Information processor, and fraudulent behavior determination method

Abstract

To provide an information processor capable of properly detecting a fraudulent act in the manual input of merchandise information.SOLUTION: The information processor includes: a count unit that counts the number of manual inputs in which a customer manually inputs merchandise information for a product that does not have a product code into an input unit; and a determination unit that determines whether there are any fraudulent activities in the manual entry based on the number of manual inputs of merchandise information of the identical product.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus and a method for determining improper behavior.

Background Art

[0002] In recent years, due to the reduction of the number of store employees in retail stores and the like, the popularity of self-checkout has been rapidly progressing. In self-checkout, since the customer himself / herself scans the barcodes of the products, measures against improper behavior such as shoplifting become important.

[0003] There is a self-checkout that uses a weight sensor to detect shoplifting. For example, the apparatus having a self-scanning function disclosed in Patent Document 1 includes a storage unit for storing products whose product codes have been read, and the storage unit has a weight sensor. When the weight of the storage unit increases without the product being scanned, the apparatus of Patent Document 1 generates an alarm.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in a self-checkout that uses a weight sensor as in Patent Document 1 to detect improper behavior of customers, there are cases where improper behavior in the manual input of products without barcodes (barcode-less products) such as vegetables and fruits cannot be appropriately detected.

[0006] For example, in the case of products without barcodes, customers may manually enter product information such as the product name and quantity through an input device such as a touch panel at self-checkout. In the manual input at self-checkout, a customer who engages in fraud may, for example, manually enter the product name of a product that is cheaper than the product actually purchased. A device that detects fraud using a weight sensor may not be able to detect fraud in the manual input of product information as described above.

[0007] Non-limiting embodiments of the present disclosure contribute to providing an information processing apparatus and a fraud determination method that can appropriately detect fraud in the manual input of product information.

Means for Solving the Problem

[0008] An information processing apparatus according to an embodiment of the present disclosure includes a counting unit that counts the number of times a customer manually enters product information of a product without a product code using an input device, and a determination unit that determines whether there is fraud in the manual input based on the number of times of manual input of product information for the same product.

[0009] A fraud determination method according to an embodiment of the present disclosure includes counting the number of times a customer manually enters product information of a product without a product code using an input device, and determining whether there is fraud in the manual input based on the number of times of manual input of product information for the same product.

[0010] These general or specific aspects may be implemented in a system, apparatus, method, integrated circuit, computer program, or recording medium, or may be implemented in any combination of a system, apparatus, method, integrated circuit, computer program, and recording medium.

Advantages of the Invention

[0011] According to an embodiment of the present disclosure, fraud in the manual input of product information can be appropriately detected.

[0012] Further advantages and effects in an embodiment of the present disclosure will be clarified from the specification and drawings. Such advantages and / or effects are respectively provided by several embodiments and the features described in the specification and drawings, but not all of them are necessarily provided in order to obtain one or more identical features.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Modes for Carrying Out the Invention

[0014] Hereinafter, embodiments of the present disclosure will be described in detail with appropriate reference to the drawings. However, a more detailed description than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted. This is to avoid making the following description unnecessarily redundant and to facilitate the understanding of those skilled in the art.

[0015] Note that the accompanying drawings and the following description are provided for those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter described in the claims.

[0016] <First Embodiment> (System Configuration) FIG. 1 is a diagram showing a configuration example of a self-checkout system including an information processing apparatus 1 according to the first embodiment. As shown in FIG. 1, the self-checkout system includes an information processing apparatus 1, scanners 2a and 2b, a camera 3, weight sensors 4a and 4b, and a display 5. In addition to the self-checkout system, FIG. 1 shows merchandise stands A1a and A1b and a stand A2.

[0017] The merchandise stand A1a is a stand on which merchandise before being scanned by the scanners 2a and 2b is placed. The merchandise before being scanned placed on the merchandise stand A1a may include a shopping basket of the store where the merchandise before being scanned is located.

[0018] The merchandise stand A1b is a stand on which merchandise after being scanned by the scanners 2a and 2b is placed. The merchandise after being scanned placed on the merchandise stand A1b may include a customer's shopping basket into which the merchandise after being scanned is placed.

[0019] The information processing apparatus 1 is a computer such as a personal computer or a server. In FIG. 1, the information processing apparatus 1 is placed outside the stand A2, but it may be placed inside the stand A2 or in the office of the store. The information processing apparatus 1 performs detection processing for illegal acts such as settlement processing of goods and illegal input by customers.

[0020] The scanner 2a is a handy type scanner. The scanner 2b is a fixed type scanner fixed to the stand A2. Hereinafter, when the scanners 2a and 2b are not distinguished, they are simply referred to as the scanner 2.

[0021] The scanner 2 is connected to the information processing apparatus 1. The scanner 2 scans the product code attached to the product. The scanner 2 transmits the scanned product code to the information processing apparatus 1. The product code is a barcode such as a JAN (Japanese Article Number) code, for example. The scanner 2 may be referred to as a barcode reader or a reader.

[0022] The camera 3 is connected to the information processing apparatus 1. The camera 3 transmits the image data of the captured image to the information processing apparatus 1.

[0023] The camera 3 is installed so as to capture the vicinity where the customer scans the product with the scanner 2 (see the dotted frame A3 in FIG. 1). For example, the camera 3 is installed above the display 5 or above the stand A2, and the viewing angle is set to include between the product placement table A1a and the product placement table A1b, that is, the vicinity where the customer scans the product with the scanner 2.

[0024] The weight sensor 4a is connected to the information processing apparatus 1. The weight sensor 4a is installed inside the product placement table A1a, for example, and transmits a signal corresponding to the weight of the product placed on the product placement table A1a (or a shopping basket in the store containing the product) to the information processing apparatus 1.

