Knowledge system

• US 20050283474A1
• Filed: 08/26/2005
• Published: 12/22/2005
• Est. Priority Date: 11/28/2001
• Status: Abandoned Application

• Current Assignee: Symbio IP Limited
• Original Assignee: Symbio IP Limited
• Inventors: Byford, Peter John, Francis, Gillian E.
• Application Number:
  US11/211,499
• Publication Number:
  US 20050283474A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]

Abstract

A method of assembling a knowledge database containing question and answer pairs, the method comprising the steps of: extracting questions from a multiplicity of electronic communications; enabling the sender of the communication to examine and select or deselect the extracted question(s); classifying each question based upon the content of the question and identifying keywords in each question; entering the questions into the database together with their respective classifications and keywords; and entering into the database answers corresponding to the entered questions; wherein an answer to a question may be found by classifying the question and identifying keywords therein, identifying questions contained in the database which have the same or a similar classification and which contain some or all of the same keywords, and identifying the corresponding answers

Claims

1. A method of operating a knowledge base, the knowledge base comprising an electronic database containing question and answer pairs and being coupled to a communications network accessible by users, the method comprising:

receiving a question created by a user;

analyzing a word content of the received question to match phrases contained within the question with functionally synonymous phrases stored in a phrase look-up table, and to match words contained within the question with functionally synonymous words stored in a word look-up table;

prioritizing different synonymous words and/or phrases and combinations of synonymous words and/or phrases according to a predefined set of rules;

identifying a classification from a predefined set of classifications on a basis of the words and/or phrases or combination of these, having a highest priority, and assigning the identified classification to the question;

identifying keywords in the question;

searching the knowledge base to identify questions having the same or related classifications to the identified classification and containing the same or some of the identified keywords; and

prioritizing the identified questions according to corresponding classifications and the identified keywords contained in the identified questions and returning the identified questions to the user in a prioritized list.

2. A method according to claim 1, wherein said step of identifying a classification comprises accessing a look-up table which maps words and phrases and combinations thereof to classifications, and retrieving from the database the classification which is mapped to the words and/or phrases or combination thereof having the highest priority.

3. A method according to claim 2, further comprising:

prioritizing combinations of words and/or phrases using said predefined set of rules in dependence upon a spacing of the words and/or phrases in the question, adjacent or closely spaced words and/or phrases being prioritised ahead of words and/or phrases which are relatively far apart.

4. A method according to claim 2, further comprising:

prioritizing words and/or phrases or combination thereof using said predefined set of rules in dependence upon corresponding locations with respect to a start of the question, wherein a higher prioritization is given to words and/or phrases or combination thereof that are closer to the start of the question.

5. A method according to claim 2, further comprising:

prioritizing combinations of words and/or phrases using said predefined set of rules according to a number of word and phrase components in each set of combinations of words and/or phrases, and giving a higher priority to combinations with higher numbers of components.

6. A method according to claim 2, further comprising:

prioritizing phrases ahead of words using said predefined set of rules; and

for combinations of words and/or phrases, prioritizing combinations having a higher number of phrases ahead of combinations having a fewer number of phrases using said predefined set of rules.

7. A method according to claim 1, wherein said analyzing the word content of the received question comprises:

replacing phrases within the question with synonymous phrases; and

replacing words within unreplaced portions of the question with synonymous words.

8. A method according to claim 1, further comprising:

extracting said question from an electronic communication generated by the user.

9. A method according to claim 1, further comprising:

receiving additional context from the user; and

performing said analyzing of the word content and said identifying of the keywords on the question and the additional context.

10. A method according to claim 1, further comprising:

receiving a user selection of the question from the provided prioritized list of questions; and

providing a corresponding answer to the user.

11. A method of assembling a knowledge database containing question and answer pairs, the method comprising:

extracting questions from a multiplicity of electronic communications originating from client terminals;

for each of said electronic communications, displaying the extracted question on a display of an originating client terminal and enabling the sender of the communication to select or deselect a question using input means of the client terminal;

classifying each selected question based upon the content of the selected question;

entering the questions into the database together with the respective classifications; and

receiving answers corresponding to the entered questions from client computer terminals belonging to recipients of the electronic communications, and entering the answers into the database,

wherein an answer to a question is found by said classifying of the question, identifying the questions contained in the database which have the same or a related classification, and identifying the corresponding answers.

13. A method according to claim 11, further comprising:

rewarding providers of the answers delivered to the user.

14. A method according to claim 11, further comprising:

allocating one of a set of access codes to each question and answer pair, each access code defining the accessibility of the corresponding question and answer pair to users.

15. A method according to claim 11, further comprising:

entering into the database charging information for experts providing answers, wherein an expert is rewarded based upon charging information for that expert and a number of times answers provided by the expert are accessed by users.

12. A method of providing information to a user from a knowledge database containing question and answer pairs, the method comprising:

extracting questions from a multiplicity of electronic communications originating from client terminals;

for each of said electronic communications, displaying the extracted question on a display of an originating client terminal and enabling the sender of the communication to select or deselect a question using input means of the client terminal;

classifying each selected question based upon the content of the selected question;

entering the questions into the database together with the respective classifications;

receiving answers corresponding to the entered questions from client computer terminals belonging to recipients of the electronic communications, and entering the answers into the database, wherein an answer to a question is found by said classifying of the question, identifying the questions contained in the database which have the same or a related classification, and identifying the corresponding answers;

searching an electronic communication prepared by the user for questions;

searching the database for matching questions; and

providing identified matching questions to the user together with links to the respective answers stored in the database.

16. A method of providing information from reports and other documents, the method comprising:

identifying sections of a report that answers specific questions;

entering the questions and the corresponding sections of the report into a database;

enabling a user to enter a question;

analyzing a word content of the received question to match phrases contained within the question with functionally synonymous phrases stored in a phrase look-up table, and to match words contained within the question with functionally synonymous words stored in a word look-up table;

prioritizing different synonymous words and/or phrases and combinations of synonymous words and/or phrases according to a predefined set of rules;

identifying a classification from a predefined set of classifications on a basis of the words and/or phrases or combination of these, having a highest priority, and assigning the identified classification to the question;

identifying keywords in the question;

searching the knowledge base to identify questions having the same or related classifications containing same or some of the identified keywords of the identified classification; and

presenting to the user a relevant section of the report having the answer corresponding to the identified question.

17. A method according to claim 16, further comprising:

rewarding the provider of the report based upon a number of times users access sections of the report.