Model training method and apparatus, service processing method and apparatus, storage medium, and device

A non-transitory computer-readable storage medium having computer executable instructions stored thereon, the computer executable instructions, when executed by one or more processors, enabling the one or more processors to, individually or collectively, implement acts comprising:

• obtaining a historical conversation;
• determining a target conversation content from the historical conversation;
• inputting the historical conversation into a to-be-trained BERT feature extraction model for the BERT feature extraction model to automatically determine a first conversation content feature corresponding to the target conversation content based on a conversation content other than the target conversation content in the historical conversation, and to automatically determine a second conversation content feature corresponding to the target conversation content based on the target conversation content;
• processing the first conversation content feature, by a first laver, to obtain a first feature;
• processing the second conversation content feature, by a second laver, to obtain a second feature;
• and
• training the BERT feature extraction model with a training goal of reducing a deviation between the first feature and the second feature, wherein the trained BERT feature extraction model is configured to determine an output conversation content feature corresponding to an input conversation content.

A computing system, comprising one or more memory devices and one or more processors, the one or more memory devices individually or collectively having computer executable instructions stored thereon, which when executed by the one or more processors, enable the one or more processors to, individually or collectively, implement acts including:

• obtaining a historical conversation;
• determining a target conversation content from the historical conversation;
• inputting the historical conversation into a to-be-trained BERT feature extraction model for the BERT feature extraction model to determine a first conversation content feature corresponding to the target conversation content based on a conversation content other than the target conversation content in the historical conversation, and to determine a second conversation content feature corresponding to the target conversation content based on the target conversation content;
• processing the first conversation content feature, by a first laver, to obtain a first feature;
• processing the second conversation content feature, by a second laver, to obtain a second feature;
• and
• training the BERT feature extraction model with a training goal of reducing a deviation between the first feature and the second feature, wherein the trained BERT feature extraction model is configured to determine an output conversation content feature corresponding to an input conversation content.