Information handling mechanism

• US 7,308,444 B2
• Filed: 11/17/2005
• Issued: 12/11/2007
• Est. Priority Date: 11/17/2004
• Status: Active Grant

• Current Assignee: Verint Systems UK Limited (Verint Systems Incorporated)
• Original Assignee: Transversal Corp. Ltd. (Verint Systems Incorporated)
• Inventors: Ryland, David Paul Austen
• Primary Examiner(s): Rimell, Sam
• Application Number:
  US11/281,842
• Publication Number:
  US 20060106790A1
• Time in Patent Office: 754 Days
• Field of Search: 707/3, 707/4, 707/5, 707/100, 705/26, 705/27, 704/9
• US Class Current: 1/1
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Conventional electronic information retrieval systems using specialist databases assume that the database being searched is appropriate to the search being conducted.

The invention solves the problem that the above assumption may be incorrect. It does this by providing mechanisms (4, 4A and 4B) for identifying concepts respectively in: the search input question, a specialist database and a non-specialist database.

A comparator 8 and associated mechanisms are able to analyze how the specialist database differs from the non-specialist database and to use this information to derive an indication of the ability of the specialist database to answer the input question. This indication can be fed to the user via interface 1 or in an alternative arrangement could be used to block inappropriate information.

Claims

1. An information handling mechanism to determine if an information source is applicable to a given information need comprising

a) an interface connected to a communication channel for receiving a communication from a user;

b) a specialist database containing information relevant to a specialist subject;

c) means for identifying concepts in the user communication;

d) means for generating concept models indicating occurrences of concepts in the specialist database and in a less specialist database;

e) means for calculating relative probability, responsive to the means for generating concept models and the means for identifying concepts in the user communication, that the identified concepts could have been generated by each concept model and to provide an output indicative of the relevance of the specialist database to the communication; and

f) an action selector for generating a signal, responsive to the output of the means for calculating relative probability, arranged either to give a user an indication of the relevance of the specialist database or to automatically redirect the communication in a way dependent on such relevance.

2. An information handling mechanism according to claim 1, wherein a plurality of different specialist databases are provided, means are provided for preselecting one of the plurality of databases as the operative database, said action selector, responsive to low relevance of the preselected database as determined from the means to calculate relative probability automatically redirects the communication to a second preselected database to determine its relevance.

3. An information handling mechanism according to claim 2, wherein the mechanism includes switch means controlled by the action selector for automatically serially checking the plurality of databases until a database is determined with an effective relevance to the communication.

4. An information handling mechanism according to claim 1, wherein the communication to the interface is an email, and the action selector controls a switch to direct the communication to a user'"'"'s inbox, to junk mail or to another dependent on relevance determined.

5. An information handling mechanism according to claim 2, wherein the plurality of databases are constituted from web pages generated by an information retrieval engine responsive to a communication input from a user, means for processing the web pages to determine their relevance with respect to the communication and to assign a value of relevance, an output filter receiving the web pages with their assigned relevance values, and means for outputting to the user the web pages having assigned values greater than a predetermined value.

6. An information handling mechanism according to claim 1 in which the concept model includes a frequency distribution.

7. An information handling mechanism according to claim 1 in which the concept model includes information about the relationship between concepts in a passage of information.

8. An information handling mechanism according to claim 1 in which the concept model includes information about the adjacency of concepts.

9. An information handling mechanism according to claim 1 including means for using the output of the means for calculating relative probability to give a user an indication of confidence in the ability of the specialist database to answer a question applied to the input.

10. An information handling mechanism according to claim 1 in which the specialist database has divisions and switch means are provided, acting responsive to the action selector signal to perform a switching operation between divisions.

11. An information handling mechanism according to claim 10 further comprising means for applying the input communication as a query to any information retrieval engine to produce a number of answers in order of relevance;

means for feeding those answers into the specialist database incrementally so as to give a series of outputs from the means for calculating relative probability for different combinations of answers loaded into the specialist database; and

means for selecting a combination which gives the optimum output value from the means for calculating relative probability.

12. An information handling mechanism according to claim 11 in which:

the “

specialist database”

is a selected website,

the input is an advertisement or text describing it;

and including means for using the output of the means for calculating relative probability to control the application of the advertisement to the selected website.

13. An information handling mechanism according to claim 1 in which the “

less specialist database”

is the World Wide Web or a part of it.