Statistical sampling security methodology for self-scanning checkout system

• US 20010015375A1
• Filed: 02/04/2000
• Published: 08/23/2001
• Est. Priority Date: 01/25/1996
• Status: Abandoned Application

• Current Assignee: Edward Beadle, Jerome Swartz, Joseph Kartz, Juditth Murrah, Raj Bridgelall, Stephen J. Shellammer, Theo Woffinden
• Original Assignee: Edward Beadle, Jerome Swartz, Joseph Kartz, Juditth Murrah, Raj Bridgelall, Stephen J. Shellammer, Theo Woffinden
• Inventors: Woffinden, Theo, Kartz, Joseph, Murrah, Juditth, Shellammer, Stephen J., Bridgelall, Raj, Beadle, Edward, Swartz, Jerome
• Application Number:
  US09/498,911
• Publication Number:
  US 20010015375A1
• Time in Patent Office: Days
• US Class Current: 235/383
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles
• CPC Class Codes: G07G 3/003 Anti-theft control theft alarms G08B13/00

Abstract

A statistical basis for use in a self-scanning checkout system determines how many items to check in a shopper'"'"'s shopping cart for incorrect or missing scans as well as which particular or types of items to check to determine if they were properly scanned, if the shopper is determined to be audited. The present invention does not audit every customer, but rather determines whether a given shopper or customer is to be audited on a given shopping trip based upon obtaining a minimum checkout loss for such customer. The methodology determines how many items to check for a given shopper as well as which particular items to check for that shopper. The following factors attempt to model the real world of shopping and may be considered, alone or in varying combinations, in determining the number of items to check for a particular shopping transaction: shopper frequency; queue length; prior audit history; store location; time of day, day of week, date of year; number of times items are returned to shelf during shopping; dwell time between scans; customer loyalty; store shopping activity and other factors. Using statistical decision theory for auditing policies a minimum loss per shopper transaction improves the security and reduces the labor of self-check out without being too intrusive to customers.

Claims

1. A method for enhancing the accuracy and reducing audit level of a self-checkout system while achieving a lowest average loss for a customer in a system wherein a customer selects a plurality of items for purchase and registers the plurality of items with a portable terminal, comprising the steps of:

a) generating at least one state space of possible events that may occur in a self-checkout by a customer;

b) generating at least one action space in response to each state space;

c) generating a loss function in response to each action space; and

d) auditing a self-check out to obtain a minimum checkout loss for a customer.

5. The method of

claim 1

wherein the state space is a statistical representation of possible events (E) that may occur in a self-checkout.

6. The method of

claim 1

wherein the action space is a statistical representation of possible actions that may be taken in response to the possible events.

7. The method of

claim 1

wherein the loss function measures a loss resulting from an action.

8. The method of

claim 1

further comprising the step of determining and defining an average loss for a self check-out as a Bayes loss.

9. The method of

claim 8

where the Bayes average loss is given by the equation:

$B<br><br>\left(a\right)=E<br><br>\left[1<br><br>\left(\mathrm{\theta <br><br>},a\right)\right]=\underset{i}{\overset{n}{\sum <br><br>}}<br><br>L<br><br>\left({\mathrm{\theta <br><br>}}_i,a\right)<br><br>P<br><br>\left({\mathrm{\theta <br><br>}}_i\right)$

where θ

_i represents random events.

10. The method of

claim 1

wherein the loss function is a function of L(c) and p where L(c) is the expected inventory loss associated with a shopper (c) and p is the probability of performing an audit on the shopper.

2. In a self-service shopping checkout system wherein a shopper is provided with a portable self-scanning terminal for scanning of a bar code of an item selected for purchase prior to depositing the item into a shopping cart, and wherein a list of items self-scanned by the shopper is compiled and made available to a cashier for surveillance and payment purposes, the improvement comprising a method for enhancing the accuracy and reducing overall audit level and achieving a lowest average loss of a self-checkout system wherein a customer selects a plurality of items for purchase and registers the plurality of items with the portable terminal, comprising the steps of:

a) determining if the customer is to be audited to obtain the lowest average loss for the customer using statistical decision analysis;

a) determining, as a function of a plurality of input criteria, the number of items n to be scanned;

b) selecting from the shopper'"'"'s cart of items presented for purchase n items to be scanned;

c) scanning a bar code located on each of said n items selected for scanning; and

d) allowing the shopping transaction if each item selected for scanning is present on the list of self-scanned items compiled by the shopper.

3. The method of

claim 2

further comprising the step of disallowing the shopping transaction if the minimum checkout loss exceeds a threshold.

