Voice Assistant Video Creation With Stepwise Editing Guidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The video production process on electronic devices is complex, leading to a poor user experience, especially for users without prior experience in video production.

Innovation Solution

A video production method utilizing a voice assistant application that guides users through the process step-by-step, including features like text and audio input windows, and provides a video production template, allowing users to add text, audio, and video content, with the option to edit, enhancing user interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional video production software is used, then video production functionality is achieved, but the process becomes complex and user experience deteriorates

Engineering Contradiction:
Improvevideo production process simplicityVSAvoidvideo production process complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The video production process is segmented into distinct stages: image selection, video generation, and text addition. Each stage is handled through separate, simplified interfaces (dialog page for video generation, text edit window for text addition), allowing users to complete tasks step-by-step without being overwhelmed by the entire process at once.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The voice assistant application serves as an intermediary between the user and the complex video production system. It provides a simplified dialog-based interface that mediates user requests and translates them into appropriate video generation and text addition operations, shielding users from underlying system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If comprehensive video production features are provided, then user customization capability is improved, but operation difficulty increases

Engineering Contradiction:
Improvevideo customization capabilityVSAvoidoperation difficulty
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system dynamically adapts its interface based on user needs. The text edit window appears only when users choose to add text, and the system provides context-aware recommendations for text content based on the selected images and video theme, making the customization process adaptive rather than static and overwhelming.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system provides self-service through automated text recommendations generated based on the video theme and selected images. Users can accept these recommendations or modify them, eliminating the need for users to manually create text content from scratch and reducing operation difficulty while maintaining customization capability.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4661408A1Video creation method and electronic device
Publication Date: 2025.12.10 HONOR DEVICE CO LTD
  • EP4661408A1 patent drawingFigure 1
  • EP4661408A1 patent drawingFigure 2
  • EP4661408A1 patent drawingFigure 3A

AI summary

This application provides a video production method and an electronic device, and relates to the field of terminal technologies. The electronic device displays a dialog page of a voice assistant application. In response to a user operation of tapping a video generation control by a user, the electronic device generates a first video, and displays a preview prompt window of the first video in the dialog page. After displaying the preview prompt window of the first video, the electronic device displays a video add card in the dialog page. If receiving a user operation of the user on the first control, the electronic device displays a text edit window in the dialog page. The electronic device obtains text content in the text edit window, and further generates a second video based on the text content and the first video, and displays a preview prompt window of the second video in the dialog page. In this way, the voice assistant application of the electronic device can guide the user to complete video production step by step, to reduce operation difficulty of the user.