Using biometric data intelligence for education management

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for developing cognitive and behavioral metrics associated with a user. In some implementations, a system obtains data from a writing implement, the data indicative of a user performing a task by writing with the writing implement against a receiving device. The system extracts features from the obtained data. The system determines metrics that reflect characteristics of the user, the metrics that reflect cognitive characteristics of the user and metrics that reflect behavioral characteristics of the user. Based on the extracted features and the determined metrics, the system generates a user profile for the user. Based on the features indicating characteristics of the writing behavior of the user, the system modifies the generated user profile as a performance of the user changes over time. The system provides recommendations to improve the performance of the user.

What is claimed is: 
     
         1 . (canceled) 
     
     
         2 . A computer-implemented method comprising:
 obtaining data from a writing implement, the data indicative of a first user writing a series of characters with the writing implement on a receiving device;   extracting features from the obtained data, the features indicating characteristics of a writing behavior of the user while writing the series of characters;   comparing a characteristic data set based on the extracted features to one or more stored characteristic datasets for the same series of characters, wherein each stored characteristic dataset of the one or more stored characteristic datasets is associated with a respective user; and   identifying a stored characteristic dataset that matches the characteristic dataset based on the extracted features; and   in response to identifying the stored characteristic dataset, validating an identity of the first user.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein the receiving device comprises at least one of paper, smart paper, a tablet, or a computer screen. 
     
     
         4 . The computer-implemented method of  claim 2 , wherein the one or more stored characteristic datasets associated with the respective user comprises the one or more stored characteristic datasets written by the respective user using a respective writing implement. 
     
     
         5 . The computer-implemented method of  claim 2 , comprising:
 obtaining, by the one or more computers, one or more of: 
 test question data that describe (i) one or more questions posed to the first user to be answered with the writing implement and the receiving device, (ii) a correct answer to each of the one or more questions, and (iii) an answer rubric, and 
 input data that describe (i) data identifying the writing implement and (ii) credentials of the first user writing with the writing implement. 
   
     
     
         6 . The computer-implemented method of  claim 2 , wherein extracting the features from the obtained data comprises one or more of:
 extracting, by the one or more computers, temporal features that describe temporal elements of handwritten movements produced by the first user with the writing implement while performing a task;   extracting, by the one or more computers, pressure features that describe a pressure recorded between a tip of the writing implement and the receiving device while the first user performs the task; and   extracting, by the one or more computers, textual features that describe characteristics of written letters and numbers with the writing implement, wherein the textual features also comprise time stamps associated with each of handwritten text.   
     
     
         7 . The computer-implemented method of  claim 6 , wherein comparing the characteristic data set based on the extracted features to the one or more stored characteristic data sets for the same series of characters further comprises:
 measuring an amount of ink for each of one or more characters of the series of characters written by the writing implement;   identifying one or more characters of the series of characters written by the writing implement; and   identifying one or more stored characteristic datasets using (i) the amount of ink for each of the one or more characters and (ii) the identification of each of the one or more characters of the series of characters, the identifying comprising comparing the measured amount of ink for each of the one or more characters of the series of characters written by the writing implement to an amount of ink for each character in the one or more stored characteristic datasets.   
     
     
         8 . The computer-implemented method of  claim 7 , wherein identifying the stored characteristic dataset that matches the characteristic dataset based on the extracted features further comprises:
 determining whether the comparison between the measured ink amounts for each of the one or more characters of the series of characters and the amount of ink for each of the one or more characters in the one or more stored characteristic datasets satisfies a threshold value;   in response to determining the comparison satisfies the threshold value for at least one of the stored characteristic datasets, identifying a corresponding stored characteristic dataset as the dataset for identity validation.   
     
     
         9 . The computer-implemented method of  claim 8 , wherein validating the identity of the first user further comprises:
 in response to identifying the corresponding stored characteristic dataset as the dataset for the identity validation, the method comprises: 
 identifying the respective user associated with the stored characteristic dataset; 
 obtaining, from a database, first user credentials of the first user writing with the writing implement; 
 obtaining second user credentials of the respective user w; and 
 comparing the first user credentials with the second user credentials to determine whether a match exists. 
   
     
     
         10 . The computer-implemented method of  claim 9 , wherein comparing the first user credentials with the second user credentials further comprises:
 in response to determining the first user credentials do not match to the second user credentials, determining that an identification of the first user does not match to an identification of the respective user; and   transmitting data to a supervisor indicating that the first user is cheating during the first user’s writing the series of characters with the writing implement on the receiving device.   
     
