| CPC G06T 17/00 (2013.01) [G06T 13/40 (2013.01); G06V 40/171 (2022.01); G06V 40/174 (2022.01); G06V 40/193 (2022.01); G06V 40/20 (2022.01)] | 20 Claims |

|
1. A virtual role-based multimodal interaction method, comprising:
acquiring input information, wherein the input information comprises one or more data types;
inputting the input information into a perception layer to enable the perception layer to recognize and process the input information according to a data type of the input information to obtain a recognition result;
inputting the recognition result into a logic decision-making layer to enable the logic decision-making layer to process the recognition result and generate a drive instruction corresponding to the recognition result;
acquiring multimodal virtual content according to the drive instruction, wherein the multimodal virtual content at least comprises a virtual role; and
outputting the acquired multimodal virtual content;
wherein the logic decision-making layer comprises a logic decision-making model, the logic decision-making model is trained based on training samples, the training samples are samples of the recognition result and samples of the drive instruction, and the training samples comprise a training set and a test set.
|