CN109902110A - A kind of system and method for multi-dimensional data assessment otherness - Google Patents
A kind of system and method for multi-dimensional data assessment otherness Download PDFInfo
- Publication number
- CN109902110A CN109902110A CN201910163348.5A CN201910163348A CN109902110A CN 109902110 A CN109902110 A CN 109902110A CN 201910163348 A CN201910163348 A CN 201910163348A CN 109902110 A CN109902110 A CN 109902110A
- Authority
- CN
- China
- Prior art keywords
- individual
- level
- curved surface
- data
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims description 14
- 238000007405 data analysis Methods 0.000 claims description 7
- 241001269238 Data Species 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000012106 screening analysis Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 206010021703 Indifference Diseases 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000002716 delivery method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of system and method for multi-dimensional data assessment otherness, method includes: Step 1: multi-dimensional data is carried out to sort out division processing；Step 2: drawing " the second level individual single index density curve " of all second level individuals；Step 3: drawing " the second level individual multi objective curved surface " of all second level individuals；Step 4: drawing " complete or collected works' indexed basis curved surface "；Step 5: extracting the highlights correlations index set of " the second level individual single index density curve " and " second level individual multi objective curved surface " after fitting；Step 6: extracting the highlights correlations index set on " the second level individual multi objective curved surface " and " complete or collected works' indexed basis curved surface " after fitting；Step 7: building " individual evaluation index curved surface "；Step 8: building " evaluation index benchmark curved surface "；Step 9: the otherness of assessment level-one individual data items and complete or collected works' data.Screening analysis is carried out to multi-dimensional data, and assesses the otherness of level-one individual data items and complete or collected works' data.
Description
Technical field
The present invention relates to the technical fields of data analysis, more particularly, to a kind of system of multi-dimensional data assessment otherness
And method.
Background technique
In data economy era, for all trades and professions just using data as core, the feature of maintenance data removes remodeling mode.According to
It has been gradually formed at present according to the new production mode of information technology, delivery method, adventure in daily life and administrative decision ability, China
The blank of " data socialization ".So-called " data socialization " is exactly that data can be used coequally by each level of society, it breaks
Physics boundary in reality, penetrates into social every nook and cranny.Ecology is realized between data-driven virtual world and society
Interaction, social resources can be reintegrated in identical platform, share, analyze, and finally realizes that its social application is worth.
Most crucial content is exactly data in data socialization process.But the existing acquisition scene of data source header isolates, is most strong
Related data is rare, the not high variety of problems of the quality of data, and high granular state is presented in data, the reality of Conjoint Analysis between data
Example is less, and data have stronger isolation, greatly hinders the development and propulsion of big data application.It is recognized herein that causing above-mentioned
Problem mainly has two aspect reasons, first is that different corner (such as credits of individual cell (such as natural person, legal person, enterprise, equipment)
Assessment, value assessment, promise breaking assessment) assessment, lack more unified theoretical model, can not be by separate sources, various dimensions
Data are effectively unified, second is that can not carry out since the data target of individual cell and data volume presence are greatly unbalanced
Equal amount of data assessment；And total amount of data is huger, the lack of uniformity is about obvious, therefore to traditional full-page proof based on tool vector
Notebook data analysis method proposes stern challenge.Herein for the above two large problems, one kind is proposed to all individual cells
Carry out what indifference was treated, the method for evaluating otherness between single individual data items and whole multi-dimensional data can be used in commenting
Skewed popularity of the valence such as personal credit degree in social whole credit rating.
Summary of the invention
One of purpose of the invention is to provide a kind of method of multi-dimensional data assessment otherness.
