WO2021033285A1 - 処理装置、処理方法及びプログラム - Google Patents

処理装置、処理方法及びプログラム Download PDF

Info

Publication number
WO2021033285A1
WO2021033285A1 PCT/JP2019/032606 JP2019032606W WO2021033285A1 WO 2021033285 A1 WO2021033285 A1 WO 2021033285A1 JP 2019032606 W JP2019032606 W JP 2019032606W WO 2021033285 A1 WO2021033285 A1 WO 2021033285A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
image
web
identification information
registered
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2019/032606
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
貴美 佐藤
岩元　浩太
壮馬 白石
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP2021541404A priority Critical patent/JP7380689B2/ja
Priority to PCT/JP2019/032606 priority patent/WO2021033285A1/ja
Priority to US17/635,049 priority patent/US12125088B2/en
Publication of WO2021033285A1 publication Critical patent/WO2021033285A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0623—Electronic shopping [e-shopping] by investigating goods or services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions

Definitions

  • the present invention relates to a processing device, a processing method and a program.
  • Patent Documents 1 to 3 are techniques for recognizing and registering a product to be accounted for based on an image of a product to be accounted for and a reference image of each product registered in advance, and are subject to accounting from a plurality of directions with a plurality of cameras. Discloses the technology for photographing the products of.
  • Patent Document 4 is a technique for recognizing and registering a product to be accounted for based on an image of a product to be accounted for and a reference image of each product registered in advance, and a plurality of products to be accounted for using a mirror. It discloses the technology for photographing the outer surface.
  • Patent Document 5 discloses a technique for associating an image generated by a camera with product identification information read by a barcode reader.
  • Patent Documents 1 to 5 describes or suggests the problem and its solution.
  • An object of the present invention is to realize a technique for efficiently registering a reference image of each product.
  • Web product image acquisition means for acquiring web product images published on web pages specified by predetermined search conditions
  • Product identification information acquisition means for acquiring product identification information of the product shown in the web product image
  • a registration means for associating the web product image with the product identification information and registering the product in the product database.
  • the computer Acquire the web product image published on the web page specified by the predetermined search conditions, Acquire the product identification information of the product shown in the web product image, A processing method for associating the web product image with the product identification information and registering the product in the product database is provided.
  • Computer Web product image acquisition means for acquiring web product images published on web pages specified by predetermined search conditions
  • Product identification information acquisition means for acquiring product identification information of the product indicated by the web product image
  • a registration means for associating the web product image with the product identification information and registering the product in the product database.
  • a program is provided to function as.
  • the processing device acquires a web product image published on a web page specified by a predetermined search condition. Next, the processing device acquires the product identification information of the product indicated by the acquired web product image. Then, the processing device associates the acquired web product image with the acquired product identification information and registers the acquired product in the product database. According to such a processing device, the reference image of each product can be efficiently registered in the product database.
  • the configuration of the processing device will be described in detail.
  • FIG. 1 shows an example of a functional block diagram of the processing device 10.
  • the processing device 10 includes a web product image acquisition unit 11, a product identification information acquisition unit 12, a registration unit 13, and a storage unit 15.
  • the processing device 10 does not have to have the storage unit 15.
  • an external device configured to be able to communicate with the processing device 10 includes a storage unit 15.
  • Each functional unit of the processing device 10 is a storage unit (stored from the stage of shipping the device in advance) such as a CPU (Central Processing Unit) of an arbitrary computer, a memory, a program loaded into the memory, and a hard disk for storing the program.
  • a storage unit such as a CPU (Central Processing Unit) of an arbitrary computer, a memory, a program loaded into the memory, and a hard disk for storing the program.
  • it can also store programs downloaded from storage media such as CDs (Compact Discs) and servers on the Internet), and is realized by any combination of hardware and software centered on the network connection interface. Program.
  • CDs Compact Discs
  • FIG. 2 is a block diagram illustrating a hardware configuration of the processing device 10.
  • the processing device 10 includes a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A.
  • the peripheral circuit 4A includes various modules.
  • the processing device 10 does not have to have the peripheral circuit 4A.
  • the processing device 10 may be composed of a plurality of physically and / or logically separated devices, or may be composed of one physically and / or logically integrated device. When the processing device 10 is composed of a plurality of physically and / or logically separated devices, each of the plurality of devices can be provided with the above hardware configuration.
