Unlock instant, AI-driven research and patent intelligence for your innovation.

An artificial intelligence prediction system for predicting the color and smell of substances based on molecular characteristics

A technology of molecular characteristics and artificial intelligence, applied in the direction of color/spectral characteristic measurement, measuring devices, and analytical materials, etc., can solve the problem that the research of material color/odor stays in physical and chemical theory, cannot be theoretically related, and stays in theoretical basis, etc. problem, to achieve the effect of convenient material color/odor prediction

Active Publication Date: 2022-05-20
ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing research on the color / odor of substances is limited to the explanation of physical and chemical theories, and only stays on the theoretical basis, which can neither relate all theories to each other, nor can it be applied to the preparation of actual chemical reagents, the production of pigments, the production of fuels, etc.

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
  • An artificial intelligence prediction system for predicting the color and smell of substances based on molecular characteristics
  • An artificial intelligence prediction system for predicting the color and smell of substances based on molecular characteristics
  • An artificial intelligence prediction system for predicting the color and smell of substances based on molecular characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 As shown, the present embodiment provides an artificial intelligence training system for predicting the color and smell of substances based on molecular characteristics, which is used to train a machine learning model for predicting the color / smell of substances based on molecular characteristics according to the training set, and the training set includes known colors Samples of substances with different molecular structures of odors;

[0047] The artificial intelligence training system for predicting the color and smell of substances based on molecular characteristics includes:

[0048] A descriptor extraction module 10, configured to extract molecular descriptors of the substance sample;

[0049] A characteristic classification module 20, configured to classify according to the color / smell of the substance sample;

[0050] The model training module 30 is used for training a machine learning model according to the molecular descriptors of the substa...

Embodiment 2

[0080]This embodiment provides an artificial intelligence system for predicting the color and smell of a substance based on molecular characteristics, which is used to predict the color / smell of the substance to be predicted, including:

[0081] Molecular descriptor extraction module, used to extract molecular descriptors from substances to be predicted;

[0082] The color / odor prediction module is used to input the molecular descriptor extracted by the molecular descriptor extraction module into the machine learning model as described in Example 1 to obtain the color prediction result / smell prediction result.

[0083] When it is necessary to predict the color / smell of a certain substance, the molecular descriptor of the substance can be extracted and input into the trained machine learning model as described in Example 1 to obtain the classification result of the color / smell, so that the substance can be predicted. Color / Odour.

[0084] It has been proved by experiments that...

Embodiment 3

[0086] This embodiment provides an artificial intelligence system for predicting the color and smell of a substance based on molecular characteristics, which is used to predict the color and / or smell of the substance to be predicted, including:

[0087] Molecular descriptor extraction module, used to extract molecular descriptors from substances to be predicted;

[0088] The color / odor prediction module is used to compare the molecular descriptors extracted by the molecular descriptor extraction module with several molecular descriptors that play the largest role in prediction as described in Example 1, and obtain color predictions according to the comparison results Result / Odor prediction result.

[0089] When it is necessary to predict the color / smell of a certain substance, the molecular descriptor of the substance can be extracted, and the extracted molecular descriptor is compared with the molecular descriptor that has the greatest effect on prediction as described in Exa...

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 an artificial intelligence prediction system for predicting the color and smell of a substance based on molecular features, which is used to train a machine learning model for predicting the color / smell of a substance based on molecular features according to a training set, the training set includes differences in known colors / smells A substance sample of molecular structure, including: a descriptor extraction module, used to extract molecular descriptors of the substance sample; a characteristic classification module, used to classify according to the color / odor of the substance sample; a model training module, used to classify the substance sample according to The molecular descriptors of the material samples extracted by the descriptor extraction module and the classification performed by the characteristic classification module are used to train a machine learning model. The present invention is based on the relationship between the molecular descriptor of the substance and the color / smell formation of the substance, and trains a machine learning model so as to predict the color / smell of the substance more accurately.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, more specifically, to an artificial intelligence prediction system for predicting the color and smell of substances based on molecular characteristics. Background technique [0002] The color and smell of a substance are closely related to its own physical and chemical properties. At present, the explanations for the color of matter are mostly focused on charge migration, energy band theory, color center theory of crystals, and light scattering, etc. There is no related algorithm that can accurately predict color. Regarding the relationship between the color and smell of substances, previous studies have carried out related experiments on the population, and the results show that the intensity of the smell that color can cause increases, that is, the smell emitted by the colored substance is stronger, but no researchers have explained the substance and smell from the substance Th...

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 Patents(China)
IPC IPC(8): G01N21/25G01N33/00G06N3/04G06N3/08
CPCG01N21/25G01N33/00G06N3/084G06N3/045
Inventor 林浩添张夏茵张凯林铎儒
Owner ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV