U.S. patent application number 15/918436 was filed with the patent office on 2018-09-20 for system and method for management of perpetual inventory values based upon customer product purchases.
The applicant listed for this patent is Walmart Apollo, LLC. Invention is credited to David B. Brightwell, Cristy C. Brooks, Greg A. Bryan, Benjamin D. Enssle, Matthew A. Jones.
Application Number | 20180268367 15/918436 |
Document ID | / |
Family ID | 63519518 |
Filed Date | 2018-09-20 |
United States Patent
Application |
20180268367 |
Kind Code |
A1 |
Bryan; Greg A. ; et
al. |
September 20, 2018 |
SYSTEM AND METHOD FOR MANAGEMENT OF PERPETUAL INVENTORY VALUES
BASED UPON CUSTOMER PRODUCT PURCHASES
Abstract
A data structure programmatically links the first product to a
second product. The second product is historically purchased by the
customer whenever the customer has also purchased the first
product. A determination is made as to whether the customer
purchased the second product together with the first product based
upon the sales data. When the customer has failed to purchase the
second product with the first product, instructions are transmitted
to the retail store over the network to perform a verification that
the second product is out-of-stock. An outcome of the verification
from the retail store is received via the network. A determination
is made as to a level of certainty that the second product is
actually out-of-stock based upon an analysis of the sales data and
the outcome of the verification. When the level of certainty
exceeds a predetermined threshold, the PI value is adjusted to
zero.
Inventors: |
Bryan; Greg A.; (Centerton,
AR) ; Brooks; Cristy C.; (Cassville, MO) ;
Brightwell; David B.; (Bentonville, AR) ; Enssle;
Benjamin D.; (Bella Vista, AR) ; Jones; Matthew
A.; (Bentonville, AR) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
Walmart Apollo, LLC |
Bentonville |
AR |
US |
|
|
Family ID: |
63519518 |
Appl. No.: |
15/918436 |
Filed: |
March 12, 2018 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
62471455 |
Mar 15, 2017 |
|
|
|
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
G06Q 10/0875 20130101;
G06Q 40/12 20131203 |
International
Class: |
G06Q 10/08 20060101
G06Q010/08; G06Q 40/00 20060101 G06Q040/00 |
Claims
1. A system that is configured to adjust perpetual inventory (PI)
values of products, the system comprising: an automated vehicle
disposed at a retail store; a sales entry device or sensor disposed
at the retail store, the sales entry device or sensor being
configured to collect sales data related to a first product
purchased by a customer at the retail store; a transceiver circuit,
the transceiver circuit being disposed at the retail store and
coupled to the sales entry device or sensor, the transceiver
circuit configured to transmit the sales data related to the first
product purchased by a customer at the retail store; a network
coupled to the transceiver circuit; an interface coupled to the
network, the interface configured to receive the sales data from
the transceiver circuit via the network, the interface disposed at
a central processing center; a database that includes a data
structure, the data structure programmatically linking the first
product to a second product, the second product being historically
purchased by the customer whenever the customer has also purchased
the first product, the database disposed at the central processing
center; a control circuit coupled to the interface and the
database, the control circuit disposed at the central processing
center and configured to: determine whether the customer purchased
the second product together with the first product based upon an
analysis of the sales data; when the customer has failed to
purchase the second product with the first product, transmit
instructions to the automated vehicle via the transceiver circuit,
the interface and the network, the instructions being effective to
cause the automated vehicle to perform a verification at the retail
store that the second product is out-of-stock; receive an outcome
of the verification from the automated vehicle, the outcome being
transmitted from the transceiver circuit at the retail store to the
network and to the interface; determine a level of certainty that
the second product is actually out-of-stock based upon an analysis
of the sales data, the outcome of the verification, and results of
verifications at other retail stores; when the level of certainty
exceeds a predetermined threshold, adjust the PI value to zero;
transmit the adjusted PI value to the transceiver circuit at the
retail store via the interface and the network.