  • the bus 5A is a data transmission path for the processor 1A, the memory 2A, the peripheral circuit 4A, and the input / output interface 3A to send and receive data to and from each other.
  • the processor 1A is, for example, an arithmetic processing unit such as a CPU or a GPU (Graphics Processing Unit).
  • the memory 2A is, for example, a memory such as a RAM (RandomAccessMemory) or a ROM (ReadOnlyMemory).
  • the input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera, etc., an interface for outputting information to an output device, an external device, an external server, etc. ..
  • the input device is, for example, a keyboard, a mouse, a microphone, a physical button, a touch panel, or the like.
  • the output device is, for example, a display, a speaker, a printer, a mailer, or the like.
  • the processor 1A can issue commands to each module and perform calculations based on the calculation results thereof.
  • the "product whose product image is not registered in the product database" which is the target of image acquisition, is not registered in the product database because it was not handled in the store until then, such as a new product. This applies to products that require product images to be registered because they will be handled by.
  • the "product whose product image is registered in the product database” to be image-acquired has been handled in the store until then, and the product image has already been registered in the product database, but the appearance due to renewal or the like. Applies to products that require new product images to be registered due to the change in.
  • the storage unit 15 stores the product database.
  • FIG. 3 schematically shows an example of a product database.
  • the product code, the product name, the unit price, the information for identifying the registered image (image identification information such as a file name), and the search condition are associated with each other.
  • the product database may include other information or may not include a part of the illustrated information.
  • a product to which image identification information is associated that is, a product to which a product image is registered
  • a product to which image identification information is not associated that is, a product to which a product image is not registered
  • a product to which image identification information is not associated is, for example, a product that is newly handled at a store and for which a product image has not yet been registered.
  • the product image is not registered, the product code, product name, unit price, and other information have already been acquired, so they are registered in the product database.
  • the web product image acquisition unit 11 performs a web search under predetermined search conditions and acquires a web product image published on the specified web page.
  • the web product image acquisition unit 11 may perform a web search at a predetermined timing (example: a predetermined time every day), or may perform a web search at a timing when an instruction is input by the user.
  • the instruction input by the user may be performed for each product.
  • a web search is performed based on the search conditions associated with the specified product.
  • the search condition may be stored in the storage unit 15. Further, the search condition may be defined / registered for each product as shown in FIG. 3, or may be defined / registered for each product without any restrictions.
  • the search condition is specified so that the web page that publishes the image to be acquired can be specified (searched) by the web search.
  • 4 to 6 show an example of such a web page. Examples of such a web page include a product information site of a product manufacturer, a news release site (see FIGS. 4 and 5), an information transmission site such as a blog of a wholesaler or a retail store (see FIG. 6), and the like. However, it is not limited to these.
  • the search condition may be, for example, directly specifying the web page of the above-mentioned site by the URL.
  • the search condition may be a condition for web search defined by connecting keywords with logical operators.
  • it may be a search condition in which keywords related to an image acquisition target (product name, maker name, etc.), keywords related to an image (image, photograph, etc.) are connected by a logical operator.
  • the search condition may include keywords that tend to be attached to the new product, such as "new product” and "New”.
  • the search condition may include keywords such as "renewal” and "design change” that tend to be attached to products whose appearance has been changed due to renewal or the like.
  • the web product image acquisition unit 11 identifies the top predetermined number of web pages among the plurality of web pages included in the search result as the result of the web search, and the web product image published on the specified web page. May be obtained.
  • the web product image acquisition unit 11 analyzes the web page specified by the web search and acquires the image (image file) published on the web page. After that, the web product image acquisition unit 11 analyzes the acquired image and removes an image satisfying a predetermined removal condition from the acquired plurality of images. Then, the web product image acquisition unit 11 acquires the image remaining after the removal as the web product image.
  • the removal conditions are "the image size is smaller than the standard value”, "pre-registered image to be removed (eg, logo not related to the product that is always displayed on the site)", "generated by machine learning”.
  • the estimation result of the subject based on the estimation model for estimating the subject included in the image is an object other than the product (eg, person, animal, mountain, sea, etc.), but the present invention is not limited to these.
  • the shape of each product may be registered in advance in the product database.
  • the shape of the product may be shown, for example, as a planar shape when the product is observed from one or a plurality of directions.
