Aviation field service report natural language processing

• US 9,886,478 B2
• Filed: 05/24/2011
• Issued: 02/06/2018
• Est. Priority Date: 10/07/2005
• Status: Expired due to Fees

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Mukherjee, Joydeb
• Primary Examiner(s): Nguyen, Chuong P
• Application Number:
  US13/115,006
• Publication Number:
  US 20110257839A1
• Time in Patent Office: 2,450 Days
• Field of Search: 701 1, 701 3, 701 291, 701 334, 701 316- 318, 704 1, 704 9, 704 4, 704 6, 704 7, 702183, 702185, 702187
• CPC Class Codes: B64F 5/40 Maintaining or repairing aircraft
• CPC Class Codes: B64F 5/60 Testing or inspecting aircraft components or systems
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

An aircraft service information handling system comprises an input module operable to collect field service narrative data. A natural language data extraction module extracts problem data and related solution data from the narrative data, and a database module populates an aircraft service information database with the extracted problem data and the related extracted solution data. The database module further searches the database for populated problem data, and retrieves the related populated solution data.

Claims

1. A method of managing aircraft service information, comprising:

collecting, by a processor, unstructured field service narrative data from a field service report utilizing self-training natural language processing algorithms;

extracting, by the processor, problem data from the narrative data;

extracting, by the processor, solution data from the unstructured field service narrative data, wherein extracting solution data is performed on the unstructured field service narrative data automatically by machine, such that a text representation of the narrative data is processed by machine to distinguish and parse at least one of problem data and solution data from the narrative by the self-training natural language processing algorithms;

tokenizing, by the processor, the extracted solution data to create word tokens;

electronically tagging, by the processor, semantic descriptors to the word tokens;

populating, by the processor, an aircraft service information database used in servicing an aircraft with the extracted problem data, the related extracted solution data, and the semantic descriptors;

querying, by a terminal, the populated problem data;

searching, by the processor, the populated problem data queried by the terminal from the aircraft service information database;

retrieving, by the processor, the related populated solution data from the aircraft service information database;

sending, by the processor, the related populated solution data to the terminal accessed by the user; and

displaying, by the terminal, the related populated solution data.

2. The method of claim 1, wherein the step of extracting problem data comprises:

performing a lexical analysis on the collected field service narrative data to identify the lexical class of each of a plurality of parts of speech existing therein;

parsing the collected field service narrative data based at least in part on the identified lexical class of each of the plurality of parts of speech; and

extracting the problem data from the narrative data based at least in part on the lexical analysis.

3. The method of claim 2, wherein in the lexical analysis comprises determining one of a metonymy relationship and hyperonomy relationship between tokens.

4. The method of claim 2, wherein in at least one of extracting problem data and extracting solution data from the narrative data comprises analysis of a statistical occurrence of specific words in at least a portion of the narrative.

5. The method of claim 2, wherein the lexical analysis comprises building conceptual vectors from one of the extracted solution data and the extracted problem data.

6. The method of claim 5, wherein an angular distance is determined between a first conceptual vector and a second conceptual vector, where a small angular distance indicates similarity between the first and the second conceptual vector and a large angular distance indicates a dissimilarity between the first and the second conceptual vector.

7. The method of claim 5, wherein contextualization is determined between a first conceptual vector and a second conceptual vector.

8. The method of claim 1, wherein populating an aircraft service information database comprises storing extracted problem data and related extracted solution data.

9. The method of claim 1, wherein the tagging the semantic descriptors is based on conceptual vectors that are defined from aircraft service language semantics.