Identification using spectroscopy

Abstract

A device may receive information identifying results of a spectroscopic measurement of an unknown sample. The device may perform a first classification of the unknown sample based on the results of the spectroscopic measurement and a global classification model. The device may generate a local classification model based on the first classification. The device may perform a second classification of the unknown sample based on the results of the spectroscopic measurement and the local classification model. The device may provide information identifying a class associated with the unknown sample based on performing the second classification.

What is claimed is: 
     
         1 . A device, comprising:
 a memory; and   one or more processors configured to:
 receive a spectroscopic measurement for a cannabis sample; 
 perform a qualitative classification of the cannabis sample; 
 perform, based on the spectroscopic measurement, a quantitative analysis of the cannabis sample by utilizing a quantification model related to the qualitative classification; and 
 provide one or more results of the quantitative analysis of the cannabis sample. 
   
     
     
         2 . The device of  claim 1 , wherein the quantification model quantifies tetrahydrocannabinol (THC) content present at a threshold level. 
     
     
         3 . The device of  claim 1 , wherein the one or more processors are further configured to:
 select, based on the qualitative classification, the quantification model from a first regression model and a second regression model.   
     
     
         4 . The device of  claim 3 , wherein the first regression model is for a first type of cannabis plant, and
 wherein the second regression model is for a second type of cannabis plant.   
     
     
         5 . The device of  claim 4 ,
 wherein the first type of cannabis plant is a cannabis plant grown indoors, and   wherein the second type of cannabis plant is a cannabis plant grown outdoors.   
     
     
         6 . The device of  claim 1 , wherein the one or more processors are further configured to:
 obtain, from a data structure, stored information identifying:
 a set of potential classes for the cannabis sample, and 
 a set of models that include the quantification model. 
   
     
     
         7 . The device of  claim 1 , wherein the qualitative classification is performed using one or more classification models that include one or more of:
 a classification model for a dry plant class, or   a classification model for a concentrate class.   
     
     
         8 . The device of  claim 1 , wherein the quantification model comprises a quantification model for a tincture. 
     
     
         9 . The device of  claim 1 , wherein the qualitative classification is performed using a local classification model that is based on a global classification model. 
     
     
         10 . A method, comprising:
 receiving, by a device, a spectroscopic measurement for a cannabis sample;   performing, by the device, a qualitative classification of the cannabis sample;   performing, by the device, a quantitative analysis of the cannabis sample based on the spectroscopic measurement and the qualitative classification; and   providing, by the device, one or more results of the quantitative analysis of the cannabis sample.   
     
     
         11 . The method of  claim 10 , further comprising:
 selecting, based on the qualitative classification, a quantification model from a first regression model and a second regression model,
 wherein the quantitative analysis is performed using the quantification model. 
   
     
     
         12 . The method of  claim 11 , wherein the first regression model is for a first type of cannabis plant, and
 wherein the second regression model is for a second type of cannabis plant.   
     
     
         13 . The method of  claim 12 ,
 wherein the first type of cannabis plant is a cannabis plant grown indoors, and   wherein the second type of cannabis plant is a cannabis plant grown outdoors.   
     
     
         14 . The method of  claim 10 , further comprising:
 obtaining, from a data structure, stored information identifying:
 a set of potential classes for the cannabis sample, and 
 a set of models that include a quantification model, 
 wherein the quantitative analysis is performed using the quantification model. 
   
     
     
         15 . The method of  claim 10 , wherein the qualitative classification is performed using one or more classification models that include one or more of:
 a classification model for a dry plant class, or   a classification model for a concentrate class.   
     
     
         16 . The method of  claim 10 ,
 wherein the quantitative analysis is performed using a quantification model that is selected based on the qualitative classification, and   wherein the quantification model comprises a quantification model for a tincture.   
     
     
         17 . The method of  claim 10 , wherein the qualitative classification is performed using a local classification model that is based on a global classification model. 
     
     
         18 . A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
 one or more instructions that, when executed by one or more processors of a device, cause the device to:
 receive a spectroscopic measurement for a cannabis sample; 
 perform, based on the spectroscopic measurement, a quantitative analysis of the cannabis sample by utilizing a quantification model; and 
 provide one or more results of the quantitative analysis of the cannabis sample. 
   
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein the quantification model quantifies tetrahydrocannabinol (THC) content present at a threshold level. 
     
     
         20 . The non-transitory computer-readable medium of  claim 18 , wherein the one or more instructions further cause the device to:
 select the quantification model from a first regression model and a second regression model,
 wherein the first regression model is for a cannabis plant grown indoors, and 
 wherein the second regression model is for a cannabis plant grown outdoors.