Learning Users’ Intention of Legal Consultation through Pattern-Oriented Tensor Decomposition with Bi-LSTM

Algorithm 2

Optimization method of users’ legal consulting pattern.

Input: , where is the user’s legal consulting statement and represents category that corresponds to

   , and the size of , , , , , , , and , where , ,

    and

Output: The optimal users’ legal consultation pattern , parameters of Bi-LSTM , , , , , ,

    and .

1 Initialize users’ legal consultation pattern , parameters of Bi-LSTM , , , , , , and ;

2 for   to   do

3   Set to zero;

4   while    do

5    Set , , , , , , ,

     , to zero;

6    for   to   do

7       ;

8       ;

9       , , , , , , , ,

       ;

10   end

11   , , , , , , , , ,,

    , , , , , , , , ;

12   end

13 end

14   return , , , , , , , and ;