Face Group Video Generation for Faster Portrait Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Complex video composition operations lead to low convenience for users due to difficulties in managing and naming face groups in video generation.

Innovation Solution

An electronic device provides a video generation method with a video production window displaying theme cards, operation windows for selecting video themes, and selection windows for facial images, allowing users to efficiently select and name face groups and portrait materials based on facial images, enhancing video composition efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If users manually manage and name face groups in video generation, then video composition accuracy can be improved, but operation complexity increases and convenience decreases

Engineering Contradiction:
Improvevideo composition accuracyVSAvoidoperation convenience
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The system automatically performs face recognition and grouping operations without requiring manual user intervention. The electronic device autonomously identifies facial images in portrait materials, groups them by person, and generates face groups with automatic naming, allowing the system to serve itself in the face management task.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs face recognition and face group generation in advance before video composition begins. By pre-processing the portrait materials to create organized face groups with identifying names, the system prepares the data structure beforehand, eliminating the need for manual management during the actual video creation process.

Inventive Principle:
Principle #10Preliminary action

2Manufacturing precision

If the system provides detailed face group management options, then video generation accuracy improves, but the number of operations and time required increases

Engineering Contradiction:
Improveface group selection accuracyVSAvoidtime for face group selection
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs face recognition and organizes face groups before the user initiates video generation. By pre-processing and preparing the face group data structure with automatic naming conventions, the system eliminates time-consuming manual management steps during actual video creation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The electronic device autonomously identifies facial images, groups them by person, and generates structured face group data without requiring user intervention. This self-service approach to face management significantly reduces the time users would otherwise spend on manual organization while maintaining high accuracy.

Inventive Principle:
Principle #25Self-service

3Manufacturing precision

If the system requires manual selection of each portrait material, then composition accuracy improves, but operation complexity and time consumption increase

Engineering Contradiction:
Improveportrait material selection accuracyVSAvoidvideo generation efficiency
Core Design Contradiction:
Manufacturing precisionVSProductivity

Solution Approach 1:

The system pre-organizes portrait materials into structured face groups with automatic naming before video composition begins. This preliminary organization allows the system to quickly retrieve and assemble appropriate portrait materials during video generation without requiring manual selection of each individual material.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system combines multiple portrait materials containing facial images of the same person into unified face groups. By merging these related materials into organized groups with automatic naming, the system enables efficient selection and assembly during video composition, improving both accuracy and productivity.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP4712492A1Video generation method and electronic device
Publication Date: 2026.03.18 HONOR DEVICE CO LTD
  • EP4712492A1 patent drawingFigure 1A
  • EP4712492A1 patent drawingFigure 1B
  • EP4712492A1 patent drawingFigure 1C

AI summary

A video generation method and an electronic device are provided. The method includes: An electronic device displays a video production window. The electronic device displays an operation window of a target video theme in response to an operation of selecting a target theme card in a plurality of theme cards by a user. When all persons corresponding to at least one face group lack name data, the operation window includes a first video creation entry; or when at least one of persons corresponding to at least one face group has name data, the operation window includes a second video creation entry. The electronic device displays a first selection window in response to an operation performed on the first video creation entry. The first selection window includes a facial image of at least one person. The electronic device generates, in response to an operation of selecting a facial image by the user, a video of a person corresponding to the facial image selected by the user. Alternatively, the electronic device generates, in response to an operation performed on the second video creation entry, a video of a person corresponding to the second video creation entry.