded in the data crawler; s1 specifically comprises the steps of collecting external big data by the data crawling component, cleaning the external big data by the data cleaning component, and structuring the cleaned external big data by the data structuring component to obtain a structured data set.
3. The data exploration method for a data analysis engine according to claim 1 or 2, wherein: each structured data in the structured data set comprises X, Y structural features of three dimensions Z; specifically, the step S2 is,
s21, calculating characterization driving values corresponding to the structural features of the three dimensions X, Y and Z respectively based on preset characterization granularity;
s22, carrying out forward characterization on the structural features of the three dimensions of the structured data X, Y and Z according to characterization driving values corresponding to the structural features of the three dimensions of the structured data X, Y and Z respectively to obtain first characteristic values of the three dimensions of the structured data X, Y and Z; reversely characterizing the structural features of the three dimensions X, Y and Z of the structured data according to the structural features X, Y and the characterization driving values corresponding to the structural features of the three dimensions Z, respectively, to obtain second feature values of the three dimensions Z and X, Y of the structured data;
s23, judging whether the first characteristic value and the second characteristic value are correspondingly matched in three dimensions X, Y and Z; if the first characteristic value and the second characteristic value are matched, taking the average value of the first characteristic value and the second characteristic value in X, Y and Z dimensions as a final characteristic value of the structured data in X, Y and Z dimensions; and if not, filtering the structured data.
4. The data exploration method for a data analysis engine according to claim 3, wherein: the deep learning data model is specifically a convolutional neural network model; specifically, the step S3 is,
s31, inputting the final eigenvalues of X, Y and Z dimensions of the structured data into the convolutional neural network model, performing forward exploration according to the exploration weight in the process of positive convolution and deconvolution processing, and outputting a one-dimensional forward exploration vector;
s32, performing difference processing on the one-dimensional forward exploration vector and a preset forward exploration vector to calculate a forward exploration loss vector;
s33, performing reverse exploration on the forward exploration loss vector in a chain mode to adjust the exploration weight, and returning to repeatedly execute the S31 and the S32 until the forward exploration loss vector is a zero vector;
and S34, taking the one-dimensional forward search vector finally output by the convolutional neural network model as a data search result.
5. The data exploration method for a data analysis engine according to claim 1, 2 or 4, wherein: after the step of S3, the method further comprises the following steps,
and S4, multimedia the data exploration result and displaying the data exploration result to the user through a display interface.
6. A data exploration system for a data analysis engine, comprising: comprises the following modules which are used for realizing the functions of the system,
the data acquisition module is used for acquiring external big data, and cleaning and structuring the external big data to obtain a structured data set;
the data characterization module is used for characterizing the structured data in the structured data set to obtain a characteristic value of each structured data and form a characteristic value set;
and the data exploration module is used for carrying out data exploration on the characteristic value set based on the deep learning data model to obtain a data exploration result.
7. The data exploration system for a data analysis engine of claim 6, wherein: in the data acquisition module, acquiring the external big data by adopting a data crawler, and cleaning and structuring the external big data, wherein a data crawling assembly, a data cleaning assembly and a data structuring assembly are embedded in the data crawler; the data acquisition module is specifically configured to,
and acquiring external big data by using the data crawling assembly, cleaning the external big data by using the data cleaning assembly, and structuring the cleaned external big data by using the data structuring assembly to obtain a structured data set.
8. The data exploration system for a data analysis engine according to claim 6 or 7, wherein: each structured data in the structured data set comprises X, Y structural features of three dimensions Z; the data characterisation module is particularly adapted to,
calculating characterization driving values respectively corresponding to the structural features of the three dimensions of the structured data X, Y and Z based on preset characterization granularity;
forward characterizing the structural features of the three dimensions of the structured data X, Y and Z according to characterization driving values corresponding to the structural features of the three dimensions of the structured data X, Y and Z, respectively, to obtain first feature values of the three dimensions of the structured data X, Y and Z; reversely characterizing the structural features of the three dimensions X, Y and Z of the structured data according to the structural features X, Y and the characterization driving values corresponding to the structural features of the three dimensions Z, respectively, to obtain second feature values of the three dimensions Z and X, Y of the structured data;
judging whether the first characteristic value and the second characteristic value are correspondingly matched in three dimensions of X, Y and Z; if the first characteristic value and the second characteristic value are matched, taking the average value of the first characteristic value and the second characteristic value in X, Y and Z dimensions as a final characteristic value of the structured data in X, Y and Z dimensions; and if not, filtering the structured data.
9. The data exploration system for a data analysis engine of claim 8, wherein: the deep learning data model is specifically a convolutional neural network model; the data exploration module comprises a forward exploration unit, a loss amount calculation unit, a weight value adjustment unit and a data exploration result determination unit;
the forward exploration unit is used for inputting final characteristic values of the structured data in three dimensions of X, Y and Z into the convolutional neural network model, carrying out forward exploration according to an exploration weight in the process of positive convolution and deconvolution processing, and outputting a one-dimensional forward exploration vector;
the loss amount calculation unit is used for performing difference processing on the one-dimensional forward exploration vector and a preset forward exploration vector to calculate a forward exploration loss vector;
the weight value adjusting unit is used for adjusting the exploration weight value by performing reverse exploration on the forward exploration loss vector in a chain manner, and returning to repeatedly execute the forward exploration unit and the loss amount calculating unit until the forward exploration loss vector is a zero vector;
and the data exploration result determining unit is used for taking the one-dimensional forward exploration vector finally output by the convolutional neural network model as a data exploration result.