[0025] The weight sensor 4b is connected to the information processing device 1. The weight sensor 4b is installed, for example, inside the product placement stand A1b, and transmits a signal corresponding to the weight of the product placed on the product placement stand A1b (or the customer's shopping basket containing the product, etc.) to the information processing device 1.

[0026] The display 5 is connected to the information processing device 1. The display 5 displays, for example, the product information of the product scanned by the customer using the scanner 2. The product information may be, for example, the name, price, and quantity of the product.

[0027] The display 5 may be provided with a touch panel on the screen surface. The touch panel receives the operations of the customer. For example, the customer manually inputs the information of products without product codes, such as vegetables and fruits, via the touch panel and registers them as purchased products. For example, when the customer purchases an apple without a barcode, the customer manually inputs the product name "apple" and the purchased quantity "X" via the touch panel and registers them as purchased products. Note that the device for receiving the operations of the customer is not limited to the touch panel. The device for receiving the operations of the customer may be, for example, a key input device separate from the display 5. Alternatively, the operations of the customer may be received using a smartphone or a mobile terminal held by the customer.

[0028] Based on the control of the information processing device 1, the display 5 displays a screen related to the detection of manual input fraud. For example, in one accounting procedure (accounting process), if a product without a barcode is manually input multiple times, the display 5 displays a screen indicating that an illegal manual input has been made.

[0029] (Consideration) In a system that allows manual input of products without barcodes, in order to handle bulk purchases by customers, etc., a system that also allows manual input of the quantity of the same product may be adopted. When a customer using such a system takes out multiple identical products from the product placement stand A1a and moves them to the product placement stand A1b, the possibility of repeating the operation of making a manual input each time a product is moved is low.

[0030] Therefore, it is assumed that it is unlikely that a customer will manually enter barcode-less items such as vegetables and fruits multiple times on an input device such as the touch panel of display 5. For example, when a customer purchases three apples, after the customer manually enters one apple (for example, manually enters the product name "apple" and the quantity "1"), scans another product with scanner 2, and then manually enters two more apples (for example, manually enters the product name "apple" and the quantity "2"), it is assumed to be unlikely. Generally, it is assumed that the customer is likely to complete the entry of three apples of the same product in one manual entry (for example, manually enter the product name "apple" and the quantity "3").

[0031] Therefore, when the same product is manually entered multiple times on the input device of the self-checkout, the information processing device 1 determines that an improper act has been committed.

[0032] (Operation example) FIG. 2 is a diagram for explaining the improper act determination of the information processing device 1. FIG. 2 shows a purchase information DB (Date Base) stored in the storage unit of the information processing device 1.

[0033] In the product column of FIG. 2, the product name of the product scanned by scanner 2 is stored. Also, in the product column of FIG. 2, the product name of the product manually entered on the input device is stored. Note that products A, B, and D in FIG. 2 indicate the product names of the products scanned by scanner 2. Product X indicates the product name of the barcode-less product manually entered on the input device.

[0034] In the quantity column of FIG. 2, the quantity of the product scanned by scanner 2 is stored. Also, in the quantity column of FIG. 2, the quantity of the product manually entered on the input device is stored.

[0035] In the amount column of FIG. 2, the amount (total amount for the quantity) of the product scanned by scanner 2 is stored. Also, in the amount column of FIG. 2, the amount (total amount for the quantity) of the product manually entered on the input device is stored.

[0036] In the example of Fig. 2, as shown by arrows A2a and A2b, the same product X has been manually entered multiple times (twice). Therefore, the information processing device 1 determines that an improper act has been committed.

[0037] As described in the above "consideration", it is assumed that it is unlikely that the same product X is manually entered multiple times. Therefore, it is highly likely that the product X in the second manual entry shown by arrow A2b is different from the actual product that the customer moved to product stand A1b. For example, it is assumed that the actual product that the customer moved to product stand A1b is a more expensive product than the manually entered product X. Therefore, when the second manual entry of product X is made, the information processing device 1 determines that an improper act has been committed.

[0038] (Block diagram) Fig. 3 is a diagram showing an example of the block configuration of the information processing device 1. As shown in Fig. 3, the information processing device 1 includes a control unit 11, a storage unit 12, and a communication unit 13.

[0039] The control unit 11 controls the entire information processing device 1. The control unit 11 may be configured by a processor such as a CPU (central processing unit), for example.

[0040] The control unit 11 includes a manual input count unit 11a, an improper act determination unit 11b, and an alarm generation unit 11c. The control unit 11 may implement the functions of the foregoing units according to a program stored in the storage unit 12.

[0041] The manual input count unit 11a counts the number of times of manual input of product information made by the customer to the input device.

[0042] The improper act determination unit 11b determines whether there is an improper act in the manual input based on the number of times of manual input of product information for the same product. For example, when the manual input of product information for the same product is performed multiple times (for example, twice), the improper act determination unit 11b determines that there is an improper act in the manual input.

[0043] When the fraud determination unit 11b determines the occurrence of fraud, the alarm generation unit 11c generates alarm information. For example, the alarm generation unit 11c generates image data of an image including characters such as "Please manually enter the product name correctly". The image data is transmitted to the display 5 via the communication unit 13.

[0044] In addition, the alarm generation unit 11c generates, for example, an alarm signal. The alarm signal is transmitted to the mobile terminal carried by the store clerk via the communication unit 13. The mobile terminal that has received the alarm signal notifies the store clerk of the occurrence of unauthorized input, for example, by sound. Alternatively, the occurrence of unauthorized input may be displayed on the cash register screen or other screens to notify the customer.

[0045] The storage unit 12 stores a program of an OS (operating system) and application programs to be executed by the control unit 11. For example, the storage unit 12 stores an application program that performs settlement processing for self-checkout and monitoring processing for shoplifting. In addition, the storage unit 12 stores various data necessary for the processing by the control unit 11. The storage unit 12 may be, for example, an SSD (solid state drive), a RAM (Random Access Memory), a flash memory, a ROM (Read Only Memory), and / or an HDD (hard disk drive).