2. The system of claim 1, wherein a human assists the automated
vehicle in making the verification.
3. The system of claim 1, wherein the automated vehicle maneuvers
to a shelf where the second product is shelved.
4. The system of claim 1, wherein the automated vehicle is an
aerial drone or a ground vehicle.
5. The system of claim 1, wherein the instructions further include
a message to an employee at the retail store to verify that that
the second product is not present at the retail store.
6. The system of claim 1, wherein the sales data is data selected
from the group consisting of: point-of-sale data indicating that a
customer purchased the first product but not the second product, a
scan of a shelf where the second product is disposed, demographic
information of the customer, information related to a weather
event, information concerning how the customer paid for the first
product, and information concerning the path of the customer
through the store.
7. The system of claim 1, wherein the network is the cloud
network.
8. A method, comprising: collecting sales at a sales entry device
or sensor disposed at a retail store, the sales data being related
to a first product purchased by a customer in the retail store;
transmitting sales data from the retail store to a central
processing center via a network; receiving the sales data at the
central processing center; storing a data structure at a database
at the central processing center, the data structure
programmatically linking the first product to a second product, the
second product being historically purchased by the customer
whenever the customer has also purchased the first product;
determining at the central processing center whether the customer
purchased the second product together with the first product based
upon the sales data; when the customer has failed to purchase the
second product with the first product, transmitting instructions to
an automated vehicle the retail store over the network to perform a
verification that the second product is out-of-stock; receiving an
outcome of the verification from the automated vehicle via the
network; determining at the central processing center a level of
certainty that the second product is actually out-of-stock based
upon an analysis of the sales data, the outcome of the
verification, and, results of verifications at other retail stores;
when the level of certainty exceeds a predetermined threshold,
adjusting the PI value to zero.
9. The method of claim 8, wherein a human assists the automated
vehicle in making the verification.
10. The method of claim 8, wherein the automated vehicle maneuvers
to a shelf where the second product is shelved.
11. The method of claim 8, wherein the automated vehicle is an
aerial drone or a ground vehicle.
12. The method of claim 8, wherein the instructions further include
a message to an employee at the retail store to verify that that
the second product is not present at the retail store.
13. The method of claim 8, wherein the sales data is data selected
from the group consisting of: point-of-sale data indicating that a
customer purchased the first product but not the second product, a
scan of a shelf where the second product is disposed, demographic
information of the customer, information related to a weather
event, information concerning how the customer paid for the first
product, and information concerning the path of the customer
through the store.
14. The method of claim 8, wherein the network is the cloud
network.
Description
CROSS-REFERENCE TO RELATED APPLICATION
[0001] This application claims the benefit of the following U.S.
Provisional Application No. 62/471,455 filed Mar. 15, 2017, which
is incorporated herein by reference in its entirety.
TECHNICAL FIELD
[0002] This invention relates generally to the management of
perpetual inventory values, and more particularly, to the
management of perpetual inventory values by analyzing customer
purchases.
BACKGROUND
[0003] Stores utilize various measures to keep track of and manage
products. One such measure is the perpetual inventory (PI) value
associated with a product. In aspects, the PI value represents the
quantity of product in the store. The PI value typically changes
over time so as to accurately reflect the number of actual products
in the store. For instance, products are purchased by customers and
removed from the store affecting the PI value. Shipments arrive at
the store and include additional products also affecting the PI
value.
[0004] Stores also utilize other measures that relate to the value
and availability of products for accounting and other purposes. For
example, a book value of a product may be the value of all of the
product present in the retail store.
[0005] Sometimes the PI value does not accurately reflect the
correct number of products in the store. This can happen for a
variety of reasons including mis-scanning products as the products
leave or depart the store, or other forms of human error. If the PI
value is incorrect, then various problems can develop. For
instance, shipments can be ordered at the wrong times and for the
wrong quantity of products.
