Data analysis method and system based on weighted positive and negative sequence pattern
A data analysis system, sequential mode technology, applied in manufacturing computing systems, electrical digital data processing, special data processing applications, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0063] The data analysis method based on weighted positive and negative sequence patterns of the present invention is used to mine data, including the following settings:
[0064] 1. Define the minimum support of the negative sequence
[0065] MIS(i) represents the minimum item support of item i, where i is a positive or negative item;
[0066] A positive element, that is, an event has occurred, and its minimum support is the minimum support value of item i in the element;
[0067] Negative elements, that is, no events, use the information of related positive elements to calculate their minimum support: MIS(-i)=1-MIS(i); for negative sequences Where a, b represent itemset elements, the minimum support of the negative sequence is:
[0068]
[0069] In the negative sequence Y, the item set element is e 1 ,e 2 ,...e r , the minimum support of the negative sequence Y is the minimum support value of the elements in the sequence, where the minimum support of Y is:
[0070]...
Embodiment 2
[0147] The data analysis system based on weighted positive and negative sequence patterns of the present invention is used to implement the data analysis method based on weighted positive and negative sequence patterns disclosed in Embodiment 1, including:
[0148] The positive sequence mining module is used to mine weighted frequent positive sequence patterns based on the connection operation and pruning operation in the GSP algorithm on the condition that the weighted support degree is greater than the set minimum support degree;
[0149] The candidate negative sequence mining module is used to generate a corresponding negative sequence seed set based on the 1-length positive sequence pattern in the weighted frequent positive sequence pattern, and generate a candidate negative sequence pattern by connecting;
[0150] The negative sequence mining module is used to mine weighted frequent negative sequence patterns by taking the weighted support degree greater than the set minim...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


