IP Library › Granted Patent US 11,238,082
Granted Patent B2
US 11,238,082 · App. 15/729,250 · Granted Feb 1, 2022

Text analysis of unstructured data

Inventors: Dileeshvar Radhakrishnan (San Jose, CA); Robert Ninness (Amsterdam, NL); Seth Stafford (San Jose, CA); Aida Rikovic Tabak (Amsterdam, NL); Shayan Shahand (Amsterdam, NL); Sumana Ravikrishnan (Sunnyvale, CA); Abhijith Nagarajan (Amstelveen, NL); Prabhakaran Subramani Thandayuthapani (Amsterdam, NL); Marta Penzo (Amsterdam, NL); Ciprian Mocanu (Amsterdam, NL)
Assignee: ServiceNow, Inc.
G06F16/358G06F3/0482G06F40/103G06F40/174G06F40/205G06F40/247G06F40/284
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,238,082
App. No.
15/729,250
Granted
Feb 1, 2022
Kind
B2
Abstract

Systems, methods, and media are presented to analyze unstructured text. Unstructured data is retrieved from a user inputs or records. The user inputs include an incident report or a problem report. Text words in the unstructured data are identified. A number of occurrences of each text word is counted. The text words are displayed in a word cloud by displaying each of the text words with a size corresponding to the number of occurrences of the respective text word. A larger number of occurrences results in a larger size of the respective text word when displayed. At least one trendline for occurrences for a corresponding text word is also displayed.

Claims (52)

1. A system comprising:

one or more processors; and

memory having instructions thereon that, when executed, are configured to cause the one or more processors to:

retrieve unstructured data from a plurality of user inputs, wherein the plurality of user inputs comprises an incident report or a problem report;

identify a plurality of text words in the unstructured data;

count a number of occurrences of each text word in the plurality of text words;

display the plurality of text words in a word cloud by displaying each of the plurality of text words with a size corresponding to the number of occurrences of the respective text word of the plurality of text words, wherein a larger number of occurrences results in a larger size of the respective text word when displayed;

cause display of a plurality of trendlines for occurrences for a corresponding text word of the plurality of text words, wherein displaying the plurality of trendlines comprises displaying a visual indicator for each trendline of the plurality of trendlines indicating that the respective trendline matches a corresponding text word in the word cloud; and

save, in the memory, words and settings used to generate the plurality of trendlines and the word cloud for reapplication to generate different word clouds and trendlines from different unstructured data at a later time.

2. The system of claim 1 , wherein retrieving the unstructured data comprises receiving the unstructured data in a plurality of reports from a remote computing device.

3. The system of claim 1 , wherein the unstructured data comprises text that is input into a comment field of the incident report or the problem report.

4. The system of claim 1 , wherein the unstructured data comprises incident reports related to technical support for devices or services.

5. The system of claim 1 , wherein the instructions are configured to cause the one or more processors to:

receive an indication of a stopword; and

omit any occurrence of the stopword in the unstructured data from the plurality of text words.

6. The system of claim 1 , wherein the instructions are configured to cause the one or more processors to:

receive a selection of a first text word of the plurality of text words in the displayed plurality of text words;

size a remaining plurality of text words strings by:

removing records that do not include the first text word from the unstructured data as remaining unstructured data to form the remaining plurality of text words; and

counting a number of occurrences of each text word of the remaining plurality of text words in the remaining unstructured data; and

cause display of the remaining plurality of text words by displaying each text word corresponding to the number of occurrences of the respective text word of the plurality of text words in the remaining unstructured data, wherein a larger number of occurrences results in a larger size of the respective text word when displayed.

7. The system of claim 1 , wherein displaying the plurality of trendlines comprises displaying the plurality of trendlines concurrently while displaying the plurality of text words.

8. The system of claim 1 , wherein the text word comprises a number, an acronym, or a combination thereof.

9. The system of claim 1 , wherein the text words are separated in the unstructured data by whitespace characters or punctuation in the unstructured data.

