Product processing equipment

Abstract

Even when repeatedly placing and removing the same type of product from a weighing pan, the goal is to avoid a deterioration in work efficiency. [Solution] The product processing device 1 according to one embodiment includes a camera 11 that captures images of products 100 placed on a product placement unit 10 and generates captured images, a display unit 12 that displays various information, a control unit 13 that estimates product candidates C based on the captured images and displays the product candidates C on the display unit 12, and a label printer 14 that prints product information related to product 100 on a label. The control unit 13, based on the product candidates C displayed on the display unit 12, causes the label printer 14 to print product information related to the identified product when a product is identified by the operator's operation, and after a product has been identified, if it is determined that a product candidate C estimated based on a captured image of another product is the same as the first product, it uses the product information related to the first product to print product information related to the other product on the label printer 14.

Description

Technical Field

[0001] The present invention relates to a merchandise processing apparatus.

Background Art

[0002] As disclosed in Patent Document 1, conventionally, a merchandise processing apparatus equipped with AI has been known.

[0003] In such a merchandise processing apparatus, when an operator places a product on a weighing pan, the AI identifies the product almost simultaneously (about 0.5 seconds) with the determination of the weight of the product, and the product information of the product is displayed on the display unit.

[0004] Subsequently, when the operator removes the product on the weighing pan, the control unit uses this as a trigger to cause the label printer to issue a priced label.

[0005] Here, in such a merchandise processing apparatus, when the AI estimates a product, it lists the product candidates in order from the ones with the highest probability. So, even if the AI's estimation is incorrect, if the operator selects the correct product from among the candidates of the product and then removes the product from the weighing pan, a priced label for the selected product will be issued.

[0006] Such a merchandise processing apparatus is a scale that weighs and prices products packed in containers by placing them on a weighing pan. So, if the work is done according to the procedure, there will be no problem. However, when such a merchandise processing apparatus is brought into the backyard and the operation of repeatedly placing and removing a large number of the same type of products on the weighing pan for pricing is carried out, problems may occur.

[0007] For example, in the case of the automatic mode where a priced label is automatically issued when the loaded product is removed from the weighing pan, if the product is removed from the weighing pan without confirming that the product name identified by the AI is incorrect, there is a problem that a priced label with an incorrect product name will be issued.

[0008] To address these issues, the product processing device is equipped with a manual mode that issues a price label when a print key is operated. When this manual mode is activated, the product name identified by the AI ​​is displayed on the screen, and a price label is issued when the operator confirms this and presses the print key, or when the operator selects the correct product from the product list and then operates the print key. [Prior art documents] [Patent Documents]

[0009] [Patent Document 1] Japanese Patent Publication No. 2023-136801 [Overview of the project] [Problems that the invention aims to solve]

[0010] However, with the aforementioned product processing device, when repeatedly placing and removing the same type of product from the weighing pan, the printing key had to be operated each time, resulting in poor work efficiency.

[0011] Furthermore, in both manual and automatic modes, if the correct product must be selected from a list of displayed products, then the same type of product must be selected again when placing it on the weighing pan. This creates a problem where, when weighing and pricing the same type of product repeatedly, the product selection process becomes cumbersome each time until the trained model is updated.

[0012] Therefore, the present invention has been made in view of the above problems, and aims to provide a product processing device that can avoid deterioration of work efficiency even when the same type of product is repeatedly placed on and removed from a weighing tray. [Means for solving the problem]

[0013] One embodiment of the product processing apparatus comprises a camera that captures images of products placed on a product placement unit and generates captured images, a display unit that displays various information, a control unit that estimates candidate products based on the captured images and displays the candidates on the display unit, and a label printer that prints product information relating to the products on a label. The gist of the apparatus is that, based on the candidates displayed on the display unit, if a product is identified by the operator, the control unit causes the label printer to print product information relating to the identified product, and after the product has been identified, if it is determined that a candidate estimated based on the captured image of another product is the same as the first product, the apparatus uses the product information relating to the first product to print product information relating to the other product on the label printer. [Effects of the Invention]

[0014] According to the present invention, it is possible to provide a product processing device that can avoid deterioration of work efficiency even when repeatedly placing and removing the same type of product from a weighing tray. [Brief explanation of the drawing]

[0015] [Figure 1] Figure 1 is a diagram showing an example of the overall configuration of the product processing apparatus 1 according to the first embodiment. [Figure 2] Figure 2 shows an example of the display screen of the display unit 12 of the product processing apparatus 1 according to the first embodiment. [Modes for carrying out the invention]

[0016] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the following drawings, the same or similar parts are denoted by the same or similar reference numerals. However, it should be noted that the drawings are schematic, and the ratios of each dimension etc. are different from the actual ones. Therefore, specific dimensions etc. should be determined in consideration of the following description. Also, there may be parts where the relationships and ratios of the dimensions to each other are different even between the drawings. In this specification and the drawings, elements having substantially the same functions and configurations are denoted by the same reference numerals to omit redundant explanations, and elements not directly related to the present invention are omitted from the illustration.