  • the planar shape may be defined as "circle”, “rectangle (aspect ratio 3: 7)", or the like, or may be defined by an image showing the silhouette of the product.
  • the shape of the product may be indicated by three-dimensional information. Then, the removal condition may be "the shape of the subject included in the image does not match the registered product shape".
  • the web product image acquisition unit 11 determines whether or not the subject included in the image acquired from the web page specified by the web search based on the search conditions of each product satisfies the shape registered in association with each product. To judge. At the time of determination, the web product image acquisition unit 11 may perform comparison with the registered plane shape while rotating the subject included in the image. In addition, the web product image acquisition unit 11 uses the three-dimensional information registered in the product database as the shape of the product to generate a flat image when the product is observed from each of a plurality of directions, and the image acquired from the web page. You may compare the shape with the subject included in.
  • the removal condition may be "specified as a removal target by the user". That is, even if the web product image acquisition unit 11 presents all or a part of the acquired images to the user (eg, displays them on a display) and accepts an input as to whether or not to leave each image as a web product image. Good. In this case, the image automatically removed under other removal conditions as described above may be excluded from the confirmation target by the user. By doing so, the burden on the user is reduced.
  • the user designates and registers a predetermined image (eg, a logo that is not related to the product that is always displayed on the site) as the above-mentioned image to be removed. You may be able to do it.
  • a predetermined image eg, a logo that is not related to the product that is always displayed on the site
  • the web product image acquisition unit 11 may perform image editing processing on the image acquired from the web screen.
  • the web product image acquisition unit 11 may perform the image editing process before the process of removing a part of the image acquired from the above-mentioned web screen and acquiring the remaining image as the web product image, or the process thereof.
  • the image editing process may be performed after the above, or a part of the image editing process may be performed before the process and the other part may be performed after the process.
  • the web product image acquisition unit 11 may specify an area in the web product image in which the product exists, and perform editing to remove other background areas.
  • the web product image acquisition unit 11 may perform editing to change the orientation of the product indicated by the web product image.
  • the perspective view is changed to the front view.
  • the web product image acquisition unit 11 may generate a plurality of images showing a state when the product indicated by the web product image is observed from each of a plurality of directions.
  • an image showing a state when the product is observed from directly above and an image showing a state when the product is observed from the side are generated.
  • the web product image acquisition unit 11 may perform image editing processing such as enlargement and rotation.
  • one web product image may include a plurality of products.
  • the web product image acquisition unit 11 may individually cut out the area of each product and edit it into separate image files.
  • the web product image acquisition unit 11 may perform these edits based on user input, automatically, or partly based on user input and automatically perform other parts.
  • the plane shape condition (image condition) of each product to be shown in the product image registered in the product database may be registered in advance.
  • the plane shape condition may be defined as, for example, a "circle", a "rectangle (aspect ratio 3: 7)", or the like, or may be defined by an image showing the silhouette of the product.
  • the web product image acquisition unit 11 sets the image conditions registered by associating the planar shape of the subject shown in the image acquired from the web page specified by the web search based on the search conditions of each product with each product.
  • Image editing is performed by rotating the subject included in the image so as to satisfy the requirements.
  • the product identification information acquisition unit 12 acquires the product identification information of the product indicated by the web product image acquired by the web product image acquisition unit 11.
  • the product identification information is a product name, a product code, or the like.
  • the product identification information acquisition unit 12 may acquire the product identification information of each web product image from the web page that publishes each web product image. Specifically, the product identification information acquisition unit 12 may search for keywords such as "product name” and "product code” from the web page. Then, a word whose positional relationship with the keyword satisfies a predetermined condition (eg, continuous) in the web page may be acquired as product identification information.
  • a predetermined condition eg, continuous
  • the product identification information acquisition unit 12 associates with each web product image and presents a candidate of product identification information of the product indicated by each web product image to the user (example: displayed on a display).
  • the product identification information selected by the user from the candidates may be acquired.
  • the product identification information acquisition unit 12 may present the product identification information of the product associated with the search condition used for searching the web page that publishes each web product image as a candidate.
