Research Article

A Type-Based Blocking Technique for Efficient Entity Resolution over Large-Scale Data

Table 1

The accuracy of splitting attributes to different blocking and attributes clustering.

NameAttribute number
EnumerationDateStringNumerical

Cylinder_out6897.06%86.67%85.71%92.6%99.67%
Cylinder_check6998.8%91.3%89.47%84.62%85.71%
Vehicle_info6198.36%87.5%84.62%90%83.33%
Gas_cylinder6698.48%91.67%87.5%83.33%99.56%
Average6698.18%89.28%86.83%87.64%92.08%