Creator road performance ability evaluation method and evaluation system based on neural network

A neural network, entrepreneur's technology, applied in the field of computer vision, can solve the problems of objectivity and accuracy need to be improved, subjective feelings of evaluators and interference of environmental factors.

Active Publication Date: 2020-01-17
SHANGHAI UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] At present, most of the evaluation methods of entrepreneurs’ roadshow ability are in the form of questionnaire scoring. Although this method can evaluate the entrepreneur’s ro

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
  • Creator road performance ability evaluation method and evaluation system based on neural network
  • Creator road performance ability evaluation method and evaluation system based on neural network
  • Creator road performance ability evaluation method and evaluation system based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A neural network-based evaluation method for entrepreneurial roadshow capabilities, such as figure 1 shown, including the following steps:

[0061] (1) Recruit N subjects to conduct a simulated roadshow, collect the roadshow video information, audio information and sight information of the subjects during the simulated roadshow, and evaluate the roadshow ability of the subjects after the simulated roadshow. The subjects were divided into three categories of good roadshow ability, medium and poor, and the roadshow ability category label of each subject was obtained.

[0062] The specific operation of the simulated roadshow is: recruit N subjects (the N subjects are all entrepreneurs who have been entrepreneurs for many years, and the time spans of entrepreneurship are different, and the entrepreneurial backgrounds are different), and the N subjects are selected from N entrepreneurial projects. Select an entrepreneurial project for a roadshow report. The roadshow report ...

Embodiment 2

[0078] A neural network-based evaluation system for entrepreneurial roadshow capabilities, such as Figure 8 As shown, it includes video acquisition equipment, audio acquisition equipment, line of sight information acquisition equipment, computer and man-machine interface terminal; said computer is built with video processing module, audio processing module, line of sight information processing module, roadshow ability evaluation corpus and embodiment The roadshow ability evaluation network model after training described in 1; the video processing module includes a human body region segmentation module, a behavior recognition module and an expression detection module, and the audio processing module includes an emotional analysis network, a language literacy network and an appealing force Analyzing the network, the line of sight information processing module includes a line of sight gaze area extraction program and an MTCNN face detection network; the video collection equipment...

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 relates to the technical field of computer vision, and discloses a creator road performance ability evaluation method and an evaluation system, and the method comprises the steps: 1) collecting the simulated road performance video, audio and sight line information of a subject, evaluating the road performance ability of the subject, and obtaining a subject road performance ability category label; 2) processing the video information, and counting the proportions of behavior types and expression types in the video sequence; 3) processing the audio information to obtain the emotiontendency, the recall tendency and the language accomplishment score of the subject; 4) processing the sight line information to obtain the eye contact frequency of the subject; (5) combining the dataobtained in the steps (2), (3) and (4) to serve as input data, constructing a data set in combination with the road performance category labels in the step (1), and training a road performance evaluation network model; and 6) collecting input data of a to-be-tested person, and inputting the input data into the trained road performance evaluation network model to obtain a road performance score ofthe to-be-tested person. The evaluation result of the method is objective and accurate.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a neural network-based evaluation method and evaluation system for entrepreneurs' roadshow ability. Background technique [0002] Entrepreneurial project roadshow is an important way to realize zero-distance dialogue, equal communication, and professional exchanges between entrepreneurs and investors. It can promote full communication and in-depth understanding between entrepreneurs and investors, and ultimately promote the financing process of entrepreneurial projects. The establishment and development of enterprises need financial support, but small and medium-sized enterprises often face the plight of lack of funds. How to obtain financing better and more efficiently is a problem that entrepreneurs need to solve. [0003] Entrepreneurship financing roadshow is one of the main ways for enterprises to obtain financing. For enterprises in the development stage, in order...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/172G06V40/174G06V40/23G06V40/18G06V20/46G06N3/045G06F18/214
Inventor 于晓宇李雅洁渠娴娴李恒宇
Owner SHANGHAI 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
Try Eureka
PatSnap group products