[0017] (First Embodiment) Hereinafter, referring to FIGS. 1 to 2, the merchandise processing apparatus 1 according to the first embodiment of the present invention will be described. FIG. 1 is a diagram showing an example of the overall configuration of the merchandise processing apparatus 1 according to the present embodiment, and FIG. 2 is a diagram showing an example of the display screen of the display unit 12 of the merchandise processing apparatus 1 according to the present embodiment.

[0018] As shown in FIG. 1, the merchandise processing apparatus 1 according to the present embodiment includes a camera 11, a display unit 12, a control unit 13, and a label printer 14.

[0019] As shown in FIG. 1, the camera 11 is housed in a shade and captures an image of the merchandise 100 placed on the merchandise placement unit 10 from above to generate a captured image. The merchandise placement unit 10 is a weighing pan for weighing the weight of the loaded merchandise 100.

[0020] The display unit 12 displays various information. As shown in FIGS. 1 and 2, the display unit 12 displays the estimated merchandise candidates C on the display screen (display) 12D according to the instructions of the control unit 13.

[0021] The label printer 14 prints merchandise information regarding the merchandise on a label. For example, the merchandise information includes the merchandise name, price, processing date and time, expiration date, weight of the merchandise, and the like.

[0022] Based on the captured image captured by the camera 11, the control unit 13 estimates the product candidate C and causes the display unit 12 to display the estimated product candidate C.

[0023] For example, the control unit 13 stores a learned model for each product 100 and uses this model to estimate the product candidate C from the captured image. Alternatively, it may estimate the product candidate C in cooperation with a learned model stored in a cloud server (not shown). In such a case, the control unit 13 transmits the captured image to the cloud server. The cloud server estimates the product candidate C based on the captured image acquired from the control unit 13 and the stored learned model, and transmits the product candidate C to the control unit 13.

[0024] Here, the cloud server may also transmit the estimation accuracy of each of the product candidates C to the control unit 13. In such a case, the control unit 13 may instruct the display unit 12 to display the product candidates C in descending order of the estimation accuracy.

[0025] Further, the cloud server periodically performs machine learning using the captured images of products and product information (teacher data), and updates the learned model.

[0026] Based on the product candidate C displayed on the display unit 12, when one product is specified by the operator's operation, the control unit 13 causes the label printer 14 to print the product information regarding the specified one product.

[0027] Also, after one product is specified, when the control unit 13 determines that the candidate estimated based on the captured image of another product is the same as the one product, it uses the product information regarding the one product to cause the label printer 14 to print the product information regarding the another product.

[0028] Hereinafter, an example of the operation when the product processing apparatus 1 prints product information on a label will be described using FIGS. 2(a) and 2(b).

[0029] Firstly, when the operator places the first product 100 (one product) on the product placement unit 10, the camera 11 captures an image of the product 100 and inputs the captured image to the control unit 13. The control unit 13 then inputs the captured image into a trained model to estimate product candidates C, and displays the estimation result as product candidate C on the display screen 12D of the display unit 12. Here, the estimation results are displayed in descending order from the most probable, so in the example of Figure 2(a), "stir-fried vegetables C1" is highlighted at the top as the product with the highest probability among product candidates C.

[0030] Secondly, if the operator determines that the first product 100 placed on the product placement unit 10 is "stir-fried vegetables C1" and that this matches the "stir-fried vegetables C1" estimated by the control unit 13, in automatic mode, the operator removes the product 100 from the product placement unit 10, and in manual mode, the operator operates the print key K. The control unit 13 then confirms the first product 100 as "stir-fried vegetables C1" and subsequently calculates the price based on the weight of the product 100 placed on the product placement unit 10.

[0031] Thirdly, the control unit 13 reads the confirmed product information for "stir-fried vegetables C1" from a product master (not shown) and sets it, along with the weight and price, in the label printer 14. As a result, the label printer 14 prints the product information, weight, and price for "stir-fried vegetables C1" onto a label and issues it.

[0032] Fourth, the worker picks up the issued price label and attaches it to product 100, and then places the second product 100 (another product) on the product placement unit 10. At this point, the image of product 100 acquired by camera 11 is input to control unit 13, and simultaneously the weighing of the second product 100 is performed. Fifth, the control unit 13 estimates a candidate product C based on the input captured image. In this case, if the second estimated product 100 is the same "stir-fried vegetables C1" as the first product 100, the control unit 13 immediately uses the product information for the first product 100 (one product) to print product information for the second product 100 (another product) on the label printer 14.

