Commodity processing device

Abstract

The commodity processing device according to one embodiment can avoid poor operability even when the work of successively placing and taking down the same kind of commodities in a measuring vessel is repeated, and comprises a camera for shooting the commodities placed in a commodity placing part and generating a shot image; a display unit that displays various kinds of information; a control unit that estimates a candidate of the product on the basis of the captured image and displays the candidate of the product on a display unit; and a label printer that prints product information relating to a product on a label, and in a case where one product is designated by an operation of an operator on the basis of the product candidates displayed by the display unit, the control unit causes the label printer to print product information relating to the designated one product. When it is determined that a candidate of a product estimated on the basis of a captured image of another product is the same as the one product after the one product is designated, the label printer is caused to print product information related to the another product using product information related to the one product.

Description

TECHNICAL FIELD

[0001] The present application relates to a commodity processing apparatus. BACKGROUND

[0002] As disclosed in Patent Literature 1, a commodity processing apparatus equipped with AI has been known in the past.

[0003] In the related commodity processing apparatus, when an operator places a commodity in a weighing pan, the AI specifies the related commodity almost simultaneously (about 0.5 seconds) with determining the weight of the commodity, and displays the commodity information of the related commodity on a display section.

[0004] Next, if the operator takes the commodity on the weighing pan away, the control section takes this as a trigger to cause the label printer to issue a price tag.

[0005] Here, in the related commodity processing apparatus, the AI sequentially displays the candidates of the commodity in order from high to low in terms of probability in the case of inferring the commodity, so even if the inference of the AI is wrong, the operator can issue the price tag of the correct commodity by selecting the correct commodity from the candidates of the related commodity and taking the commodity from the weighing pan.

[0006] The related commodity processing apparatus is a scale of a type that places a commodity inserted into a container in a weighing pan to perform pricing, so there is no problem if the operation is performed according to the procedure, but in the case where the related commodity processing apparatus is brought into the back office and repeatedly performs the operation of placing a large number of the same commodity in the weighing pan and taking it away in succession to perform pricing, there can be a problem.

[0007] For example, in the case of an automatic mode that automatically issues a price tag if the loaded commodity is taken away from the weighing pan, if the commodity is taken away from the weighing pan without confirming that the commodity name specified by the AI is wrong, there is a problem point that a price tag of an incorrect commodity name is issued.

[0008] In order to address the related problem point, in the related commodity processing apparatus, a manual mode is provided in which a price tag is issued only when a print key is operated, and is configured to display the commodity name specified by the AI on the display screen in the case where the manual mode is switched, and if the operator confirms this and presses the print key, or selects the correct commodity from the commodity list and operates the print key, a price tag is issued.

[0009] Patent Literature 1: Japanese Patent Application Publication No. 2023-136801

[0010] However, in the above-described commodity processing apparatus, there is a problem point that in the case where the operation of placing the same kind of commodity in the weighing pan and taking it away in succession is repeatedly performed, the print key must be operated every time, so the operability is poor.

[0011] In addition, in such a manual mode, automatic mode, there is a problem that in a case where a correct product must be selected from among the products displayed in the list, even if the same kind of product is placed on the weighing dish next, the correct product must be similarly selected from among the products displayed in the list, and thus in a case where the same kind of product is weighed and priced in succession, the product selection operation is tedious each time before the learning completed model is updated. SUMMARY

[0012] Therefore, the present application was accomplished in view of the above technical problems, and aims to provide a product handling device that can avoid poor operability even in a case where the operation of placing and removing the same kind of product on and from the weighing dish is repeated.

[0013] A product handling device according to an embodiment includes a camera that images a product placed on a product placement portion and generates an image, a display portion that displays various information, a control portion that infers a candidate of the product based on the image and causes the display portion to display the candidate, and a label printer that prints product information related to the product on a label, wherein, in a case where one product is specified by an operator's operation based on the candidate displayed by the display portion, the control portion causes the label printer to print product information related to the specified one product, and wherein, in a case where the control portion determines that a candidate inferred based on an image of another product is the same as the one product after the one product is specified, the control portion causes the label printer to print product information related to the another product using product information related to the one product.

[0014] EFFECT OF THE INVENTION

[0015] According to the present application, a product handling device that can avoid poor operability even in a case where the operation of placing and removing the same kind of product on and from the weighing dish is repeated can be provided. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 FIG. 1 is a diagram showing one example of the overall configuration of a product handling device 1 according to a first embodiment.

[0017] Figure 2 FIG. 2 is a diagram showing one example of a display screen of a display portion 12 of the product handling device 1 according to the first embodiment. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present application will be described in detail below with reference to the accompanying drawings. Note that like or similar components in the drawings are designated by like reference numerals, and description thereof will not be repeated. It should be noted that the drawings are schematic and the ratios of the sizes of the respective elements, etc. are not necessarily the same as those in reality. Therefore, specific sizes, etc. should be judged in light of the following description. Also, even in the drawings, there can be parts where the dimensional relationship, the ratio, etc. are different from one another. In this specification and the drawings, for elements that have substantially the same function or constitute, the same reference numerals are applied, and repeated description is omitted. Also, illustration of elements that are not directly related to the present application is omitted.