BRIEF DESCRIPTION OF THE DRAWINGS
[0006] Disclosed herein are embodiments of systems, apparatuses and
methods pertaining to managing perpetual inventory values based
upon customer purchases. This description includes drawings,
wherein:
[0007] FIG. 1 is a block diagram showing one example of a system
that adjusts the PI of a product using customer sales data in
accordance with some embodiments;
[0008] FIG. 2 is a flowchart showing one example of an approach for
adjusting the PI of a selected product using customer sales data in
accordance with some embodiments;
[0009] FIG. 3 is a block diagram of a data structure used in a
system that adjusts the PI of a product using customer sales data
in accordance with some embodiments;
[0010] FIG. 4 is a flowchart of one approach for determining the
confidence level of adjusting the PI value in accordance with some
embodiments.
[0011] Elements in the figures are illustrated for simplicity and
clarity and have not necessarily been drawn to scale. For example,
the dimensions and/or relative positioning of some of the elements
in the figures may be exaggerated relative to other elements to
help to improve understanding of various embodiments of the present
invention. Also, common but well-understood elements that are
useful or necessary in a commercially feasible embodiment are often
not depicted in order to facilitate a less obstructed view of these
various embodiments of the present invention. Certain actions
and/or steps may be described or depicted in a particular order of
occurrence while those skilled in the art will understand that such
specificity with respect to sequence is not actually required. The
terms and expressions used herein have the ordinary technical
meaning as is accorded to such terms and expressions by persons
skilled in the technical field as set forth above except where
different specific meanings have otherwise been set forth
herein.
DETAILED DESCRIPTION
[0012] Generally speaking, systems, apparatuses and methods are
provided that adjust perpetual inventory values based upon customer
purchases. Two different products are typically purchased together
by a customer, but on one occasion the customer only purchases one
product and not the other. However, the PI value of the
non-purchased product still shows the non-purchased product as
being available in the retail store. In the present approaches, the
PI value of the non-purchased product is adjusted with a degree of
confidence as to the accuracy of the adjustment. In aspects, the
degree of confidence is determined based upon taking actions such
as verifying that the item is not on the shelf. The degree of
confidence is also influenced by other information, e.g.,
demographic information about the customer, or whether there was a
weather event that may have influenced shipments to the store, to
mention two examples.
[0013] In many of these embodiments, a system that is configured to
adjust perpetual inventory (PI) values of products includes a
transceiver circuit, a network, an interface, a database, and a
control circuit.
[0014] The transceiver circuit is disposed at a retail store, and
is configured to transmit sales data related to a first product
purchased by a customer at the retail store. The network is coupled
to the transmitter circuit. The interface is coupled to the
network, and is configured to receive the sales data from the
transceiver circuit via the network. The interface is disposed at a
central processing center.
[0015] The database includes a data structure. The data structure
programmatically links the first product to a second product. The
second product is historically purchased by the customer whenever
the customer has also purchased the first product. The database is
disposed at the central processing center.
[0016] The control circuit is coupled to the interface and the
database. The control circuit is disposed at the central processing
center and configured to determine whether the customer purchased
the second product together with the first product based upon
analyzing the sales data. The control circuit is configured to,
when the customer has failed to purchase the second product with
the first product, transmit instructions to the transceiver circuit
via the interface and network to perform a verification at the
retail store that the second product is out-of-stock. The control
circuit is additionally configured to receive an outcome of the
verification from the transceiver circuit at the retail store via
the network and the interface. The control circuit is further
configured to determine a level of certainty that the second
product is actually out-of-stock based upon an analysis of the
sales data and the outcome of the verification. The control circuit
is configured to, when the level of certainty exceeds a
predetermined threshold, adjust the PI value to zero. The control
circuit is configured to transmit the adjusted PI value to the
transceiver circuit at the retail store via the interface and the
network.
[0017] In aspects, the system also includes an automated vehicle at
the retail store. The instructions cause the automated vehicle at
the retail store to verify that that the second product is not
present at the retail store. In other aspects, the automated
vehicle maneuvers to a shelf where the second product is shelved.
