Method and apparatus for recalling news based on artificial intelligence, device and storage medium

A computer device, comprising a memory, a processor and a computer program which is stored on the memory and runs on the processor, wherein the processor, upon executing the program, implements the following operation:

• building an index repository according to candidate news, the index repository including M search trees, M being a positive integer, each search tree being a complete binary tree including at least two layers, each non-leaf node in each search tree corresponding to a semantic index vector, each piece of candidate news corresponding to a leaf node in each search tree;
• when news needs to be recommended to a user, generating the user's semantic index vector according to the user's interest tag;
• with respect to each search tree, regarding a first layer of non-leaf nodes in the search tree as a start of a path, and regarding the first layer of non-leaf nodes as to-be-processed non-leaf nodes, determining a path from a first layer of non-leaf nodes to a leaf node, and regarding candidate news corresponding to the leaf node on the path as a recall result by performing the following processing:
• performing linear projection for the user's semantic index vector and semantic index vectors corresponding to the to-be-processed non-leaf nodes, selecting a node from next layer of nodes of the to-be-processed non-leaf nodes according to a projection result, and adding the node into the path;
• wherein the selecting a node from next layer of nodes of the to-be-processed non-leaf nodes according to a projection result comprises:
• when the projection result is positive, regarding a left node in the next layer of nodes as the selected node, when the projection result is negative, regarding a right node in the next layer of nodes as the selected node;
• or, when the projection result is negative, regarding a left node in the next layer of nodes as the selected node, when the projection result is positive, regarding a right node in the next layer of nodes as the selected node;
• when the selected node is a non-leaf node, regarding the selected non-leaf node as the to-be-processed non-leaf node, and repeatedly performing the predetermined processing;
• when the selected node is a leaf node, regarding candidate news corresponding to the leaf node as the recall result.

A computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements the following operation:

• building an index repository according to candidate news, the index repository including M search trees, M being a positive integer, each search tree being a complete binary tree including at least two layers, each non-leaf node in each search tree corresponding to a semantic index vector, each piece of candidate news corresponding to a leaf node in each search tree;
• when news needs to be recommended to a user, generating the user's semantic index vector according to the user's interest tag;
• with respect to each search tree, regarding a first layer of non-leaf nodes in the search tree as a start of a path, and regarding the first layer of non-leaf nodes as to-be-processed non-leaf nodes, determining a path from a first layer of non-leaf nodes to a leaf node, and regarding candidate news corresponding to the leaf node on the path as a recall result by performing the following processing:
• performing linear projection for the user's semantic index vector and semantic index vectors corresponding to the to-be-processed non-leaf nodes, selecting a node from next layer of nodes of the to-be-processed non-leaf nodes according to a projection result, and adding the node into the path;
• wherein the selecting a node from next layer of nodes of the to-be-processed non-leaf nodes according to a projection result comprises:
• when the projection result is positive, regarding a left node in the next layer of nodes as the selected node, when the projection result is negative, regarding a right node in the next layer of nodes as the selected node;
• or, when the projection result is negative, regarding a left node in the next layer of nodes as the selected node, when the projection result is positive, regarding a right node in the next layer of nodes as the selected node;
• when the selected node is a non-leaf node, regarding the selected non-leaf node as the to-be-processed non-leaf node, and repeatedly performing the predetermined processing;
• when the selected node is a leaf node, regarding candidate news corresponding to the leaf node as the recall result.