[0019] (First Embodiment)

[0020] Next, the preferred embodiments of the present application will be described in detail with reference to the accompanying drawings. Note that like or similar components in the drawings are designated by like reference numerals, and description thereof will not be repeated. It should be noted that the drawings are schematic and the ratios of the sizes of the respective elements, etc. are not necessarily the same as those in reality. Therefore, specific sizes, etc. should be judged in light of the following description. Also, even in the drawings, there can be parts where the dimensional relationship, the ratio, etc. are different from one another. In this specification and the drawings, for elements that have substantially the same function or constitute, the same reference numerals are applied, and repeated description is omitted. Also, illustration of elements that are not directly related to the present application is omitted. Figures 1-2 The commodity processing apparatus 1 according to the first embodiment of the present application will be described. Figure 1 is a view showing one example of the overall configuration of the commodity processing apparatus 1 according to the present embodiment, Figure 2 is a view showing one example of the display screen of the display section 12 of the commodity processing apparatus 1 according to the present embodiment.

[0021] As shown in Figure 1 , the commodity processing apparatus 1 according to the present embodiment is provided with a camera 11, a display section 12, a control section 13, and a label printer 14.

[0022] As shown in Figure 1 , the camera 11 is housed in a light shield cover and takes an image of a commodity 100 placed on a commodity placement section 10 from above and generates a captured image.

[0023] The display section 12 displays various information. As shown in Figure 1 and Figure 2 , the display section 12 displays a candidate C of a commodity that is inferred on a display screen (display) 12D in response to an instruction from the control section 13.

[0024] The label printer 14 prints commodity information related to a commodity on a label. For example, the commodity information includes a commodity name, a price, a processing date and time, an expiration date, a weight of the commodity, and the like.

[0025] The control section 13 infers a candidate C of a commodity based on a captured image taken by the camera 11 and causes the display section 12 to display the candidate C of the commodity that is inferred.

[0026] For example, the control section 13 stores a learned model with respect to each of the products 100, and uses the model to infer the product candidates C from the captured image. Alternatively, the product candidates C can be inferred in cooperation with a learned model stored in a cloud server (not shown). In the relevant case, the control section 13 transmits the captured image to the cloud server. The cloud server infers the product candidates C based on the captured image acquired from the control section 13 and the stored learned model, and transmits the product candidates C to the control section 13.

[0027] Here, the cloud server can also transmit the respective inference accuracies of the product candidates C to the control section 13. In the relevant case, the control section 13 can also instruct the display section 12 to display the product candidates C from top to bottom in order of the relevant inference accuracies from high to low.

[0028] In addition, the cloud server periodically performs machine learning using captured images of products and product information (training data), and updates the learned model.

[0029] In a case where one product is specified by an operator's operation based on the product candidates C displayed by the display section 12, the control section 13 causes the label printer 14 to print product information related to the specified one product.

[0030] In addition, the control section 13, in a case where it is determined that a candidate inferred based on a captured image of another product is the same as the one product after the one product is specified, causes the label printer 14 to print product information related to the another product using product information related to the one product.

[0031] Hereinafter, one example of the operation of the product processing apparatus 1 when printing product information on a label will be described using (a) of Figure 2 and (b) of Figure 2 .

[0032] First, when the operator places the first product 100 (one product) on the product placement section 10, the camera 11 captures the product 100, and inputs the captured image thereof to the control section 13. Next, the control section 13 inputs the captured image to the learned model to infer the product candidates C, and displays the inference result as the product candidates C on the display screen 12D of the display section 12. Here, the inference result is displayed in descending order from high to low in probability, and thus, in the example of (a) of Figure 2 , "stir-fried vegetables C1" is highlighted as the product with the highest probability among the product candidates C at the top.

[0033] Second, when the operator determines that the first item of the product 100 placed on the product placement section 10 is "stir-fried vegetables Cl" and that it is consistent with "stir-fried vegetables Cl" inferred by the control section 13, the product 100 is removed from the product placement section 10 in the automatic mode, and the print key K is operated in the manual mode. Then, the control section 13 determines the first item of the product 100 as "stir-fried vegetables Cl", and then calculates the price based on the weight of the product 100 placed on the product placement section 10.

[0034] Third, the control section 13 reads the product information of the determined "stir-fried vegetables Cl" from a product master not shown, and sets it on the label printer 14 together with the weight and the price. Thus, the label printer 14 prints the product information and the weight and the price related to "stir-fried vegetables Cl" on a label to issue it.

[0035] Fourth, the operator takes the issued label and attaches it to the product 100, and then places the second item of the product 100 (another product) on the product placement section 10. Then, the imaging image of the product 100 acquired by the camera 11 is input to the control section 13, and at the same time, the weighing of the second item of the product 100 is performed.