[0046] The communication unit 13 communicates with the scanner 2, the camera 3, the weight sensors 4a, 4b, and the display 5 by wire or wirelessly. In addition, the communication unit 13 communicates wirelessly with the mobile terminal carried by the store clerk.

[0047] (Operation flow) FIG. 4 is a flowchart showing an operation example in the fraud determination of the information processing apparatus 1.

[0048] The information processing device 1 determines whether or not a customer has scanned all the products placed on the product stand A1a with the scanner 2 (S1). The information processing device 1 may determine whether or not all the products placed on the product stand A1a have been scanned with the scanner 2 based on, for example, the signal of the weight sensor 4a.

[0049] When the information processing device 1 determines that the customer has not scanned all the products placed on the product stand A1a with the scanner 2 (No in S1), it determines whether or not product information has been manually input (S2). For example, the information processing device 1 determines whether or not the customer has input the product name and quantity of the product via an input device such as the touch panel of the display 5.

[0050] When the information processing device 1 determines that the product information has not been manually input (No in S2), it transfers the process to S1.

[0051] On the other hand, when the information processing device 1 determines that the product information has been manually input (Yes in S2), it determines whether or not the same product has been manually input multiple times (S3).

[0052] When the information processing device 1 determines that the same product has not been manually input multiple times (No in S3), it transfers the process to S1.

[0053] On the other hand, when the information processing device 1 determines that the same product has been manually input multiple times (Yes in S3), it determines that an irregularity has occurred (S4). For example, as described with reference to FIG. 2, when it is determined that the product X has been manually input twice (see arrow A2b in FIG. 2), it is determined that an irregularity has occurred. When the information processing device 1 determines an irregularity, it generates alarm information and an alarm signal and transfers the process to S1.

[0054] When the information processing device 1 determines in S1 that the customer has scanned all the products placed on the product stand A1a with the scanner 2 (Yes in S1), it executes accounting processing (S5). For example, the information processing device 1 displays the total amount of the products purchased by the customer on the display 5 and executes payment processing.

[0055] (Summary of the First Embodiment) As described above, the information processing apparatus 1 counts the number of times of customer manual input. The information processing apparatus 1 determines whether there is any fraud in the manual input based on the number of times of manual input of product information for the same product. Thereby, the information processing apparatus 1 can appropriately detect fraud in the manual input of product information. For example, when there are multiple manual inputs of product information for the same product, the information processing apparatus 1 determines that there is fraud in the manual input and can appropriately detect fraud in the manual input of product information.

[0056] (Modification 1) As described in the above "consideration", it is assumed that the customer takes out the same product from the product stand A1a and moves it to the product stand A1b. Therefore, the customer may manually input the same product continuously.

[0057] For example, in the case of a product with soil such as a potato, the customer may pack the product in a plastic bag and then move it to the product stand A1b. In this case, the customer may manually input the same product continuously. For example, assume the customer purchases 5 potatoes. Suppose 3 potatoes are put in one plastic bag. In this case, the customer may pack 3 potatoes in the bag and manually input (manually input the product name "potato" and the quantity "3"), and then pack 2 potatoes in the bag and manually input (manually input the product name "potato" and the quantity "2").

[0058] Also, customers who are not used to handling self-checkout, such as the elderly or customers who rarely use self-checkout, may manually input the same product continuously.

[0059] Therefore, the information processing apparatus 1 does not determine that fraud has been committed for continuous manual inputs performed multiple times.

[0060] FIG. 5 is a diagram for explaining fraud determination in Modification 1 of the first embodiment. FIG. 5 shows a purchase information DB stored in the storage unit of the information processing apparatus 1. Each column of the purchase information DB shown in FIG. 5 is the same as each column of the purchase information DB described in FIG. 2, and the description thereof is omitted.

[0061] In the example of FIG. 5, as shown by arrows A5a and A5b, the same product X is manually input a plurality of times (twice) in succession. The information processing apparatus 1 does not determine that fraud has been committed for a plurality of consecutive manual inputs of the same product X. That is, the information processing apparatus 1 does not determine that fraud has been committed for the manual input of product X shown by arrow A5b in FIG. 5.

[0062] Note that FIG. 5 shows an example in which the same product Z is manually input a plurality of times (twice) discontinuously, as shown by arrows A5c and A5d. The information processing apparatus 1 determines that fraud has been committed for a plurality of manual inputs of the same product Z. That is, the information processing apparatus 1 determines that fraud has been committed for the manual input of product Z shown by arrow A5d in FIG. 5.

[0063] FIG. 6 is a flowchart showing an operation example of the information processing apparatus 1 in Modification 1 of the first embodiment. In the flowchart of FIG. 6, the same processes as those in the flowchart of FIG. 4 are denoted by the same reference numerals. Note that in the flowchart of FIG. 6, the process of S11a is added to the flowchart of FIG. 4. Hereinafter, processes different from those in the flowchart of FIG. 4 will be described.

[0064] The information processing apparatus 1 determines whether or not a manual input of the same product has been performed a plurality of times in S3. If it is determined that a manual input of the same product has been performed a plurality of times (Yes in S3), the information processing apparatus 1 determines whether or not the plurality of manual inputs are consecutive manual inputs (S11a).

[0065] If the information processing apparatus 1 determines that the plurality of manual inputs are consecutive manual inputs (Yes in S11a), the process proceeds to S1. For example, as described with reference to FIG. 5, when it is determined that there are consecutive manual inputs of product X, the process proceeds to S1.

[0066] On the other hand, when the information processing apparatus 1 determines that the multiple manual inputs are not consecutive manual inputs (No in S11a), it determines that an improper act has been committed (S4). For example, as described with reference to FIG. 5, when the manual input of product Z (non-consecutive manual input) is determined twice, it is determined that an improper act has been committed. When the information processing apparatus 1 determines an improper act, it generates alarm information and an alarm signal, and shifts the process to S1.

[0067] As described above, the information processing apparatus 1 does not determine that an improper act has been committed for multiple consecutive manual inputs. Thus, the information processing apparatus 1 can appropriately determine an improper act.

[0068] (Modification 2) Customers who are not used to using self-checkout, such as the elderly or customers who rarely use self-checkout, may enter product information multiple times. Therefore, the information processing apparatus 1 does not determine that an improper act has been committed for multiple manual inputs by a customer who is not used to using self-checkout (hereinafter sometimes referred to as a specific customer).

[0069] The information processing apparatus 1 may determine a customer who is not used to using self-checkout based on, for example, an image from the camera 3. For example, the information processing apparatus 1 may analyze the behavior of a customer based on a known image analysis program and determine a customer who is not used to using self-checkout.

[0070] The information processing apparatus 1 may determine the age of a customer based on, for example, an image from the camera 3. For example, the information processing apparatus 1 may analyze the appearance of a customer based on a known image analysis program and determine an elderly person.

[0071] The information processing apparatus 1 may store a face image of a specific customer in the storage unit 12. For example, the information processing apparatus 1 may store a face image of a customer in the storage unit 12 upon a request from a visiting customer. The information processing apparatus 1 may compare the image from the camera 3 with the stored face image to determine a specific customer.

[0072] FIG. 7 is a flowchart showing an operation example of the information processing apparatus 1 in Modification 2 of the first embodiment. In the flowchart of FIG. 7, the same processes as those in the flowchart of FIG. 4 are denoted by the same reference numerals. Note that in the flowchart of FIG. 7, the process of S11b is added to the flowchart of FIG. 4. Hereinafter, the processes different from those in the flowchart of FIG. 4 will be described.

[0073] The information processing apparatus 1 determines whether the manual input of the same product has been performed a plurality of times in S3. If it is determined that the manual input of the same product has been performed a plurality of times (Yes in S3), the information processing apparatus 1 determines whether the customer is a specific customer (S11b).

[0074] If the information processing apparatus 1 determines that the customer is a specific customer (Yes in S11b), the process proceeds to S1. That is, the information processing apparatus 1 does not determine that an illegal act has been committed for multiple manual inputs by a specific customer.

[0075] On the other hand, if the information processing apparatus 1 determines that the customer is not a specific customer (No in S11b), it determines that an illegal act has been committed (S4).

[0076] As described above, the information processing apparatus 1 does not determine that an illegal act has been committed for multiple manual inputs by a specific customer. Thereby, the information processing apparatus 1 can appropriately determine an illegal act.

[0077] Note that when the information processing apparatus 1 determines a specific customer, it may display a button image for calling a store clerk on the display 5.

[0078] Further, the information processing apparatus 1 may determine, for example, a customer who needs assistance in the self-checkout based on the image of the camera 3. When the information processing apparatus 1 determines a customer who needs assistance, it may display a button image for calling a store clerk on the display 5. The information processing apparatus 1 may notify the terminal held by the store clerk that there is a customer who needs assistance. Even if the customer does not touch the button image for calling the store clerk, when a specific customer is determined, the information processing apparatus 1 may notify the store clerk that the specific customer has visited the store.

[0079] (Modification Example 3) Based on the type of product, the upper limit of the number of manual inputs may be changed. For example, for product X, when it is manually input twice, the information processing apparatus 1 may determine an illegal act, and for product Y, when it is manually input three times, the information processing apparatus 1 may determine an illegal act.

[0080] The upper limit may be arbitrarily set by, for example, a store clerk at the store. For example, for products packed in plastic bags, multiple products are packed in one bag and often only one manual input is required. Therefore, for products that may be packed in bags, the upper limit may be set low, and for products that are less likely to be packed in bags, the upper limit may be set high. Of course, depending on the product, even for products that may be packed in bags, the upper limit may be set high, and for products that are less likely to be packed in bags, the upper limit may be set low. The upper limit is stored in the storage unit 12.

[0081] FIG. 8 is a diagram for explaining illegal act determination in Modification Example 3 of the first embodiment. FIG. 8 shows a purchase information DB stored in the storage unit of the information processing apparatus 1. Each column of the purchase information DB shown in FIG. 8 is the same as each column of the purchase information DB described in FIG. 2, and the description thereof is omitted.

[0082] In the example of FIG. 8, the upper limit of the number of manual inputs for product X without a barcode is set to 2 times. The upper limit of the number of manual inputs for product Z without a barcode is set to 1 time.

[0083] As shown by arrows A8a and A8b, a product X without a barcode has been manually entered multiple times (twice). Since the upper limit of the number of manual entries for product X is two times, the information processing device 1 does not determine that an improper act has been committed for the multiple manual entries of product X. That is, the information processing device 1 does not determine that an improper act has been committed for the manual entry of product X shown by arrow A8b in FIG. 8.

[0084] As shown by arrows A8c and A8d, a product Z without a barcode has been manually entered multiple times (twice). Since the upper limit of the number of manual entries for product Z is one time, the information processing device 1 determines that an improper act has been committed for the multiple manual entries of product Z. That is, the information processing device 1 determines that an improper act has been committed for the manual entry of product Z shown by arrow A8d in FIG. 8.

[0085] FIG. 9 is a flowchart showing an operation example of the information processing device 1 in Modification 3 of the first embodiment. In the flowchart of FIG. 9, the same processes as those in the flowchart of FIG. 4 are denoted by the same reference numerals. Note that, in the flowchart of FIG. 9, the process of S11c is added to the flowchart of FIG. 4. Hereinafter, the processes different from those in the flowchart of FIG. 4 will be described.

[0086] The information processing device 1 determines whether the manual entry of the same product has been performed multiple times in S3. If it is determined that the manual entry of the same product has been performed multiple times (Yes in S3), the information processing device 1 determines whether the number of manual entries is greater than the upper limit number (S11c).

