Computing technologies for diagnosis and therapy of language-related disorders

Abstract

The present disclosure relates to computing technologies for diagnosis and therapy of language-related disorders. Such technologies enable computer-generated diagnosis and computer-generated therapy delivered over a network to at least one computing device. The diagnosis and therapy are customized for each patient through a comprehensive analysis of the patient's production and reception errors, as obtained from the patient over the network, together with a set of correct responses at each phase of evaluation and therapy.

What is claimed is: 
     
         1 . A method comprising:
 receiving, by a server, over a network, in real-time, a user request from a client in communication with a camera and operated by a user having a face with a pair of eyes;   hosting, by the server, over the network, in real-time, responsive to the user request, a secure session with the client; and   during the secure session:
 selecting, by the server, a first node containing a first type value in a first graph based on a comparison of a first matrix specific to the user against a second matrix not specific to the user; 
 selecting, by the server, a second node containing a first audio task or a first image task in a second graph based on the first type value and the comparison; 
 serving, by the server, over the network, the first audio task or the first image task from the second node to the client; 
 instructing, by the server, over the network, the client to activate the camera such that the camera captures a video depicting the face with the pair of eyes while the first audio task or the first image task is output via the client; 
 receiving, by the server, over the network, a user input and the video from the client responsive to the first audio task or the first image task being output via the client; 
 writing, by the server, the user input into the first matrix; 
 identifying, by the server, the pair of eyes in the video; 
 determining, by the server, an eye gaze value or a blinking rate based on the pair of eyes identified in the video; 
 writing, by the server, the eye gaze value or the blinking rate into the first matrix; 
 selecting, by the server, the first node or a third node containing a second type value in the first graph, wherein the second type value is different from the first type value; 
 selecting, by the server, the second node or a fourth node containing a second audio task or a second image task in the second graph based on the first type value or the second type value, wherein the second audio task or the second image task is respectively different from the first audio task or the first image task; 
 generating, by the server, a corrective or evaluative feedback message containing the second audio or the second image; and 
 serving, by the server, the corrective or evaluative feedback message to the client such that the corrective or evaluative feedback message is output to the user via the client. 
   
     
     
         2 . The method of  claim 1 , wherein the user has a pair of lips, and further comprising:
 during the secure session:
 instructing, by the server, over the network, the client to activate the camera such that the camera captures the video depicting the face with the pair of eyes and the pair of lips while the first audio task or the first image task is output via the client; 
 identifying, by the server, the pair of lips in the video; 
 determining, by the server, a lip movement value based on the pair of lips identified in the video; 
 writing, by the server, the lip movement value into the first matrix; 
 selecting, by the server, the first node or the third node containing the second type value in the first graph. 
   
     
     
         3 . The method of  claim 2 , further comprising:
 during the secure session:
 selecting, by the server, the first node or the third node containing the second type value in the first graph. 
   
     
     
         4 . The method of  claim 2 , further comprising:
 during the secure session:
 selecting, by the server, the first node or the third node containing the second type value in the first graph. 
   
     
     
         5 . The method of  claim 2 , further comprising:
 during the secure session:
 selecting, by the server, the first node or the third node containing the second type value in the first graph. 
   
     
     
         6 . The method of  claim 1 , further comprising:
 during the secure session:
 serving, by the server, the corrective or evaluative feedback message to the client such that the corrective or evaluative feedback message is unobtrusively output to the user. 
   
     
     
         7 . The method of  claim 1 , wherein the client is a wearable. 
     
     
         8 . The method of  claim 7 , wherein the client is an eyewear unit or an optical head-mounted display (OHMD) having the camera. 
     
     
         9 . The method of  claim 1 , wherein the client is a phone or a tablet that hosts the camera, wherein the camera is a front-facing camera. 
     
     
         10 . The method of  claim 1 , wherein the client runs a browser through which the secure session takes place. 
     
     
         12 . The method of  claim 1 , wherein the client is in communication with a vibrator configured for a bone conduction to the user, and further comprising:
 serving, by the server, the corrective or evaluative feedback message to the client such that the corrective or evaluative feedback message is output to the user via the client instructing the vibrator to output the corrective or evaluative feedback message via the bone conduction.   
     
     
         13 . The method of  claim 1 , further comprising:
 during the secure session:
 identifying, by the server, the face in the video; 
 determining, by the server, an emotion of the user based on the face being identified in the video; 
 writing, by the server, the emotion into the first matrix; 
 selecting, by the server, the first node or the third node containing the second type value in the first graph. 
   
     
     
         14 . The method of  claim 1 , further comprising:
 during the secure session:
 identifying, by the server, the face in the video; 
 extracting, by the server, a geometrical feature of the face; 
 producing, by the server, a temporal profile for each of a plurality of movements of the face in the video; 
 writing, by the server, the temporal profiles to the first matrix such that an iterative feedback loop is formed during the comparison. 
   
     
     
         15 . The method of  claim 1 , further comprising:
 during the secure session:
 selecting, by the server, the first node or the third node containing the second type value in the first graph. 
   
