Device, system, and method for data analysis and diagnostics utilizing dynamic word entropy
Devices, systems, and methods for data analysis and diagnostics utilizing Dynamic Word Entropy. A method includes: obtaining a text of a user; determining word entropy values which correspond to different lengths of text-portions of the text of the user; generating a Dynamic Word Entropy table which corresponds to the text of the user; analyzing the table, and determining whether or not the user has a particular medical condition, or determining whether or not a particular intervention has positively affected the user or has negatively affected the user or has not affected the user.
1. A computer implemented method of determining efficacy of an intervention administered to a person, the method comprising using at least one computer processor for:
processing a digital representation of a first text, the first text is generated by the person before administering the intervention to the person, the processing comprising:
a) determining that a first text comprises N words;
calculating a first collection of Dynamic Word Entropy (DWE) values comprising N−K+1 values, K being an integer smaller than N; and wherein each DWE value is calculated for a respective i th text-segment of the first text, each text-segment consists of first K+i−1 words of the text;
applying at least one Transformation Function to the first collection of DWE values, and generating a first respective Transformed Value corresponding to the first collection of DWE values;
processing a digital representation of a second text, the second text is generated by the person after administering the intervention to the person, the processing comprising:
b) determining that a second text comprises N words;
calculating a second collection of Dynamic Word Entropy (DWE) values comprising N−K+1 values, K being an integer smaller than N; and wherein each DWE value is calculated for a respective i th text-segment of the second text, each text-segment consists of second K+i−1 words of the text;
applying at least one Transformation Function to the second collection of DWE values, and generating a second respective Transformed Value corresponding to the second collection of DWE values;
based on a difference between the first Transformed Value cone sponding to the first collection of DWE values and the second Transformed Value corresponding to the second collection of DWE values, determining whether the intervention had a positive, a negative, or a neutral effect on speech characteristics of the person.
2. The computer implemented method of claim 1 , wherein the at least one Transformation Function comprises at least one of: average; median; variance standard deviation.
3. The computer implemented method of claim 1 , wherein the intervention includes any one of:
medical treatment including administration of a medicine or a drug; learning session; psychotherapy treatment; and behavioral treatment.
4. The computer implemented method of claim 1 , further comprising:
storing the collection of DWE values in a DWE table, wherein the DWE table comprises 1+N−K rows and wherein each row in the DWE table has a row-number denoted i, wherein each row in the DWE table comprises a Word Entropy value determined for the respective i t text-segment.
5. The computer implemented method of claim 1 further comprising:
generating the digital representation of the text, by any one of:
(i) obtaining a printed item having printed thereon text of the person, and performing Optical Character Recognition (OCR) on said printed item;
(ii) obtaining a handwritten item having handwritten thereon text of the user, and performing Optical Character Recognition (OCR) on said handwritten; and
(iii) obtaining an audio recording of the user and performing speech-to-text conversion on said audio recording.
6. A computer system comprising at least one processor operatively connected to a computer memory configured to:
process a digital representation of a first text generated by the person before administering the intervention to the person, the processing comprising:
a) determining that a first text comprises N words;
calculating a first collection of Dynamic Word Entropy (DWE) values comprising N−K+1 values, K being an integer smaller than N; and wherein each DWE value is calculated for a respective i th text-segment of the first text, each text-segment consists of first K+i−1 words of the text;
applying at least one Transformation Function to the first collection of DWE values, and generating a first respective Transformed Value corresponding to the first collection of DWE values;
processing a digital representation of a second text generated by the person after administering the intervention to the person, the processing comprising:
b) determining that a second text comprises N words;
calculating a second collection of Dynamic Word Entropy (DWE) values comprising N−K+1 values, K being an integer smaller than N; and wherein each DWE value is calculated for a respective ith text-segment of the second text, each text-segment consists of second K+i−1 words of the text;
applying at least one Transformation Function to the second collection of DWE values, and generating a second respective Transformed Value corresponding to the second collection of DWE values;
based on a difference between the first Transformed Value corresponding to the first collection of DWE values and the second Transformed Value corresponding to the second collection of DWE values, determining whether the intervention had a positive, a negative, or a neutral effect on speech characteristics of the person.
7. The computer system of claim 6 , wherein the at least one Transformation Function comprises at least one of: average; median; variance standard deviation.
8. The computer system of claim 6 , wherein the intervention includes any one of:
medical treatment; administration of a medicine or a drug; therapeutic treatment; learning session; focusing session; psychotherapy treatment; and behavioral treatment.
9. The computer system of claim 6 , wherein the at least one processor is further configured to:
store the collection of DWE values in a DWE table, wherein the DWE table comprises 1+N−K rows and wherein each row in the DWE table has a row-number denoted i, wherein each row in the DWE table comprises a Word Entropy value determined for the respective i th text-segment.
