Solving problems in data processing systems based on text analysis of historical data

• US 9,087,121 B2
• Filed: 04/12/2012
• Issued: 07/21/2015
• Est. Priority Date: 04/12/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhatt, Dhruv A., McNeil, Kristin E., Patel, Nitaben A.
• Primary Examiner(s): Leroux, Etienne
• Assistant Examiner(s): BIBBEE, JARED M
• Application Number:
  US13/445,137
• Publication Number:
  US 20130275392A1
• Time in Patent Office: 1,195 Days
• Field of Search: 707/692
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3331 Query processing

Abstract

Computer program products and systems, determine solutions to a problem experienced by a data processing system user. A query is received from the user. The query includes a problem description of the problem experienced by the user with respect to the data processing system. One or more keywords are extracted from the received problem description. An index of problems and associated solutions is searched using the one or more extracted keywords. The index of problems and associated solutions is created by analyzing a document collection describing problems and associated solutions with a text analytics application. One or more documents are returned that contains words or phrases that are similar to the keywords used for searching the index of problems and associated solutions. The documents relevant for the problem and associated solutions are presented to the user.

Claims

1. A computer program product for determining solutions to a problem experienced by a user with respect to a data processing system, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to select a collection of documents;

computer readable program code configured to analyze the text in each document using plain text analysis and an unstructured information management application containing text analytics rules to identify problems and associated solutions, the plain text analysis using a problem dictionary containing words and phrases that identify sentences describing problems and a solution dictionary containing words and phrases that identify sentences describing solutions to problems;

computer readable program code configured to create a searchable index of problems and associated solutions and storing the index in a database;

computer readable program code configured to receive a problem description from a user of the problem experienced by the user with respect to the data processing system, after creating the searchable index;

computer readable program code configured to analyze the received problem description using plain text analysis to extract one or more keywords from the problem description;

computer readable program code configured to search the index of problems and associated solutions using the one or more extracted keywords;

computer readable program code configured to return one or more documents containing words or phrases that are similar to the one or more extracted keywords; and

computer readable program code configured to present the documents relevant for the problem and associated solutions to the user.

2. The computer program product of claim 1, wherein:

the collection of documents is a collection of documents related to problem reports.

3. The computer program product of claim 1, wherein the computer readable program code configured to present the documents includes:

computer readable program code configured to organize the documents relevant for the problem and associated solutions based on a correlation of keywords and frequency of solutions.

4. The computer program product of claim 1, wherein the document collection includes one or more of:

forums, problem reports, blogs, emails, product manuals and product documentation.

5. The computer program product of claim 1, further comprising:

computer readable program code configured to receive a user input associating a problem and a solution; and

computer readable program code configured to update the index of problems and associated solutions with the received user input.

6. The computer program product of claim 1, further comprising:

computer readable program code configured to receive a user input identifying erroneous solutions to a problem; and

computer readable program code configured to remove erroneous solutions from the index of problems and associated solutions, based on the received user input.

7. The computer program product of claim 1, wherein the computer readable program code configured to present the documents includes:

computer readable program code configured to include a reference to the original source of a problem and associated solution that is retrieved from the index of problems and associated solutions.

8. A system for determining solutions to a problem experienced by a user with respect to a data processing system, comprising:

a processor;

a memory storing instructions operable to be executed by the processor, wherein the instructions include instructions to;

select a collection of documents;

analyze the text in each document using plain text analysis and an unstructured information management application containing text analytics rules to identify problems and associated solutions, the plain text analysis using a problem dictionary containing words and phrases that identify sentences describing problems and a solution dictionary containing words and phrases that identify sentences describing solutions to problems;

create a searchable index of problems and associated solutions and storing the index in a database;

receive a problem description from a user of the problem experienced by the user with respect to the data processing system, after creating the searchable index;

analyze the received problem description using plain text analysis to extract one or more keywords from the problem description;

search the index of problems and associated solutions using the one or more extracted keywords;

return one or more documents containing words or phrases that are similar to the one or more extracted keywords; and

present the documents relevant for the problem and associated solutions to the user.

9. The system of claim 8, wherein:

the collection of documents is a collection of documents related to problem reports.

10. The system of claim 8, wherein the instructions to present the documents include instructions to organize the documents relevant for the problem and associated solutions based on a correlation of keywords and frequency of solutions.

11. The system of claim 8, wherein the document collection includes one or more of:

forums, problem reports, blogs, emails, product manuals and product documentation.

12. The system of claim 8, wherein the memory further comprises instructions to:

receive a user input associating a problem and a solution; and

update the index of problems and associated solutions with the received user input.

13. The system of claim 8, wherein the memory further comprises instructions to:

receive a user input identifying erroneous solutions to a problem; and

remove erroneous solutions from the index of problems and associated solutions, based on the received user input.

14. The system of claim 8, wherein the instructions to present the documents include instructions to include a reference to the original source of a problem and associated solution that is retrieved from the index of problems and associated solutions.