[0087] If the information processing device 1 determines that the number of manual entries is not greater than the upper limit number (No in S11c), the process proceeds to S1. For example, as described with reference to FIG. 8, since the upper limit of the number of manual entries for product X is two times, the information processing device 1 does not determine that an improper act has been committed even if the manual entry of product X is determined twice as shown by arrow A8b, and the process proceeds to S1.

[0088] On the other hand, when the information processing apparatus 1 determines that the number of manual inputs is greater than the upper limit number (Yes in S11c), it determines that an improper act has been committed (S4). For example, as described with reference to FIG. 8, since the upper limit number of manual inputs for product Z is 1, when the information processing apparatus 1 determines that the manual input for product Z has been performed twice as shown by arrow A8d, it determines that an improper act has been committed.

[0089] As described above, when the number of manual inputs performed multiple times exceeds the upper limit number, the information processing apparatus 1 determines that an improper act has been committed. Thereby, the information processing apparatus 1 can appropriately determine an improper act.

[0090] (Modification Example 4) Regarding improper acts by manual input, it is assumed that in many cases, an inexpensive product is manually input for a high-priced product. For example, a customer may manually input a fruit priced at y yen (y < x) instead of a fruit priced at x yen.

[0091] Therefore, when the manual input of an inexpensive product is performed multiple times, the information processing apparatus 1 determines that an improper act has been committed. For example, when the unit price of a product that has been manually input multiple times is less than or equal to a predetermined amount (determination amount), the information processing apparatus 1 determines that an improper act has been committed. Note that the determination amount is stored in the storage unit 12. The determination amount may be set by a store clerk of the store.

[0092] FIG. 10 is a diagram for explaining improper act determination in Modification Example 4 of the first embodiment. FIG. 10 shows a purchase information DB stored in the storage unit of the information processing apparatus 1. Each column of the purchase information DB shown in FIG. 10 is the same as each column of the purchase information DB described with reference to FIG. 2, and the description thereof is omitted.

[0093] In the example of FIG. 10, let the unit price of product X without a barcode be x. Let the unit price of product Z without a barcode be z. The unit price x is greater than the determination amount, and the unit price z is less than or equal to the determination amount.

[0094] As shown by arrows A10a and A10b, product X without a barcode has been manually entered twice. Since the unit price x of product X is greater than the determination amount, the information processing device 1 does not determine that an improper act has been committed for the multiple manual entries of product X. That is, the information processing device 1 does not determine that an improper act has been committed for the manual entry of product X shown by arrow A10b in FIG. 10.

[0095] As shown by arrows A10c and A10d, product Z without a barcode has been manually entered twice. Since the unit price z of product Z is less than the determination amount, the information processing device 1 determines that an improper act has been committed for the multiple manual entries of product Z. That is, the information processing device 1 determines that an improper act has been committed for the manual entry of product Z shown by arrow A10d in FIG. 10.

[0096] FIG. 11 is a flowchart showing an operation example of the information processing device 1 in Modification 3 of the first embodiment. In the flowchart of FIG. 11, the same processes as those in the flowchart of FIG. 4 are denoted by the same reference numerals. Note that in the flowchart of FIG. 11, the process of S11d is added to the flowchart of FIG. 4. Hereinafter, the processes different from those in the flowchart of FIG. 4 will be described.

[0097] The information processing device 1 determines whether the manual entry of the same product has been performed multiple times in S3. If it is determined that the manual entry of the same product has been performed multiple times (Yes in S3), the information processing device 1 determines whether the unit price of the manually entered product is less than or equal to the determination amount (S11d).

[0098] If the information processing device 1 determines that the unit price of the product manually entered multiple times is not less than or equal to the determination amount (No in S11d), the process proceeds to S1. For example, as described with reference to FIG. 10, since the unit price x of product X manually entered twice is greater than the determination amount, the information processing device 1 does not determine that an improper act has been committed even if the manual entry of product X is determined twice as shown by arrow A10b, and the process proceeds to S1.

[0099] On the other hand, when the information processing apparatus 1 determines that the unit price of a product manually input multiple times is less than or equal to the determination amount (Yes in S11d), it determines that an illegal act has been committed (S4). For example, as described with reference to FIG. 10, since the unit price z of product Z manually input twice is less than or equal to the determination amount, the information processing apparatus 1 determines that an illegal act has been committed when the manual input of product Z is determined twice, as indicated by arrow A10d.

[0100] As described above, when the unit price of a product manually input multiple times is less than or equal to the determination amount, the information processing apparatus 1 determines that an illegal act has been committed. Thereby, the information processing apparatus 1 can appropriately determine an illegal act.

[0101] (Modification Example 5) The technology in the first embodiment may be applied to products with barcodes. For example, in the case of a product for which a barcode can be scanned and the quantity can be input, the technology in the above-described first embodiment may be applied.

[0102] <Second Embodiment> In the second embodiment, the method for detecting illegal acts in multiple product inputs (product registration) is changed depending on whether multiple products have been manually input.

[0103] For example, when multiple products have not been manually input in an input device such as the touch panel of the display 5, in other words, when multiple products have been scanned by the scanner 2, the information processing apparatus 1 performs illegal act determination using the weight sensor 4b.

[0104] On the other hand, when multiple products have been manually input, the information processing apparatus 1 performs illegal act determination without using the weight sensor 4b.

[0105] More specifically, when no plurality of products are manually input, the information processing apparatus 1 determines whether there is any improper conduct based on whether the number of times the plurality of products are scanned by the scanner 2 matches the number of times the weight of the product stand A1b increases. When the number of times the products are scanned by the scanner 2 is less than the number of times the weight of the product stand A1b increases, assuming that the products are moved from the product stand A1a to the product stand A1b without being scanned by the scanner 2, the information processing apparatus 1 determines that there is improper conduct.