  • the product identification information acquisition unit 12 may present a word extracted from the web page and / or the URL of the web page as a candidate. For example, the product identification information acquisition unit 12 searches for keywords such as "product name” and "product code” from a web page, and presents words displayed within a predetermined number of characters before and after the keyword as candidates. You may.
  • the product identification information acquisition unit 12 may calculate the degree of similarity between the web product image and each product image of a plurality of products registered in the product database.
  • the similarity may be indicated by, for example, a value of 0 to 100% (the closer it is to 100%, the more similar it is), or 0 to 1 (the closer it is to 1, the more similar it is). It may be expressed by other methods.
  • the product identification information acquisition unit 12 may present the product identification information of the product having the similarity degree of the first predetermined value or more as a candidate.
  • the product identification information acquisition unit 12 may present the product identification information of the product for which the product image is not registered in the product database as a candidate. ..
  • the product identification information acquisition unit 12 presents the product identification information of the product for which the product image is not registered in the product database as a candidate. May be good.
  • a predetermined keyword is a wording that tends to be attached to a new product, such as "new product” or "New".
  • the registration unit 13 links the web product image acquired by the web product image acquisition unit 11 with the product identification information acquired by the product identification information acquisition unit 12 and registers it in the product database.
  • the web product image acquisition unit 11 performs a web search under predetermined search conditions at a predetermined timing, and acquires an image published on the specified web page.
  • the predetermined timing may be a predetermined timing (eg, a predetermined time every day), or may be a timing in which an instruction is input by the user.
  • the web product image acquisition unit 11 may perform editing processing on the acquired image. Since the details of the editing process are as described above, the description here will be omitted.
  • the web product image acquisition unit 11 removes an image satisfying the removal condition from the acquired images, and acquires the remaining image as a web product image.
  • the web product image acquisition unit 11 may present all or part of the acquired image to the user (eg, display it on a display) and accept an input as to whether or not to leave each image as a web product image. Good.
  • the web product image acquisition unit 11 may remove an image satisfying the removal condition from the acquired images by another process.
  • the web product image acquisition unit 11 may perform an editing process on the acquired web product image. Since the details of the editing process are as described above, the description here will be omitted.
  • the product identification information acquisition unit 12 acquires the product identification information of the product indicated by the web product image acquired in S10.
  • the product identification information acquisition unit 12 may acquire the product identification information by other processing.
  • the product identification information acquisition unit 12 calculates the degree of similarity between the web product image and the product image of each of the plurality of products registered in the product database (S20). Next, the product identification information acquisition unit 12 determines whether or not a product image having a similarity of the first predetermined value or more is registered in the product database (S21).
  • the product identification information acquisition unit 12 inputs the product identification information associated with the product image in the product database. Presented as a candidate (S22).
  • the product identification information acquisition unit 12 is the product of the product for which the product image is not registered in the product database. Identification information (product identification information to which image identification information is not associated) is presented as a candidate (S23).
  • the product identification information acquisition unit 12 acquires the selected product identification information (S25).
  • the registration unit 13 associates the web product image acquired in S10 with the product identification information acquired in S11 and registers it in the product database.
  • the processing device 10 of the present embodiment described above it is possible to acquire the product image published on the web page and register it in the product database.
  • the reference image of each product used in the technology for recognizing and registering the product to be accounted for is efficiently registered in the product database based on the photographed image of the product to be accounted for and the reference image of each product registered in advance. can do.
  • the processing device 10 of the present embodiment not only the product image but also the product identification information can be acquired by using the web page. Therefore, the work of registering the reference image in the product database can be made more efficient.
  • a candidate for product identification information is automatically generated, and the product image is linked to the product identification information selected by the user. Can be registered.
  • the confirmation / selection process by the user, it is possible to suppress the inconvenience of registering the product image acquired from the web page by associating it with the incorrect product identification information. Further, since the user work is a simple work of selecting from the candidates, the burden on the user can be reduced.