In examples, the automated vehicle is an aerial drone or a ground
vehicle.
[0018] In other examples, the instructions are a message to an
employee at the retail store to verify that that the second product
is not present at the retail store. The network may be any type of
network such as the cloud network.
[0019] The sales data can be a wide variety of data. For example,
the sales data may include point-of-sale data indicating that a
customer purchased the first product but not the second product, a
scan of a shelf where the second product is disposed, demographic
information of the customer, information related to a weather
event, information concerning how the customer paid for the first
product, or information concerning the path of the customer through
the store. Other examples are possible.
[0020] In other embodiments, sales data related to a first product
purchased by a customer in a retail store is transmitted from the
retail store to a central processing center. The sales data is
received at the central processing center. A data structure at a
database at the central processing center is stored. The data
structure programmatically links the first product to a second
product. The second product is historically purchased by the
customer whenever the customer has also purchased the first
product. At the central processing center, a determination is made
as to whether the customer purchased the second product together
with the first product based upon the sales data.
[0021] When the customer has failed to purchase the second product
with the first product, instructions are transmitted to the retail
store over the network to perform a verification that the second
product is out-of-stock. An outcome of the verification from the
retail store is received via the network. At the central processing
center, a determination is made as to a level of certainty that the
second product is actually out-of-stock based upon an analysis of
the sales data and the outcome of the verification. When the level
of certainty exceeds a predetermined threshold, the PI value is
adjusted to zero.
[0022] In still others of these embodiments, a system is configured
to adjust perpetual inventory (PI) values of products. The system
includes an automated vehicle, a sales entry device or sensor, a
transceiver circuit, a network, an interface, a database, and a
control circuit.
[0023] The automated vehicle is disposed at a retail store. The
sales entry device or sensor is disposed at the retail store. The
sales entry device or sensor is configured to collect sales data
related to a first product purchased by a customer at the retail
store.
[0024] The transceiver circuit is disposed at the retail store and
coupled to the sales entry device or sensor. The transceiver
circuit is configured to transmit the sales data related to the
first product purchased by a customer at the retail store. The
network is coupled to the transceiver circuit.
[0025] The interface is coupled to the network and is configured to
receive the sales data from the transceiver circuit via the
network. The interface is disposed at a central processing
center.
[0026] The database includes a data structure. The data structure
programmatically links the first product to a second product. The
second product is historically purchased by the customer whenever
the customer has also purchased the first product. The database is
disposed at the central processing center.
[0027] The control circuit is coupled to the interface and the
database. The control circuit is disposed at the central processing
center and is configured to determine whether the customer
purchased the second product together with the first product based
upon an analysis of the sales data. The control circuit is further
configured to, when the customer has failed to purchase the second
product with the first product, transmit instructions to the
automated vehicle via the transceiver circuit, the interface and
the network. The instructions are effective to cause the automated
vehicle to perform a verification at the retail store that the
second product is out-of-stock.
[0028] The control circuit is also configured to receive an outcome
of the verification from the automated vehicle. The outcome is
transmitted from the transceiver circuit at the retail store to the
network and to the interface.
[0029] The control circuit is further configured to determine a
level of certainty that the second product is actually out-of-stock
based upon an analysis of the sales data, the outcome of the
verification, and results of verifications at other retail stores.
The control circuit is configured to, when the level of certainty
exceeds a predetermined threshold, adjust the PI value to zero. The
control circuit is still further configured to transmit the
adjusted PI value to the transceiver circuit at the retail store
via the interface and the network.
[0030] Referring now to FIG. 1, one example of a system 100 for
adjusting the PI value of a selected product in a retail store 102
is described. The retail store 102 may be any type of retail store,
for example, a discount center, a grocery store, a department
store, or a hardware store to mention a few examples.