10. The system of claim 9 , wherein the whitespace character comprises an ASCII space or a tab.

11. A method comprising:

retrieve unstructured data from a plurality of user inputs, wherein the plurality of user inputs comprises a plurality of reports;

identify a plurality of text words in the unstructured data;

count a number of occurrences of each text word in the plurality of text words;

display the plurality of text words in a word cloud by displaying each of the plurality of text words with a size corresponding to the number of occurrences of the respective text word of the plurality of text words, wherein a larger number of occurrences results in a larger size of the respective text word when displayed;

display a plurality of trendlines for occurrences of the plurality of text words, wherein displaying the plurality of trendlines comprises displaying a visual indicator for each trendline of the plurality of trendlines indicating that the respective trendline matches a corresponding text word in the word cloud;

save settings used to generate the word cloud and the plurality of trendlines;

retrieve an additional plurality of text words in additional data from an additional plurality of reports, wherein the additional plurality of reports has a different type than a type of the plurality of reports;

display the additional plurality of text words in an additional word cloud in an auxiliary frame using the saved settings; and

display an additional plurality of trendlines for occurrences of the additional plurality of text words using the saved settings.

12. The method of claim 11 , wherein counting the number of occurrences comprises counting the respective text word once per report of the plurality of reports.

13. The method of claim 11 , wherein counting the number of occurrences comprises counting each occurrence of the respective text word multiple times in a report of the plurality of reports.

14. The method of claim 11 , wherein retrieving, identifying, counting, and displaying is performed in a multi-instance architecture having a primary virtual machine and a second virtual machine.

15. The method of claim 11 , wherein the plurality of reports comprises records corresponding to incident reports or problem reports.

16. Tangible, non-transitory, and computer-readable medium having instructions stored thereon, wherein the instructions are configured to cause one or more processors to:

retrieve unstructured data from a report comprising a plurality of user inputs, wherein the report comprises a plurality of incident reports or problem reports;

identify a first plurality of text words in the unstructured data;

count a number of occurrences of each text word in the first plurality of text words;

cause display of the first plurality of text words in a first word cloud in a first frame by displaying one or more of the first plurality of text words with a size corresponding to the number of occurrences of the respective text word of the first plurality of text words, wherein a larger number of occurrences results in a larger size of the respective text word when displayed;

cause display of a first plurality of trendlines in the first frame for occurrences for corresponding text words of the first plurality of text words, wherein causing display of the first plurality of trendlines comprises causing display of a visual indicator for each trendline of the first plurality of trendlines indicating that the respective trendline matches a corresponding text word in the first word cloud;

save settings used to generate the first word cloud and the first plurality of trendlines;

cause display of a second plurality of text words in a second word cloud in a second frame using the saved settings; and

cause display of a second plurality of trendlines in the second frame using the saved settings, wherein the first plurality of text words and the second plurality of text words correspond to different time periods of compiled incident reports or problem reports.

17. The tangible, non-transitory, and computer-readable medium of claim 16 , wherein the instructions are configured to cause the one or more processors to receive a limit on a number of text words in the unstructured data to be included in the first word cloud, wherein displaying one or more of the first plurality of text words comprises displaying no more than the number of text words in the first word cloud.

18. The tangible, non-transitory, and computer-readable medium of claim 16 , wherein the instructions are configured to cause the one or more processors to receive a limit on a number of the first plurality of trendlines, wherein displaying the first plurality of trendlines comprises displaying no more trendlines than the limit on the number.

19. The tangible, non-transitory, and computer-readable medium of claim 16 , wherein the visual indicator of each trendline of the first plurality of trendlines comprises a color that is the same color as used to fill the corresponding text word in the first word cloud.

20. The system of claim 1 , wherein the visual indicator of each trendline of the plurality of trendlines comprises a color that is the same color as used to fill the corresponding text word in the word cloud.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 5, 2018
From: RADHAKRISHNAN, DILEESHVAR; NINNESS, ROBERT; STAFFORD, SETH; TABAK, AIDA RIKOVIC; SHAHAND, SHAYAN; RAVIKRISHNAN, SUMANA; NAGARAJAN, ABHIJITH; THANDAYUTHAPANI, PRABHAKARAN SUBRAMANI; PENZO, MARTA; MOCANU, CIPRIAN
To: SERVICENOW, INC.
Reel/Frame 044548/0627 →
Continuity (2)
Provisional Application 62568087 · Oct 4, 2017
Related Publication 20190102455A1 · Apr 4, 2019