We are a price comparison website and currently looking for professional service to help us resolve the following issue:
We have strings of keywords variety and I'm looking for a method to identify which keywords are similar and which are not.
For example, how do we determine that the following keywords are identical products:
- "Apple iPad 32GB WiFi"
- "iPad 32 gb wi+fi"
- "Sale ipad 32gb wi fi"
- "Brand new iPad 32GB wifi MCZA1P/Z"
On other case, the above keywords are NOT similar to these:
- "Apple iPad 32GB WiFi 3G"
- "iPad 32gb+wifi+3g"
- "Apple iPad 32GB 3g WiFi"
- "Apple ipad 32GB 3g wifi exclusive deals from AT&T"
Fyi, the site is running on PHP scripts and MySQL.