     
     
         16 . The method of  claim 1 , further comprising:
 during the secure session:
 selecting, by the server, the first node or a third node containing a second type value in the first graph. 
   
     
     
         17 . The method of  claim 1 , further comprising:
 during the secure session:
 selecting, by the server, the first node or a third node containing a second type value in the first graph. 
   
     
     
         18 . The method of  claim 1 , wherein the client is in communication with a videogame controller, wherein the user input is via the videogame controller. 
     
     
         19 . The method of  claim 1 , wherein the corrective or evaluative feedback message containing the second audio or the second image is informative of a symptom of a language-related disorder with which the user is diagnosed. 
     
     
         20 . A computer program comprising a set of instructions for execution via a hardware processor, wherein the set of instructions instructing the hardware processor to implement a method, wherein the method comprising:
 diagnosing a language-related disorder in real-time based at least in part on a deterministic model via:
 obtaining ( 702 ) a first set of criteria via a first computer ( 304 ), wherein the first set of criteria is based on a first analysis of a patient data structure against a master data structure, wherein the patient data structure comprising a set of actual patient task responses including errors and correct responses, wherein the master data structure comprising a set of cell generation data and a set of predicted patient task responses for a plurality of patients including predicted errors and predicted correct responses, wherein the predicted errors are classified into categories and the predicted errors within each category are sub-classified and represented in graphs wherein each node of each graph is a predicted error; 
 the first computer selecting ( 704 ) a first diagnostic shell based on the first set of criteria, wherein the first diagnostic shell is a type of test serving as a test of a language function; 
 the first computer generating ( 706 ) a first diagnostic cell based on the first diagnostic shell and the set of cell generation data, wherein the first diagnostic cell comprising test content data defining a test to be performed; 
 the first computer communicating ( 708 ) the first diagnostic cell to a second computer; 
 the first computer receiving a first result from the second computer, wherein the first result representing a real-time patient input at the second computer in response to the first diagnostic cell; 
 storing ( 710 ) the first result in the patient data structure via the first computer; 
 obtaining ( 714 ) a second set of criteria via the first computer, wherein the second set of criteria is based on a second analysis of the patient data structure, including the first result, against the master data structure; 
 analyzing ( 716 ) patient performance based on the second set of criteria in order to determine ( 718 ,  720 ) at least one of whether to generate ( 724 ) a second diagnostic cell and whether to select ( 726 ) a second diagnostic shell via the first computer, wherein the second diagnostic cell is based on the first diagnostic shell, wherein the first diagnostic shell and the second diagnostic shell are different in task type; and 
 upon determining ( 718 ) not to generate a further diagnostic cell and determining ( 720 ) not to select a further diagnostic shell, determining ( 722 ) that the diagnosis is complete, wherein the diagnosed language-related disorder is at least one of dyslexia, specific language impairment, auditory processing disorder, and aphasia. 
   
     
     
         21 . A system comprising:
 a first computer ( 304 ) facilitating a diagnosis of a language-related disorder in real-time based at least in part on a deterministic model via:
 obtaining ( 702 ) a first set of criteria, wherein the first set of criteria is based on a first analysis of a patient data structure against a master data structure, wherein the patient data structure comprising a set of actual patient task responses including errors and correct responses, wherein the master data structure comprising a set of cell generation data and a set of predicted patient task responses for a plurality of patients including predicted errors and predicted correct responses, wherein the predicted errors are classified into categories and the predicted errors within each category are sub-classified and represented in graphs, wherein each node of each graph is a predicted error; 
 selecting ( 704 ) a first diagnostic shell based on the first set of criteria, wherein the first diagnostic shell is a type of test serving as a test of a language function; 
 generating ( 706 ) a first diagnostic cell based on the first diagnostic shell and the set of cell generation data, wherein the first diagnostic cell comprising test content data defining a task to be performed; 
 communicating ( 708 ) the first diagnostic cell to a second computer ( 308 ); 
 receiving a first result from the second computer, wherein the first result representing a patient input at the second computer in response to the first diagnostic cell; 
 storing ( 710 ) the first result in the patient data structure; 
 obtaining ( 714 ) a second set of criteria, wherein the second set of criteria is based on a second analysis of the patient data structure, including the first result, against the master data structure; 
 analyzing ( 716 ) patient performance based on the second set of criteria in order to determine ( 718 ,  720 ) at least one of whether to generate ( 724 ) a second diagnostic cell and whether to select ( 726 ) a second diagnostic shell, wherein the second diagnostic cell is based on the first diagnostic shell, wherein the first diagnostic shell and the second diagnostic shell are different in task type; and 
 upon determining ( 718 ) not to generate a further diagnostic cell and determining ( 720 ) not to select a further diagnostic shell, determining ( 722 ) that the diagnosis is complete, wherein the diagnosed language-related disorder is at least one of dyslexia, specific language impairment, auditory processing disorder, and aphasia.