Generation of support data records using natural language processing

• US 9,864,798 B2
• Filed: 03/31/2015
• Issued: 01/09/2018
• Est. Priority Date: 09/22/2014
• Status: Active Grant

• Current Assignee: BMC Software Incorporated (KKR & Co., Inc.)
• Original Assignee: BMC Software Incorporated (KKR & Co., Inc.)
• Inventors: Hall, Jonathan W., Chu, Sun Chun, Cline, Troy, Phadke, Nilesh
• Primary Examiner(s): Misir, Dave
• Application Number:
  US14/674,742
• Publication Number:
  US 20160085856A1
• Time in Patent Office: 1,015 Days
• Field of Search: 706 46, 707739
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/3346 using probabilistic model
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance

Abstract

A view generator receives support text characterizing a support requirement for available information technology (IT) support, the support text being received in sentence form via a graphical user interface (GUI). A text analyzer performs natural language processing on the support text and thereby identifies at least one sentence part and at least one named entity within the support text. A support record generator relates each of the at least one sentence part and the at least one named entity to a support record type, and generates a support data record for the support requirement, including filling individual fields of the support data record using the at least one sentence part and the at least one named entity.

Claims

1. A system including instructions stored on a non-transitory computer readable storage medium and executable by at least one processor, the system comprising:

a view generator configured to cause the at least one processor to receive support text characterizing a support requirement for information technology (IT) support, the support text being received via a graphical user interface (GUI);

a text analyzer configured to cause the at least one processor to perform natural language processing on the support text to identify at least one sentence part and at least one named entity within the support text; and

a support record generator configured to cause the at least one processor to relate each of the at least one sentence part and the at least one named entity to a support record type, and further configured to cause the at least one processor to generate a support data record for the support requirement, including filling individual fields of the support data record using the at least one sentence part and the at least one named entity, wherein the support record generator includes

a sentence part score calculator configured to provide a sentence part score for the at least one sentence part, the sentence part score representing a first probabilistic determination that the at least one sentence part is associated with each of a plurality of support record types, including the support record type,

a named entity score calculator configured to provide a named entity score for the at least one named entity, the named entity score representing a second probabilistic determination that the at least one named entity is associated with each of the plurality of support record types, including the support record type, and

a support record type identifier configured to determine the support record type based on a combination of the first probabilistic determination and the second probabilistic determination.

2. The system of claim 1, wherein the view generator is further configured to provide the GUI with a single field dialog box for receiving the support text.

3. The system of claim 1, wherein the text analyzer includes a sentence parser configured to identify individual sentences within the support text and parse the individual sentences to obtain individual words and numbers.

4. The system of claim 1, wherein the text analyzer includes a sentence part identifier configured to identify and label the at least one sentence part within the support text, based on a context of a use thereof within the support text.

5. The system of claim 1, wherein the text analyzer includes a named entity extractor configured to execute at least one query against support-related data to identify the at least one named entity of the at least one sentence part.

6. The system of claim 1, wherein the support record generator is configured to present the support record type among a plurality of support record types, and to receive confirmation of correct association of the support record type with the support text, using the GUI.

7. The system of claim 1, wherein the support record generator is configured to execute at least one machine learning algorithm to classify the at least one sentence part and the at least one named entity with respect to a plurality of support record types, including the support record type.

8. The system of claim 1, wherein the support record generator is configured to generate an initial support record type, and includes a score modifier configured to receive a modification of the initial support record type, in response to a determination that the initial support record type does not correspond to the support text, wherein the score modifier is configured to adjust one or both of the sentence part score and the named entity score and thereby enable generation of the support record type based thereon.

9. The system of claim 1, wherein the support record generator includes a support record field mapper configured to fill individual fields of the support data record using the at least one sentence part and the at least one named entity, including mapping a label identifying the at least one sentence part and a name of the at least one named entity, to corresponding ones of the individual fields of the support data record.

10. A method comprising:

receiving support text characterizing a support requirement for available information technology (IT) support, the support text being received in sentence form via a graphical user interface (GUI);

identifying at least one sentence part within the support text;

calculating a sentence part score relating the at least one sentence part to at least one support type of the available IT support;

providing the sentence part score for the at least one sentence part, the sentence part score representing a first probability that the at least one sentence part is associated with each of a plurality of support types, including the at least one support type;

identifying at least one named entity within the support text, including executing a query against support-related data, using the support text;

calculating a named entity score relating the at least one named entity to the at least one support type;

providing the named entity score for the at least one named entity, the named entity score representing a second probability that the at least one named entity is associated with each of the plurality of support types, including the at least one support type;

combining the sentence part score and the named entity score to represent a third probability that the support requirement is for the at least one support type; and

filling the at least one sentence part and the at least one named entity within corresponding fields of a support data record of the at least one support type, based on the combined sentence part score and the named entity score.

11. The method of claim 10, wherein the identifying at least one sentence part includes performing natural language processing of the support text.

12. A computer program product including instructions recorded on a non-transitory computer readable storage medium and configured, when executed by at least one semiconductor processor, to cause the at least one semiconductor processor to:

receive support text characterizing a support requirement for information technology (IT) support, the support text being received in sentence form via a graphical user interface (GUI);

identify at least one sentence part within the support text;

calculate a sentence part score relating the at least one sentence part to at least one support type of the available IT support;

provide the sentence part score for the at least one sentence part, the sentence part score representing a first probability that the at least one sentence part is associated with each of a plurality of support types, including the at least one support type;

identify at least one named entity within the support text, including executing a query against support-related data, using the support text;

calculate a named entity score relating the at least one named entity to the at least one support type;

provide the named entity score for the at least one named entity, the named entity score representing a second probability that the at least one named entity is associated with each of the plurality of support types, including the at least one support type;

combine the sentence part score and the named entity score to represent a third probability that the support requirement is for the at least one support type; and

fill the at least one sentence part and the at least one named entity within corresponding fields of a support data record of the at least one support type, based on the combined sentence part score and the named entity score.

13. The computer program product of claim 12, wherein the instructions, when executed, are further configured to cause the at least one processor to:

execute at least one machine learning algorithm to classify the at least one sentence part and the at least one named entity with respect to a plurality of support types, including the at least one support type.

14. The computer program product of claim 12, wherein the instructions, when executed, are further configured to cause the at least one processor to:

fill individual fields of the support data record using the at least one sentence part and the at least one named entity, including mapping a label identifying the at least one sentence part and a name of the at least one named entity, to corresponding ones of the individual fields of the support data record.

15. The computer program product of claim 12, wherein the instructions, when executed, are further configured to cause the at least one processor to:

present the support type among a plurality of support types, and to receive confirmation of correct association of the support type with the support text, using the GUI.