[0031] The retail store 102 includes a database 152 that stores for
each product a PI value 122. The PI value 122 for the selected
product indicates the amount of a selected product in the retail
store.
[0032] The database 152 may also include sales data 124. The sales
data 124 can be a wide variety of information. For example, the
sales data 124 may include point-of-sale data indicating that a
customer purchased the first product but not the second product, a
scan of a shelf where the second product is disposed, demographic
information of the customer, information related to a weather
event, information concerning how the customer paid for the first
product, or information concerning the path of the customer through
the store. The sales data 124 may be obtained by sales entry
devices or sensors 158 (e.g., cameras, other sensing devices (RFID
sensors), or cash registers) or may be manually entered into the
database 152.
[0033] A communication device 154 allows the retail store 102 to
communicate with devices and entities that are external to the
store. The communication device 154 may include any combination of
hardware or software that allows communications to be received at
the retail store 102, and makes transmissions from the retail store
102. In one example, the communication device 154 may be a
transceiver circuit. The communication device 154 may be deployed
within or at another device (e.g., a modem, a smart phone, or a
personal computer, to mention a few examples). The communication
device 154 may transmit the PI value 122 and the sales data 124
from the retail store 102.
[0034] Cloud network 104 is coupled to the communication device 154
(e.g., a transceiver) at the retail store 102. The cloud network
104 may be any type of computer or communication network and may
include routers, gateways, and servers to mention a few examples of
devices that can form or be utilized in the network 104. The cloud
network 104 may also be combinations of various types of
networks.
[0035] The apparatus 106 includes an interface 130, a control
circuit 132, and a database 134. The interface 130 is configured to
receive from the retail store 102 the perpetual inventory (PI)
value 122 associated with the selected product and the sales data
124. The database 134 stores the PI value 122 and the sales data
124. The apparatus 106 may be deployed at a central processing
center such as the home office of the retail store.
[0036] In aspects, the apparatus 106 may be disposed at a central
processing center or location such as a business headquarters. In
other examples, the apparatus 106 is disposed at one or more remote
locations (e.g., retail stores). Advantageously, disposing the
apparatus at a central processing center reduces data storage cost,
since all data can be stored at a single location instead of at
multiple locations.
[0037] The control circuit 132 is coupled to the interface 130 and
the database 134. The control circuit 132 is configured to obtain
the PI value 122 and the sales data 124 from the database 134. It
will be appreciated that as used herein the term "control circuit"
refers broadly to any microcontroller, computer, or processor-based
device with processor, memory, and programmable input/output
peripherals, which is generally designed to govern the operation of
other components and devices. It is further understood to include
common accompanying accessory devices, including memory,
transceivers for communication with other components and devices,
etc. These architectural options are well known and understood in
the art and require no further description here. The control
circuit 132 may be configured (for example, by using corresponding
programming stored in a memory as will be well understood by those
skilled in the art) to carry out one or more of the steps, actions,
and/or functions described herein.
[0038] The control circuit 132 is configured to, when the customer
has failed to purchase the second product with the first product,
transmit instructions to the communication device (e.g.,
transceiver circuit) 154 via the interface 130 and network 104 to
perform a verification at the retail store that the second product
is out-of-stock. The verification may be accomplished using the
automated vehicle 156, which is in communication with the
communication device 154. The control circuit 132 is additionally
configured to receive an outcome of the verification from the
transceiver circuit 154 at the retail store 102 via the network 104
and the interface 130. The control circuit 132 is configured to
determine a level of certainty that the second product is actually
out-of-stock based upon an analysis of the sales data 124 and the
outcome of the verification. Additionally, the results of
verifications (or certainty level calculations) performed or made
at other retail stores can be considered (e.g., whether the product
was ever located). These may be stored in the database 134. Thus,
the experience and knowledge gained from decisions made with
respect to other stores can be applied to obtain better decisions
with respect to levels of certainty for the current store being
evaluated.
