Dynamic categorization of it service tickets using natural language description

1. A computer-based method of categorizing information technology (IT) service tickets, the method comprising:

pre-populating a description field of an IT service ticket with words that are predetermined to appear in IT service tickets;

logging the IT service ticket when text is entered into the description field, wherein the text defines a plurality of technological issues;

creating a filtered description field by removing triggers from the text entered into the description field, wherein the triggers are numerical dates;

computing a set of exponential weights based on the text in the filtered description field, wherein the text in the filtered description field includes a plurality of different strings of words, wherein each of the strings of words is associated with a different one of the technological issues;

assigning weightages of the set of exponential weights only to the different strings of words in the filtered description field, wherein the weightages of the exponential weights are assigned to the words of each string of words based on a length of the string of words of the filtered description field, wherein the weightages are assigned to the words in a decreasing value order in each string of words such that words that occur relatively earlier in the string of words are assigned relatively greater weightages than weightages assigned to other words that occur relatively later in the string of words;

multiplying the set of exponential weights by a Term Frequency-Inverse Document Frequency (TF-IDF) score associated with the words; and

determining an IT service ticket category based on a result generated by the multiplying.

2. The method of claim 1 , wherein the IT service ticket is logged via a medium selected from a group consisting of phone call, email, chat, text message, walk-in, web services, mobile app, and direct input, wherein the words that are predetermined to appear in IT service tickets are selected from the group of words consisting of: help, assist and unable.

3. The method of claim 1 , wherein geometric progression 1, α, α 2 , α 3 , . . . α n is used to assign the weightages to the words of the strings of words in the filtered description field.

4. The method of claim 3 , wherein the geometric progression 1, α, α 2 , α 3 , . . . α n is normalized by dividing the geometric progression 1, α, α 2 , α 3 , . . . α n by a total sum of weight

1

1

-

α

to get

1

1

-

α

,

α

1

-

α

,

α

2

1

-

α

,

α

3

1

-

α

,

…

⁢

⁢

α

n

1

-

α

,

to assign the weightages to the words of the strings of words in the filtered description field.

5. The method of claim 4 , further comprising:

generating features for machine learning;

utilizing the generated features for building a supervised machine learning model; and

evaluating the supervised machine learning model through analyzation of data from historical IT service tickets.

6. The method of claim 5 , wherein the supervised machine learning model recognizes and memorizes the data from the historical IT service tickets.

7. A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

pre-populating a description field of an IT service ticket with words that are predetermined to appear in IT service tickets;

logging the IT service ticket when text is entered into the description field, wherein the text defines a plurality of technological issues;

creating a filtered description field by removing triggers from the text entered into the description field, wherein the triggers are numerical dates;

computing a set of exponential weights based on the text in the filtered description field, wherein the text in the filtered description field includes a plurality of different strings of words, wherein each of the strings of words is associated with a different one of the technological issues;

assigning weightages of the set of exponential weights only to the different strings of words in the filtered description field, wherein the weightages of the exponential weights are assigned to the words based on a length of the string of words of the filtered description field, wherein the weightages are assigned to the words of each string of words based on a length of the string of words of the filtered description field, wherein the weightages are assigned to the words in a decreasing value order in each string of words such that words that occur relatively earlier in the string of words are assigned relatively greater weightages than weightages assigned to other words that occur relatively later in the string of words;

multiplying the set of exponential weights by a Term Frequency-Inverse Document Frequency (TF-IDF) score associated with the words; and

determining an IT service ticket category based on a result generated by the multiplying.

8. The computer system of claim 7 , wherein the IT service ticket is logged via a medium selected from a group consisting of phone call, email, chat, text message, walk-in, web services, mobile app, and direct input.

9. The computer system of claim 7 , wherein geometric progression 1, α, α 2 , α 3 , . . . α n is used to assign the weightages to the words of the strings of words in the filtered description field.

10. The computer system of claim 9 , wherein the geometric progression 1, α, α 2 , α 3 , . . . α n is normalized by dividing the geometric progression 1, α, α 2 , α 3 , . . . α n by a total sum of weight

1

1

-

α

to get

1

1

-

α

,

α

1

-

α

,

α

2

1

-

α

,

α

3

1

-

α

,

…

⁢

⁢

α

n

1

-

α

,

to assign the weightages to the words of the strings of words in the filtered description field.

11. The computer system of claim 10 , further comprising:

generating features for machine learning;

utilizing the generated features for building a supervised machine learning model; and

evaluating the supervised machine learning model through analyzation of data from historical IT service tickets.

12. The computer system of claim 11 , wherein the supervised machine learning model recognizes and memorizes the data from the historical IT service tickets.

13. A computer program product for transforming a general-purpose computer into a special-purpose computer, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

pre-populating a description field of an IT service ticket with words that are predetermined to appear in IT service tickets;

logging the IT service ticket when text is entered into the description field, wherein the text defines a plurality of technological issues;

creating a filtered description field by removing triggers from the text entered into the description field, wherein the triggers are numerical dates;

computing a set of exponential weights based on the text in the filtered description field, wherein the text in the filtered description field includes a plurality of different strings of words, wherein each of the strings of words is associated with a different one of the technological issues;

assigning weightages of the set of exponential weights only to the different strings of words in the filtered description field, wherein the weightages of the exponential weights are assigned to the words of each string of words based on a length of the string of words of the filtered description field, wherein the weightages are assigned to the words in a decreasing value order in each string of words such that words that occur relatively earlier in the string of words are assigned relatively greater weightages than weightages assigned to other words that occur relatively later in the string of words;

multiplying the set of exponential weights by a Term Frequency-Inverse Document Frequency (TF-IDF) score associated with the words; and

determining an IT service ticket category based on a result generated by the multiplying.

14. The computer program product of claim 13 , wherein the IT service ticket is logged via a medium selected from a group consisting of phone call, email, chat, text message, walk-in, web services, mobile app, and direct input, wherein a second of the words that are predetermined to appear in IT service tickets is selected from the group of words consisting of: assist and unable.

15. The computer program product of claim 14 , wherein geometric progression 1, α, α 2 , α 3 , . . . α n is used to assign the weightages to the words of the strings of words in the filtered description field.

16. The computer program product of claim 15 , wherein the geometric progression 1, α, α 2 , α 3 , . . . α n is normalized by dividing the geometric progression 1, α, α 2 , α 3 , . . . α n by a total sum of weight

1

1

-

α

to get

1

1

-

α

,

α

1

-

α

,

α

2

1

-

α

,

α

3

1

-

α

,

…

⁢

⁢

α

n

1

-

α

,

to assign the weightages to the words of the strings of words in the filtered description field.

17. The computer program product of claim 16 , further comprising:

generating features for machine learning;

utilizing the generated features for building a supervised machine learning model; and

evaluating the supervised machine learning model through analyzation of data from historical IT service tickets.

18. The computer program product of claim 17 , wherein a first of the words that are predetermined to appear in IT service tickets includes the word “help”.