Methods and apparatuses for showing target object sequence to target user

A computer-implemented system, comprising:

• one or more computers;
• and
• one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
• determining an initial ranking of a plurality of target objects in a target object sequence, wherein the initial ranking is performed in descending order based on correlation degrees between the plurality of target objects and a target user;
• obtaining a plurality of object features respectively corresponding to the plurality of target objects in the target object sequence;
• inputting, based on the initial ranking, the plurality of object features into a reranking model, wherein the reranking model comprises an encoder and a decoder;
• encoding the plurality of object features using the encoder to obtain a context representation vector corresponding to the target object sequence;
• obtaining a reranking of the plurality of target objects in the target object sequence based on the context representation vector using the decoder, wherein obtaining the reranking of the plurality of target objects comprises:
• processing the context representation vector into a first output vector, wherein the first output vector has a same number of dimensions as the plurality of target objects;
• applying a softmax function to the first output vector to obtain scores of the plurality of target objects;
• and
• outputting the reranking of the plurality of target objects in the target object sequence based on a descending order of the scores of the plurality of target objects;
• and
• displaying the target object sequence to the target user based on the reranking of the plurality of target objects.

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

• determining an initial ranking of a plurality of target objects in a target object sequence, wherein the initial ranking is performed in descending order based on correlation degrees between the plurality of target objects and a target user;
• obtaining a plurality of object features respectively corresponding to the plurality of target objects in the target object sequence;
• inputting, based on the initial ranking, the plurality of object features into a reranking model, wherein the reranking model comprises an encoder and a decoder;
• encoding the plurality of object features using the encoder to obtain a context representation vector corresponding to the target object sequence;
• obtaining a reranking of the plurality of target objects in the target object sequence based on the context representation vector using the decoder, wherein obtaining the reranking of the plurality of target objects comprises:
• processing the context representation vector into a first output vector, wherein the first output vector has a same number of dimensions as the plurality of target objects;
• applying a softmax function to the first output vector to obtain scores of the plurality of target objects;
• and
• outputting the reranking of the plurality of target objects in the target object sequence based on a descending order of the scores of the plurality of target objects;
• and
• displaying the target object sequence to the target user based on the reranking of the plurality of target objects.