Scene rendering method and device, storage medium and electronic equipment

Abstract

The invention provides a scene rendering method and device, a storage medium and electronic equipment, and the method comprises the steps: receiving a rendering instruction sent by a user through a client, and obtaining a question text and a response text corresponding to the rendering instruction; performing semantic scene analysis on the question text and the response text, and determining a semantic scene corresponding to the rendering instruction; and acquiring a scene picture sequence corresponding to the semantic scene, generating a scene rendering data stream based on the scene picture sequence, and sending the scene rendering data stream to the client, so that the client renders response data by applying the scene rendering data stream. The semantic scene is determined by analyzing the question text and the response text, and the scene rendering data stream is generated based on the scene picture sequence corresponding to the semantic scene, so that the client renders the response scene based on the scene rendering data stream, a neural network does not need to be trained for each scene in the process, the time and cost investment can be reduced, and the scene rendering cost is reduced.

Description

technical field [0001] The present invention relates to the technical field of human-computer interaction, and in particular to a scene rendering method and device, a storage medium and electronic equipment. Background technique [0002] With the development of computer technology, there are more and more scenarios where digital humans can be applied. When using digital humans to provide services to customers, it can provide customers with an immersive experience by rendering the scenes involved in the interaction process between customers and digital humans. , thus providing customers with better application experience and services. [0003] The current 2D digital human is rendered using a neural network. In order to render scenes to customers and achieve an immersive effect, the neural network needs to be trained for each scene in order to render the corresponding scene, and the number and types of scenes are numerous. , it takes a lot of time and cost to train the neural...

AI Technical Summary

Problems solved by technology

[0003] The current 2D digital human is rendered using a neural network. In order to render scenes to customers and achieve an immersive effect, the neural network needs to be trained for each scene in order to render the corresponding scene, and the number and types of scenes are numerous. , it takes a lot of time and cost to train the neural network, resulting in a lot of cost to render the scene using the current method

Images