Foregoing invention purpose of the invention has the technical scheme that a kind of multi-dimensional data assessment is poor
Anisotropic method, comprising:
Step 1: multi-dimensional data is carried out to sort out division processing；
By multi-dimensional data according to the different demarcation level-one individual of data source individual, all level-one individuals with general character are classified as
The same second level individual, all second level individual integration are used as complete or collected works；
And the different achievement datas of same individual are divided, and by all achievement datas according to respective value in same index value
In accounting generalization processing form unified index density；
Step 2: drawing " the second level individual single index density curve " of all second level individuals；
Step 3: drawing " the second level individual multi objective song of all second level individuals according to " second level individual single index density curve "
Face "；
Step 4: according to " second level individual multi objective curved surface " drafting " complete or collected works' indexed basis curved surface "；
Step 5: the height for extracting " the second level individual single index density curve " and " second level individual multi objective curved surface " after fitting is closed
Join index set；
Step 6: " the second level individual multi objective curved surface " that extracts after fitting refers to the highlights correlations on " complete or collected works' indexed basis curved surface "
Mark set；
Step 7: building " individual evaluation index curved surface "；
Step 8: building " evaluation index benchmark curved surface "；
Step 9: the otherness of assessment level-one individual data items and complete or collected works' data.
By using above-mentioned technical proposal, screening analysis is carried out to multi-dimensional data, and assesses level-one individual data items and complete
Collect the otherness of data.
The present invention is further arranged to: in step 2, by the same index number of the intraindividual all level-one individuals of identical second level
According to the coordinate system upper set at " time --- index density ", fitting theory using Moving Least based on point, from
Define match point between scatterplot, divide support region radius, assign the weight of each point in support region, make the weight of point of proximity change by
Step decaying, realizes the partial approximation of matched curve, ultimately forms " second level individual single index density curve ".
By using above-mentioned technical proposal, the curve that a certain index of second level individual changes along timeline is obtained.
The present invention is further arranged to: in step 3, by all " second level individual single index density songs of identical second level individual
Line " is in the coordinate system upper set of " time --- index density --- individual pointer type ", by all " individual lists of same individual
Index curve " obtains required coefficient by least square method, generates fit equation, substitutes into initial data and obtains fitting result,
Finally it is fitted to " second level individual multi objective curved surface ".
By using above-mentioned technical proposal, it is calculated what the different indexs of same individual were formed along timeline comprehensive change
Curved surface.
The present invention is further arranged to: in step 4, all " second level individual multi objective curved surfaces " being utilized least square
Then method finds out nodal value on mesh point first by fitted area gridding, finally connect grid node formation be fitted to one it is whole
Body curved surface ultimately forms " complete or collected works' indexed basis curved surface ".
By using above-mentioned technical proposal, it is calculated what the different indexs of complete or collected works' data were formed along timeline comprehensive change
Curved surface.
The present invention is further arranged to:, will each " second level individual single index density curve " and " second level individual in step 5
Multi objective curved surface " compares, and calculating each " second level individual single index density curve " is inclined with " second level individual multi objective curved surface "
Margin P1, when P1 be less than or equal to setting value a1 when, then should " second level individual single index density curve " be included into highlights correlations index
Set M1；When P1 is greater than the set value a1, then not should " second level individual single index density curve " be included into highlights correlations index set
Close M1.
By using above-mentioned technical proposal, when the P1 value acquired is greater than the set value a1, judges the index curve and refer to more
The correlation degree for marking curve is lower, judges that the index of individual is the index for not meeting screening and requiring, excludes the data, increase meter
Calculate the accuracy of result.
The present invention is further arranged to:, will each " second level individual multi objective curved surface " and " complete or collected works' indexed basis in step 6
Curved surface " compares, and calculates the degree of deviation P2 of each " second level individual multi objective curved surface " and " complete or collected works' indexed basis curved surface "；Work as P2
When less than or equal to setting value a2, then should " second level individual single index density curve " be included into highlights correlations index set M2；Work as P2
When being greater than the set value a2, then not should " second level individual single index density curve " be included into highlights correlations index set M2.
By using above-mentioned technical proposal, when the P2 value acquired is greater than the set value a1, the multi objective curved surface and complete is judged
The correlation degree for collecting indexed basis is lower, judges the individual not meet the individual that screening requires, excludes the data, increases and calculate
As a result accuracy.
