Secure services

• US 20030009321A1
• Filed: 08/14/2002
• Published: 01/09/2003
• Est. Priority Date: 03/14/2000
• Status: Active Grant

• Current Assignee: British Telecommunications PLC (BT Group PLC)
• Original Assignee: British Telecommunications PLC (BT Group PLC)
• Inventors: Marsh, Paul FR, Attwater, David J, Fisher, John S
• Granted Patent: US 7,225,132 B2
• Time in Patent Office: Days
• US Class Current: 704/6
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

An identification code is assigned to a user by making a selection from a closed set of possible tokens. The selection is determined algorithmically by user identity data. The format of the identification code may comprise a sequence of natural language words chosen from closed sets and a separator character having a fixed value or a small range of possible values. The closed sets may be programmed in the recognition grammar of a speech interface to secure services such as banking.

Claims

1. A method of assigning an identification code from a finite grammar defining all possible identification codes, the method comprising the steps:

a) selecting a word from each of a plurality of predetermined sets of words according to identification data relating to a user;

b) concatenating said words to form a sequence for use as the identification code; and

c) storing a record of the sequence and of the identity of the user associated with said identification code.

2. A method according to claim 1 in which the selecting step a) comprises sub steps of

d) receiving from a user, identification data comprising a number of attributes, each attribute corresponding to one of said predetermined sets;

e) selecting for each user attribute, a word from the associated predetermined set which is related to the supplied user attribute.

3. A method according to claim 2 in which the selecting sub step e) comprises selecting a word which is equal to the supplied user attribute if the supplied user attribute is a member of the associated predetermined set, otherwise selecting a word from the associated predetermined set which is related to the spelling of the supplied user attribute.

4. A method according to claim 1, in which the selection of words at step a) is determined both by the user identification data and by a parameter dependent on the number of enrolled users having the same user identification data.

5. A method according to any one of the preceding claims, in which one of the predetermined sets of words comprises personal names, the method including

receiving from a user the user'"'"'s name

comparing the user'"'"'s name with the set of personal names,

when the users name is included in the set of personal names, assigning to the user an identification code including the user'"'"'s name,

or otherwise assigning to the user an identification code including a different word in place of the user'"'"'s name.

6. A method according to claim 1 wherein the finite grammar includes a separator word between a first predetermined set of words and a second predetermined set of words.

7. A method according to claim 6, in which the set of possible separator tokens has a single member only.

8. A method according to claim 1, wherein the finite grammar includes a phrase associated with one of said predetermined sets of words and in which the phrase distinguishes between homonyms in said one set of predetermined words.

9. A method according to claim 8, in which the said phrase is a number.

10. A method of operating a customer service, including at

receiving from a user a user identification code,

verifying the user identification code, and

executing a transaction with the user

characterised in that the identification code comprises an identification code assigned by a method according to any one of the preceding claims.

11. A method according to claim 10, in which the step of receiving from the user the user identification code includes receiving a spoken identification code at a speech recognition device pre-programmed with a recognition grammar comprising the said sets of natural language words.

12. A method according to claim 10 or 11, the method including receiving some identification codes and executing some transactions via a text interface, and receiving other identification codes and executing other transactions via a speech interface.