  • the probability that true product identification information is included in the candidates is high.
  • the processing device 10 of the present embodiment when a product image having a degree of similarity with the product image acquired from the web page is registered in the product database with a first predetermined value or more, the similar product image is registered.
  • the product identification information of the product specified in can be presented as a candidate.
  • the product image whose similarity with the product image acquired from the web page is equal to or higher than the first predetermined value is not registered in the product database, the product indicated by the product image acquired from the web page is a store until then.
  • the processing device 10 for determining the candidate the probability that the true product identification information is included in the candidate is high.
  • the processing device 10 of the present embodiment when a predetermined keyword that tends to be attached to a new product such as "new product” or "New” in the web page is included, it is acquired from the web page. Since the product shown in the product image is likely to be a new product, the product identification information of the product for which the product image is not registered in the product database can be presented as a candidate. According to the processing device 10 for determining the candidate in this way, the probability that the true product identification information is included in the candidate is high.
  • the processing device 10 of the present embodiment is registered with the web product image acquired by the web product image acquisition unit 11. It differs from the first embodiment in that the difference from the product image is determined, and when it is determined that there is a difference, the web product image is newly registered in the product database. The details will be described below.
  • FIG. 12 shows an example of a functional block diagram of the processing device 10.
  • the processing device 10 includes a web product image acquisition unit 11, a product identification information acquisition unit 12, a registration unit 13, a determination unit 14, and a storage unit 15.
  • the determination unit 14 sets the web product image and the registered product image. Determine if there is a difference. "No difference” may be a concept that includes not only the case where the web product image and the registered product image are completely the same, but also the case where there is a slight difference.
  • the determination unit 14 outputs a web product image and a registered product image (example: displayed on a display), and accepts a user input indicating the presence or absence of a difference.
  • the determination unit 14 may output the web product image and the registered product image side by side.
  • the determination unit 14 may determine the presence or absence of a difference based on the degree of similarity between the web product image and the registered product image. For example, the determination unit 14 may determine that there is a difference when the degree of similarity between the web product image and the registered product image is less than the second predetermined value.
  • the first predetermined value described in the first embodiment and the second predetermined value may be the same or different.
  • the registration unit 13 registers the web product image in the product database when the product identification information acquisition unit 12 acquires the product identification information of the product whose product image has been registered in the product database and when the determination unit 14 determines that there is a difference. If the determination unit 14 determines that there is no difference, the web product image is not registered in the product database.
  • Other configurations of the registration unit 13 are the same as those in the first embodiment.
  • the configuration of the web product image acquisition unit 11, the product identification information acquisition unit 12, and the storage unit 15 is the same as that of the first embodiment.
  • the web product image acquisition unit 11 performs a web search under predetermined search conditions at a predetermined timing, and acquires a web product image published on the specified web page.
  • the product identification information acquisition unit 12 acquires the product identification information of the product indicated by the web product image acquired in S30.
  • the processing of S30 and S31 is the same as the processing of S10 and S11 described in the first embodiment.
  • the determination unit 14 confirms whether or not the product identification information acquired in S31 is the product identification information of the product for which the product image has been registered in the product database (S32).
  • the determination unit 14 When the product image is the product identification information of the registered product (Yes in S32), the determination unit 14 is registered in association with the web product image acquired in S30 and the product identification information acquired in S31. It is determined whether or not there is a difference from the product image (S33). For example, the determination unit 14 outputs the web product image and the registered product image side by side (example: displayed on a display), and accepts a user input indicating the presence or absence of a difference.
  • the registration unit 13 links the web product image acquired in S30 with the product identification information acquired in S31 and registers it in the product database (Yes). S35).
  • the registration unit 13 does not register the web product image acquired in S30 in the product database.
  • the registration unit 13 uses the web product image acquired in S30 for the product identification acquired in S31. It is linked to the information and registered in the product database (S35).