[0039] The control circuit 132 is configured to, when the level of
certainty exceeds a predetermined threshold, adjust the PI value
122 to zero. The control circuit 132 is configured to transmit the
adjusted PI value 122 to the transceiver circuit 154 at the retail
store via the interface and the network.
[0040] In aspects, the system also includes an automated vehicle
156 deployed at the retail store 102. The instructions formed by
the control circuit 132 cause the automated vehicle 156 at the
retail store 102 to verify that that the second product is not
present at the retail store. In other aspects, the automated
vehicle 156 maneuvers to a shelf where the second product is
shelved. In examples, the automated vehicle is an aerial drone or a
ground vehicle.
[0041] In other examples, the instructions are a message to an
employee at the retail store 102 to verify that that the second
product is not present at the retail store 102.
[0042] Referring now to FIG. 2, one example of an approach for
managing the PI value of a selected product based upon sales
information is described. At step 202, sales data related to a
first product purchased by a customer in a retail store is
transmitted from the retail store to a central processing center.
The sales data may be structured according to any type of data
format.
[0043] At step 204, the sales data is received at the central
processing center. A data structure is created and stored at a
database at the central processing center. The data structure
programmatically links the first product to a second product. The
second product is historically purchased by the customer whenever
the customer has also purchased the first product. For example, the
customer may always purchase apples and bananas together.
[0044] At step 206, at the central processing center, a
determination is made as to whether the customer purchased the
second product together with the first product based upon the sales
data. In these regards, the sales data may include information
about each customer trip to the retail store and the purchases made
during that trip. An analysis of this information locates the first
product within the data for a particular customer trip and
determines whether the customer purchases the second product during
the same customer trip.
[0045] At step 208, when the customer has failed to purchase the
second product with the first product, instructions are transmitted
from the central processing center to the retail store over the
network to perform a verification that the second product is
out-of-stock. The instructions may be in any type of format and may
cause an automated vehicle to search the entire store (or portions
of the store such as the shelves or other areas where the product
is placed for retail sales) to verify that the product is missing.
Alternatively, instructions can be sent to the retail store (or an
employee of the retails store) to have the employee search for the
product.
[0046] At step 210, an outcome of the verification from the retail
store is received at the central processing center via the network.
The verification can be received, in aspects, from an automated
vehicle or an employee and indicates whether the product was
located.
[0047] At step 212 and at the central processing center, a
determination is made as to a level of certainty that the second
product is actually out-of-stock based upon an analysis of the
sales data and the outcome of the verification. As discussed
elsewhere herein, various approaches can be used to determine
whether the level of certainty is high or low. Different inputs
(e.g., visual images from the store, the customer's path through
the store, the customer's purchase history, to mention a few
examples of information) can be used to determine the level of
certainty. Additionally, the results of verifications (or certainty
level calculations) performed or made at other retail stores can be
considered (e.g., whether the product was ever located). Thus, the
experience and knowledge gained from decisions made with respect to
other stores can be applied to obtain better decisions with respect
to levels of certainty for the current store being evaluated. Each
of these inputs can be weighted. The level of certainty may be
calculated as a number by summing the weighted contribution of each
input.
[0048] At step 214 when the level of certainty exceeds a
predetermined threshold, the PI value is adjusted to zero. In this
case, a high degree of confidence exists that the item is missing
from the store such that the PI value can be set to 0 (or in some
cases, some other appropriate number). When the level of certainty
does not exceed the threshold, no change to the PI is made. In this
later case, there is not a high enough degree of certainty that the
product is missing from the store.
[0049] Referring now to FIG. 3, one example of a data structure 300
that may be used in the approaches of FIG. 1 and FIG. 2 is
described. In aspects, the data structure 300 may be stored at a
database at the central processing center.
[0050] The data structure 300 programmatically links a first
product 302 to a second product 304. The second product 304 is
historically purchased by the customer whenever the customer has
also purchased the first product 302.
