Database query based recommendation engine
Abstract:
A method may include generating a first database query to retrieve user profiles from a database. The user profiles may include a first attribute and a second attribute associated with a plurality of users. Reference data may be generated based on the user profiles. The reference data may include matrix representations of the user profiles. A clustering technique may be applied to the reference data in order to determine that a first user is similar to a second user with respect to the first attribute. In response to determining that the first user is similar to the second user, a second database query may be generated to retrieve a user profile of the first user from the database. A first recommendation for the second user may be determined based on the user profile of the first user. The first recommendation may include the second attribute of the first user.
Public/Granted literature
Information query
Patent Agency Ranking
0/0