Data mining method based on item-set entropy
A data mining and itemset technology, applied in the field of data mining based on itemset entropy, can solve the problems of different importance and low accuracy of mining results, and achieve the effect of improving accuracy
Inactive Publication Date: 2017-06-06
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The technical problem to be solved by the present invention is to overcome the problem of low accuracy of mining results due to the different importance of data records and data items in the data set, and provide a data mining method based on item set entropy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0051] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.
[0052] Step 1: Preprocess the collected data and convert it into a transaction data set of the same latitude and store it in the database;
[0053] Step 2: Retrieve the database to obtain the support of the single item set and the multi-item set;
[0054] Step 3: Calculate the weight of the single item set according to the item set entropy, and calculate the weighted support of the single item set according to the weight of the single item set;
[0055] Step 4: Remove the one-itemset whose weighted support does not meet the support threshold, and obtain the weighted frequent one-itemset;
[0056] Step 5: Calculate the weight of multiple sets according to the weight of single item set, and calculate the weighted sup...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a data mining method based on item-set entropy. The method comprises the steps of preprocessing collected data and converting the data into transaction data at the same latitude and storing the transaction data in a database; retrieving the database and obtaining a support degree for single-item sets and multi-item sets; calculating the weights of the single-item sets according to the item-set entropy and calculating the weighing support degrees of the single-item sets according to the weights of the single-item sets; removing the single-item sets with the weighing support degrees not satisfying a support degree threshold, and obtaining a weighted frequent single-item set; calculating the weights of the multi-item sets according to the weights of the single-item set and calculating weighing support degrees of the multi-item sets according to the weights of the multi-item sets; removing the multi-item sets with the weighing support degrees not satisfying the support degree threshold, and obtaining a weighted frequent multi-item set; obtaining an improved association rule according to the weighting support degree and confidence degree of the weighted frequent item sets satisfying a confidence degree threshold. The method introduces the concept of item-set entropy to improve the association rule, and improves the accuracy of the association rule during data mining.
Description
technical field [0001] The invention relates to the field of data mining association rules, in particular to a data mining method based on item set entropy. Background technique [0002] Data mining refers to the extraction of knowledge that people are interested in from large databases or data warehouses, which are implicit, previously unknown and potentially useful information. Data mining is an advanced process that identifies knowledge represented by patterns from data sets. Advanced processing refers to a multi-step processing process. Multiple steps interact with each other and adjust repeatedly to form a spiral upward process. Commonly used data mining tools and methods include classification, clustering, association rules, pattern recognition, visualization, decision trees, genetic algorithms, uncertainty reasoning, etc. [0003] An association rule is a rule of the form, "Among the customers who bought bread and butter, some also bought milk" bread ten butter milk...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F17/30
CPCG06F16/2465G06F2216/03
Inventor 邓珍荣张晶晶朱益立龚敏黄文明
Owner GUILIN UNIV OF ELECTRONIC TECH