10. The computer system of claim 6 , wherein the at least one processor is further configured to generate the digital representation of the text, by any one of:
(i) obtaining a printed item having printed thereon text of the person, and performing Optical Character Recognition (OCR) on said printed item;
(ii) obtaining a handwritten item having handwritten thereon text of the user, and performing Optical Character Recognition (OCR) on said handwritten; and
(iii) obtaining an audio recording of the user and performing speech-to-text conversion on said audio recording.
11. A non-transitory storage medium having stored thereon instructions that, when executed by a computer, cause the computer to perform a method comprising:
processing a digital representation of a first text generated by the person before administering the intervention to the person, the processing comprising:
a) determining that a first text comprises N words;
calculating a first collection of Dynamic Word Entropy (DWE) values comprising N−K+1 values, K being an integer smaller than N; and wherein each DWE value is calculated for a respective i th text-segment of the first text, each text-segment consists of first K+i−1 words of the text;
applying at least one Transformation Function to the first collection of DWE values, and generating a first respective Transformed Value corresponding to the first collection of DWE values;
processing a digital representation of a second text generated by the person after administering the intervention to the person, the processing comprising:
b) determining that a second text comprises N words;
calculating a second collection of Dynamic Word Entropy (DWE) values comprising N−K+1 values, K being an integer smaller than N; and wherein each DWE value is calculated for a respective i th text-segment of the second text, each text-segment consists of second K+i−1 words of the text;
applying at least one Transformation Function to the second collection of DWE values, and generating a second respective Transformed Value corresponding to the second collection of DWE values;
based on a difference between the first Transformed Value corresponding to the first collection of DWE values and the second Transformed Value corresponding to the second collection of DWE values, determining whether the intervention had a positive, a negative, or a neutral effect on speech characteristics of the person.
12. The computerized method of claim 1 , wherein the intervention includes any one of: therapeutic treatment; and focusing session.
13. The computer system of claim 6 , wherein the intervention includes any one of: therapeutic treatment; and focusing session.
14. A computer implemented method of generating text by a machine, the method comprising using at least one computer processor for:
executing a first text-generating computer program for automatically generating a first text and executing a second text-generating computer program for automatically generating a second text;
processing the first text, the processing comprises:
a) determining that the first text comprises N1 words;
calculating a first collection of Dynamic Word Entropy (DWE) values comprising N1−K+ 1 values, K being an integer smaller than N1; and wherein each DWE value is calculated for a respective i th text-segment of the first text, each text-segment consists of first K+i−1 words of the text;
applying at least one Transformation Function to the first collection of DWE values, and generating a first respective Transformed Value corresponding to the first collection of DWE values;
processing the second text, comprising:
b) determining that the second text comprises N2 words;
calculating a second collection of Dynamic Word Entropy (DWE) values comprising N2-K+1 values, K being an integer smaller than N2; and wherein each DWE value is calculated for a respective i th text-segment of the second text, each text-segment consists of second K+i−1 words of the text;
applying at least one Transformation Function to the second collection of DWE values, and generating a second respective Transformed Value corresponding to the second collection of DWE values;
based on a difference between the first Transformed Value cone sponding to the first collection of DWE values and the second Transformed Value corresponding to the second collection of DWE values, selecting a superior text-generating computer program from among the first text-generating computer program and the second generating computer program.
15. The computer implemented method of claim 14 , wherein first text-generating computer program and second text-generating computer program are each machine learning computer programs.
16. The computer implemented method of claim 14 , wherein the at least one Transformation Function comprises at least one of: average; median; variance standard deviation.
17. A computer system comprising at least one processor operatively connected to a computer memory configured to:
execute a first text-generating computer program for automatically generating a first text and execute a second text-generating computer program for automatically generating a second text;
process the first text, the processing comprises:
a) determine that the first text comprises N1 words;
calculating a first collection of Dynamic Word Entropy (DWE) values comprising N1−K+1 values, K being an integer smaller than N1; and wherein each DWE value is calculated for a respective i th text-segment of the first text, each text-segment consists of first K+i−1 words of the text;
applying at least one Transformation Function to the first collection of DWE values, and generating a first respective Transformed Value corresponding to the first collection of DWE values;
processing the second text, comprising:
b) determine that the second text comprises N2 words;
calculating a second collection of Dynamic Word Entropy (DWE) values comprising N2-K+1 values, K being an integer smaller than N2; and wherein each DWE value is calculated for a respective i th text-segment of the second text, each text-segment consists of second K+i−1 words of the text;
applying at least one Transformation Function to the second collection of DWE values, and generating a second respective Transformed Value corresponding to the second collection of DWE values;
based on a difference between the first Transformed Value cone sponding to the first collection of DWE values and the second Transformed Value corresponding to the second collection of DWE values, selecting a superior text-generating computer program from among the first text-generating computer program and the second generating computer program.
18. The system of claim 17 , wherein first text-generating computer program and second text-generating computer program are each machine learning computer programs.
19. The system of claim 18 , wherein the at least one Transformation Function comprises at least one of: average; median; variance standard deviation.