Neutral sales consultant

• US 7,574,427 B2
• Filed: 06/03/2005
• Issued: 08/11/2009
• Est. Priority Date: 05/17/2002
• Status: Expired due to Fees

• Current Assignee: Patrick Y. Delefevre
• Original Assignee: Patrick Y. Delefevre
• Inventors: Delefevre, Patrick Y.
• Primary Examiner(s): Mahmoudi; Tony
• Assistant Examiner(s): Truong; Dennis
• Application Number:
  US11/144,432
• Publication Number:
  US 20070011131A1
• Time in Patent Office: 1,530 Days
• Field of Search: 707/3, 707/4, 707/5, 707/6, 707/104.1, 709/224, 709/217, 709/225, 709/226, 709/229, 382/116, 382/124, 382/305
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

An expert system is provided for answering questions provided by a potential purchaser of goods or services using a neutral sales consultant in which a question sentence entered by the purchaser is understood using specialized library tables developed to understand both the subject and form of the question sentence. Thereafter an appropriate or relevant answer to the question is automatically given relating to sale of the product or service. The result is that questions are more easily understood by the system and more relevant answers can be given because both relate to specialized fingerprint parameters and the use of neutral experts.

Claims

1. A method for giving a user information about a category of product or service in which the user initially submits a query in the form of a question sentence using a fingerprint query system, comprising the steps of:

during setup, creating libraries constituting contextual relation tables including a General Library of Question Forms, and a General Library of Subjects of Questions organized based upon fingerprint parameters, their values and their relationships, the library set up by an expert who selects the values based on relationships between the values and populates the answers in the Library of Subjects of Questions, whereby subjects can be analyzed on a contextual basis based on parameters, the values thereof and relations between the values to arrive at a verified subject;

during runtime, providing an analyzing engine that analyzes the question sentence to ascertain context by dividing the question sentence into a subject of the question sentence and the form of the question sentence, the analyzing engine analyzing the subject of the question sentence utilizing the Library of Subjects of Questions to arrive at a verified subject, the analyzing engine analyzing the form of the question sentence using the verified subject by matching the detected question form with question forms in the General Library of Question Forms;

upon a question form match for a verified subject accessing a Neutral Consultant Library set up by an expert to provide a predetermined answer to the question;

wherein the libraries include a General Library having a set of General Library Tables that reflect all possible items related to a predetermined category and that are organized into lists;

further including the step of forming a relationship matrix of all words that constitute parameters, variable table entries and items in libraries in which the relationship matrix defines the relationship between two units taken from the group consisting of parameters, variable table entries and items constituting a basket;

submitting the basket to experts to ascertain which of the relationships correspond to real world relationships as they relate to a category, thus to constitute expert verified relationships; and

populating an Expert General Library Table from the expert verified relationships, thus to decide from the relationship matrices which relationships exist as determined by experts and thus what questions cart be asked about a specific relationship.

2. The method of claim 1, wherein the libraries include the General Library of Subjects of Questions for the recognition of subjects of a question through the setup of General Library Tables populated using fingerprint parameters.

3. The method of claim 2, wherein the General Library Tables are subdivided into a number of lists.

4. The method of claim 3, wherein only a selected limited number of lists are consulted to determine the subject matter of the question sentence.

5. The method of claim 3, wherein the selected limited number of lists include words, their synonyms, corresponding symbols and corresponding jargon.

6. The method of claim 3, wherein the General Library Table lists are filtered into a Selected General Library Table based on relationships between items in the lists specified by experts so as to make available only lists that make sense in terms of expert-defined relationships so that corresponding libraries can be readily accessed by a user'"'"'s question sentence.

7. The method of claim 1, wherein the libraries are set up using specialized parameters formulated for fingerprint inquiries relating to the purchasing of an item or service.

8. The method of claim 1, and further including the steps of experts deciding from the questions that can be asked about a subject what relationships make sense, what are the most likely questions issuing from those relationships that make sense and what the corresponding answers should be;

and

forming a List of Experts'"'"' Questions and a List of Experts'"'"' Answers therefrom.

9. The method of claim 8, and further including the steps of generating an Alternative List of Experts'"'"' Questions and Experts'"'"' Answers populated by a number of ways a given question can be asked and still obtain the same answer;

and

forming an English Expert Library therefrom.

10. The method of claim 9, wherein during runtime a user'"'"'s question sentence interrogates the Experts'"'"' General Library table to establish a match and thus units that are recognized as being part of a subject.

11. The method of claim 10, wherein any remaining unmatched units interrogate the Selected General Library Table to determine if there are more units that are subjects.

12. The method of claim 10, and further including the step of ascertaining the subject of a question sentence if the question sentence is of an expert-recognized form by interrogating the General Library of Question Forms, with a match indicating a legitimate question and a legitimate subject.

13. The method of claim 12, wherein the step of generating an answer to a question includes the step of submitting the legitimate subject having a legitimate form to the List of Experts'"'"' Answers.

14. The method of claim 12, and further including the steps of providing the user with all questions that relate to an already identified subject if no legitimate question form is matched by the question sentence;

and, having the user select from all of the questions what question is to be answered.