Dialogue model training method

An electronic device, comprising:

• one or more processors;
• and
• a memory storing one or more programs configured to be executed by the one or more processors, wherein the one or more programs comprising instructions for:
• obtaining a first sample dataset, wherein the first sample dataset includes at least one piece of first sample data and at least one piece of second sample data, wherein each of the at least one piece of first sample data includes a first question text and a first answer text, and wherein each of the at least one piece of second sample data includes a second question text;
• performing following first training process by using the first sample dataset to train a dialog model:
• inputting at least one first question text corresponding to the at least one piece of first sample data into the dialog model separately to obtain at least one first answer prediction result corresponding to the at least one first question text output by the dialog model;
• performing following operations for the second question text of each of the at least one piece of second sample data:
• inputting the second question text into the dialog model to obtain a second answer prediction result output by the dialog model;
• and
• inputting the second answer prediction result into a reward model to obtain a score of the second answer prediction result output by the reward model, wherein the reward model is obtained through training based on at least one sample question, a plurality of answer texts corresponding to each of the at least one sample question, and a label of each of the plurality of answer texts indicating a user satisfaction degree of corresponding answer text;
• determining a comprehensive loss based on the at least one first answer prediction result, the first answer text of each of the at least one piece of first sample data, and a score corresponding to each of the at least one piece of second sample data;
• and
• adjusting at least one parameter of the dialog model based on the comprehensive loss.

A non-transitory computer-readable storage medium, storing one or more programs comprising instructions that, when executed by one or more processors of a computing device, cause the computing device to perform operations comprising:

• obtaining a first sample dataset, wherein the first sample dataset includes at least one piece of first sample data and at least one piece of second sample data, wherein each of the at least one piece of first sample data includes a first question text and a first answer text, and wherein each of the at least one piece of second sample data includes a second question text;
• performing following first training process by using the first sample dataset to train a dialog model:
• inputting at least one first question text corresponding to the at least one piece of first sample data into the dialog model separately to obtain at least one first answer prediction result corresponding to the at least one first question text output by the dialog model;
• performing following operations for the second question text of each of the at least one piece of second sample data:
• inputting the second question text into the dialog model to obtain a second answer prediction result output by the dialog model;
• and
• inputting the second answer prediction result into a reward model to obtain a score of the second answer prediction result output by the reward model, wherein the reward model is obtained through training based on at least one sample question, a plurality of answer texts corresponding to each of the at least one sample question, and a label of each of the plurality of answer texts indicating a user satisfaction degree of corresponding answer text;
• determining a comprehensive loss based on the at least one first answer prediction result, the first answer text of each of the at least one piece of first sample data, and a score corresponding to each of the at least one piece of second sample data;
• and
• adjusting at least one parameter of the dialog model based on the comprehensive loss.