     
         11 . The computer-implemented method of  claim 9 , wherein comparing the first user credentials with the second user credentials further comprises:
 in response to determining the first user credentials do match to the second user credentials, determining an identification of the first user does match to an identification of the respective user; and   validating the identity of the first user based on the first user’s writing the series of characters with the writing implement on the receiving device.   
     
     
         12 . The computer-implemented method of  claim 8 , further comprising: in response to determining the comparison does not satisfy the threshold value for at least one of the stored characteristic datasets, determining an identification of the first user is unknown. 
     
     
         13 . A system comprising:
 one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising: 
 obtaining data from a writing implement, the data indicative of a first user writing a series of characters with the writing implement on a receiving device; 
 extracting features from the obtained data, the features indicating characteristics of a writing behavior of the user while writing the series of characters; 
 comparing a characteristic data set based on the extracted features to one or more stored characteristic datasets for the same series of characters, wherein each stored characteristic dataset of the one or more stored characteristic datasets is associated with a respective user; and 
 identifying a stored characteristic dataset that matches the characteristic dataset based on the extracted features; and 
 in response to identifying the stored characteristic dataset, validating an identity of the first user. 
   
     
     
         14 . The system of  claim 13 , wherein the receiving device comprises at least one of paper, smart paper, a tablet, or a computer screen. 
     
     
         15 . The system of  claim 13 , wherein the one or more stored characteristic datasets associated with the respective user comprises the one or more stored characteristic datasets written by the respective user using a respective writing implement. 
     
     
         16 . The system of  claim 13 , comprising:
 obtaining, by the one or more computers, one or more of: 
 test question data that describe (i) one or more questions posed to the first user to be answered with the writing implement and the receiving device, (ii) a correct answer to each of the one or more questions, and (iii) an answer rubric, and 
 input data that describe (i) data identifying the writing implement and (ii) credentials of the first user writing with the writing implement. 
   
     
     
         17 . The system of  claim 13 , wherein extracting the features from the obtained data comprises one or more of:
 extracting, by the one or more computers, temporal features that describe temporal elements of handwritten movements produced by the first user with the writing implement while performing a task;   extracting, by the one or more computers, pressure features that describe a pressure recorded between a tip of the writing implement and the receiving device while the first user performs the task; and   extracting, by the one or more computers, textual features that describe characteristics of written letters and numbers with the writing implement, wherein the textual features also comprise time stamps associated with each of handwritten text.   
     
     
         18 . The system of  claim 17 , wherein comparing the characteristic data set based on the extracted features to the one or more stored characteristic data sets for the same series of characters further comprises:
 measuring an amount of ink for each of one or more characters of the series of characters written by the writing implement;   identifying one or more characters of the series of characters written by the writing implement; and   identifying one or more stored characteristic datasets using (i) the amount of ink for each of the one or more characters and (ii) the identification of each of the one or more characters of the series of characters, the identifying comprising comparing the measured amount of ink for each of the one or more characters of the series of characters written by the writing implement to an amount of ink for each character in the one or more stored characteristic datasets.   
     
     
         19 . The system of  claim 18 , wherein identifying the stored characteristic dataset that matches the characteristic dataset based on the extracted features further comprises:
 determining whether the comparison between the measured ink amounts for each of the one or more characters of the series of characters and the amount of ink for each of the one or more characters in the one or more stored characteristic datasets satisfies a threshold value; in response to determining the comparison satisfies the threshold value for at least one of the stored characteristic datasets, identifying a corresponding stored characteristic dataset as the dataset for identity validation.   
     
     
         20 . The system of  claim 19 , wherein validating the identity of the first user further comprises:
 in response to identifying the corresponding stored characteristic dataset as the dataset for the identity validation, the system comprises: 
 identifying the respective user associated with the stored characteristic dataset; 
 obtaining, from a database, first user credentials of the first user writing with the writing implement; 
 obtaining second user credentials of the respective user w; and 
 comparing the first user credentials with the second user credentials to determine whether a match exists. 
   
     
     
         21 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
 obtaining data from a writing implement, the data indicative of a first user writing a series of characters with the writing implement on a receiving device;   extracting features from the obtained data, the features indicating characteristics of a writing behavior of the user while writing the series of characters;   comparing a characteristic data set based on the extracted features to one or more stored characteristic datasets for the same series of characters, wherein each stored characteristic dataset of the one or more stored characteristic datasets is associated with a respective user; and   identifying a stored characteristic dataset that matches the characteristic dataset based on the extracted features; and   in response to identifying the stored characteristic dataset, validating an identity of the first user.