[0106] On the other hand, when a plurality of products are manually input, the information processing apparatus 1 determines whether there is any improper conduct based on object detection from the image of the camera 3. For example, the information processing apparatus 1 determines the products and the number of products taken out from the product stand A1a based on the image of the camera 3, and compares them with the products and the number of products manually input by the customer to determine whether there is any improper conduct. When either or both of the products and the number of products detected based on the image of the camera 3 do not match either or both of the products and the number of products manually input by the customer, assuming that improper manual input has been performed, the information processing apparatus 1 determines that there is improper conduct.

[0107] Note that the system configuration in the second embodiment is the same as that in FIG. 1, and the description thereof is omitted. Also, the block configuration in the second embodiment is the same as that in FIG. 3, but the function of the control unit 11 is different. For example, the control unit 11 determines whether a plurality of products without barcodes are input, and changes the method for detecting improper conduct based on the determination result. For example, when a plurality of products are manually input, the control unit 11 performs improper conduct determination without using the weight sensor 4b, such as based on the image of the camera 3, and when no plurality of products are manually input, the control unit 11 performs improper conduct determination using the weight sensor 4b. Known technologies such as artificial intelligence may be applied to the detection of products and the number of products based on the image of the camera 3.

[0108] (Operation Flow) FIG. 12 is a flowchart showing an operation example in the improper conduct determination of the information processing apparatus 1.

[0109] The information processing device 1 determines whether the customer has scanned all the products placed on the product stand A1a with the scanner 2 (S21). The information processing device 1 may determine whether the customer has scanned all the products placed on the product stand A1a with the scanner 2 based on, for example, the signal of the weight sensor 4a.

[0110] If the information processing device 1 determines that the customer has not scanned all the products placed on the product stand A1a with the scanner 2 (No in S21), it determines whether a plurality of products without barcodes have been manually entered (S22).

[0111] If the information processing device 1 determines that a plurality of products without barcodes have not been entered (No in S22), that is, if it determines that a plurality of products have been scanned using the scanner 2, it executes fraud detection processing using the weight sensor 4b (S23).

[0112] For example, the information processing device 1 detects the presence or absence of fraud based on whether the number of times a plurality of products are scanned by the scanner 2 matches the number of times the weight of the product stand A1b increases. After executing the fraud detection processing in S23, the information processing device 1 transfers the processing to S1. Note that when the information processing device 1 detects fraud in the execution of the fraud detection processing in S23, it generates alarm information and an alarm signal and transfers the processing to S1.

[0113] On the other hand, if the information processing device 1 determines that a plurality of products without barcodes have been entered (Yes in S22), that is, if it determines that manual entry has been performed using the input device, it executes fraud detection processing without using the weight sensor 4b (S24).

[0114] For example, based on the image from camera 3, the information processing device 1 determines the products taken out from product stand A1a and the quantity, and detects fraud based on whether it matches the products and quantity manually input by the customer into the input device. After executing the fraud detection process in S24, the information processing device 1 transfers the process to S1. Note that when detecting fraud in the execution of the fraud detection process in S24, the information processing device 1 generates alarm information and an alarm signal, and transfers the process to S1.

[0115] Note that in the process of S24, the information processing device 1 may execute the fraud detection process described in the first embodiment. When detecting fraud in both the fraud detection process described in the first embodiment and the fraud detection process using the image from camera 3, the information processing device 1 may determine that there is fraud. Or, when detecting fraud in at least one of the fraud detection process described in the first embodiment and the fraud detection process using the image from camera 3, the information processing device 1 may determine that there is fraud.

[0116] When the information processing device 1 determines in S21 that the customer has scanned all the products placed on product stand A1a with scanner 2 (Yes in S21), it executes the accounting process (S25). For example, the information processing device 1 displays the total amount of the products purchased by the customer on display 5 and executes the payment process.

[0117] (Summary of the Second Embodiment) As described above, when manual input is performed with the input device, the information processing device 1 compares the product information obtained based on the image from camera 3 with the manually input product information, and determines whether there is fraud in the manual input. Thereby, the information processing device 1 can appropriately detect fraud in the manual input of product information.

[0118] (Modification 1) When it is determined that a plurality of bar code-less items have been input (see Yes in S22 of FIG. 12), the information processing apparatus 1 may calculate the total weight of the bar code-less items using the weight sensor 4b and execute fraud detection processing.

[0119] For example, the information processing apparatus 1 stores, in advance in the storage unit 12, the weight per unit (reference weight) for each bar code-less item. The information processing apparatus 1 calculates the total weight of the plurality of manually input bar code-less items based on the reference weight in the storage unit 12. When the calculated total weight is less than the total weight of the bar code-less items placed on the product stage A1b calculated based on the signal from the weight sensor 4b, the information processing apparatus 1 determines that fraud has been committed. That is, when the customer manually inputs a smaller number of bar code-less items, the information processing apparatus 1 determines that fraud has been committed.

[0120] As described above, the information processing apparatus 1 uses the weight sensor 4b to detect fraud by the customer. Thereby, the information processing apparatus 1 can detect fraud by the customer without using the camera 3, and can reduce costs.

[0121] Note that, although described in the third embodiment, the reference weight may have a range.

[0122] (Modification 2) When it is determined that a plurality of bar code-less items have been input (see Yes in S22 of FIG. 12), the information processing apparatus 1 may execute fraud detection processing using the number of weight increases in the weight sensor 4b and the number of bar code-less items input by the customer to the input device.

[0123] For example, when the number of weight increases in the weight sensor 4b is greater than the number of bar code-less items input by the customer to the input device, the information processing apparatus 1 determines that fraud has been committed. That is, when the customer manually inputs a smaller number of bar code-less items, the information processing apparatus 1 determines that fraud has been committed.

[0124] In addition, even when the number of times the weight increases in the weight sensor 4b is smaller than the number of items without barcodes that the customer has entered into the input device, it may be determined that an illegal act has been committed. However, when the customer puts multiple items without barcodes into a bag or the like and moves them together, the number of times the weight increases will be smaller than the number of items without barcodes even if no illegal act has been committed. Therefore, when determining that an illegal act has been committed even when the number of times the weight increases is smaller than the number of items without barcodes, it may be configured to give a notice that takes into account not to damage the customer's impression, such as notifying only the store clerk.

[0125] As described above, the information processing apparatus 1 uses the weight sensor 4b to detect an illegal act by the customer. Thereby, the information processing apparatus 1 can detect an illegal act by the customer without using the camera 3, and can reduce costs.

[0126] (Modification Example 3) When the information processing apparatus 1 determines that a plurality of items without barcodes have been input (see Yes in S22 of FIG. 12), it may execute an illegal act detection process using the weight values based on the signals of the weight sensors 4a and 4b.

[0127] For example, when the weight value in the weight sensor 4a decreases and the weight value in the weight sensor 4b does not increase by the amount of the decreased weight value, the information processing apparatus 1 determines that an illegal act has been committed. That is, when the customer does not place the item taken out from the product stand A1a on the product stand A1b, the information processing apparatus 1 determines that an illegal act has been committed.

[0128] As described above, the information processing apparatus 1 uses the weight sensors 4a and 4b to detect an illegal act by the customer. Thereby, the information processing apparatus 1 can detect an illegal act by the customer without using the camera 3, and can reduce costs.

[0129] (Modification Example 4) After the customer makes a manual input, the information processing device 1 does not detect a product in product detection based on the image of the camera 3 until the next product is scanned by the scanner 2. When the weight value based on the weight sensor 4b increases multiple times, it does not determine that shoplifting has occurred. That is, the information processing device 1 does not determine that shoplifting has occurred in a situation where products without barcodes are placed on the product stand A1b in multiple batches.

[0130] (Modification Example 5) A weight sensor may be provided on the cart. The weight sensor provided on the cart may wirelessly transmit a signal corresponding to the weight of the product placed in the cart to the information processing device 1.

[0131] When a weight sensor is provided on the cart, the customer can take out a product from the cart, scan the product with the scanner 2 without placing it on the product stand A1a, or make a manual input.

[0132] That is, the configuration of this modification example can be said to be a configuration in which the product stand A1a is arranged on the cart.

[0133] Note that the product stand A1a may be provided on both the stand A2 and the cart. In this case, the product stand A1a provided on the stand A2 and the product stand A1a provided on the cart may be handled without distinction. For example, when a product is taken out from the product stand A1a provided on the cart and moved to the product stand A1a provided on the stand A2, although the product is moving between the cart and the stand A2, it may be handled as if the product has been returned to the product stand A1a without distinguishing between the cart and the stand A2. Also, since customers who use a basket or the like instead of a cart are also assumed, a weight sensor may be provided on the basket or the like.

[0134] <The Third Embodiment> As described in Modification Example 1 of the Second Embodiment, the weight per product without a barcode (reference weight) is stored in the storage unit 12. In the Third Embodiment, the information processing device 1 calculates the reference weight through training and stores it in the storage unit 12.

[0135] The information processing apparatus 1 may execute training, for example, when a customer is actually using self-checkout. For example, when the customer moves an item without a barcode from the product placement stand A1a to the product placement stand A1b, the information processing apparatus 1 may calculate (train) the reference weight of the item without a barcode. Alternatively, during a time period such as before the store opens, a store clerk may actually use self-checkout to execute training.

[0136] More specifically, when one item X without a barcode is taken out from the product placement stand A1a and the weight value at the weight sensor 4a decreases, the information processing apparatus 1 may use the decreased weight value as the reference weight of the item X without a barcode. Alternatively, when one item X without a barcode is placed on the product placement stand A1b and the weight value at the weight sensor 4b increases, the information processing apparatus 1 may use the increased weight value as the reference weight of the item X without a barcode. Alternatively, the information processing apparatus 1 may use the average of the reference weight obtained from the weight sensor 4a and the reference weight obtained from the weight sensor 4b as the reference weight of the item without a barcode.

[0137] The information processing apparatus 1 may use the average of the reference weights during a specific period such as in the morning as the reference weight. Note that, for example, even for the same apple, if the date changes, the production location may change and the reference weight may also change. Therefore, it is preferable for the information processing apparatus 1 to perform training of the reference weight during an early time period of the day such as in the morning. Note that the average is just an example, and other statistical values such as the median may be used as the reference weight.

[0138] Also, while the longer the training period, the more the influence of outliers on the reference weight can be reduced, the shorter the training period, the longer the fraud detection process using the latest reference weight can be performed. Therefore, depending on whether to prioritize the accuracy of the reference weight or the length of the period during which the fraud detection process can be performed, the specific period may be made shorter or longer.

[0139] Also, in a time period when the training of the reference weight is not sufficiently performed, such as immediately after the store opening, the past reference weight or the reference weight set by the user may be used as the reference weight.

[0140] In the case of a barcode-free product with individual differences in weight, the information processing device 1 may give a width to the reference weight. The information processing device 1 may reduce the width of the reference weight as the training time elapses.

[0141] The information processing device 1 may also calculate the reference weight for in-store products such as meat and fish and store it in the storage unit 12. For example, the information processing device 1 may acquire the price information of in-store products from the POS (Point of Sale) data, convert the price information into weight information, and calculate the reference weight of in-store products. The information processing device 1 may also give a width to the reference weight of in-store products.

[0142] Note that the system configuration in the third embodiment is the same as that in FIG. 1, and the description thereof is omitted. Also, the block configuration in the third embodiment is the same as that in FIG. 3, but the function of the control unit 11 is different. The control unit 11 has a training unit that calculates the reference weight and stores it in the storage unit 12.

[0143] (Operation flow) FIG. 13 is a flowchart showing an operation example in the reference weight collection of the information processing device 1.

[0144] The information processing device 1 determines whether or not all the products placed on the product stand A1a by the customer have been scanned by the scanner 2 (S31). The information processing device 1 may determine whether or not all the products placed on the product stand A1a have been scanned by the scanner 2 based on, for example, the signal of the weight sensor 4a.

[0145] When the information processing device 1 determines that not all the products placed on the product stand A1a by the customer have been scanned by the scanner 2 (No in S31), it determines whether or not a barcode-free product has been manually input (S32).

[0146] When the information processing device 1 determines that a barcode-less product has been manually entered (Yes in S32), it collects and averages the weight values of the weight sensors 4a and 4b (S33). The information processing device 1 stores the averaged weight value, that is, the reference weight of the barcode-less product, in the storage unit 12, and transfers the process to S31.

[0147] When the information processing device 1 determines that a barcode-less product has not been manually entered (Yes in S32), that is, when it determines that a product has been scanned using the scanner 2, it determines whether the scanned product is an in-store product (S34).

[0148] When the information processing device 1 determines that the scanned product is an in-store product (Yes in S34), it collects price information from the POS data, converts the price information into weight information, and calculates the reference weight of the in-store product (S35). The information processing device 1 stores the calculated reference weight of the in-store product in the storage unit 12, and transfers the process to S31.

[0149] On the other hand, when the information processing device 1 determines that the scanned product is not an in-store product (No in S34), it acquires the reference weight of the product that is not an in-store product scanned from the reference weight table of products (S36), stores it in the storage unit 12, and transfers the process to S31.

[0150] When the information processing device 1 determines in S31 that the customer has scanned all the products placed on the product stand A1a with the scanner 2 (Yes in S31), it executes the accounting process (S37). For example, the information processing device 1 displays the total amount of the products purchased by the customer on the display 5 and executes the payment process.

[0151] (Summary of the Third Embodiment) As described above, during the training period, the information processing device 1 collects and averages the weight per product from the weight sensors, and calculates the reference weight. Thereby, the information processing device 1 can appropriately calculate the weight of the barcode-less product and can appropriately detect fraud in the manual input of product information.

[0152] The embodiments have been described above with reference to the drawings, but the present disclosure is not limited to such examples. It is obvious that those skilled in the art can conceive various modification examples or correction examples within the scope described in the claims. Such modification examples or correction examples are also understood to belong to the technical scope of the present disclosure. Further, within the scope not departing from the gist of the present disclosure, the constituent elements in the embodiments may be arbitrarily combined. The embodiments may be arbitrarily combined. The modification examples may be arbitrarily combined.

[0153] In the above-described embodiments, the notation “... part” used for each constituent element may be replaced with other notations such as “... circuitry”, “... assembly”, “... device”, “... unit”, or “... module”.

[0154] The present disclosure can be realized by software, hardware, or software in cooperation with hardware. Each functional block used in the description of the above embodiments is realized as an LSI which is an integrated circuit, partially or entirely, and each process described in the above embodiments may be controlled, partially or entirely, by one LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of one chip so as to include a part or all of the functional blocks. The LSI may have an input and output of data. Depending on the degree of integration, the LSI may also be referred to as an IC, a system LSI, a super LSI, or an ultra LSI.

[0155] The method of integrating into a circuit is not limited to LSI, and it may be realized by a dedicated circuit, a general-purpose processor, or a dedicated processor. Further, after manufacturing the LSI, an FPGA (Field Programmable Gate Array) that can be programmed, or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used. The present disclosure may be realized as digital processing or analog processing.

[0156] Furthermore, if an integrated circuit technology that replaces the LSI emerges due to the progress of semiconductor technology or another derived technology, it is natural that the integration of functional blocks may be performed using such technology. The application of biotechnology, etc. may be possible.

Industrial Applicability

[0157] The present disclosure is useful for detecting fraudulent manual input in self-checkout.

Explanation of Signs

[0158] 1 Information processing apparatus 2, 2a, 2b Scanner 3 Camera 4a, 4b Weight sensor 5 Display A4a, A4b Product placement stand

Claims

1. a counting unit that allows a customer to manually input product information of a product not having a product code into an input device and counts the number of times the customer manually inputs product information; a determination unit that determines whether or not there has been any fraudulent activity in the manual input based on the number of times product information of the same product has been manually input; An information processing device having the above configuration.

2. The determination unit determines that fraud has occurred in the manual input based on whether product information of the same product has been manually input multiple times. The information processing device according to claim 1 .

3. the determination unit determines that there has been fraudulent manual input when the number of times product information about the same product has been manually input is greater than an upper limit number set for each type of product. The information processing device according to claim 2 .

4. The determination unit is If the product information of the same product is input multiple times non-consecutively, it is determined that there has been fraudulent activity in the manual input; If the product information of the same product is input multiple times in succession, it is not determined that there has been any fraudulent activity in the manual input. The information processing device according to claim 2 .

5. The determination unit further determines, when product information of the same product is manually input multiple times, whether or not there has been any fraudulent activity in the manual input based on the unit price of the product in the product information. The information processing device according to claim 2 .

6. The determination unit determines that there has been fraudulent activity in the manual input when the unit price is equal to or less than a determination amount set for each type of product. The information processing device according to claim 5 .

7. The determination unit further compares product information of the product detected from the camera image with manually input product information, and determines whether or not there has been any fraudulent activity in the manually input. The information processing device according to claim 1 .

8. The determination unit further calculates a total weight of the manually inputted products from the reference weight per unit of the products, and compares the calculated total weight with the manually inputted total weight of the products obtained from the weight sensor to determine whether or not there has been any fraudulent activity in the manual input. The information processing device according to claim 1 .

9. and a training unit that, during a training period, collects and averages the weight of each of the products from the weight sensor and calculates the reference weight. The information processing device according to claim 8.

10. A customer manually inputs product information of a product that does not have a product code into an input device, and the number of times the customer manually inputs product information is counted; determining whether or not there has been any fraudulent activity in the manual input based on the number of times product information for the same product has been manually input; Methods for determining misconduct.

Images