The present invention is further arranged to: in step 7, two belonging to " the second level individual single index density curve " in M1
When " the second level individual multi objective curved surface " of grade individual belongs to M2 simultaneously, extracting should " second level individual single index density curve " building
" the second level individual single index density curve " of all extractions is passed through least square by the method for " second level individual multi objective curved surface "
Method is fitted to " individual evaluation index curved surface ".
By using above-mentioned technical proposal, " the individual evaluation index song of each individual is formed by the data after screening
Face ".
The present invention is further arranged to: in step 8, according to the building mode of " complete or collected works' indexed basis curved surface ", by all ginsengs
" evaluation index benchmark curved surface " is fitted to by least square method with " the individual evaluation index curved surface " of assessment.
By using above-mentioned technical proposal, " evaluation index benchmark curved surface " is formed by the data after screening, due to using
Be effective manifold, therefore result is more accurate.
The present invention is further arranged to: in step 9, level-one individual data items and " evaluation index benchmark curved surface " being compared, meter
Calculate all indexs accumulation vector deviation with " evaluation index benchmark curved surface " on the time line of level-one individual.
By using above-mentioned technical proposal, the otherness of first order calculation individual data items and complete or collected works' data.
It is a further object to provide a kind of systems of multi-dimensional data assessment otherness.
Foregoing invention purpose of the invention has the technical scheme that a kind of various dimensions assessment otherness
System, including input module, data statistics module, data screening module, data analysis module；
Input module, for inputting the data for needing to analyze；
Data modeling module establishes two dimensional model according to the variation that the same data of same individual occur at any time, and according to same
The different data of one individual establishes threedimensional model；
Screening module, the high data of the screening degree of association；
Data analysis module analyzes the high degree of association data of all individuals, judges deviation of the single individual in entirety
Property.
By using above-mentioned technical proposal, multi-dimensional data is analyzed by above system and method, and evaluates it
In all single individuals data skewed popularity.
In conclusion advantageous effects of the invention are as follows:
1. screening analysis can be carried out to multi-dimensional data, and assess the otherness of level-one individual data items and complete or collected works' data；
2. " evaluation index benchmark curved surface " is formed by the data after screening, since using effective manifold, result is more
Accurately.
Detailed description of the invention
Fig. 1 is second level individual single index densogram；
Fig. 2 is second level individual multi objective surface chart；
Fig. 3 is complete or collected works' indexed basis surface chart；
Fig. 4 is individual evaluation index surface chart；
Fig. 5 is evaluation index benchmark surface chart.
Specific embodiment
Below in conjunction with attached drawing, invention is further described in detail.
A kind of system of various dimensions assessment otherness, including input module, data statistics module, data screening module, number
According to analysis module.
Input module, for inputting the data for needing to analyze.
Data modeling module establishes two dimensional model, and root according to the variation that the same data of same individual occur at any time
Threedimensional model is established according to the different data of same individual.
Screening module, the high data of the screening degree of association.
Data analysis module analyzes the high degree of association data of all individuals, judges single individual in entirety
Skewed popularity.
A kind of method of multi-dimensional data assessment otherness, comprising:
Step 1: multi-dimensional data is carried out to sort out division processing；
By multi-dimensional data according to the different demarcation level-one individual of data source individual, all level-one individuals with general character are classified as
The same second level individual, all second level individual integration are used as complete or collected works.
The different achievement datas of same individual are divided into a class data, b class data, c class data ....And by all indexs
Data form unified index density according to accounting generalization processing of the respective value in same index value.
Step 2: drawing single class index curve of all second level individuals；
By the same achievement data of the intraindividual all level-one individuals of identical second level " time x --- index density y " coordinate system
Upper set is drawn as shown in Figure 1, the fitting theory using Moving Least based on point, defines match point between discrete point
Divide support region radius, assign the weight of each point in support region, changes the weight of point of proximity and gradually decay, realize matched curve
Partial approximation, ultimately form " second level individual single index density curve " F.
