Time-Aware IoE Service Recommendation on Sparse Data

Algorithm 1

.

Inputs:

   : a set of users in user-service invocation & rating network;

  : a set of web services in user-service invocation & rating network;

  : a set of historical user-service rating records;

  : target user who requires service recommendation.

Output: : service set recommended to

  Set user similarity threshold   ()

  for  each   do // Step  1

 calculate based on (1)–(6)

 if  

  then  put into set

 end  if

  end  for

  for  each   do // Step  2

 determine ’s friend based on (6) and (8)

 if  probability in (10) is larger than

 then  put into

 end  if

 determine ’s enemy based on (6) and (7)

 if  probability in (9) is larger than

 then  put into

 end  if

  end  for

  for  each   do

 determine ’s enemy based on (6) and (7)

 if  probability in (11) is larger than

 then  put into

 end  if

 determine ’s friend based on (6) and (8)

 if  probability in (12) is larger than

 then  put into

 end  if

  end  for

  repeat Line –Line until stays stable

   // Step  3

  for  each   do

 for  each   do

  if  

  then  put into set

  end  if

 end  for

  end  for

  return