[0033] Specifically, since the product information for the first product 100 is already set in the label printer 14, the control unit 13 calculates the price based on the weight of the second product 100 that has just been placed on the product placement unit 10, and sets the calculated price and the newly acquired weight as the print information for the second product in the label printer 14.

[0034] Sixth, the label printer 14 prints the weight and price of the second product 100, which was set later, on the label, adding the product information for the first product 100 (one product), "stir-fried vegetables C1," which has already been set. In this case, even in manual mode, the operator can issue a price-labeled label without operating (pressing) the print key.

[0035] In the second operation described above, if the operator determines that the product 100 placed on the product placement unit 10 is "potato salad C2" as shown in Figure 2(b) and not "stir-fried vegetables C1", the operator selects "potato salad C2" as shown in Figure 2(b) on the display screen 12D. Then, in automatic mode, the operator removes the product 100 from the product placement unit 10, or in manual mode, the operator operates the print key K, at which point the product 100 placed on the product placement unit 10 is confirmed as "potato salad C2".

[0036] Then, if the second product 100 placed on the product placement unit 10 is also "potato salad C2", the control unit 13 immediately issues a label printed with "potato salad C2" to be affixed to the second product 100, as described above. Furthermore, if the first product 100 (product one) is "stir-fried vegetables C1" and a label for "stir-fried vegetables C1" is issued based on that, and if the candidate product C estimated based on the photographed image of the second product 100 (another product) is "potato salad C2", and this is confirmed by the operator's operation, the control unit 13 reads the product information for potato salad C2 from the product master and sets it in the label printer 14. Subsequently, when the second product is removed from the product placement unit 10, or when the print key is operated (pressed), the control unit 13 calculates the weight and price of the second product 100 and sets it in the label printer 14.

[0037] According to the above configuration, once the first product 100 on the product placement unit 10 is identified and product information for the identified first product 100 is printed on the label, if the second product 10 placed on the product placement unit 10 is of the same type as the first product 100, the same type of label is automatically issued. Therefore, the same type of product 100 can be placed on the product placement unit 10 one after another, and price labels can be issued repeatedly.

[0038] Furthermore, after the control unit 13 identifies the first product 100 (product 1) using the trained model, it may compare the features extracted from the image of product 1 with the features extracted from the image of another product placed second, to determine whether product 1 and the other product are identical.

[0039] With this configuration, if the product estimation by the trained model is unsatisfactory, for example, as shown in Figure 2(b), even in cases where the user is forced to select the correct product from a list of displayed products, if the correct product is identified through product selection, the features of the correct product can be stored. By comparing the stored features of the correct product with features obtained from other products added later, the similarities and differences between the two can be immediately determined.

[0040] According to this embodiment, even when repeatedly placing and removing the same type of product from a weighing tray, it is possible to issue price labels one after another, thereby avoiding deterioration in the pricing process for similar products.

[0041] Although the present invention has been described in detail using the embodiments described above, it will be clear to those skilled in the art that the present invention is not limited to the embodiments described herein. The present invention can be implemented in modified and altered forms without departing from the spirit and scope of the invention as defined by the claims. Therefore, the description herein is for illustrative purposes only and is not intended to be restrictive in any way to the present invention. [Explanation of Symbols]

[0042] 1…Product processing equipment 10…Product placement section 11…Camera 12...Display section 12D…Display screen 13…Control Unit 14…Label printer 100...products C...Product candidates K...Printed key

Claims

1. A camera that captures images of products placed on the product placement area and generates captured images, A display unit that displays various information, A control unit that estimates candidate products based on the captured image and displays the candidates on the display unit, The system includes a label printer that prints product information relating to the aforementioned product onto a label, The control unit, If a product is identified by the operator based on the candidates displayed on the display unit, the label printer is instructed to print product information for the identified product. A product processing device that, after the first product has been identified, determines that a candidate estimated based on a photographic image of another product is the same as the first product, uses the product information of the first product to cause the label printer to print product information of the other product.

2. The product processing apparatus according to claim 1, wherein the control unit compares the feature quantities extracted from the image of one product with the feature quantities extracted from the image of another product to determine whether the candidate estimated based on the image of the other product is the same as the first product.

3. The product processing apparatus according to claim 1, wherein even in a mode in which it is necessary to operate a print key to print product information relating to the product on the label, if the control unit determines that a candidate estimated based on a photographed image of the other product is the same as the first product, it causes the label printer to print product information relating to the other product without operating the print key.

Images