10. The data exploration system for a data analysis engine of claim 6, 7 or 9, wherein: also comprises a data exploration result display module which is used for displaying the data exploration result,
and the data exploration result display module is used for carrying out multimedia on the data exploration result and displaying the data exploration result to a user through a display interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011381625.9A CN112579582A (en) | 2020-11-30 | 2020-11-30 | Data exploration method and system of data analysis engine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011381625.9A CN112579582A (en) | 2020-11-30 | 2020-11-30 | Data exploration method and system of data analysis engine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112579582A true CN112579582A (en) | 2021-03-30 |
Family
ID=75126561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011381625.9A Pending CN112579582A (en) | 2020-11-30 | 2020-11-30 | Data exploration method and system of data analysis engine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112579582A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5259037A (en) * | 1991-02-07 | 1993-11-02 | Hughes Training, Inc. | Automated video imagery database generation using photogrammetry |
US20020107858A1 (en) * | 2000-07-05 | 2002-08-08 | Lundahl David S. | Method and system for the dynamic analysis of data |
CN104820661A (en) * | 2015-05-11 | 2015-08-05 | 苏州国云数据科技有限公司 | Exploratory data analysis system based on business object |
CN106445914A (en) * | 2016-09-13 | 2017-02-22 | 清华大学 | Microblog emotion classifier establishing method and device |
CN108460087A (en) * | 2018-01-22 | 2018-08-28 | 北京邮电大学 | Heuristic high dimensional data visualization device and method |
CN111582440A (en) * | 2020-04-15 | 2020-08-25 | 马鞍山师范高等专科学校 | Data processing method based on deep learning |
CN111680856A (en) * | 2020-01-14 | 2020-09-18 | 国家电网有限公司 | User behavior safety early warning method and system for power monitoring system |
-
2020
- 2020-11-30 CN CN202011381625.9A patent/CN112579582A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5259037A (en) * | 1991-02-07 | 1993-11-02 | Hughes Training, Inc. | Automated video imagery database generation using photogrammetry |
US20020107858A1 (en) * | 2000-07-05 | 2002-08-08 | Lundahl David S. | Method and system for the dynamic analysis of data |
CN104820661A (en) * | 2015-05-11 | 2015-08-05 | 苏州国云数据科技有限公司 | Exploratory data analysis system based on business object |
CN106445914A (en) * | 2016-09-13 | 2017-02-22 | 清华大学 | Microblog emotion classifier establishing method and device |
CN108460087A (en) * | 2018-01-22 | 2018-08-28 | 北京邮电大学 | Heuristic high dimensional data visualization device and method |
CN111680856A (en) * | 2020-01-14 | 2020-09-18 | 国家电网有限公司 | User behavior safety early warning method and system for power monitoring system |
CN111582440A (en) * | 2020-04-15 | 2020-08-25 | 马鞍山师范高等专科学校 | Data processing method based on deep learning |
Non-Patent Citations (1)
Title |
---|
刘晓娟等: "基于关联数据的探索式检索系统研究与实现", 《图书情报工作》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537191B (en) | Three-dimensional face recognition method based on structured light camera | |
CN109214349B (en) | Object detection method based on semantic segmentation enhancement | |
CN112232214A (en) | Real-time target detection method based on depth feature fusion and attention mechanism | |
CN110120020A (en) | A kind of SAR image denoising method based on multiple dimensioned empty residual error attention network | |
CN108304920B (en) | Method for optimizing multi-scale learning network based on MobileNet | |
CN112819853B (en) | Visual odometer method based on semantic priori | |
CN111738344A (en) | Rapid target detection method based on multi-scale fusion | |
CN113989261A (en) | Unmanned aerial vehicle visual angle infrared image photovoltaic panel boundary segmentation method based on Unet improvement | |
CN111524117A (en) | Tunnel surface defect detection method based on characteristic pyramid network | |
CN114782737A (en) | Image classification method, device and storage medium based on improved residual error network | |
CN111160356A (en) | Image segmentation and classification method and device | |
CN114612306A (en) | Deep learning super-resolution method for crack detection | |
CN115439483A (en) | High-quality welding seam and welding seam defect identification system, method and storage medium | |
CN105893941A (en) | Facial expression identifying method based on regional images | |
CN114299305A (en) | Salient object detection algorithm for aggregating dense and attention multi-scale features | |
CN112579582A (en) | Data exploration method and system of data analysis engine | |
CN116935203B (en) | Diver intelligent monitoring method and system based on acousto-optic fusion | |
CN113095479A (en) | Method for extracting ice-below-layer structure based on multi-scale attention mechanism | |
CN113343760A (en) | Human behavior recognition method based on multi-scale characteristic neural network | |
CN112926595A (en) | Training device for deep learning neural network model, target detection system and method | |
CN113744205B (en) | End-to-end road crack detection system | |
CN116311492A (en) | Gesture recognition method and system based on depth camera and contour extraction | |
CN114052675B (en) | Pulse abnormality judging method and system based on fused attention mechanism | |
NL2029191B1 (en) | Autonomous underwater vehicle -based method and system for counting fish resources in river | |
CN114998866A (en) | Traffic sign identification method based on improved YOLOv4 |
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: 20210330 |