Quality of records containing service data

• US 8,478,624 B1
• Filed: 07/17/2012
• Issued: 07/02/2013
• Est. Priority Date: 03/22/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bivens, John A., Salapura, Valentina, Vukovic, Maja
• Primary Examiner(s): Sterrett, Jonathan G
• Assistant Examiner(s): Lan, Tzu-Hsiang
• Application Number:
  US13/551,277
• Time in Patent Office: 350 Days
• Field of Search: None
• US Class Current: 705/7.12
• CPC Class Codes: G06Q 10/06395 Quality analysis or management

Abstract

An embodiment of the invention, directed to assessing quality of recorded service data, comprises the step of receiving a record containing service data at a service record evaluator. The method further comprises selecting at least one information field of a plurality of information fields contained in the received record, and determining a numerical quality score for each selected information field. Each of the quality scores is used to compute a cumulative quality score for the record, and it is determined whether the cumulative quality score is no less than a minimum quality threshold.

Claims

1. A method for assessing quality of recorded service data, comprising the steps of:

a computer selecting and processing multiple tickets to produce a keyword dictionary of terms in the multiple tickets;

the computer receiving, by the processor, a record containing service data at a service record evaluator, the record comprising a specified ticket having a plurality of information fields, the plurality of information fields including a pull down field and an open end text field;

the computer selecting the pull down field and the open end text field;

the computer determining a first numerical quality score for the pull down field;

the computer, using the keyword dictionary, identifying keywords included in the open end text field;

the computer determining a second numerical quality score for the open end text field by multiplying a count of the keywords in the open end text field times a length of a work order description in the open end text field and a coefficient that normalizes the length of the work order description against a corpus of the multiple tickets;

the computer combining the first numerical quality score and the second numerical quality score to obtain a cumulative quality score for the record;

the computer determining that the cumulative quality score is less than a minimum quality threshold; and

the computer generating, responsive to determining that the cumulative quality score is less than the minimum quality threshold, a message indicating one or more fields with insufficient quality scores.

2. The method of claim 1, wherein the pull down field is selected from a group that includes at least a worktype field, a failure class field, and a failure symptom field.

3. The method of claim 1, wherein:

the open end text field is selected from a group that includes at least a work order description field, and a classification description field.

4. The method of claim 1, wherein the quality score for at least one information field is selectively weighted.

5. The method of claim 1, wherein the ticket will be closed only if the cumulative quality score is no less than the minimum quality threshold.

6. The method of claim 5, wherein:

the computer, responsive to a failure to close the ticket, generates a message which includes comments regarding ticket documentation.

7. The method of claim 6, wherein:

the message indicates respective fields that have insufficient quality scores.

8. The method of claim 6, further comprising:

the computer, responsive to generating the message, receives selective revisions of information contained in the ticket.

9. The method of claim 1, further comprising:

the computer determining the quality score for the open end text field includes determining a text length of said open end text field.

10. The method of claim 9, further comprising:

the computer determining the quality score for the open end text field includes multiplying the length thereof by a selected coefficient.

11. The method of claim 1, further comprising:

the computer calculating a contextual relevance of T(k) against Hi, where T is a weighted vector and T(k) is an importance or a quality of k, wherein k is a pull down field or an open ended text field, and wherein Hi is a history buffer minus a cluster of tickets.