Step 3: drawing the multi objective curved surface of all second level individuals；
By all " the second level individual single index density curves " of identical second level individual in " time x --- index density y --- individual
The coordinate system upper set of pointer type z ", as shown in Fig. 2, all " the individual single index curves " of same individual is passed through minimum two
Multiplication obtains required coefficient, generates fit equation, substitutes into initial data and obtains fitting result, is finally fitted to " second level individual
Multi objective curved surface " S.
Step 4: drawing " complete or collected works' indexed basis curved surface "；
All " second level individual multi objective curved surfaces " is gathered, as shown in figure 3, using least square method, first by fitted area grid
Change, then find out nodal value on mesh point, finally connects grid node formation and be fitted to a whole curved surface, ultimately form " complete
Collect indexed basis curved surface " B.
Step 5: extracting the height of " the second level individual single index density curve " and " second level individual multi objective curved surface " after fitting
Spend coupling index set；
Each " second level individual single index density curve " is compared with " second level individual multi objective curved surface ", calculates each " second level
The degree of deviation of individual single index density curve " and " second level individual multi objective curved surface ":
Wherein t is the total time span of data statistics.
When P1 be less than or equal to setting value a1 when, then should " second level individual single index density curve " be included into highlights correlations index
Set M1.
When P1 is greater than the set value a1, then not should " second level individual single index density curve " be included into highlights correlations index set
Close M1.
Step 6: the height extracted on " the second level individual multi objective curved surface " and " complete or collected works' indexed basis curved surface " after fitting is closed
Join index set；
Each " second level individual multi objective curved surface " is compared with " complete or collected works' indexed basis curved surface ", calculating is each, and " second level individual is more
The degree of deviation of index curved surface " and " complete or collected works' indexed basis curved surface ":
When P2 be less than or equal to setting value a2 when, then should " second level individual single index density curve " be included into highlights correlations index set
M2。
When P2 is greater than the set value a2, then not should " second level individual single index density curve " be included into highlights correlations index set
Close M2.
Step 7: building " individual evaluation index curved surface "；
" the second level individual multi objective curved surface " of the second level individual belonging to " the second level individual single index density curve " in M1 is simultaneously
When belonging to M2, the method for being somebody's turn to do " second level individual single index density curve " building " second level individual multi objective curved surface " is extracted, such as Fig. 4 institute
Show, " the second level individual single index density curve " of all extractions is fitted to " individual evaluation index song by least square method
Face " S '.
Step 8: building " evaluation index benchmark curved surface "；
As shown in figure 5, according to the building mode of " complete or collected works' indexed basis curved surface ", by all " individual evaluation indexes for participating in assessment
Curved surface " is fitted to " evaluation index benchmark curved surface " B ' by least square method.
Step 9: the otherness of assessment level-one individual data items and complete or collected works' data；
By level-one individual data items and its deviation of " evaluation index benchmark curved surface " comparative evaluation.
The a certain index of the level-one individual vector deviation with " evaluation index benchmark curved surface " at some time point are as follows:
The a certain index of the level-one individual accumulation vector deviation with " evaluation index benchmark curved surface " on the time line are as follows:
All indexs of level-one individual accumulation vector deviation with " evaluation index benchmark curved surface " on the time line are as follows:
The embodiment of present embodiment is presently preferred embodiments of the present invention, not limits protection model of the invention according to this
Enclose, therefore: the equivalence changes that all structures under this invention, shape, principle are done, should all be covered by protection scope of the present invention it
It is interior.
