| 摘要 |
<p>A recommender engine (100) for recommending content items to a user comprises
- a profile generation unit having a pre-profile input unit (110), which is configured to receive pre-profile data comprising pre-profile text data suitable for identifying entities of interest to a given user, and having a pre-profile analysis unit (112), which is connected with the pre-profile input unit (110) and configured to extract from the pre-profile data identification data identifying the entities of interest and to generate an initial user profile data set for the given user from the extracted identification data;
- a query generation unit (120) , which is connected with the profile generation unit and configured to generate, using the extracted identification data from the initial user profile data set, at least two queries semantically different from each other to be directed to at least one content repository;
- a content retrieval unit (128), which is connected with the query generation unit (120) and configured to issue the generated queries to the at least one content repository (122) and which is configured to receive from the at least one content repository, in response to the queries, content-related response data comprising respective hit lists having at least one respective content-location identifier indicative of a storage location of a respective content item; and
- an interleaver unit (132), which is connected with the content retrieval unit and which is configured to generate from the different hit lists a single recommendation list by interleaving the content-location identifiers comprised in different ones of the hit lists with each other.</p> |