  • the same effects as those of the first embodiment are realized. Further, according to the processing device 10 of the present embodiment, after acquiring the product image of a certain product from the web page, the difference between the product image and the already registered product image of the product is determined, and there is a difference. In case, the product image acquired from the web page can be registered. According to such a processing device 10, the product image acquired from the web page can be registered only when the appearance of the product changes due to renewal or the like and it is necessary to update the registered product image or the like.
  • acquisition means “to get data stored in another device or storage medium by own device” based on user input or program instruction (active). (Acquisition) ”, for example, requesting or inquiring about another device to receive the data, accessing another device or a storage medium, and reading the data.
  • acquisition means “inputting data output from another device to the own device (passive acquisition)” based on user input or program instruction, for example, distribution (or distribution (or).
  • Transmission, push notification, etc. may include receiving data.
  • acquisition means to select and acquire from received data or information, and “edit data (text conversion, data sorting, partial data extraction, file format change, etc.)". It may include “to generate new data and acquire the new data”.
  • Web product image acquisition means for acquiring web product images published on web pages specified by predetermined search conditions, and Product identification information acquisition means for acquiring product identification information of the product shown in the web product image, and A registration means for associating the web product image with the product identification information and registering the product in the product database. Processing equipment with. 2. 2. The processing device according to 1, wherein the product identification information acquisition means acquires the product identification information from the web page. 3. 3. The processing device according to 1, wherein the product identification information acquisition means acquires the product identification information selected by the user from the candidates for the product identification information. 4. Product images of each of a plurality of products are registered in the product database.
  • the processing device wherein the product identification information acquisition means presents the product identification information of a product whose similarity between the product image and the web product image is equal to or higher than a predetermined value as the candidate.
  • Product images of each of a plurality of products are registered in the product database. Among the products registered in the product database, there are products in which the product image is registered and products in which the product image is not registered. When there is no product in which the similarity between the product image and the web product image is equal to or higher than a predetermined value, the product identification information acquisition means uses the product identification information of the product for which the product image is not registered as the candidate.
  • the processing apparatus according to 3 or 4 to be presented. 6.
  • Product images of each of a plurality of products are registered in the product database.
  • the product identification information acquisition means displays the product identification information of a product for which the product image is not registered as the candidate. 7.
  • Product images of each of a plurality of products are registered in the product database.
  • the registration means registers the web product image in the product database when there is a difference.
  • the processing device any one of 1 to 6, wherein the web product image is not registered in the product database when there is no difference.
  • the determination means outputs the web product image and the registered product image, and accepts a user input indicating a difference.
  • the determination means determines a difference based on the degree of similarity between the web product image and the registered product image. 10.
  • the processing device edits the web product image so that the product shape indicated by the web product image satisfies a predetermined condition.
  • the predetermined condition is pre-registered for each product registered in the product database.
  • the computer Acquire the web product image published on the web page specified by the predetermined search conditions, Acquire the product identification information of the product shown in the web product image, A processing method of associating the web product image with the product identification information and registering the product in the product database. 13.
  • Computer Web product image acquisition means for acquiring web product images published on web pages specified by predetermined search conditions
  • Product identification information acquisition means for acquiring product identification information of the product indicated by the web product image
  • a registration means for associating the web product image with the product identification information and registering the product in the product database.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Processing Or Creating Images (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2019/032606 2019-08-21 2019-08-21 処理装置、処理方法及びプログラム Ceased WO2021033285A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2021541404A JP7380689B2 (ja) 2019-08-21 2019-08-21 処理装置、処理方法及びプログラム
PCT/JP2019/032606 WO2021033285A1 (ja) 2019-08-21 2019-08-21 処理装置、処理方法及びプログラム
US17/635,049 US12125088B2 (en) 2019-08-21 2019-08-21 Processing apparatus, processing method, and non-transitory storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2019/032606 WO2021033285A1 (ja) 2019-08-21 2019-08-21 処理装置、処理方法及びプログラム