Claims (10)
1. a kind of method of multi-dimensional data assessment otherness, characterized in that include:
Step 1: multi-dimensional data is carried out to sort out division processing；
By multi-dimensional data according to the different demarcation level-one individual of data source individual, all level-one individuals with general character are classified as
The same second level individual, all second level individual integration are used as complete or collected works；
And the different achievement datas of same individual are divided, and by all achievement datas according to respective value in same index value
In accounting generalization processing form unified index density；
Step 2: drawing " the second level individual single index density curve " of all second level individuals；
Step 3: drawing " the second level individual multi objective song of all second level individuals according to " second level individual single index density curve "
Face "；
Step 4: according to " second level individual multi objective curved surface " drafting " complete or collected works' indexed basis curved surface "；
Step 5: the height for extracting " the second level individual single index density curve " and " second level individual multi objective curved surface " after fitting is closed
Join index set；
Step 6: " the second level individual multi objective curved surface " that extracts after fitting refers to the highlights correlations on " complete or collected works' indexed basis curved surface "
Mark set；
Step 7: building " individual evaluation index curved surface "；
Step 8: building " evaluation index benchmark curved surface "；
Step 9: the otherness of assessment level-one individual data items and complete or collected works' data.
2. the method for multi-dimensional data assessment otherness according to claim 1, characterized in that, will be identical in step 2
The same achievement data of the intraindividual all level-one individuals of second level utilizes shifting in the coordinate system upper set of " time --- index density "
Dynamic fitting theory of the least square method based on point, defines match point between discrete point, divides support region radius, assigns support region
The weight of interior each point changes the weight of point of proximity and gradually decays, realizes the partial approximation of matched curve, ultimately form " two
The individual single index density curve of grade ".
3. the method for multi-dimensional data assessment otherness according to claim 2, characterized in that, will be identical in step 3
All " the second level individual single index density curves " of second level individual is at " time --- index density --- individual pointer type "
All " the individual single index curves " of same individual is obtained required coefficient by least square method by coordinate system upper set, raw
At fit equation, substitutes into initial data and obtain fitting result, be finally fitted to " second level individual multi objective curved surface ".
4. the method for multi-dimensional data assessment otherness according to claim 3, characterized in that in step 4, will own
Then " second level individual multi objective curved surface " finds out node on mesh point first by fitted area gridding using least square method
Value finally connects grid node formation and is fitted to a whole curved surface, ultimately forms " complete or collected works' indexed basis curved surface ".
5. the method for multi-dimensional data assessment otherness according to claim 4, characterized in that, will be each in step 5
" second level individual single index density curve " calculates each " second level individual single index compared with " second level individual multi objective curved surface "
The degree of deviation P1 of density curve " and " second level individual multi objective curved surface " then should " second level when P1 is less than or equal to setting value a1
Individual single index density curve " is included into highlights correlations index set M1；It, then should " second level when P1 is greater than the set value a1
Body single index density curve " is included into highlights correlations index set M1.
6. the method for multi-dimensional data assessment otherness according to claim 5, characterized in that, will be each in step 6
" second level individual multi objective curved surface " compared with " complete or collected works' indexed basis curved surface ", calculate each " second level individual multi objective curved surface " with
The degree of deviation P2 of " complete or collected works' indexed basis curved surface "；It, then should " second level individual single index be close when P2 is less than or equal to setting value a2
Write music line " it is included into highlights correlations index set M2；It, then should " second level individual single index density when P2 is greater than the set value a2
Curve " is included into highlights correlations index set M2.
7. the method for multi-dimensional data assessment otherness according to claim 6, characterized in that in step 7, when in M1
" second level individual single index density curve " belonging to second level individual " second level individual multi objective curved surface " simultaneously when belonging to M2, take out
The method for taking " the second level individual single index density curve " building " second level individual multi objective curved surface " the, by " second level of all extractions
Individual single index density curve " is fitted to " individual evaluation index curved surface " by least square method.
8. the method for multi-dimensional data assessment otherness according to claim 7, characterized in that in step 8, according to " complete
The building mode of collection indexed basis curved surface ", all " individual evaluation index curved surfaces " for participating in assessment are quasi- by least square method
It synthesizes " evaluation index benchmark curved surface ".
9. the method for multi-dimensional data assessment otherness according to claim 8, characterized in that in step 9, by level-one
Individual data items and " evaluation index benchmark curved surface " compare, all indexs of first order calculation individual on the time line with " evaluation index
The accumulation vector deviation of benchmark curved surface ".
