Information processing method and related device

An information processing method, wherein the method comprises:

• inputting a first question to a deep learning model, and obtaining a first answer corresponding to the first question;
• determining a second question based on the first answer, wherein the second question carries information in the first answer;
• and
• inputting the second question to the deep learning model, and obtaining a second answer corresponding to the second question, wherein the first question and the second question correspond to a same traffic scene.

An information processing method, wherein the method is used to train a deep learning model, the deep learning model comprises at least two training phases, the at least two training phases comprise a first training phase and a second training phase, and the method comprises:

• in the first training phase, inputting a third question to the deep learning model, and obtaining a predicted answer corresponding to the third question;
• and
• in the second training phase, inputting a fourth question to the deep learning model, and obtaining a predicted answer corresponding to the fourth question, wherein
• a first loss function is used to train the deep learning model;
• in the first training phase, the first loss function indicates a similarity between the predicted answer and an expected answer that correspond to the third question;
• in the second training phase, the first loss function indicates a similarity between the predicted answer and an expected answer that correspond to the fourth question;
• both the third question and the fourth question are related to a traffic scene;
• and the third question and the fourth question are used to obtain information at different levels.

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:
• input, to a deep learning model, first information corresponding to a traffic scene around an ego vehicle, wherein the first information comprises first text information;
• and
• obtain second information corresponding to the first information, wherein the second information is obtained based on the deep learning model, and the second information corresponds to any one of the following tasks:
• making a decision on behavior of the ego vehicle, planning a trajectory for the ego vehicle, or controlling the ego vehicle.