Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Audience evaluation data-driven silent product video creation auxiliary method and device

A data-driven, product-based technology, applied in the field of video creation assistance methods and devices for silent products, can solve problems such as difficult video optimization, insufficient feature analysis provided by creators, and inability to solve practical problems for novices, so as to optimize video production and reduce The effect of the challenge

Active Publication Date: 2022-02-01
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the previous method mainly completed the function of predicting the evaluation results, and could not provide creators with insufficient feature analysis. Therefore, it was difficult to help novices to optimize the video, and they could not solve the practical problems of novices in the production process. Content screening for the platform

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Audience evaluation data-driven silent product video creation auxiliary method and device
  • Audience evaluation data-driven silent product video creation auxiliary method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention provides an auxiliary method for video creation of silent products driven by audience evaluation data, such as figure 1 As shown, the specific steps are:

[0058] S1: Construct a product video sample set and a high-quality case library, and mark the initial sample set of product videos obtained under mute playback through audience evaluation. Watch the initial sample set of product videos, and mark the information usefulness and visual comfort of the product video samples through a 7-point scale. Each product video sample collects at least 3 people’s annotation data;

[0059] The evaluation tags are information usefulness tags and visual comfort tags. Among them, information usefulness refers to the degree to which viewers can obtain useful information about products through videos to help purchase decisions; visual comfort refers to the process by which viewers obtain information from videos. The ease and clarity of medium visual perception;

[...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an audience evaluation data-driven silent product video creation auxiliary method, which comprises the following steps that: label consistency screening is performed on a video initial sample set to obtain a product video sample set, the product video sample set is divided into an appearance type product video sample set and a function type product video sample set based on product categories, a high-quality case library is constructed, and an evaluation prediction model is constructed through an XGBoost method; an evaluation and prediction model interpreter is constructed through an SHAP algorithm, high-quality cases matched with materials, video attributes and product types provided by a user are screened out from a high-quality case library, high-quality characteristics of the high-quality cases are obtained through the prediction model interpreter to assist the user in completing video creation, and evaluation results of video fragments are predicted through an evaluation and prediction model; and a model interpreter is used to obtain the feature that the SHAP value of the video fragment is negative and the target value domain of feature optimization, and a user is assisted to adjust the feature value of the feature so as to complete optimization of the video fragment. According to the method, high-quality reference cases can be provided, and evaluation and optimization prompting can be carried out on video slices made by a user.

Description

technical field [0001] The invention belongs to the technical field of computer vision and computer-aided design, and in particular relates to an auxiliary method and device for video creation of silent products driven by audience evaluation data. Background technique [0002] With the upgrading of Internet consumption, the way for merchants to compete for the market is no longer just "price war", but to improve the consumption experience. Therefore, in recent years, intuitive and rich product videos have gradually become the most popular product display method on e-commerce platforms. The product video, also known as the main image video, is located on the first screen of the details page. Its main function is to help consumers obtain rich and in-depth product information efficiently and comfortably, thereby promoting purchase decisions. Compared with the graphic introduction of the previous e-commerce platform, the information carrying capacity of the product video is lar...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06V20/40G06V20/62G06V10/74G06V10/774G06K9/62G06Q10/06G06Q30/06
CPCG06Q10/06393G06Q30/0631G06F18/22G06F18/214G06F18/24323
Inventor 孙凌云鲁雨佳陈实王禹溪杨昌源
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products