Artificial intelligence-based food flavor sensory evaluation system and establishment method thereof

A technology of sensory evaluation and artificial intelligence, applied in the direction of instruments, data processing applications, and analytical materials, can solve problems such as difficult to control product quality, lack of self-learning and comprehensive analysis capabilities, difficult flavor evaluation, etc., and achieve comprehensive and reliable evaluation results , Overcome the effect of one-sidedness and manual repeatability detection

Active Publication Date: 2018-06-08
SOUTH CHINA AGRI UNIV
View PDF7 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, no matter whether it is artificial sensory evaluation, instrumental analysis or electronic nose that simulates human senses, it cannot meet the needs of the development of the food industry.
Although artificial sensory evaluation can comprehensively evaluate food flavor, with the development of large-scale and group food production, it is difficult to achieve the purpose of controlling product quality only by professionals. Physiological effects, human errors are inevitable, and sensory evaluation cannot know the material basis that affects the flavor of food; although evaluation techniques such as chemical analysis and instrumental analysis can accurately and quantitatively analyze the main typical flavor substances in food, it is difficult for professionals. The same comprehensive evaluation of flavor as evaluation; although the electronic nose can analyze the smell of specific components, but limited by the development of sensor technology, it is difficult to make satisfactory analysis and evaluation of trace components and complex smells, lacking self-learning and comprehensive Skills of analyze

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
  • Artificial intelligence-based food flavor sensory evaluation system and establishment method thereof
  • Artificial intelligence-based food flavor sensory evaluation system and establishment method thereof
  • Artificial intelligence-based food flavor sensory evaluation system and establishment method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Embodiment 1: artificial intelligence sensory evaluation food flavor system and its construction method

[0027] Such as figure 1 As shown, an artificial intelligence sensory evaluation food flavor system is composed of a component sensory detection system, a computer intelligent analysis system and a food odor database. The component sensory detection system consists of GC-MS (gas chromatography mass spectrometry detector) and GC-O (Gas Chromatography Olfactory Detector), GC-MS is used to obtain the original data of the odor characteristics of food samples composed of chromatographic and mass spectrometry data, and GC-O is used to obtain the artificial sensory evaluation data of the odor of food samples; the computer intelligent analysis system , used for preprocessing and feature extraction of the original data of odor characteristics obtained by the sensory detection system and artificial sensory evaluation data, and performing dimensionality reduction and cluster an...

Embodiment 2

[0036] Example 2: Using the artificial intelligence sensory evaluation food flavor system to evaluate the flavor of Xinhui tangerine peel with different storage years.

[0037] As a traditional Chinese medicinal material for regulating qi, tangerine peel has been said to be "good for a long time" since ancient times. Its volatile aroma is prominent, and with the extension of storage years, the content of volatile components and aroma characteristics will change. By establishing the volatile components of tangerine peel The database is used to build an artificial intelligence evaluation system for the smell of tangerine peel, which can be used to identify tangerine peel of different years and origins. In addition, the evaluation system can correlate the flavor of the corresponding samples by comparing the GC-MS data of the orange peel samples, saving labor and obtaining the flavor data of the samples more accurately.

[0038] (1) Data collection

[0039] Such as figure 1 As s...

Embodiment 3

[0054] Example 3: Flavor evaluation of ethanol solutions with different concentrations.

[0055] (1) Establish sensory evaluation database and flavor intelligent evaluation model:

[0056] At room temperature of 20°C, take 21 clean and dry 100 ml volumetric flasks, and accurately measure 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70 , 75, 80, 85, 90, 95, and 100ml of absolute ethanol were placed in a 100ml volumetric flask, and water was added to make up the volume to obtain a concentration of 0%, 5%, 10%, 15%, 20%, and 25%. , 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95%, 100%, a total of 21 ethanol solutions standard sample.

[0057] With the 21 standard samples of ethanol solution, the smellers of the sensory evaluation team were trained by the smell paper method to determine the preliminary artificial sensory evaluation. The method refers to GB / T 22366-2008 as follows: provide an ethanol solution of one concentration together with two s...

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 provides an artificial intelligence-based food flavor sensory evaluation system and an establishment method thereof. The food flavor sensory evaluation system comprises a component sensory detection system, a computer intelligent analysis system and a food flavor database, wherein the component sensory detection system consists of a GC-MS and a GC-O; the GC-MS is used for obtaining flavor feature original data of foods; the GC-O is used for obtaining artificial sensory evaluation data of food flavors; the computer intelligent analysis system is used for performing preprocessing and feature extraction on the flavor feature original data and the artificial sensory evaluation data, and performing dimension reduction and clustering analysis on the original data; and the food flavor database is established by performing fitting analysis on the flavor feature original data and the artificial sensory evaluation data obtained by the sensory detection system by a computer, combines the flavor original data and the artificial evaluation data, and comprises various data of mutual association of food volatile components. The instrument analysis is combined with the human body sensory evaluation, so that the one-sidedness and the defect of manual repetitive detection in an existing food flavor detection method are overcome, and an evaluation result is more comprehensive and reliable.

Description

technical field [0001] The invention relates to a system for evaluating food flavor, in particular to a system for evaluating food flavor based on artificial intelligence. Background technique [0002] As the source and driving force of original innovation in the food industry, food flavor (smell) is an important feature reflecting food quality, and its rapid and comprehensive evaluation, material basis and change law are worthy of in-depth study. In my country, especially in Guangdong Province, sensory flavor evaluation has a long history, especially in the production, processing and distribution management of traditional liquor, tea and tobacco. Flavor sensory evaluation technology mainly goes through three stages, namely: starting from the manager’s evaluation; professional sensory evaluation group evaluation as the main body, multi-disciplinary interdisciplinary and application, sensory evaluation activities standardization; sensory analysis combined with physical and ch...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G01N30/02
CPCG01N30/02G06Q10/0639
Inventor 曹庸丘芷柔常会友陈浩然孙圣伟胡勇军陈彤
Owner SOUTH CHINA AGRI 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