Address learning system and method for using same

• US 6,954,729 B2
• Filed: 01/26/2001
• Issued: 10/11/2005
• Est. Priority Date: 01/27/2000
• Status: Expired due to Fees

• Current Assignee: Bell & Howell LLC (Böwe Systec AG)
• Original Assignee: Bowe Bell & Howell Company
• Inventors: Chan, Tony, Shah, Amit, Bourek, Lee, Lee, Raymond
• Primary Examiner(s): Weiss, John G.
• Assistant Examiner(s): OUELLETTE, JONATHAN P
• Application Number:
  US09/770,984
• Publication Number:
  US 20010054031A1
• Time in Patent Office: 1,719 Days
• Field of Search: 705/1, 705/401, 382/101
• US Class Current: 705/1.1
• CPC Class Codes: B07C 3/00 Sorting according to destination collating the pages of a book B42C1/00
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/262 using context analysis, e.g. lexical, syntactic or semantic context
• CPC Class Codes: G07B 17/00435 Details specific to central, non-customer apparatus, e.g. servers at post office or vendor

Abstract

A computerized method for learning a delivery point of a first mail piece by using unmatched and/or unused data from at least one other mail piece is disclosed. The method comprises the steps of: (a) capturing a text string from said other mail piece using capture means; (b) comparing said text string to a first set of preexisting data in an address database to determine a match for said other mail piece according to a first set of predetermined rules; (c) separating the matched and used data from the unmatched and unused data for said other mail piece determined by step (b); and (d)correlating said unmatched and/or unused data from said other mail piece to a second set of preexisting data relating to said first mail piece according to a second set of predetermined rules, wherein upon the presentation of a third mail piece to the capture means with the same intended delivery point as the first mail piece and having similar unmatched and/or unused data as the at least one other mail piece, the correct point of delivery for the third mail piece can be automatically determined.

The invention further comprises a computerized system for learning a delivery point of a first mail piece by using unmatched data from at least one other mail piece, comprising: (a) means for capturing a data string of address information from said other mail piece; (b) a directory retrieval system database comprising a set of preexisting data relating to said other mail piece and further comprising means for separating matched data from the unmatched data; (c) a tag database comprising the unmatched data; (d) a tag archive; (e) means for correlating the unmatched data to the set of preexisting data according to a plurality of predetermined rules; (f) a rules database comprising said plurality of predetermined rules; and (g) a learning database to determine said delivery point of said first mail piece upon its presentation to the capture means after said other mail piece has been processed by the system.

Claims

1. A computerized method for learning a delivery point address and updating a database of such delivery point addresses by using unmatched or unused data from at least one mail piece, wherein the method comprises:

a. capturing a text string from an image of a first mail piece;

b. comparing the text string to a first set of preexisting data in the database to determine a match for the data on the mail piece according to a first set of predetermined rules;

c. separating the matched or used data from the unmatched data or unused data for the mail piece determined by step (b);

d. automatically correlating the unmatched or unused data from the mail piece to a second set of preexisting data according to a set of predetermined rules to define a set of correlated data; and

e. updating the database with the unmatched or unused data so that a point of delivery for a second mail piece with the same intended delivery point as the first mail, piece and having similar unmatched or unused data as the first mail piece can be automatically determined.

2. The method of claim 1 wherein the image of the first mail piece is captured by an optical character recognition system.

3. The method of claim 1, wherein said correlation step is performed utilizing a search engine.

4. A computerized system for learning a delivery point address and updating a database of such delivery point addresses using unmatched or unused data from at least a first mail piece, comprising:

means for capturing a data string of address information from said at least a first mail piece;

a directory retrieval system database comprising a set of preexisting data relating to an address to which said at least a first mail piece is directed;

means for comparing the data string to the preexisting data and for separating matched or used data on the at least a first mail piece from the unmatched or unused data;

a database for storing the unmatched or unused data;

a rules database comprising a plurality of predetermined rules;

means for correlating the unmatched or unused data to the set of preexisting data according to the plurality of predetermined rules to define a set of correlated data; and

a learning database comprising preexisting data and updated with correlated unmatched or unused data, used to determine said delivery point of a subsequent mail piece upon its presentation to the capture means after said at least a first mail piece has been processed by the system.

5. The system of claim 4 wherein said capture means comprise an optical character recognition device.

6. The system of claim 5 wherein said correlation means comprise a search engine.

7. A method of associating unmatched address data with preexisting delivery point address data, the method comprising the steps of:

obtaining address data;

comparing the address data with the pre-existing delivery point address data;

identifying unmatched address data which differs from the preexisting delivery point address data;

analyzing the unmatched data;

automatically associating the unmatched data with the pre-existing delivery point address data to define a set of associated data; and

storing the associated data in a learning database.

8. The method of claim 7, further comprising the step of updating the preexisting delivery point address data with the associated data when the associated data meets criteria for promotion.

9. The method of claim 7, wherein the address data is obtained from mail pieces.

10. The method of wherein claim 7, wherein the address data is obtained from the Internet.

11. The method of claim 7, wherein the step of analyzing the unmatched data comprises:

identifying a data type for the unmatched data; and

identifying the corresponding data for that data type in the pre-existing delivery point address data.

12. The method of claim 7, wherein the step of associating the unmatched data comprises:

creating an alias record correlating the unmatched data to corresponding data in the preexisting delivery point address data.

13. The method of claim 8, wherein the step of updating the preexisting delivery point address data comprises:

adding an alias record to a corresponding alias table associated with the preexisting delivery point address data.

14. The method of claim 13, wherein the criteria for promotion includes a threshold number of uses of the alias record.

15. The method of claim 8, wherein the step of updating the preexisting delivery point address data comprises:

adding a new delivery point address to the preexisting delivery point address data in the event that the associated data does not correspond to an existing delivery point address.

16. The method of claim 8, further comprising the step of selectively removing from the preexisting delivery point address data the associated data when the associated data meets criteria for demotion.

17. The method of claim 7, further comprising the step of prioritizing the unmatched data according to selection criteria prior to analyzing the unmatched data.

18. A system for associating unmatched address data from at least one mail piece with preexisting delivery point address data, the system comprising:

means for identifying unmatched address data which differs from the preexisting delivery point address data;

means for analyzing the unmatched data;

means for associating the unmatched data with the pre-existing delivery point address data; and

means for updating the preexisting delivery point address data with the unmatched data when the unmatched data meets criteria for promotion.