[0036] Fifth, the control section 13 infers the candidate C of the product based on the input imaging image. In this case, when the inferred second item of the product 100 is "stir-fried vegetables Cl" which is the same as the first item of the product 100, the control section 13 directly uses the product information related to the first item of the product 100 (one product) to cause the label printer 14 to print the product information related to the second item of the product 100 (another product).

[0037] Specifically, because the product information related to the first item of the product 100 has already been set on the label printer 14, the control section 13 calculates the price based on the weight of the second item of the product 100 newly placed on the product placement section 10, and sets the calculated price and the newly acquired weight as the print information of the second item of the product on the label printer 14.

[0038] Sixth, the label printer 14 adds the weight and the price related to the second item of the product 100 newly set to the product information of "stir-fried vegetables Cl" related to the first item of the product 100 (one product) already set and prints it on a label. In the related case, even in the manual mode, the operator can issue the label without operating (pressing) the print key.

[0039] Note that, in the second operation, in the case where the operator determines that the product 100 placed on the product placement section 10 is not "stir-fried vegetables Cl" but "potato salad C2" shown in (b) of the above (b), Figure 2 the operator selectsFigure 2 After "Potato salad C2" of (b) is selected, the product 100 is removed from the product placement section 10 in the automatic mode, and when the print key K is operated in the manual mode, the product 100 placed on the product placement section 10 is determined to be "Potato salad C2".

[0040] Then, when the second product 100 placed on the product placement section 10 is also "Potato salad C2", as described above, the control section 13 directly issues the label on which "Potato salad C2" is printed, which is attached to the second product 100.

[0041] In addition, when the first product 100 (one product) is "Sauteed vegetables Cl", and the candidate C of the product inferred on the basis of the captured image of the second product 100 (another product) is "Potato salad C2", and the case is determined by the operation of the operator, the control section 13 reads out the product information related to the potato salad C2 from the product master, and sets it to the label printer 14, and then, if the second product is removed from the product placement section 10, or the print key is operated (pressed), the control section 13 calculates the weight and the price of the second product 100, and sets it to the label printer 14.

[0042] According to the above-described configuration, after the first product 100 on the product placement section 10 is specified, and the product information related to the specified first product 100 is printed on the label, when the second product 100 placed on the product placement section 10 is the same kind of product as the first product 100, the same kind of label is automatically issued, and therefore, the same kind of product 100 can be placed in succession on the product placement section 10 to repeatedly issue the price tag.

[0043] In addition, the control section 13 can compare the feature amount extracted from the captured image of the one product with the feature amount extracted from the captured image of the another product placed on the second product, to determine whether the one product and the another product are the same, after the one product (one product) is specified using the learned model.

[0044] According to the related configuration, even in the case where the inference of the product using the learned model is not satisfactory, for example, as shown in (b) of Figure 2 by storing the feature amount of the correct product when the correct product is specified by the product selection, it is possible to directly determine the difference between the two by comparing the stored feature amount of the correct product with the feature amount acquired from the another product placed later.

[0045] According to the present embodiment, even in a case where the same kind of goods are sequentially placed on and removed from the weighing dish repeatedly, the price tag can be sequentially issued, and the pricing operation difference of the same kind of goods can be avoided.

[0046] While the present application has been described in detail using the above-described embodiments, the present application is obviously not limited to the embodiments described in the present specification. The present application can be implemented as modifications and changes without departing from the spirit and scope of the present application defined by the recitations of the claims. Therefore, the recitations of the present specification are intended to be illustrative, and do not have any limiting meaning on the present application.

[0047] Explanation of Reference Signs

[0048] 1: merchandise processing apparatus; 10: merchandise placement portion; 11: camera; 12: display portion; 12D: display screen; 13: control portion; 14: label printer; 100: merchandise; C: candidate of merchandise; K: print key.

Claims

1. A commodity processing apparatus, comprising: The camera captures images of the goods placed in the goods display area and generates captured images; The display section shows various information; The control unit infers candidate products based on the captured images and causes the display unit to display the candidate products; as well as The label printer prints product information related to the product onto the label. When an operator selects an item based on the candidates displayed on the display unit, the control unit instructs the label printer to print product information related to the selected item. If, after a product is designated, the control unit determines that a candidate product inferred from an image of another product is the same as the product in question, it uses product information related to the product in question to cause the label printer to print product information related to the other product.

2. The commodity processing apparatus according to claim 1, wherein, The control unit compares the feature values ​​extracted from the camera image of the product with the feature values ​​extracted from the camera image of the other product to determine whether the candidate inferred from the camera image of the other product is the same as the product.

3. The commodity processing apparatus according to claim 1, wherein, Even in a mode where the print button needs to be operated to print product information related to the product on the label, if the control unit determines that the candidate inferred from the captured image of the other product is the same as the product, the label printer will print product information related to the other product without operating the print button.

Images