4. A self-service shopping checkout system comprising:

a) a plurality of portable self-checkout devices, each of said self-checkout devices to be used by a customer to scan a bar code located on an item to be purchased so as to record therein a list of such items to be purchased, each of said devices comprising bar code scanning means for scanning and decoding a bar code located on an item to be purchased, means for compiling a list of items scanned by said customer, and a data output port for allowing transfer of said scanned item list to an associated data port located external to said portable device;

b) a stationary dispenser unit for the releasable containment of said plurality of portable self-checkout devices, said dispenser unit comprising;

(i) a plurality of device containment slots, each of said slots being configured for releasable containment of a mating self-scanning device, each of said slots having associated therewith a data input port suitable for mating with a data output port located on a portable self-checkout device; and

(ii) a printer for printing a tally list of items scanned for purchase by said shopper, said tally list being supplied by a self-checkout device after said self-checkout device is returned to a device containment slot after being used by a shopper, said tally list further comprising a two-dimensional bar code encoded with said items scanned by said shopper, a unique identification record associated with said shopper, and the number of items scanned by said shopper;

c) a plurality of point of sale terminals, each of said point of sale terminal comprising;

(i) bar code reading means for reading said two-dimensional bar code from a tally list presented to a cashier operating said point of sale terminal, said bar code reading means providing as output data signals representing said items scanned by said shopper, said unique identification record associated with said shopper, and said number of items scanned by said shopper;

said bar code reading means also configured so as to scan select items presented for checking by said cashier;

(d) means for generating at least one state space of possible events (E) that may occur in a self-checkout by a shopper;

(e) means for generating an action space in response to each state space;

(f) means for generating a loss function in response to each action space; and

(g) means for auditing a self-check out to obtain a minimum checkout loss for a customer.

11. A method of selecting a best action for auditing a customer in a self-check out system comprising the steps of:

a) generating at least one state space of possible events that may occur in a self-checkout by the customer;

b) generating at least one action space in response to each state space;

c) generating a loss function in response to each action space; and

d) selecting the action that gives the smallest loss function on the average.

12. A method of selecting a best action for auditing a customer in a self-check out system comprising the steps of:

a) generating at least one state space of possible events that may occur in a self-checkout by the customer;

b) generating at least one action space in response to each state space;

c) generating a Bayes'"'"' loss function in response to each action space; and

d) randomly selecting the action with the probability inversely proportional to the Bayes'"'"' loss associated with taking that action.

13. A method of selecting a best action for auditing a customer in a self-check out system comprising the steps of:

a) determining if the customer is to be audited for items on a given shopping trip based upon a lowest average loss to the self-check out system; and

b) determining how many items to audit based on a statistical decision analysis applied to self shopping if step a) determines the customer should be audited.

14. In a customer self-check out system, a method of estimating the probability of a customer making an error comprising the steps of:

a) scanning into the self-check out system a customer history of prior audit results; and

b) estimating the probability of the customer making an error in a self-check out using the prior history results.

15. In a self-check out system, a method of determining the average loss for a customer in a self-check out, comprising the steps of:

a) identifying a plurality of factors including store busy;

level of audit (full, patial, none) and affecting the self-check out;

b) selecting a at least one of the plurality of the events; and

c) calculating the average loss for the customer in the self-check out using a Bayes'"'"' loss factor based upon the selected at least plurality of events.

16. A self-service shopping checkout system for enhancing the accuracy and reducing overall audit level while achieving a lowest average loss of a self-checkout by a customer, comprising:

a) means for registering a plurality of items by the customer using a portable terminal;

b) means for determining if the customer is to be audited to obtain the lowest average loss for the customer using statistical decision analysis;

c) means for determining, as a function of a plurality of input criteria, which items n and the number thereof to be scanned;

d) means for selecting from the shopper'"'"'s cart of items presented for purchase n items to be scanned;

e) means for properly scanning a bar code located on each of said n items selected for scanning; and

f) means for allowing the shopping transaction if each item selected for scanning is present on a list of self-scanned items compiled by the shopper.

17. The system of

claim 16

further comprising:

a) means for disallowing the transaction if any item selected for scanning is not present on the list of self-scanned items compiled by the shopper.

18. An article of manufacture, comprising:

a computer usable medium having computer readable program code means embodied therein for enhancing the accuracy and reducing overall audit level while achieving a lowest average loss of a self-checkout by a customer in a self-check out system including a plurality of portable self-checkout devices, each of said self-checkout devices to be used by a customer to scan a bar code located on an item to be purchased so as to record therein a list of such items to be purchased, each of said devices comprising bar code scanning means for scanning and decoding a bar code located on an item to be purchased and means for compiling a list of items scanned by said customer, the computer readable program code means in said article of manufacturing, comprising;

(a) computer readable program code means for registering a plurality of items by the customer using a portable terminal;

b) computer readable program code means for determining if the customer is to be audited to obtain the lowest average loss for the customer using statistical decision analysis;

c) computer readable program code means for determining, as a function of a plurality of input criteria, which items n and the number thereof to be scanned;

d) computer readable program code means for selecting from the shopper'"'"'s cart of items presented for purchase n items to be scanned;

e) computer readable program code means for properly scanning a bar code located on each of said n items selected for scanning; and

f) computer readable program code means for allowing the shopping transaction if each item selected for scanning is present on a list of self-scanned items compiled by the shopper or disallowing the transaction if each item selected for scanning is not present on the list of self-scanned items compiled by the shopper.