Publications (1)

Publication Number Publication Date
WO2021033285A1 true WO2021033285A1 (ja) 2021-02-25

Family

ID=74660679

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/032606 Ceased WO2021033285A1 (ja) 2019-08-21 2019-08-21 処理装置、処理方法及びプログラム

Country Status (3)

Country Link
US (1) US12125088B2 (https=)
JP (1) JP7380689B2 (https=)
WO (1) WO2021033285A1 (https=)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003055826A (ja) * 2001-08-17 2003-02-26 Minolta Co Ltd サーバおよび仮想試着用データ管理方法
JP2009251850A (ja) * 2008-04-04 2009-10-29 Albert:Kk 類似画像検索を用いた商品推薦システム
JP2018128883A (ja) * 2017-02-09 2018-08-16 株式会社 Ｖａｓｉｌｙ 情報処理装置、方法およびプログラム

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20030047885A (ko) * 2000-05-05 2003-06-18 가부시끼가이샤 메가 칩스 지연된 브라우징을 위해 정보를 획득하고 저장하는 시스템및 방법
JP2003065826A (ja) 2001-08-22 2003-03-05 Morinaga Milk Ind Co Ltd 液体のバッチ式計量装置及び粉体のバッチ式計量溶解装置
JP2004030409A (ja) 2002-06-27 2004-01-29 Dainippon Screen Mfg Co Ltd 複数の画像と画像対象物情報との関連付け
FR2863086B1 (fr) 2003-11-28 2006-03-10 Ge Med Sys Global Tech Co Llc Procede de production d'une sequence d'images volumiques d'une zone d'un organe d'un etre vivant.
US8838484B2 (en) * 2008-10-27 2014-09-16 Bay Photo, Inc. Embeddable distributed E-commerce and community building system for digital media
GB0909844D0 (en) * 2009-06-08 2009-07-22 Codigital Ltd Method and system for generating collaborative content
JP5447126B2 (ja) 2010-04-16 2014-03-19 株式会社Ｊｖｃケンウッド テレビ放送受信装置、取得目的情報生成方法、プログラム、取得目的情報生成装置、テレビ放送システム
JP6222345B2 (ja) 2014-03-20 2017-11-01 日本電気株式会社 Ｐｏｓ端末装置、ｐｏｓシステム、画像処理方法及びプログラム
KR20160022407A (ko) * 2014-08-19 2016-03-02 (주)에이디79 하나의 이미지 내에 포함된 다수의 제품 이미지 영역의 자동분할을 통한 다수의 정보제공방법
JP6311590B2 (ja) 2014-12-10 2018-04-18 カシオ計算機株式会社 商品処理システム及び商品処理方法
JP6556003B2 (ja) 2015-09-25 2019-08-07 シャープ株式会社 商品情報入力機能を備えた複合機
JP6283806B2 (ja) 2016-06-01 2018-02-28 サインポスト株式会社 情報処理システム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003055826A (ja) * 2001-08-17 2003-02-26 Minolta Co Ltd サーバおよび仮想試着用データ管理方法
JP2009251850A (ja) * 2008-04-04 2009-10-29 Albert:Kk 類似画像検索を用いた商品推薦システム
JP2018128883A (ja) * 2017-02-09 2018-08-16 株式会社 Ｖａｓｉｌｙ 情報処理装置、方法およびプログラム

Also Published As

Publication number Publication date
JP7380689B2 (ja) 2023-11-15
US20220284493A1 (en) 2022-09-08
US12125088B2 (en) 2024-10-22
JPWO2021033285A1 (https=) 2021-02-25

Similar Documents

Publication Publication Date Title
JP4366108B2 (ja) 文書検索装置、文書検索方法及びコンピュータプログラム
US20140254942A1 (en) Systems and methods for obtaining information based on an image
CN109189879B (zh) 电子书籍显示方法及装置
EP2356583B1 (en) Method and system for analysing an image generated by at least one camera
JP2010518507A (ja) 特徴マッチング方法
US20110131529A1 (en) Information Processing Apparatus, Information Processing Method, Computer Program, and Information Processing Server
JP5808371B2 (ja) 画像認識装置、画像認識方法及び画像認識プログラム
CN111198962A (zh) 信息处理装置、系统、方法、类似与否判断方法以及介质
JP2013109773A (ja) 特徴マッチング方法及び商品認識システム
JP7405144B2 (ja) 処理装置、処理方法及びプログラム
JP7235119B2 (ja) 処理装置、会計装置、処理方法及びプログラム
JP2005151127A5 (https=)
WO2019215966A1 (ja) 登録システム、登録方法及びプログラム
JP2016110256A (ja) 情報処理装置及び情報処理プログラム
JP7380689B2 (ja) 処理装置、処理方法及びプログラム
EP4060521A1 (en) Method for providing tag, and electronic device for supporting same
WO2021090753A1 (ja) 処理装置、処理方法及びプログラム
US20080071553A1 (en) Generation of Commercial Presentations
KR102477841B1 (ko) 상품 검색 장치, 서버 및 검색 시스템의 제어 방법
JP6974222B2 (ja) 検索装置、検索方法および検索プログラム
JP6303742B2 (ja) 画像処理装置、画像処理方法、および画像処理プログラム
WO2019163095A1 (ja) 登録装置、登録方法及びプログラム
CN115983936A (zh) 一种搜索信息展示方法、装置、计算机设备及存储介质
US12482136B2 (en) Registration system, processing device, and processing method
CN117291681B (zh) 基于3d物品定制化的设计素材管理系统及相关装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19942240

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021541404

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19942240

Country of ref document: EP

Kind code of ref document: A1