Computer based system and method of determining a satisfaction index of a text

• US 7,430,552 B2
• Filed: 07/09/2002
• Issued: 09/30/2008
• Est. Priority Date: 07/09/2001
• Status: Expired due to Term

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services GmbH (Accenture PLC)
• Inventors: Cameron, Richard Neill, Baumhackl, Michael, Aragues, Ramon
• Primary Examiner(s): Wong; Don
• Assistant Examiner(s): Thai; Hanh B
• Application Number:
  US10/344,328
• Publication Number:
  US 20030191760A1
• Time in Patent Office: 2,275 Days
• Field of Search: 707 1- 7, 707200-204
• US Class Current: 1/1
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The invention relates to a computer based method and system for automatically determining in a document an object satisfaction score (44), choosing at least one of either a positive score or a negative score, comprising the steps of: subdividing the document into windows of words; selecting one of said windows when it contains at least one descriptive property corresponding to a key subject of said object and/or when it does not contain any descriptive property corresponding to an anti-key subject of said object; processing each selected window to determine a positive or negative score of said window by counting the occurrences of positive and negative concepts; and cumulating the scores of the selected windows to obtain said object satisfaction score for the document.

Claims

1. A computer based method for automatically determining an object satisfaction index of an object, among documents contained in at least one local or remote memory storage, the method comprising the steps of:

selecting from the memory storage documents relating to said object based on occurrences in the documents of at least one anti-key subject of the object;

processing each of the selected documents according to the following steps;

subdividing the document into windows of words;

selecting, automatically by a computer, one of said windows if it either does not contain any descriptive property corresponding to at least one anti-key subject of said object, or contains at least one descriptive property corresponding to a key subject of said object and does not contain any descriptive property corresponding to at least one anti-key subject of said object;

processing each selected window to determine a positive or negative score of said window by counting occurrences of positive and negative concepts;

cumulating the scores of the selected windows and calculating said object satisfaction score for the document, the object satisfaction score indicative of a number of occurrences of positive or negative opinions conveyed in relation to the object; and

storing in a computer memory data representing the scores and the related windows, and data representing the object satisfaction score for the document;

cumulating the scores of the selected documents by adding said object satisfaction score for the document to a cumulative score only if an absolute value of a difference between the positive and negative scores of the document is higher than a predetermined satisfaction threshold, or is otherwise considered as opinionless and deducing from obtained cumulated scores said object satisfaction index; and

outputting a report of the object, the object satisfaction index, and the scores of the related documents;

whereby a trend in people'"'"'s perception regarding the object can be determined.

2. The computer based method of claim 1, wherein the object is selected from the group consisting of a product, a service, a brand, and an event.

3. A computer based method for automatically determining an object satisfaction index of an object, among documents contained in at least one local or remote memory storage, the method comprising the steps of:

selecting from the memory storage documents relating to said object based on occurrences of at least one anti-key subject of the object;

processing each of the selected documents according to the following steps;

subdividing the document into windows of words;

selecting, automatically by a computer, one of said windows if it either does not contain any descriptive property corresponding to at least one anti-key subject of said object, or contains at least one descriptive property corresponding to a key subject of said object and does not contain any descriptive property corresponding to at least one anti-key subject of said object;

processing each selected window to determine a positive or negative score of said window by counting occurrences of positive and negative concepts;

cumulating the scores of the selected windows and calculating said object satisfaction score for the document, the object satisfaction score indicative of a

number of occurrences of positive or negative opinions conveyed in relation to the object; and

storing in a computer memory data representing the scores and the related windows, and data representing the object satisfaction score for the document;

counting a number of occurrences of competitor subjects in the document;

cumulating the scores of the selected documents by adding said object satisfaction score for the document to a cumulative score only if said number of competitor subject occurrences is lower than a predetermined comparison threshold and deducing from obtained cumulated scores said object satisfaction index; and

outputting a report of the object, the object satisfaction index, and the scores of the related documents;

whereby a trend in people'"'"'s perception regarding the object can be determined.

4. The computer based method of claim 3, wherein the competitor subjects are part of the anti-key subjects and are counted during said processing step of each selected window.

5. The computer based method of claim 3, wherein the object is selected from the group consisting of a product, a service, a brand, and an event.