Data processing method and related device

A data processing method, wherein the method comprises:

• obtaining attribute information of a user and attribute information of an item;
• obtaining first preference information of the user for the item based on the attribute information by using a second neural network model;
• predicting second preference information of the user for the item based on actual interaction duration of the user for the item and a cost variable by using a preset second mapping relationship, wherein the cost variable is information that affects interaction duration of the user for the item;
• and
• updating the second neural network model and the cost variable based on the first preference information and the second preference information.

An electronic device, comprising:

• a memory configured to store instructions;
• and
• a processor, coupled to the memory, is configured to execute the instructions to cause the electronic device to:
• obtain attribute information of a user and attribute information of an item;
• and
• obtain preference information of the user for the item based on the attribute information;
• determine predicted interaction duration of the user for the item based on the preference information and a cost variable by using a preset first mapping relationship, wherein the cost variable is information that affects interaction duration of the user for the item;
• and
• recommend the item to the user when the predicted interaction duration meets a preset condition.

An electronic device, comprising:

• a memory configured to store instructions;
• and
• a processor, coupled to the memory, is configured to execute the instructions to cause the electronic device to:
• obtain attribute information of a user and attribute information of an item;
• and
• obtain first preference information of the user for the item based on the attribute information by using a second neural network model;
• predict second preference information of the user for the item based on actual interaction duration of the user for the item and a cost variable by using a preset second mapping relationship, wherein the cost variable is information that affects interaction duration of the user for the item;
• and
• update the second neural network model and the cost variable based on the first preference information and the second preference information.