10. a kind of system of various dimensions assessment otherness, it is characterized in that: including input module, data statistics module, data screening
Module, data analysis module；
Input module, for inputting the data for needing to analyze；
Data modeling module establishes two dimensional model according to the variation that the same data of same individual occur at any time, and according to same
The different data of one individual establishes threedimensional model；
Screening module, the high data of the screening degree of association；
Data analysis module analyzes the high degree of association data of all individuals, judges deviation of the single individual in entirety
Property.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2018113963509 | 2018-11-22 | ||
| CN201811396350 | 2018-11-22 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109902110A true CN109902110A (en) | 2019-06-18 |
| CN109902110B CN109902110B (en) | 2024-03-01 |
Family
ID=66946265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910163348.5A Active CN109902110B (en) | 2018-11-22 | 2019-03-05 | System and method for evaluating variability of multidimensional data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109902110B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845767A (en) * | 2016-12-16 | 2017-06-13 | 浙江大学 | A kind of industry development in science and technology power quantitative estimation method and assessment system |
| CN107454105A (en) * | 2017-09-15 | 2017-12-08 | 北京理工大学 | A kind of multidimensional network safety evaluation method based on AHP and grey correlation |
-
2019
- 2019-03-05 CN CN201910163348.5A patent/CN109902110B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845767A (en) * | 2016-12-16 | 2017-06-13 | 浙江大学 | A kind of industry development in science and technology power quantitative estimation method and assessment system |
| CN107454105A (en) * | 2017-09-15 | 2017-12-08 | 北京理工大学 | A kind of multidimensional network safety evaluation method based on AHP and grey correlation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109902110B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wei et al. | Urban land expansion and regional inequality in transitional China | |
| CN104462184B (en) | A kind of large-scale data abnormality recognition method based on two-way sampling combination | |
| CN110413707A (en) | The excavation of clique's relationship is cheated in internet and checks method and its system | |
| CN106355011B (en) | Geochemical data element sequence structure analysis method and device | |
| CN106384282A (en) | Method and device for building decision-making model | |
| CN103775075B (en) | A kind of full well section Lithology Identification Methods | |
| CN106845717A (en) | A kind of energy efficiency evaluation method based on multi-model convergence strategy | |
| CN112417176B (en) | Method, equipment and medium for mining implicit association relation between enterprises based on graph characteristics | |
| CN106991446A (en) | A kind of embedded dynamic feature selection method of the group policy of mutual information | |
| CN110619084B (en) | Method for recommending books according to borrowing behaviors of library readers | |
| CN105678590A (en) | topN recommendation method for social network based on cloud model | |
| CN107491508A (en) | A kind of data base querying time forecasting methods based on Recognition with Recurrent Neural Network | |
| Liu et al. | Application of hierarchical clustering in tax inspection case-selecting | |
| CN106980930A (en) | It is a kind of to carry out the method that population migrates analysis with big data multi-point contact technology | |
| CN110263021A (en) | A kind of theme library generating method based on personalized labels system | |
| CN107944750A (en) | A kind of poverty depth analysis method and system | |
| Aldi et al. | University Student Satisfaction Analysis on Academic Services by Using Decision Tree C4. 5 Algorithm (Case Study: Universitas Putra Indonesia “yPTK” Padang) | |
| CN101404073B (en) | Complex product fuzz hierarchy collocation method | |
| CN106326335A (en) | Big data classification method based on significant attribute selection | |
| CN109684460A (en) | A kind of calculation method and system of the negative network public-opinion index based on deep learning | |
| CN106815320B (en) | Investigation big data visual modeling method and system based on expanded three-dimensional histogram | |
| CN109902110A (en) | A kind of system and method for multi-dimensional data assessment otherness | |
| Singh et al. | Performance analysis of faculty using data mining techniques | |
| CN109828995A (en) | A kind of diagram data detection method, the system of view-based access control model feature | |
| CN109523143B (en) | Land evaluation method based on multi-granularity calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |