Information processing device and fraudulent act determination method

Abstract

This information processing device comprises: a counting unit that counts the number of times of manual inputs to an input device by a customer of product information of a product without a product code attached; and a determination unit that determines whether or not there has been a fraudulent act in the manual inputs on the basis of the number of times of manual inputs of product information in the same product.

Description

Information processing device and fraudulent activity determination method

[0001] The present disclosure relates to an information processing device and a method for determining fraudulent activity.

[0002] In recent years, the spread of self-checkout systems has been rapidly increasing in order to reduce the man-hours of store staff in retail stores. However, since customers scan the barcodes of products themselves, it is important to take measures to prevent fraudulent activities such as shoplifting.

[0003] There are self-checkout registers that use weight sensors to detect shoplifting. For example, a device with a self-scanning function disclosed in Patent Document 1 includes a storage unit that stores products whose product codes have been read, and the storage unit has a weight sensor. The device in Patent Document 1 issues an alarm if the weight of the storage unit increases without a product being scanned.

[0004] Japanese Patent Application Publication No. 7-141569

[0005] However, self-checkout registers that use weight sensors such as those in Patent Document 1 to detect customer fraudulent behavior may not be able to properly detect fraudulent behavior when items that do not have barcodes, such as vegetables and fruits, are manually entered (non-barcoded items).

[0006] For example, for products without barcodes, customers may manually input product information such as the product name and quantity into a self-checkout register using an input device such as a touch panel. When manually entering product information into a self-checkout register, fraudulent customers may, for example, manually enter the product name of a product that is cheaper than the product they actually purchase. Devices that detect fraudulent behavior using weight sensors may not be able to detect fraudulent behavior in the manual entry of product information as described above.

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

[0008] An information processing device according to one embodiment of the present disclosure includes a counting unit that allows a customer to manually input product information for a product that does not have a product code into an input device and counts the number of times the manual input is made, and 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 for the same product has been manually input.

[0009] A fraudulent activity determination method according to one embodiment of the present disclosure involves a customer manually entering product information for a product that does not have a product code into an input device, counting the number of times the manual entry is made, and determining whether or not there has been fraudulent activity in the manual entry based on the number of times the product information for the same product has been manually entered.

[0010] These comprehensive or specific aspects may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a recording medium, or may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

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

[0012] Further advantages and benefits of an embodiment of the present disclosure will become apparent from the specification and drawings. Such advantages and / or benefits may be provided by some of the embodiments and features described in the specification and drawings, respectively, but not necessarily all of them may be provided to obtain one or more identical features.

[0013] FIG. 1 shows an example of the configuration of a self-checkout system including an information processing device according to a first embodiment. FIG. 2 shows an example of the configuration of an information processing device. FIG. 3 shows an example of the operation of an information processing device in determining fraudulent activity. FIG. 4 shows an example of the operation of an information processing device in collecting reference weights. FIG. 5 shows an example of the operation of an information processing device in determining fraudulent activity in a first modified example of the first embodiment.

[0014] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings as appropriate. However, more detailed explanation than necessary may be omitted. For example, detailed explanation of already well-known matters or redundant explanation of substantially identical configurations may be omitted. This is to avoid unnecessary redundancy in the following explanation and to facilitate understanding by those skilled in the art.

[0015] The accompanying drawings and the following description are provided to enable 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 an example of the configuration of a self-checkout system including an information processing device 1 according to a first embodiment. As shown in Fig. 1, the self-checkout system has an information processing device 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 also shows product stands A1a and A1b and a stand A2.

[0017] The product stand A1a is a stand on which products are placed before being scanned by the scanners 2a and 2b. The products placed on the product stand A1a before being scanned may include a shopping basket or the like from a store containing products before being scanned.

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

[0019] The information processing device 1 is, for example, a computer such as a personal computer or a server. In Fig. 1, the information processing device 1 is placed outside the table A2, but it may be placed inside the table A2 or in the store's office. The information processing device 1 performs, for example, a payment process for products and a process for detecting fraudulent activities such as fraudulent manual input by customers.

[0020] The scanner 2a is a handheld scanner, and the scanner 2b is a fixed scanner fixed to a stand A2. Hereinafter, when there is no need to distinguish between the scanners 2a and 2b, they will be simply referred to as the scanner 2.

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

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

[0023] Camera 3 is installed so as to capture the area around where customers scan products with scanner 2 (see dotted frame A3 in FIG. 1 ). For example, camera 3 is installed above display 5 or above stand A2, and the angle of view is set so as to include the area between product stand A1a and product stand A1b, i.e., the area around where customers scan products with scanner 2.

[0024] The weight sensor 4a is connected to the information processing device 1. The weight sensor 4a is installed, for example, inside the product stand A1a, and transmits a signal to the information processing device 1 according to the weight of the product placed on the product stand A1a (or a shopping basket or the like containing the product).

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

[0026] The display 5 is connected to the information processing device 1. The display 5 displays, for example, product information of a product scanned by a 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 its screen surface. The touch panel accepts customer operations. A customer manually inputs information about a product without a product code, such as vegetables or fruits, via the touch panel and registers the product as a purchased product. For example, when a customer purchases apples without a barcode, the customer manually inputs the product name "apples" and the purchase quantity "X" via the touch panel and registers the product as a purchased product. Note that the device that accepts customer operations is not limited to a touch panel. The device that accepts customer operations may be, for example, a key input device separate from the display 5. Alternatively, customer operations may be accepted using a smartphone or mobile terminal owned by the customer.

[0028] The display 5 displays a screen related to the detection of manual input fraudulent activity under the control of the information processing device 1. For example, if a product without a barcode is manually entered multiple times in a single checkout procedure (checkout process), the display 5 displays a screen indicating that fraudulent manual entry has occurred.

[0029] (Consideration) In systems that allow manual input of products without barcodes, a system may be adopted that also allows manual input of the number of the same product to accommodate bulk purchases by customers, etc. When a customer using such a system removes multiple identical products from product stand A1a and moves them to product stand A1b, it is unlikely that the customer will have to repeatedly perform the action of manually inputting the number of products each time they move one product.

[0030] Therefore, it is assumed that a customer is unlikely to manually input barcode-less products such as vegetables and fruits multiple times into an input device such as a touch panel on the display 5. For example, if a customer purchases three apples, it is assumed that the customer is unlikely to manually input one apple (e.g., manually inputting the product name "apple" and the quantity "1"), then scan another product with the scanner 2, and then manually input two apples again (e.g., manually inputting the product name "apple" and the quantity "2"). In general, it is assumed that a customer is likely to manually input three apples of the same product in a single input (e.g., manually inputting the product name "apple" and the quantity "3").

[0031] Therefore, the information processing device 1 determines that fraud has occurred if the same product is manually entered multiple times into the input device of the self-checkout.

[0032] (Example of Operation) Fig. 2 is a diagram for explaining fraudulent activity determination by 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] The product column in Fig. 2 stores the product names of products scanned by the scanner 2. The product column in Fig. 2 also stores the product names of products manually input using the input device. Note that products A, B, and D in Fig. 2 indicate the product names of products scanned by the scanner 2. Product X indicates the product name of a product without a barcode manually input using the input device.

[0034] The number of products scanned by the scanner 2 is stored in the number column in Fig. 2. The number of products manually input via the input device is also stored in the number column in Fig. 2.

[0035] The price column in Fig. 2 stores the prices (total price for each quantity) of the products scanned by the scanner 2. The price column in Fig. 2 also stores the prices (total price for each quantity) of the products manually input using the input device.

[0036] 2, as indicated by arrows A2a and A2b, the same product X has been manually entered multiple times (twice). Therefore, the information processing device 1 determines that fraud has occurred.

[0037] As explained in the "Consideration" section above, it is assumed that the possibility of the same product X being manually input multiple times is low. Therefore, it is assumed that the product X in the second manual input indicated by arrow A2b is likely to be 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 input product X. Therefore, the information processing device 1 determines that fraud has occurred when the product X is manually input for the second time.

[0038] (Block Diagram) Fig. 3 is a diagram showing an example of a block configuration of the information processing device 1. As shown in Fig. 3, the information processing device 1 has 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 counting unit 11 a, a fraud determination unit 11 b, and an alarm generation unit 11 c. The control unit 11 may implement the functions of the above-mentioned units in accordance with a program stored in the storage unit 12.

[0041] The manual input counting unit 11a counts the number of times that a customer manually inputs product information into the input device.

[0042] The fraud determination unit 11b determines whether or not there has been fraud in the manual input based on the number of times product information for the same product has been manually input. For example, if product information for the same product has been manually input multiple times (for example, twice), the fraud determination unit 11b determines that there has been fraud in the manual input.

[0043] When the fraudulent activity determination unit 11b determines that fraudulent activity has occurred, the alarm generation unit 11c generates alarm information. For example, the alarm generation unit 11c generates image data of an image including text such as "Please manually enter the product name correctly." The image data is sent to the display 5 via the communication unit 13.

[0044] The alarm generation unit 11c also generates, for example, an alarm signal. The alarm signal is sent to a mobile terminal carried by the store clerk via the communication unit 13. The mobile terminal that receives the alarm signal notifies the store clerk of the occurrence of unauthorized manual entry, for example, by sound. Alternatively, the occurrence of unauthorized manual entry may be displayed on a cash register screen or another screen to notify the customer.

[0045] The storage unit 12 stores an operating system (OS) program and application programs to be executed by the control unit 11. For example, the storage unit 12 stores an application program that processes payments at self-checkout registers and monitors shoplifting attempts. The storage unit 12 also stores various data necessary for processing by the control unit 11. The storage unit 12 may be, for example, a solid state drive (SSD), random access memory (RAM), flash memory, read only memory (ROM), and / or a hard disk drive (HDD).

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

[0047] (Operation Flow) FIG. 4 is a flowchart showing an example of the operation of the information processing device 1 in determining whether or not there is any fraudulent activity.

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

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

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

[0051] On the other hand, when it is determined that the product information has been manually input (Yes in S2), the information processing device 1 determines whether the same product has been manually input multiple times (S3).

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

[0053] On the other hand, if the information processing device 1 determines that the same product has been manually entered multiple times (Yes in S3), it determines that fraudulent activity has occurred (S4). For example, as described in Fig. 2, if it determines that product X has been manually entered twice (see arrow A2b in Fig. 2), it determines that fraudulent activity has occurred. If the information processing device 1 determines that fraudulent activity has occurred, it generates alarm information and an alarm signal and proceeds to S1.

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

[0055] (Summary of the First Embodiment) As described above, the information processing device 1 counts the number of times a customer manually inputs information. The information processing device 1 determines whether or not there has been any fraudulent manual input based on the number of times product information for the same product has been manually input. This allows the information processing device 1 to appropriately detect any fraudulent manual input of product information. For example, if product information for the same product has been manually input multiple times, the information processing device 1 determines that there has been any fraudulent manual input, and can appropriately detect any fraudulent manual input of product information.

[0056] (Variation 1) As explained in the above "Consideration," it is assumed that a customer will take the same product from product stand A1a and move it to product stand A1b. Therefore, a customer may manually input the same product repeatedly.

[0057] For example, when purchasing soiled products such as potatoes, a customer may place the products in a plastic bag and then move the product to the product stand A1b. In this case, the customer may manually input the same product repeatedly. For example, a customer purchases five potatoes. Assume that one plastic bag holds three potatoes. In this case, the customer may place three potatoes in the bag and manually input the number (manually inputting the product name "Potato" and the quantity "3"), and then place two potatoes in the bag and manually input the number (manually inputting the product name "Potato" and the quantity "2").

[0058] Additionally, customers who are unfamiliar with using self-checkouts, such as elderly people or customers who rarely use self-checkouts, may repeatedly enter the same items manually.

[0059] Therefore, the information processing device 1 does not determine that manual input performed multiple times in succession is fraudulent behavior.

[0060] Fig. 5 is a diagram illustrating fraudulent activity determination in Variation 1 of the first embodiment. Fig. 5 shows a purchase information DB stored in the storage unit of information processing device 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 therefore description thereof will be omitted.

[0061] In the example of Fig. 5, the same product X is manually input multiple times (twice) in succession, as indicated by arrows A5a and A5b. The information processing device 1 does not determine that fraudulent activity has occurred in response to multiple consecutive manual inputs of the same product X. In other words, the information processing device 1 does not determine that the manual input of product X indicated by arrow A5b in Fig. 5 is fraudulent activity.

[0062] 5 shows an example in which the same product Z is manually input multiple times (twice) in a non-consecutive manner, as indicated by arrows A5c and A5d. The information processing device 1 determines that multiple manual inputs of the same product Z constitute fraudulent activity. That is, the information processing device 1 determines that the manual input of product Z indicated by arrow A5d in FIG. 5 constitutes fraudulent activity.

[0063] Fig. 6 is a flowchart showing an example of the operation of the information processing device 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 assigned the same reference numerals. Note that the flowchart of Fig. 6 adds a process of S11a to the flowchart of Fig. 4. The following describes the processes that differ from those in the flowchart of Fig. 4.

[0064] The information processing device 1 determines in S3 whether the same product has been manually entered multiple times, and if it determines that the same product has been manually entered multiple times (Yes in S3), it determines whether the multiple manual entries are consecutive manual entries (S11a).

[0065] When the information processing device 1 determines that the multiple manual inputs are consecutive manual inputs (Yes in S11a), the process proceeds to S1. For example, as described in FIG. 5, when the information processing device 1 determines that the product X has been manually input consecutively, the process proceeds to S1.

[0066] On the other hand, if the information processing device 1 determines that the multiple manual inputs are not consecutive manual inputs (No in S11a), it determines that fraudulent activity has occurred (S4). For example, as described in Fig. 5, if it determines that product Z has been manually input twice (non-consecutive manual inputs), it determines that fraudulent activity has occurred. If the information processing device 1 determines that fraudulent activity has occurred, it generates alarm information and an alarm signal and proceeds to S1.

[0067] As described above, the information processing device 1 does not determine that manual input performed multiple times in succession is fraudulent, thereby enabling the information processing device 1 to appropriately determine fraudulent activity.

[0068] (Variation 2) Customers who are unfamiliar with using self-checkouts, such as elderly people or customers who rarely use self-checkouts, may manually input product information multiple times. Therefore, the information processing device 1 does not determine that fraud has occurred when a customer who is unfamiliar with using self-checkouts (hereinafter, sometimes referred to as a specific customer) manually inputs product information multiple times.

[0069] The information processing device 1 may determine whether a customer is unfamiliar with using a self-checkout register, for example, based on an image from the camera 3. For example, the information processing device 1 may analyze customer behavior based on a known image analysis program and determine whether a customer is unfamiliar with using a self-checkout register.

[0070] The information processing device 1 may determine the age of a customer based on, for example, an image captured by the camera 3. For example, the information processing device 1 may analyze the appearance of a customer based on a known image analysis program to determine whether the customer is elderly.

[0071] The information processing device 1 may store a facial image of a specific customer in the storage unit 12. For example, the information processing device 1 may store a facial image of a customer in the storage unit 12 at the request of the customer who visits the store. The information processing device 1 may determine the specific customer by comparing the image from the camera 3 with the stored facial image.

[0072] Fig. 7 is a flowchart showing an example of the operation of the information processing device 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 assigned the same reference numerals. Note that the flowchart of Fig. 7 adds a process of S11b to the flowchart of Fig. 4. The following describes the processes that differ from those in the flowchart of Fig. 4.

[0073] The information processing device 1 determines in S3 whether the same product has been manually entered multiple times, and if it determines that the same product has been manually entered multiple times (Yes in S3), it determines whether the customer is a specific customer (S11b).

[0074] If the information processing device 1 determines that the customer is a specific customer (Yes in S11b), the process proceeds to S1. In other words, the information processing device 1 does not determine that multiple manual inputs by a specific customer constitute fraudulent activity.

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

[0076] As described above, the information processing device 1 does not determine that a fraudulent act has been committed when a specific customer manually inputs multiple times. This allows the information processing device 1 to appropriately determine whether a fraudulent act has been committed.

[0077] When the information processing device 1 determines that the customer is a specific customer, the information processing device 1 may display on the display 5 a button image for calling a store clerk.

[0078] Furthermore, the information processing device 1 may determine, for example, based on an image from the camera 3, a customer who needs assistance in using the self-checkout. If the information processing device 1 determines that a customer needs assistance, it may display a button image on the display 5 for calling a store clerk. The information processing device 1 may notify a terminal carried by the store clerk that there is a customer who needs assistance. Note that, if a specific customer is determined to be a specific customer, the store clerk may be notified that the specific customer has visited the store, even if the customer does not touch the button image for calling a store clerk.

[0079] (Variation 3) The upper limit of the number of times that the product can be manually entered may be changed based on the type of product. For example, the information processing device 1 may determine that fraud has occurred when the product X is manually entered twice, and may determine that fraud has occurred when the product Y is manually entered three times.

[0080] The upper limit number of times may be arbitrarily set by, for example, a store clerk. For example, in the case of products to be packed in plastic bags, multiple products are packed in one bag, and one manual input is often sufficient. Therefore, the upper limit number of times may be set low for products that are likely to be bagged, and high for products that are unlikely to be bagged. Of course, depending on the product, the upper limit number of times may be set high even for products that are likely to be bagged, and the upper limit number of times may be set low even for products that are unlikely to be bagged. The upper limit number of times is stored in the memory unit 12.

[0081] Fig. 8 is a diagram illustrating fraudulent activity determination in Modification 3 of the first embodiment. Fig. 8 shows a purchase information DB stored in the storage unit of information processing device 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 therefore description thereof will be omitted.

[0082] In the example of Fig. 8, the upper limit of the number of times that product X without a barcode can be manually entered is set to 2. The upper limit of the number of times that product Z without a barcode can be manually entered is set to 1.

[0083] As shown by arrows A8a and A8b, product X without a barcode is manually entered multiple times (twice). Because the upper limit for the number of times product X can be manually entered is two, the information processing device 1 does not determine that fraud has occurred with the multiple manual entries of product X. In other words, the information processing device 1 does not determine that fraud has occurred with the manual entry of product X shown by arrow A8b in FIG. 8.

[0084] As indicated by arrows A8c and A8d, product Z without a barcode has been manually entered multiple times (twice). Because the upper limit for the number of times product Z can be manually entered is one, the information processing device 1 determines that fraud has been committed with respect to the multiple manual entries of product Z. In other words, the information processing device 1 determines that the manual entry of product Z indicated by arrow A8d in FIG. 8 is fraud.

[0085] Fig. 9 is a flowchart showing an example of the operation 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 assigned the same reference numerals. Note that the flowchart of Fig. 9 adds a process of S11c to the flowchart of Fig. 4. The following describes the processes that differ from those in the flowchart of Fig. 4.

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

[0087] If the information processing device 1 determines that the number of manual inputs is not greater than the upper limit (No in S11c), the information processing device 1 proceeds to S1. For example, as described in Fig. 8, the upper limit for manual inputs for product X is two times. Therefore, even if the information processing device 1 determines that product X has been manually input twice, as indicated by arrow A8b, the information processing device 1 does not determine that fraud has occurred and proceeds to S1.

[0088] On the other hand, if the information processing device 1 determines that the number of manual inputs is greater than the upper limit (Yes in S11c), it determines that fraudulent activity has been committed (S4). For example, as described in Fig. 8, since the upper limit for manual input for product Z is one time, the information processing device 1 determines that fraudulent activity has been committed if it determines that product Z has been manually input twice, as shown by arrow A8d.

[0089] As described above, the information processing device 1 determines that fraudulent activity has occurred when the number of manual inputs performed multiple times exceeds the upper limit. This allows the information processing device 1 to appropriately determine whether fraudulent activity has occurred.

[0090] (Variation 4) It is assumed that manual entry fraudulent acts often involve manually entering a cheaper product in comparison with a more expensive product. For example, a customer may manually enter a fruit that costs y yen (y<x) even though the fruit actually costs x yen.

[0091] Therefore, the information processing device 1 determines that fraud has occurred if a product with a low unit price is manually entered multiple times. For example, the information processing device 1 determines that fraud has occurred if the unit price of the product manually entered multiple times is equal to or less than a predetermined amount (determined amount). The determined amount is stored in the storage unit 12. The determined amount may be set by a store clerk.

[0092] Fig. 10 is a diagram illustrating fraudulent activity determination in Variation 4 of the first embodiment. Fig. 10 shows a purchase information DB stored in the storage unit of information processing device 1. Each column of the purchase information DB shown in Fig. 10 is the same as each column of the purchase information DB described in Fig. 2, and therefore description thereof will be omitted.

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

[0094] As shown by arrows A10a and A10b, product X without a barcode has been manually entered twice. Because the unit price x of product X is greater than the determined amount, the information processing device 1 does not determine that fraud has occurred with respect to the multiple manual entries of product X. In other words, the information processing device 1 does not determine that fraud has occurred with respect to 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. Because the unit price z of product Z is smaller than the determined amount, the information processing device 1 determines that fraud has been committed with respect to the multiple manual entries of product Z. In other words, the information processing device 1 determines that fraud has been committed with respect to the manual entry of product Z indicated by arrow A10d in FIG. 10 .

[0096] Fig. 11 is a flowchart showing an example of the operation 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 assigned the same reference numerals. Note that the flowchart of Fig. 11 adds a process of S11d to the flowchart of Fig. 4. The following describes the processes that differ from those in the flowchart of Fig. 4.

[0097] The information processing device 1 determines in S3 whether the same product has been manually entered multiple times, and if it determines that the same product has been manually entered multiple times (Yes in S3), it determines whether the unit price of the manually entered product is less than the determined amount (S11d).

[0098] If the information processing device 1 determines that the unit price of the product that has been manually input multiple times is not equal to or less than the determined amount (No in S11d), the information processing device 1 proceeds to S1. For example, as described in Fig. 10, since the unit price x of product X that has been manually input twice is greater than the determined amount, the information processing device 1 does not determine that fraud has occurred even if it determines that product X has been manually input twice, as shown by arrow A10b, and proceeds to S1.

[0099] On the other hand, if the information processing device 1 determines that the unit price of the product that has been manually input multiple times is equal to or less than the determined amount (Yes in S11d), it determines that fraudulent activity has occurred (S4). For example, as described in Fig. 10, since the unit price z of product Z that has been manually input twice is equal to or less than the determined amount, the information processing device 1 determines that fraudulent activity has occurred when it determines that product Z has been manually input twice, as shown by arrow A10d.

[0100] As described above, the information processing device 1 determines that fraud has occurred if the unit price of a product that has been manually input multiple times is equal to or less than the determined amount. This allows the information processing device 1 to appropriately determine whether fraud has occurred.

[0101] (Variation 5) The technique in the first embodiment may be applied to products with barcodes. For example, in the case of products for which the barcode can be scanned and the quantity can be input, the technique in the first embodiment may be applied.

[0102] Second Embodiment In a second embodiment, the method of detecting fraudulent activity in the input of multiple products (product registration) is changed depending on whether multiple products have been manually input.

[0103] For example, if multiple products are not manually input using an input device such as a touch panel on the display 5, in other words, if multiple products are scanned using the scanner 2, the information processing device 1 performs a fraudulent activity determination using the weight sensor 4b.

[0104] On the other hand, when multiple products are manually input, the information processing device 1 performs fraudulent activity determination without using the weight sensor 4b.

[0105] More specifically, when multiple products have not been manually input, the information processing device 1 determines whether fraud has occurred based on whether the number of times the multiple products have been scanned by the scanner 2 matches the number of times the weight of the product stand A1b has increased. If the number of times the products have been scanned by the scanner 2 is less than the number of times the weight of the product stand A1b has increased, the information processing device 1 determines that fraud has occurred, assuming that the products have been moved from the product stand A1a to the product stand A1b without being scanned by the scanner 2.

[0106] On the other hand, when multiple products are manually input, the information processing device 1 determines fraudulent activity based on object detection using images from the camera 3. For example, the information processing device 1 determines the products and number of products removed from the product stand A1a based on images from the camera 3, and compares these with the products and number manually input by the customer into the input device to determine fraudulent activity. When the products and / or number detected based on the images from the camera 3 do not match the products and / or number manually input by the customer, the information processing device 1 determines that fraudulent activity has occurred, assuming that fraudulent manual input has been performed.

[0107] The system configuration in the second embodiment is the same as that in FIG. 1 , and therefore a description thereof will be omitted. 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 multiple items without barcodes have been entered, and changes the fraud detection method based on the determination result. For example, when multiple items have been manually entered, the control unit 11 performs a fraud detection without using the weight sensor 4b, such as an image from the camera 3, whereas when multiple items have not been manually entered, the control unit 11 performs a fraud detection using the weight sensor 4b. Known technologies, such as artificial intelligence, may be applied to the detection of items and the number of items based on the image from the camera 3.

[0108] (Operation Flow) FIG. 12 is a flowchart showing an example of the operation of the information processing device 1 in determining whether or not there is any fraudulent activity.

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

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

[0111] If the information processing device 1 determines that multiple barcode-less products have not been input (No in S22), that is, if it determines that multiple products have been scanned using the scanner 2, it executes a fraud detection process using the weight sensor 4b (S23).

[0112] For example, the information processing device 1 detects whether or not fraudulent activity has occurred based on whether the number of times multiple products are scanned by the scanner 2 matches the number of times the weight of the product stand A1b increases. After executing the fraudulent activity detection process of S23, the information processing device 1 transitions to S1. Note that if fraudulent activity is detected during the execution of the fraudulent activity detection process of S23, the information processing device 1 generates alarm information and an alarm signal, and transitions to S1.

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

[0114] For example, the information processing device 1 determines the products and the number of products removed from the product stand A1a based on the image from the camera 3, and detects fraudulent activity by determining whether the products and the number match the products and the number manually entered by the customer into the input device. After executing the fraudulent activity detection process of S24, the information processing device 1 shifts the process to S1. Note that if the information processing device 1 detects fraudulent activity during the execution of the fraudulent activity detection process of S24, it generates alarm information and an alarm signal, and shifts the process to S1.

[0115] Note that the information processing device 1 may execute the fraudulent activity detection process described in the first embodiment in the process of S24. The information processing device 1 may determine that fraudulent activity has occurred when fraudulent activity is detected in both the fraudulent activity detection process described in the first embodiment and the fraudulent activity detection process using an image from the camera 3. Alternatively, the information processing device 1 may determine that fraudulent activity has occurred when fraudulent activity is detected in at least one of the fraudulent activity detection process described in the first embodiment and the fraudulent activity detection process using an image from the camera 3.

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

[0117] (Summary of the Second Embodiment) As described above, when manual input is performed on the input device, the information processing device 1 compares the product information acquired based on the image from the camera 3 with the manually input product information, and determines whether or not there has been any fraudulent activity in the manual input. This allows the information processing device 1 to appropriately detect any fraudulent activity in the manual input of product information.

[0118] (Variant 1) If the information processing device 1 determines that multiple products without barcodes have been input (see Yes in S22 of Figure 12), it may use the weight sensor 4b to calculate the total weight of the products without barcodes and perform fraud detection processing.

[0119] For example, the information processing device 1 pre-stores the weight (reference weight) of each non-barcoded product in the memory unit 12. The information processing device 1 calculates the total weight of multiple manually input non-barcoded products based on the reference weight in the memory unit 12. The information processing device 1 determines that fraud has occurred if the calculated total weight is less than the total weight of the non-barcoded products placed on the product stand A1b, calculated based on a signal from the weight sensor 4b. In other words, if a customer manually inputs an insufficient number of non-barcoded products, the information processing device 1 determines that fraud has occurred.

[0120] As described above, the information processing device 1 detects fraudulent behavior by a customer using the weight sensor 4b. This allows the information processing device 1 to detect fraudulent behavior by a customer without using the camera 3, thereby reducing costs.

[0121] As will be explained in the third embodiment, the reference weight may have a range.

[0122] (Variant 2) If the information processing device 1 determines that multiple products without barcodes have been input (see Yes in S22 of Figure 12), it may perform fraud detection processing using the number of weight increases in the weight sensor 4b and the number of products without barcodes input by the customer into the input device.

[0123] For example, the information processing device 1 determines that fraud has occurred if the number of weight increases detected by the weight sensor 4b is greater than the number of non-barcoded products input by the customer into the input device. In other words, if the customer manually inputs an insufficient number of non-barcoded products, the information processing device 1 determines that fraud has occurred.

[0124] It is also possible to determine that fraud has occurred when the number of weight increases detected by weight sensor 4b is smaller than the number of non-barcoded products input by the customer into the input device. However, if a customer places multiple non-barcoded products in a bag or the like and moves them all together, the number of weight increases will be smaller than the number of non-barcoded products even if fraud has not occurred. Therefore, if it is determined that fraud has occurred even when the number of weight increases is smaller than the number of non-barcoded products, the notification may be configured to be given in a way that takes care not to damage the customer's image, such as by notifying only store staff.

[0125] As described above, the information processing device 1 detects fraudulent behavior by a customer using the weight sensor 4b. This allows the information processing device 1 to detect fraudulent behavior by a customer without using the camera 3, thereby reducing costs.

[0126] (Variant 3) If the information processing device 1 determines that multiple products without barcodes have been input (see Yes in S22 of Figure 12), it may perform fraud detection processing using weight values ​​based on signals from weight sensors 4a and 4b.

[0127] For example, the information processing device 1 determines that fraud has occurred if the weight value detected by weight sensor 4a decreases and the weight value detected by weight sensor 4b does not increase by the weight value detected by weight sensor 4a. In other words, the information processing device 1 determines that fraud has occurred if a customer does not place a product that they have taken from product stand A1a on product stand A1b.

[0128] As described above, the information processing device 1 detects fraudulent behavior by customers using the weight sensors 4 a and 4 b. This allows the information processing device 1 to detect fraudulent behavior by customers without using the camera 3, thereby reducing costs.

[0129] (Variation 4) After the customer manually inputs the information, if the information processing device 1 does not detect any products in the product detection based on images from the camera 3 until the next product is scanned by the scanner 2, and the weight value based on the weight sensor 4b increases multiple times, the information processing device 1 does not determine that shoplifting has occurred. In other words, the information processing device 1 does not determine that shoplifting has occurred when products without barcodes are placed on the product stand A1b in multiple installments.

[0130] (Variation 5) A weight sensor may be provided in the cart. The weight sensor provided in 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] If the cart is equipped with a weight sensor, the customer can take the product out of the cart and scan it with the scanner 2 or manually input the weight without placing it on the product stand A1a.

[0132] In other words, the configuration of this modified example can be said to be a configuration in which the product stand A1a is arranged on a 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 treated without distinction. For example, when a product is removed from the product stand A1a provided on the cart and moved to the product stand A1a provided on the stand A2, the product is moved between the cart and the stand A2, but the product may be treated as having been returned to the product stand A1a without distinguishing between the cart and the stand A2. In addition, since it is anticipated that some customers may use baskets or the like instead of carts, a weight sensor may be provided on the basket or the like.

[0134] As described in the first modification of the second embodiment, the weight (reference weight) of each barcode-less product 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] For example, the information processing device 1 may perform training while a customer is actually using the self-checkout register. For example, the information processing device 1 may calculate (train) the reference weight of a product without a barcode when a customer moves the product without a barcode from product stand A1a to product stand A1b. Alternatively, training may be performed by a store employee actually using the self-checkout register during a time period such as before the store opens.

[0136] More specifically, when one non-barcoded product X is removed from product stand A1a and the weight value measured by weight sensor 4a decreases, the information processing device 1 may use the decreased weight value as the reference weight of the non-barcoded product X. Alternatively, when one non-barcoded product X is placed on product stand A1b and the weight value measured by weight sensor 4b increases, the information processing device 1 may use the increased weight value as the reference weight of the non-barcoded product X. Alternatively, the information processing device 1 may use the average of the reference weight obtained from weight sensor 4a and the reference weight obtained from weight sensor 4b as the reference weight of the non-barcoded product.

[0137] The information processing device 1 may use the average of the reference weights for a specific period, such as the morning, as the reference weight. For example, even for the same apples, the production location may change depending on the day, which may change the reference weight. Therefore, it is preferable for the information processing device 1 to perform training for the reference weight in an early time period of the day, such as the morning. The average is an example, and other statistical values, such as the median, may also be used as the reference weight.

[0138] Furthermore, a longer training period can reduce the impact of outliers on the reference weight, while a shorter training period can allow longer fraud detection processing using the latest reference weight. Therefore, the specified period may be made shorter or longer depending on whether priority is given to the accuracy of the reference weight or the length of time over which fraud detection processing can be performed.

[0139] Furthermore, during times when training at the reference weight has not been sufficiently performed, such as immediately after opening, a past reference weight or a reference weight set by the user may be used as the reference weight.

[0140] The information processing device 1 may set a range for the reference weight for products without barcodes that have individual differences in weight. The information processing device 1 may narrow the range of the reference weight as training time passes.

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

[0142] The system configuration in the third embodiment is the same as that in Fig. 1, and therefore a description thereof will be omitted. The block configuration in the third embodiment is also the same as that in Fig. 3, but differs in the function of the control unit 11. The control unit 11 has a training unit that calculates a reference weight and stores it in the memory unit 12.

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

[0144] The information processing device 1 determines whether the customer has scanned all of the products placed on the product stand A1a with the scanner 2 (S31). The information processing device 1 may determine whether all of the products placed on the product stand A1a have been scanned with the scanner 2, for example, based on a signal from the weight sensor 4a.

[0145] If the information processing device 1 determines that the customer has not scanned all of the products placed on the product stand A1a with the scanner 2 (No in S31), it determines whether or not products without barcodes have been manually entered (S32).

[0146] If the information processing device 1 determines that a product without a barcode has been manually entered (Yes in S32), it collects and averages the weight values ​​from the weight sensors 4a and 4b (S33). The information processing device 1 stores the averaged weight value, i.e., the reference weight of the product without a barcode, in the memory unit 12 and returns to S31.

[0147] If the information processing device 1 determines that a product without a barcode has not been manually entered (Yes in S32), that is, if it determines that the product has been scanned using the scanner 2, it determines whether the scanned product is an in-store product (S34).

[0148] If 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 memory unit 12, and proceeds to S31.

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

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

[0151] As described above, the information processing device 1 collects and averages the weights of individual products from the weight sensors during the training period to calculate the reference weight. This enables the information processing device 1 to properly calculate the weights of products without barcodes and properly detect fraudulent behavior in the manual input of product information.

[0152] Although the embodiments have been described above with reference to the drawings, the present disclosure is not limited to such examples. It is clear that a person skilled in the art can conceive of various modifications or alterations within the scope of the claims. It is understood that such modifications or alterations also fall within the technical scope of the present disclosure. Furthermore, the components in the embodiments may be combined in any manner without departing from the spirit of the present disclosure. The embodiments may be combined in any manner. The modified examples may be combined in any manner.

[0153] In the above-described embodiments, the notation "... part" used for each component may be replaced with other notations such as "... circuit," "... assembly," "... device," "... unit," or "... module."

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

[0155] The integrated circuit method is not limited to LSI, and may be realized by a dedicated circuit, a general-purpose processor, or a dedicated processor. Also, a field programmable gate array (FPGA) that can be programmed after LSI manufacturing, or a reconfigurable processor that can reconfigure the connections and settings of circuit cells within 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 can replace LSI emerges due to advances in semiconductor technology or other derivative technologies, it is natural that such technology may be used to integrate functional blocks. The application of biotechnology, etc. is also a possibility.

[0157] The disclosures of the specifications, drawings and abstracts contained in Japanese patent applications No. 2023-198191 filed on November 22, 2023 and No. 2024-020362 filed on February 14, 2024 are incorporated herein by reference in their entirety.

[0158] The present disclosure is useful for detecting manual input fraud at self-checkout registers.

[0159] REFERENCE SIGNS LIST 1 Information processing device 2, 2a, 2b Scanner 3 Camera 4a, 4b Weight sensor 5 Display A4a, A4b Product stand

Claims

1. An information processing device having: a counting unit that allows a customer to manually input product information for a product that does not have a product code into an input device and counts the number of times said manual input is made; and 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 for the same product is manually input.

2. The information processing device according to claim 1, wherein the determination unit determines that there has been fraudulent activity in the manual input based on whether product information for the same product has been manually input multiple times.

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

4. The information processing device according to claim 2, wherein the determination unit determines that there has been fraudulent activity in the manual input if product information for the same product is entered multiple times non-consecutively, and does not determine that there has been fraudulent activity in the manual input if product information for the same product is entered multiple times consecutively.

5. The information processing device according to claim 2, wherein the determination unit further determines, when product information for 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.

6. The information processing device according to claim 5, wherein 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.

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

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

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

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

Images