[0051] The data structure 300 programmatically links a third
product 306 to a fourth product 308, and a fifth product 310. The
fourth product 308 and the fifth product 310 are historically
purchased by the customer whenever the customer has also purchased
the third product 306.
[0052] It will be appreciated that the data structure 300 may be
implemented in any programming language with any type of data
elements. For example, the data structure 300 may be implemented as
a look-up table or with pointers.
[0053] Referring now to FIG. 4, one example of an approach for
determining the level of certainty is described. It will be
appreciated that the approach of FIG. 4 is one example and
considers only some factors. The particular factors selected and
the weight attached to these factors can vary according to the
needs of the system or the user. It will be appreciated that the
approach of FIG. 4 may be performed at a central processing
center.
[0054] At step 402, inputs are received. The inputs include sales
data from the store. This may be obtained from point-of-sale
devices such as cash registers. Information concerning the path a
customer the customer takes through the store can also be obtained.
Customer movement information may be obtained by sensors (e.g.,
cameras recording the movement of the customer, or sensing RFID
tags of products in the shopping cart of a customer and tracking
these as the customer moves through the store). Information
concerning weather events may also be received. In some aspects,
this information may be manually entered into the system by an
employee. Other information concerning whether the item is in the
store may also be received. In aspects, this information may
include visible images obtained by various cameras in various
locations in the store. These images may confirm that the product
is not present, for example, on the shelves or in a back room (that
is not accessible to the public).
[0055] The analysis of these inputs to determine a confidence level
occurs at steps 404, 406, 408, and 410. If a test at each of these
steps confirms that the factor is true, then the weighted value of
the factor is included in a summation. The summation represents the
confidence level that the product is truly out of stock. For
instance, assuming that each step has a weighting factor of 0.25,
if all steps were true, then the confidence level is 1 indicating a
very high confidence the product is missing from the store. If only
two out of four were true, the confidence level would be 0.25 plus
0.25 to equal 0.5, representing a 50 percent chance the product is
missing.
[0056] Now considering these steps in greater detail, at step 404,
it is determined whether the customer followed their usual path
through the store. For example, information received at step 402
(showing the customer's path through the store), may be compared to
the path usually followed through the store. If the current path
deviates beyond a predetermined amount or distance from the usual
path, then factor 404 may be set to false. Otherwise, the result of
step 404 is set to be true (indicating the customer intended not to
purchase the second product).
[0057] At step 406, images from the store may be analyzed to
determine if the product is in the store. When the images do not
contain the product, this factor may be set to true. Otherwise, the
result of step 406 is set to false.
[0058] At step 408, the sales data from the store is analyzed. For
example, no recent purchases of the item from the store may
indicate the product is not available and this factor may be set to
true. Otherwise, the result of step 408 is set to false.
[0059] At step 410, analysis may be made to determine if a special
weather event occurred. For example, occurrence of a severe weather
event may cause this factor to be set to true (e.g., indicating a
shipment has been missed due to the weather and that the product is
missing from the store). The non-occurrence of a weather event may
cause this factor to be set to false.
[0060] At step 412, results at each of the steps 404, 406, 408, and
410 are weighted and summed together. The weights in one aspect
should sum to be 1.00. Assuming that each step has a weighting
factor of 0.25, if all steps were true, then the confidence level
is 1 indicating a very high confidence the product is missing from
the store. If only two out of four were true, the confidence level
would be 0.25 plus 0.25 or 0.5 representing a 50 percent chance the
product is missing.
[0061] Once the confidence level is determined, it can be utilized
to determine whether the PI is to be changed. In one example, if
the confidence level exceeds a predetermined level (e.g., 90%),
then the PI value can be changed to 0.
[0062] Those skilled in the art will recognize that a wide variety
of other modifications, alterations, and combinations can also be
made with respect to the above described embodiments without
departing from the scope of the invention, and that such
modifications, alterations, and combinations are to be viewed as
being within the ambit of the inventive concept.
* * * * *